Traditional 3D reconstruction models have consistently encountered a challenge: attaining high recall of object edges while preserving precision. In this paper, we introduce a post-processing method Multi-Head Attention Refiner (MA-R) aimed at tackling this challenge by integrating a multi-head attention mechanism within the U-Net style refiner module. The 3D reconstruction model applying this method demonstrates excellence in parsing intricate image details, resulting in significant enhancement of boundary predictions and increased recall rates. In our experiments, our method significantly enhances the reconstruction performance of Pix2Vox++ when multiple images are utilized as input. Specifically, it achieves an enhanced Intersection Over Union score of approximately 1.1% compared to the original Pix2Vox++ model when 16-view images are employed.

This project investigates the behavior of multi-head attention in Transformer models, specifically focusing on the differences between benign and trojan models in the context of sentiment analysis. Trojan attacks cause models to perform normally on clean inputs but exhibit misclassifications when presented with inputs containing predefined triggers. We characterize attention head functions in trojan and benign models, identifying specific 'trojan' heads and analyzing their behavior.

This paper presents ConF, a novel deep learning model designed for accurate and efficient prediction of non-coding RNA families. NcRNAs are essential functional RNA molecules involved in various cellular processes, including replication, transcription, and gene expression. Identifying ncRNA families is crucial for comprehensive RNA research, as ncRNAs within the same family often exhibit similar functionalities. Traditional experimental methods for identifying ncRNA fam-ilies are time-consuming and labor-intensive. Computational approaches relying on annotated secondary structure data face limitations in handling complex structures like pseudoknots and have restricted applicability, resulting in suboptimal prediction performance. To overcome these chal-lenges, ConF integrates mainstream techniques such as residual networks with dilated convolutions and cross multi-head attention mechanisms. By employing a combination of dual-layer convolu-tional networks and BiLSTM, ConF effectively captures intricate features embedded within RNA sequences. This feature extraction process leads to significantly improved prediction accuracy compared to existing methods. Experimental evaluations conducted on a ten-fold publicly available dataset demonstrate the superiority of ConF in terms of accuracy, sensitivity, and other perfor-mance metrics. Overall, ConF represents a promising solution for accurate and efficient ncRNA family prediction, addressing the limitations of traditional experimental and computational methods.

Sarcasm is a linguistic expression often used to communicate the opposite of what is said, usually something that is very unpleasant with an intention to insult or ridicule. Inherent ambiguity in sarcastic expressions, make sarcasm detection very difficult. In this work, we focus on detecting sarcasm in textual conversations from various social networking platforms and online media. To this end, we develop an interpretable deep learning model using multi-head self-attention and gated recurrent units. Multi-head self-attention module aids in identifying crucial sarcastic cue-words from the input, and the recurrent units learn long-range dependencies between these cue-words to better classify the input text. We show the effectiveness of our approach by achieving state-of-the-art results on multiple datasets from social networking platforms and online media. Models trained using our proposed approach are easily interpretable and enable identifying sarcastic cues in the input text which contribute to the final classification score. We visualize the learned attention weights on few sample input texts to showcase the effectiveness and interpretability of our model.

Deep convolutional neural network (CNN) has shown their great advantages in the single image deraining task. However, most existing CNN-based single image deraining methods still suffer from residual rain streaks and details lost. In this paper, we propose a deep neural network including the Multi-scale feature extraction module and the channel attention module, which are embed in the feature extraction sub-network and the rain removal sub-network respectively. In the feature extraction sub-network, the Multi-scale feature extraction module is constructed by a Multi-layer Laplacian pyramid, and is then integrated multi-scale feature maps by a feature fusion module. In the rain removal sub-network, the channel attention module, which assigns different weights to the different channels, is introduced for preserving image details. Experimental results on visually and quantitatively comparison demonstrate that the proposed method performs favorably against other state-of-the-art approaches

The object detection task is usually affected by complex backgrounds. In this paper, a new image object detection method is proposed, which can perform multi-feature selection on multi-scale feature maps. By this method, a bidirectional multi-scale feature fusion network is designed to fuse semantic features and shallow features to improve the detection effect of small objects in complex backgrounds. When the shallow features are transferred to the top layer, a bottom-up path is added to reduce the number of network layers experienced by the feature fusion network, reducing the loss of shallow features. In addition, a multi-feature selection module based on the attention mechanism is used to minimize the interference of useless information on subsequent classification and regression, allowing the network to adaptively focus on appropriate information for classification or regression to improve detection accuracy. Because the traditional five-parameter regression method has severe boundary problems when predicting objects with large aspect ratios, the proposed network treats angle prediction as a classification task. The experimental results on the DOTA dataset, the self-made DOTA-GF dataset and the HRSC 2016 dataset show that, compared with several popular object detection algorithms, the proposed method has certain advantages in detection accuracy.

Ensuring the accuracy of wind power prediction is paramount for the reliable and stable operation of power systems. This study introduces a novel approach aimed at enhancing the precision of wind power prediction through the development of a multiscale hybrid model. This model integrates advanced methodologies including Improved Intrinsic Mode Function with Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Permutation Entropy(PE), Least Squares Support Vector Regression (LSSVR), Regularized Extreme Learning Machine(RELM), Multi-head Attention (MHA), and Bidirectional Gated Recurrent Unit (BiGRU). Firstly, the ICEEMDAN technique is employed to decompose the non-stationary raw wind power data into multiple relatively stable sub-modes, while concurrently utilizing PE to assess the complexity of each sub-mode. Secondly, the dataset is reconstituted into three distinct components: high-frequency, mid-frequency, and low-frequency, to alleviate data complexity. Following this, the LSSVR, RELM, and MHA-BiGRU models are individually applied to predict the high, mid,and low-frequency components, respectively. Thirdly, the parameters of the low-frequency prediction model are optimized utilizing the Dung Betele Optimizer(DBO) algorithm. Ultimately, the predicted results of each component are aggregated to derive the final prediction. Empirical findings illustrate the exceptional predictive performance of the multiscale hybrid model incorporating LSSVR, RELM,and MHA-BiGRU. In comparison to other benchmark models, the proposed model exhibits a reduction in Root Mean Square Error(RMSE) values of over 10%, conclusively affirming its superior predictive accuracy.

This paper proposes an innovative approach to address the challenge of softening deformation of thermal-curable thermosets during additive manufacturing. This approach involves the development of a composite powder composed of thermosetting materials with distinct curing temperatures, the utilization of Cold Spray Additive Manufacturing (CSAM) technology for 3D printing, and the application of a stepwise isothermal curing process. The corresponding effectiveness is validated by case studies. The results demonstrate that samples printed via CSAM maintain a solid state without deformation. During the post-curing process, each component of the composite material cures independently while the other components remain in a solid state, providing structural support for the whole material, thereby effectively reducing the softening deformation during the post-curing process. This approach offers a novel perspective for the additive manufacturing of thermal-curable thermosets.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

Grain yield prediction affects policy making in various aspects such as agricultural production planning, food security assurance, and adjustment of foreign trade. Accurately predicting grain yield is of great significance in ensuring global food security. This paper is based on the MODIS remote sensing image data products from 2010 to 2020, and adds band information such as vegetation index and temperature to form composite remote sensing data as a data set. Aiming at the lack of models for large-scale forecasting and the need for human intervention in traditional models, this paper proposes a grain production estimation model based on deep learning. First, image cropping and yield mapping techniques are used to process the data to generate training samples. Then the channel and spatial attention mechanism (Convolutional Block Attention Module, CBAM) is added for extracting spatial information in different remote sensing bands to improve the efficiency of the model. Long Short-Term Memory (LSTM) neural networks is also added to obtain feature information in the time dimension. Finally, a national-scale grain yield prediction model is constructed. The proposed model was tested on data from 2018 to 2020 showing an average R2 of 0.940 and an average RMSE of 80,020 tons, indicating that it can predict Chinese grain yield better. The model proposed in this paper extracts grain yield information directly from the composite remote sensing data, and solves the problem of small-scale research and imprecise yield prediction in an end-to-end manner.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, \eg{} low accuracy, slow speed, \etc The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Luoyang Pedestrian Dataset \footnote{The dataset can be downloaded through this anonymous link: \url{https://drive.google.com/drive/folders/13po1FX7Qk5RDgb60-dzOi74cq_kqDJtM?usp=sharing} }, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Luoyang Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperform the most commonly used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

The rational design of magnetic carbon composites, encompassing both composition and microstructure, holds significant potential for achieving exceptional electromagnetic wave absorbing materials (EAMs). In this study, FeCo@CM composites was efficiently fabricated through an advanced microwave plasma assisted reduction chemical vapor deposition (MPARCVD) technique, offering high efficiency, low cost, and energy-saving benefits. By depositing graphitized carbon microspheres, the dielectric properties were significantly enhanced, resulting in improved electromagnetic wave absorption performances through optimized impedance matching and a synergistic effect with magnetic loss. A systematic investigation revealed that the laminar-stacked structure of FeCo exhibited superior properties compared to its spherical counterpart, supplying a higher number of exposed edges and enhanced catalytic activity, which facilitated the deposition of uniform and low-defect graphitized carbon microspheres. Consequently, the dielectric loss performance of the FeCo@CM composites was dramatically improved due to increased electrical conductivity and the formation of abundant heterogeneous interfaces. At a 40 wt% filling amount and a frequency of 7.84 GHz, the FeCo@CM composites achieved a minimum reflection loss value of -58.2 dB with an effective absorption bandwidth (fE) of 5.13 GHz. This study presents an effective strategy for developing high-performance EAMs.

Microscopic vision plays an important role in automated micro-assembly. However, some uncertain factors in the assembly process, such as occlusion and stains can lead to the mistakes of feature extraction. Herein, to solve the problem, the deep learning techniques are introduced into the feature recognition tasks, focusing on the attention mechanism and visualizing CNNs for DL-based microscopic vision. The main contributions are summarized as follows: The CBAM attention mechanism is combined with the YOLOv5 algorithm to improve the accuracy and robustness of feature extraction. The micropart feature occlusion experiment results show that at 70% occlusion degree, YOLOV5-CBAM can reach 97.9% [email protected], which is 4.6% higher than the original one. Visualization analysis of DL-based model is conducted using Grad-CAM to make the decision result more transparent and avoid potential visual detection risks during assembly. The heatmap matching degree between GT area and high-light area is increased by 27.81% on average, which further verify the effectiveness of attention mechanism in micropart feature localization. Additionally, micropart surface stain and droplet quality classification models based on ResNet50 are trained to replace the manual sorting. The visual results are consistent with human eye discernment and judgement, confirming the reliability of parts and droplets sorting.

Real-time object detection remains a pivotal topic in the realm of computer vision. Balancing the accuracy and speed of object detectors poses a formidable challenge for both academic researchers and industry practitioners. While recent transformer-based models have showncase the prowess of the attention mechanism, delivering remarkable performance improvements over CNNs, their computational demands can hinder their effectiveness in real-time detection tasks. In this paper, we elect to use YOLOX as our robust starting point and introduce a series of effective enhancements, culminating in a new high-performance detector named YOLOAX. To further exploit the power of the attention mechanism, we devise multi-dimensional attention-based modules that activate CNNs, emphasizing the most pertinent regions and bolstering the capacity to learn the most informative image representations from feature maps. Moreover, we introduce a novel leading label assignment strategy called STA, along with a groundbreaking loss function named GEIOU Loss, to further refine our detector's performance. We provide extensive ablation studies on the COCO and PASCAL VOC 2012 detection datasets to validate our proposed methods. Remarkably, our YOLOAX is trained solely on the MS-COCO dataset from scratch, without leveraging any prior knowledge, which achieves an impressive 54.2% AP on the COCO 2017 test set while maintaining a real-time speed of 72.3 fps, surpassing YOLOX by a significant margin of 3.0% AP. Our source code and pre-trained models are openly accessible at https://github.com/KejianXu/yoloax.

Earth observation satellites can capture images of specific areas in Earth's orbit based on user requirements. Despite the high demand for satellite imagery, satellites remain a scarce resource. When there are many observation tasks that are large and dense, they may interfere with each other due to satellite mobility. To address this issue, a multi-satellite scheduling algorithm based on a task merging mechanism has been proposed. This paper proposes a two-stage approach to the problem: task merging phase and merging task scheduling phase. The task merging phase introduces two methods based on Mean Shift and Complete Graph to generate the merging task set. In the merging task scheduling phase, a multi-satellite scheduling algorithm based on merging tasks is employed to solve the problem. Finally, certain measurement experiments suggest the effectiveness of the algorithm.

The planar cell polarity (PCP) of epithelial ciliated cells is essential for effective mucociliary clearance (MCC) in the sinonasal mucosa. We hypothesize that MCC coordination is impaired in nasal polyp (NP) mucosae due to suppressed expression of a series of CPLANE (ciliogenesis and planar cell polarity effector) complex proteins in chronic rhinosinusitis (CRS) patients. To inves-tigate this hypothesis, we subjected sinonasal mucosal samples to live video recording to measure mucociliary transport velocity (MCTV) and scanning electron microscopy to evaluate surface morphology. The expression and distribution of a panel of PCP proteins, e.g. WDPCP and FUZ, were investigated in relation to inflammatory cytokine levels and clinical features. The mean MCTV of NP mucosae was significantly lower than that of the inferior turbinate mucosae. The CRS group with NPs (CRSwNP group) (n=28) showed increased expression of IL-13 and CCL26 mRNA compared to CRS patients without NPs (n=25) and controls (n=30). WDPCP and FUZ mRNA levels were significantly decreased in NP mucosae compared to ethmoid sinus mucosae in CRSwNP patients. WDPCP protein distribution was reduced in the cytoplasmic region of ciliated cells in CRSwNP patients. We conclude that suppression of WDPCP in ciliated cells is responsible for the impaired MCC of nasal polyps with type-2 inflammation. This mechanism might explain the decreased clearance and the potential for worsening symptoms of CRSwNP.

Remote sensing imagery is of great significance for policy decisions, especially for disaster assessment and disaster relief. To ensure the privacy and inviolability of personal buildings, the information containing these buildings must be anonymized during the remote sensing mapping process. Traditional processing methods for these targets in remote sensing mapping are mainly based on manual retrieval and image editing tools, which are inefficient. Deep learning provides a new direction for target hiding. Although the image inpainting method based on deep learning is faster than the manual method, the cost of training calculation is a disadvantage. And the element-wise product operation used in the model increases the risk of vanished or exploded gradients. We propose a Residual Attention Target Hiding (RATH) model for remote sensing target hiding based on deep learning. RATH uses residual attention modules to replace gated convolutions, reducing parameters and mitigating gradient issues. The residual attention module preserves gated convolution performance but provides an adjustable kernel size. RATH retains gated convolutions for dynamic feature selection and balances model depth and width. Furthermore, this paper modifies the contextual attention layer by adjusting the fusion process to enlarge the fusion patch size. Finally, we extend the edge-guided function to preserve the original target information and confound viewers. Ablation studies on an open dataset prove RATH’s efficiency for image inpainting and target hiding. RATH achieves state-of-the-art results with lower complexity. And it has the highest similarity for edge-guided target hiding. RATH enables robust, efficient target hiding for privacy protection in remote sensing imagery while balancing performance and complexity. Experiments show RATH's superiority over existing methods in hiding arbitrary-shaped targets.

Background/Objectives: Conventional surgery gland using the naked eye remains the standard for submandibular gland resection. Owing to its excellent automatic focus and high magnification, the ORBEYE 3D system introduces precise submandibular resection with less stress. Therefore, we examined the usefulness of the exoscope in submandibular gland resection for the first time. Methods: This retrospective study enrolled 12 patients who underwent submandibular gland resection using an ORBEYE exoscope at the Department of Head and Neck Surgery and Otorhinolaryngology at Kansai Medical University from April 2021 to March 2024. Surgical outcomes were retrospectively reviewed. Results: The mean age of the 12 patients (six females and six males) was 58.5 years (23–83 years). The final histopathology showed pleomorphic adenoma in eight cases, non-sebaceous-type lymphadenoma and carcinoma ex pleomorphic adenoma in one case each, and sialolithiasis with chronic inflammation in two cases. We performed facial artery and vein sparing in all cases except one in which level I neck dissection, including the submandibular gland, was performed. In all cases, we identified the marginal mandibular branches of the facial, hypoglossal, and lingual nerves, as well as the submandibular duct. No postoperative complications occurred in any patient. The mean operative time was 104 min (80–129 min). The mean blood volume lost was 20 mL (5–43 mL). Conclusions: Using ORBEYE in submandibular gland resection will contribute to preserving the mandibular marginal branch of the facial and lingual nerves and the facial artery and vein, and visualizing the submandibular duct, which are important structures surrounding the submandibular gland.

The demand for precise indoor localization services is steadily increasing. Among various methods, fingerprint-based indoor localization has become a popular choice due to its exceptional accuracy, cost-effectiveness, and ease of implementation. However, its performance degrades significantly as a result of multipath signal attenuation and environmental changes. In this paper, we propose an indoor localization method based on fingerprints using self-attention and long short-term memory (LSTM). By integrating a self-attention mechanism and LSTM network, the proposed method exhibits outstanding positioning accuracy and robustness in diverse experimental environments. The performance of the proposed method is evaluated under two different experimental scenarios, which involve 2D and 3D moving trajectories, respectively. The experimental results demonstrate that our approach achieves an average localization error of 1.76 m and 2.83 m in the respective scenarios, outperforming the existing state-of-the-art methods by 42.67% and 31.64%.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method Let-Net(Large kernel and attention mechanism Network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to broaden the receptive field and incorporates depthwise convolution with residual connections to reduce parameter count. Secondly, Let-Net integrates an attention mechanism to enhance the information flows in channels and spaces for more comprehensive and distinctive FV feature extraction. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

Cloud detection in remote sensing images is a crucial preprocessing step that efficiently identifies and extracts cloud-covered areas within the images, ensuring the precision and reliability of subsequent analyses and applications. Given the diversity of clouds and the intricacies of the surface, distinguishing the boundaries between thin clouds and the underlying surface is a major challenge in cloud detection. To address these challenges, an advanced cloud detection method, CloudformerV3, is presented in this paper. The proposed method employs a multi-scale adapter to incorporate dark and bright channel prior information into the model's backbone, enhancing the model's ability to capture prior information and multi-scale details from remote sensing images. Additionally, multi-level large window attention is utilized, enabling high-resolution feature maps and low-resolution feature maps to mutually focus and subsequently merge during the resolution recovery phase. This facilitates the establishment of connections between different levels of feature maps and offers comprehensive contextual information for the model's decoder. Experimental results on the GF1_WHU dataset demonstrate that the method introduced in this paper exhibits superior detection accuracy when compared to state-of-the-art cloud detection models. Furthermore, enhanced detection performance is achieved along cloud edges and with respect to thin clouds, showcasing the efficacy of the proposed method.

Quick and appropriate diagnostics and the use of intraoperative monitoring (IM) of hearing during vestibular schwannoma (VS) resection increase the likelihood of hearing preservation. During surgery, various methods of IM can be used, i.e. auditory brainstem responses (ABR), transtympanic electrocochleography (TT-ECochG) and direct cochlear nerve action potentials. The aim of the study was to evaluate the prognostic values of IM of hearing using ABR and TT-ECochG in predicting postoperative hearing preservation, as well as to evaluate relationships between them during various stages of surgery. This retrospective study presents the pre- and postoperative audiological test results and IM of hearing records (TT-ECochG and ABR) in 75 (43 women, 32 men, aged 18-69) patients with diagnosed VS. The preoperative pure tone average hearing threshold was 25.02 dB HL, while after VS resection it worsened on average by 30.03 dB HL. According to the American Academy of Otolaryngology-Head and Neck Surgery (AAO-HNS) Hearing Classification, before and after (pre/post) the surgery, there were 47/24 patients in hearing class A, 9/8-B, 2/1-C, and 17/42-D. In speech audiometry, the average preoperative speech discrimination score at an intensity of 60 dB SPL was 70.93%, and after VS resection it worsened to 38.93%. The analysis of electrophysiological tests showed that before the tumor removal the I-V ABR interlatencies was 5.06 ms, and after VS resection it was 6.43 ms. The study revealed correlations between worse postoperative hearing and changes in intraoperatively measured ABR and TT-ECochG. IM of hearing is very useful in predicting postoperative hearing in VS patients and increases the chance of postoperative hearing preservation in these patients.

Ménière's disease (MD) has an unclear cause. The microvascular dysregulation of the inner ear has been increasingly pointed as a potential contributor. This study investigates the prevalence of cardiovascular risk factors (CVRFs) in MD patients compared to those with posterior circulation cerebral infarction (POCI). CVRFs like hypertension, diabetes, dyslipidemia, obesity, coronary heart disease, and smoking were assessed in both MD and POCI patients. Brain MRI identified POCI etiology as "small vessel occlusion" (SVO) or "other etiology" (OE). The study included 64 MD and 84 POCI patients. Compared to MD, POCI OE showed a higher prevalence of CVRFs across various age groups, including hypertension, diabetes, dyslipidemia, and smoking. Notably, the odds of having POCI OE were significantly higher for individuals with hypertension and smoking. On the other hand, POCI SVO showed similar prevalence of CVRFs compared to MD. This study reveals no significant difference in CVRF prevalence between MD and smaller vessel POCI. However, a clear distinction emerges when comparing MD to POCI with involvement of larger blood vessels. Further research is needed to confirm these findings and explore potential shared risk factors between POCI (SVO) and MD.

Speech Emotion Recognition (SER) is an interesting and difficult problem to handle. In this paper, we deal with it through the implementation of deep learning networks. We have designed and implemented six different deep learning networks, a Deep Belief Network (DBN), a simple deep neural network (SDNN), a LSTM network (LSTM), a LSTM network with the addition of an attention mechanism (LSTM-ATN), a Convolutional neural network (CNN), and a Convolutional neural network with the addition of an attention mechanism (CNN-ATN), having in mind, apart from solving the SER problem, to test the impact of attention mechanism to the results. Dropout and Batch Normalization techniques are also used to improve the generalization ability (prevention of overfitting) of the models as well as to speed up the training process. The Surrey Audio-Visual Expressed Emotion database (SAVEE), and the Ryerson Audio-Visual Database (RAVDESS) database were used for training and evaluation of our models. The results showed that networks with the addition of the attention mechanism did better than the others. Furthermore, they showed that CNN-ATN was the best among tested networks, achieving an accuracy of 74% for the SAVEE and 77% for the RAVDESS dataset, and exceeded existing state-of-the-art systems for the same datasets.

In the past decade, it has been discovered that intestinal flora can influence various organ-specific cancers by altering the body's energy balance, increasing obesity, synthesizing genetic toxins and small signaling molecules, initiating and modulating immune responses, and metabolizing indigestible dietary components, exogenous substances, and drugs. In this review, we will focus on elucidating the role of gut flora based on its molecular mechanisms and its potential therapeutic implications in head and neck tumors in the near future.

The study evaluated the regenerative responses of the lacrimal functional unit (LFU) after Lacrimal Gland (LG) ablation. The LG of Wistar rats were submitted to G1) partial LG ablation, G2) partial ablation and transplantation of an allogeneic LG, or G3) total LG ablation, (n=7-10/group). The eye wipe test, slit-lamp image, tear flow, and histology were evaluated. RT-PCR analyzed inflammatory and proliferation mediators. The findings were compared to naïve controls after 1 and 2 months (M1 and M2). G3 presented increased corneal sensitivity, and the 03 groups have shown corneal neovascularization. Histology revealed changes in LG, and corneal inflammation. In the LG, there was an increase in MMP-9 mRNA of G1 and G2 at M1 and M2 and RUNX-1 at M1 and M2 in G1 and RUNX-3 mRNA at M1 in G1, and in G2 at M2. TNF-α mRNA rose in the corneas of G1 and G2 at M2. There was an increase in the IL-1β mRNA in the Trigeminal Ganglion of G1 at M1. Without changes in tear flow or evidence of LG regeneration, LG ablation or grafting are unreliable models for dry eye or LG repair in rats. The surgical manipulation extended inflammation to the LFU.

Addressing real-time aircraft target detection in microsatellite-based visible light remote sensing video imaging requires considering the limitations of imaging payload resolution, complex ground backgrounds, and the relative positional changes between the platform and aircraft. These factors lead to multi-scale variations in aircraft targets, making high-precision real-time detection of small targets in complex backgrounds a significant challenge for the detection algorithms. Hence, this paper introduces a real-time aircraft target detection algorithm for remote sensing imaging using an improved lightweight attention mechanism that relies on the YOLOv7 framework (SE-CBAM-YOLOv7). The proposed algorithm replaces the standard convolution (Conv) with a lightweight convolutional SEConv to reduce the computational parameters and accelerate the detection process of small aircraft targets, thus enhancing real-time onboard processing capabilities. Besides, the SEConv-based SPPCSPC (Spatial Pyramid Pooling and Connected Spatial Pyramid Convolution) module extracts image features. It improves detection accuracy while the feature fusion section integrates the CBAM hybrid attention network, forming the CBAMCAT module. Furthermore, it optimizes small aircraft target features in channel and spatial dimensions, improving the model's feature fusion capabilities. Experiments on public remote sensing datasets reveal the proposed SE-CBAM-YOLOv7 improves detection accuracy by 3% and mAP value by 4.2% compared to YOLOv7, significantly enhancing the detection capability for small-sized aircraft targets in satellite remote sensing imaging.

One of the most crucial elements in deeply understanding humans on a psychological level is manifested through facial expressions. The analysis of a human behavior can be informed by their facial expressions, making it essential to employ indicators such as expression (Expr), valence-arousal (VA), and action units (AU). In this paper, we introduce the method proposed in the Challenge of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW) at CVPR 2024. Our proposed method utilizes the multi-modal Aff-wild2 dataset, which is splitted into spatial and audio modalities. For the spatial data, we extract features using a SimMiM model that was pre-trained on a diverse set of facial expression data. For the audio data, we extract features using a WAV2VEC model. To fusion the extracted spatial and audio features, we employed the cascaded cross-attention mechanism of a transformer.

The adapted Posner spatial cue-target paradigm was used to explore the relationship between exogenous temporal attention caused by rhythm and endogenous and exogenous spatial attention. The study was divided into two experiments. In Experiment 1, 33 participants used arrow cues to orient endogenous spatial attention and rhythm to orient exogenous temporal attention. In Experiment 2, with 29 participants, exogenous spatial attention was directed by highlighting the cue box. Exogenous temporal attention was directed by rhythm. Experiment 1 indicated that RTs were faster for attended targets than the unattended. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. RTs were faster for late compared to synchrony. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was not significant. Experiment 2 demonstrated that exogenous spatial attention only exhibited IOR under early four stimulus repetitions. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was significant. The results indicated that rhythmic temporal attention supported foreperiod effects. Exogenous temporal attention and endogenous spatial attention independently affect behavior, while exogenous temporal attention and exogenous spatial attention mutually influenced behavior.

Viral co-infections, where a host is infected by multiple viruses simultaneously, are common in the human population. Human viral co-infections can lead to complex interactions between viruses and the host immune system, affecting the clinical outcome and posing challenges for treatment. Understanding the types, mechanisms, impacts, and identification methods of human viral co-infections is crucial for the prevention and control of viral diseases. In this review, we first introduce the significance of studying human viral co-infections and summarize the current research progress and gaps in this field. We then classify human viral co-infections into four types based on the pathogenic properties and species of the viruses involved. Next, we discuss the molecular mechanisms of viral co-infections, focusing on virus-virus interactions, host immune responses, and clinical manifestations. We also summarize the experimental and computational methods for identifying viral co-infections, emphasizing the latest advances in high-throughput sequencing and bioinformatics approaches. Finally, we highlight the challenges and future directions in human viral co-infection research, aiming to provide new insights and strategies for the prevention, control, diagnosis, and treatment of viral diseases. This review provides a comprehensive overview of the current knowledge and future perspectives on human viral co-infections, and underscores the need for interdisciplinary collaborations to address this complex and important topic.

The normal growth and development of skeletal muscle is essential for the health of the body. The regulation of skeletal muscle by intestinal microorganisms and their metabolites has been continuously revealed. Acetate is the predominant short-chain fatty acid synthesized by gut microbiota through the fermentation of dietary fiber, however, the underlying molecular mechanisms governing the interaction between acetate and skeletal muscle during rapid growth stage remain to be further elucidated; Here, specific pathogen-free (SPF) mice, germ-free (GF) mice, and germ-free mice supplemented with sodium acetate (GS) were used to evaluate the effects of acetate on skeletal muscle growth and development of young mice with gut microbiota deficiency; We found the concentration of serum acetate, body mass gain, succinate dehydrogenase activity and expression of myogenesis maker gene of skeletal muscle in the GS group was higher than GF group following sodium acetate supplement. Furthermore, the transcriptome analysis revealed that acetate activated biological processes regulating skeletal muscle growth and development in GF group that are inhibited due to gut microbiota deficiency. In vitro experiment, we proved that acetate up-regulated Gm16062 to promote skeletal muscle cell differentiation; Overall, our findings proved that acetate promote skeletal muscle growth and development in young mice via increase Gm16062 expression.

The detection accuracy of bridge superficial defect using the deep neural network approach decreases significantly under light variation and weak texture condition. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network-attention-YOLO (DAC-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s-1.

Underwater image processing faces significant challenges due to the absorption and scattering of light as it travels through water. A self-supervised learning network based on the self-attention mechanism is proposed for underwater visual applications in this paper. The goal is to improve the effectiveness and stability of feature extraction from underwater images. By incorporating self-attention mechanism, the sensitivity of the original network architecture to degraded features of blurred underwater images is enhanced. The network proposed in this paper is trained using transfer learning and evaluated on various underwater image datasets. With distributive, quantitative, and qualitative advantages compared with other methods, experimental results have demonstrated that the algorithm presented shows a slighter decline in feature extraction ability for blurred images as the turbidity of water increases.

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and patho-logical detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse at-tention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edge features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy re-duces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation tech-niques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare profes-sionals.

Focusing on the problem of identifying and classifying aero-engine models, this paper measures the infrared spectrum data of aero-engine hot jets using a telemetry Fourier transform infrared spectrometer. Simultaneously, infrared spectral data sets with the six different types of aero-engines are created. For the purpose of classifying and identifying infrared spectral data, a CNN architecture based on the continuous wavelet transform peak seeking attention mechanism (CWT-AM-CNN) is suggested. This method calculates the peak value of middle wave band by continuous wavelet transform, and the peak data is extracted by the statistics of the wave number locations with high frequency. Attention mechanism is used for the peak data, and the attention mechanism is weighted to the feature map of the feature extraction block. The training set, vali-dation set and prediction set are divided in the ratio of 8:1:1 for the infrared spectral data sets. For three different data sets, CWT-AM-CNN proposed in this paper is compared with the classical classifier algorithm based on CO2 feature vector and the popular AE, RNN and LSTM spectral processing networks. The prediction accuracy of the proposed algorithm in the three data sets is as high as 97%, and the lightweight network structure design not only guarantees high precision, but also has a fast running speed, which can realize the rapid and high-precision classification of the infrared spectral data of the aero-engine hot jets.

Compressed Sensing (CS) MRI has shown great potential in enhancing time efficiency. Deep learning techniques, specifically Generative Adversarial Networks (GANs), have emerged as potent tools for speedy CS-MRI reconstruction. Yet, as the complexity of deep learning recon-struction models increases, this can lead to prolonged reconstruction time and challenges in achieving convergence. In this study we present a novel GAN-based model that delivers superior performance without escalating model complexity. Our generator module, built on the U-net architecture, incorporates dilated residual (DR) networks, thus expanding the network's receptive field without increasing parameters or computational load. At every step of the downsampling path, this revamped generator module includes a DR network, with the dilation rates adjusted according to the depth of the network layer. Moreover, we have introduced a channel attention mechanism (CAM) to distinguish between channels and reduce background noise, thereby fo-cusing on key information. This mechanism adeptly combines global maximum and average pooling approaches to refine channel attention. We conducted comprehensive experiments with the designed model using public domain MRI datasets of the human brain. Ablation studies af-firmed the efficacy of the modified modules within the network. Compared to other relevant models, our proposed model exhibits exceptional performance, achieving not only excellent sta-bility but also outperforming other networks in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The model presents a promising pathway for enhancing the efficiency and quality of CS-MRI reconstruction.

Nowadays, Multi-needle electrospinning has used to be an efficient method for producing nanofiber membranes. But in the process, the fluctuation errors in electrospinning fluid flow rate have directly influence the membrane quality, which bringing instability and still have not been solved yet. For finding out the solution to the inaccurate flow control in multi-needle, it is necessary to develop a multi-stage flow runner spinneret for large-scale production of nanofiber membrane. At first, the paper uses the finite element software COMSOL to numerically simulate the polymer flow in the runner of spinneret. Based on it, the velocity field distribution curve was draw and the velocity instability coefficient of the polymer flow was attained, which are providing theoretical guidance for the optimal design of spinneret. Next, the response surface analysis method (RSM) was used to establish a regression model between the average diameter of the nanofiber membrane and the process parameters. Then, above regression model used to perform variance data processing between the average diameter and the process parameter configuration. After that, the 2D and 3D response surface profiles and the significance analysis were completed. Finally, the stability of the nanofibers production was improved, which attained the optimal adjustment of process configuration in multi-needle electrospinning.

Purposes: To provide abdominal contrast-enhanced MR image synthesis, we developed an image gradient regularized multi-modal multi-discrimination sparse-attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. Methods: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural-similarity-index (SSIM), and mean-squared-error (MSE). A Turing test and experts’ contours evaluated the image synthesis quality. Results: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values <0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90, compared to the inter-operator DICE of 0.91. Conclusion: We demonstrated the function of a novel multi-modal MR image synthesis neural network, GRMM-GAN, for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Speech emotion recognition is a critical component for achieving natural human-robot interaction. The modulation-filtered cochleagram is a feature based on auditory modulation perception, which contains multi-dimensional spectral-temporal modulation representation. In this study, we propose an emotion recognition framework that utilizes a multi-level attention network to recognize emotions from the modulation-filtered cochleagram. The channel-level attention and spatial-level attention modules are used to capture emotional saliency maps of channel and spatial feature representations from the 3D convolution feature maps, respectively. Furthermore, the temporal-level attention module captures significant emotional regions from the concatenated feature sequence of the emotional saliency maps. Our experiments on the IEMOCAP dataset demonstrate that the modulation-filtered cochleagram significantly improves the prediction performance of categorical emotion compared to other evaluated features. Moreover, our emotion recognition framework achieves a better unweighted accuracy of 71% in categorical emotion recognition than several existing approaches in the experiments. In summary, our study demonstrates the effectiveness of the modulation-filtered cochleagram in speech emotion recognition, and our proposed multi-level attention framework provides a promising direction for future research in this field.

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

The unstable international economic situation is reflected in the supply chain stress, lack or increased cost of some raw materials, fuel or semi-finished products is forcing organizations to perform new optimization initiatives in the utilization of their equipment and assets pointed to obtain the maximum value from them, while maintaining and even improving the quality of their products. The achievement of these objectives involves the reduction or minimization of equipment downtime to maintain the advantage over their competitors and ensure the organization's competitiveness. The intelligent maintenance system (IMS) provides adequate support for decision-making related to equipment maintenance, since poor maintenance results in unplanned stoppages, with the consequent additional cost and increased customer dissatisfaction, and an over-maintenance can result in an additional labor cost, time and the replacement of parts that are in good conditions. The utilization of new tools and technologies introduced by Industry 4.0 offers multiple opportunities for enhancement through communication and computerized data processing, aiming to improve the maintainability of a hydrogen compressor using neural networks based on attention mechanisms combined with linear regression.

Abstract: Ovarian cancer (OC) ranks as the fifth most common cancer among women in the United States and globally, posing a significant health threat. Reactive oxygen species (ROS) have emerged as critical factors in the pathophysiology of this malignancy. ROS, characterized by their instability due to an unpaired electron, are involved in essential cellular functions and play a crucial role in the immune response under normal physiological conditions. However, an imbalance in ROS homeostasis, leading to excessive ROS production, results in oxidative stress (OS), which can cause indiscriminate damage to cellular structures and contribute to the pathogenesis of specific diseases, including OC. OC is primarily classified based on the originating cell type into epithelial, stromal, and germinal tumors, with epithelial tumors being the most prevalent. Despite advancements in medical technology, early detection of OC remains challenging, often leading to delayed treatment initiation. Current therapeutic approaches include surgical excision of tumor tissue, radiotherapy and chemotherapy. While these treatments are effective in early-stage OC, high mortality rates and frequent relapse underscore the urgent need for novel diagnostic and therapeutic strategies. This review aims to elucidate the role of ROS in OC, emphasizing the potential for developing innovative diagnostic tools and treatments that target ROS-mediated pathways. Given the critical impact of early detection and effective treatment, advancing our understanding of ROS in the context of OC could significantly enhance patient outcomes.

Parkinson’s Disease (PD) is a neurodegenerative disorder characterized by motor and non-motor impairment with various implications on patients’ quality of life. Since currently available therapies are only symptomatic, identifying individuals with prodromal, preclinical or early-stage PD is crucial, as they would be ideal candidates for future disease-modifying therapies. Our analysis aims to develop a robust model for accurate PD detection using accelerometer data collected from PD and non-PD individuals with mild or no tremor during phone conversations. An open-access dataset comprising accelerometer recordings from 22 PD patients and 11 healthy controls (HC) was utilized. The data were pre-processed to extract relevant time, frequency and energy-related features, and a Bidirectional Long Short-Term Memory (Bi-LSTM) model with attention mechanism was employed for classification. The performance of the model was evaluated using 5-fold cross-validation, and metrics of accuracy, precision, recall, specificity, and f1-score were computed. The proposed model demonstrated high accuracy (98%), precision (99%), recall (98%), specificity (96%), and f1-score (98%) in accurately distinguishing PD patients from HC. Our findings indicate that the proposed model outperforms existing approaches and holds promise for detection of PD with subtle symptoms, like tremor, in the wild. Such symptoms can present in the early or even prodromal stage of the disease, and appropriate mobile-based applications may be a practical tool in real-life settings to alert individuals at risk to seek medical assistance or give patients feedback in monitoring their symptoms.

Since the discovery of the Coronavirus disease 2019 (COVID-19) outbreak, a vast majority of studies have been carried out that confirmed the worst outcome of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in people with preexisting health conditions, including diabetes, obesity, hypertension, cancer, and cardiovascular diseases. Likewise, diabetes itself is one of the leading causes of global public health concerns that impose a heavy global burden on public health as well as socio-economic development. Both diabetes and SARS-CoV-2 infection have their independent ability to induce the pathogenesis and severity of multi-system organ dysfunction, while the co-existence of these two culprits can accelerate the pathophysiology and magnify the severity of the diseases. However, the exact pathophysiology of multi-system organ failure in diabetic patients after SARS-CoV-2 infection is still obscure. This review summarized the organ-specific possible molecular mechanisms of SARS-CoV-2 and diabetes-induced pathophysiology of several diseases of multiple organs, including the lungs, heart, kidney, brain, eyes, gastrointestinal system, and bones, and subsequent manifestation of multi-system organ failure.

Tinnitus is a common phantom auditory percept, believed to be related to plastic changes in the brain due to hearing loss. However, tinnitus can also occur in absence of any clinical hearing loss. Then, since there is no hearing loss, the mechanisms that drive plastic changes remain largely enigmatic. Previous studies showed subtle differences in sound-evoked brain activity associated with tinnitus in subjects with tinnitus and otherwise, normal hearing, but the results are not consistent across studies. Here, we aim to investigate those differences using monaural rather than binaural stimuli. Sound-evoked responses were measured using functional magnetic resonance imaging (MRI) in participants with and without tinnitus. All participants had clinically normal audiograms. The stimuli were pure tones with frequencies between 353 and 8000 Hz, presented monaurally. A Principal Component Analysis (PCA) of the response in the auditory cortex revealed no difference in tonotopic organization, which confirmed earlier studies. A GLM analysis showed hyperactivity in the lateral areas of the bilateral auditory cortex. Consistent with the tonotopic map, this hyperactivity mainly occurred in response to low stimulus frequencies. This may be related to hyperacusis, which was associated with tinnitus found in the parahippocampus. This may reflect an interference between tinnitus and spatial orientation.

With the recent advances in Machine Learning (ML), several models have been successfully applied to financial and accounting data to predict the likelihood of companies’ bankruptcy. However, time series have received little attention in literature with a lack of studies on the application of Deep Learning sequence models as Recurrent Neural Networks (RNN) and the recent Attention-based models in general. In this research work, we investigated the application of Long Short Term Memory (LSTM) networks to exploit time series of accounting data for bankruptcy prediction. The main contributions of our work are the following: a) we have proposed a Multi-head LSTM that models each financial variable in a time window independently and compared it with a single-input LSTM and other traditional ML models. The Multi-head LSTM outperforms all the other models; b) We identify the optimal time series length for bankruptcy prediction to be equal to 4 years of accounting data; c) We made public the dataset we used for the experiments that include data from 8262 different public companies in the American stock market generated in the period between 1999-2018. Furthermore, we prove the efficacy of the Multi-head LSTM models in terms of lower false positives and better division of the two classes.

Land cover mapping provides spatial information on the physical properties of the Earth’s surface, for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems such as destruction of important wetlands/forests, and loss of fish and wildlife habitats. This has made land cover mapping one of the most widespread application areas in remote sensing computational imaging. However, due to the differences between modalities in terms of resolutions, content, and sensors, integrating complementary information that multi-modal remote sensing imagery exhibits into a robust and accurate system still remains challenging, and classical segmentation approaches generally do not give satisfactory results for land cover mapping. In this paper, we propose a novel dynamic deep network architecture, AMM-FuseNet, that promotes the use of multi-modal remote sensing images for the purpose of land cover mapping. The proposed network exploits the hybrid approach of the Channel Attention mechanism and Densely Connected Atrous Spatial Pyramid Pooling (DenseASPP). In the experimental analysis, in order to to verify the validity of the proposed method, we test AMM-FuseNet applied to four datasets whilst comparing it to the 6 state-of-the-art models of DeepLabV3+, PSPNet, UNet, SegNet, DenseASPP, and DANet. In addition, we also demonstrate the capability of AMM-FuseNet under minimal training supervision (reduced number of training samples) compared to the state-of-the-art, achieving less accuracy loss even for the case with 1/20 of the training samples.

Measuring pulmonary nodules accurately can help with early diagnosis of lung cancer, which can improve a patient’s chances of survival. Many methods for segmenting nodules have been developed, but they all rely on input from radiologists in the form of a 3D volume of interest (VOI) or use a constant region of interest (ROI) and only consider the presence of nodule within the given VOI. These approaches limit the networks’ ability to detect nodules outside the given VOI and can also include unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation by using 2D region of interest (ROI) inputted from radiologist or computer-aided detection (CADe) system. Particularly, we design a dual-encoder-based hard attention network (DEHA-Net) which incorporates the full slice of thoracic computed tomography scan along with the ROI mask to produce an accurate segmentation mask of lung nodule in the given slice. The proposed architecture exploits the adaptive region of interest (A-ROI) algorithm to automatically investigates the penetration of lung nodule into surrounding slices while eliminating the need to drawing separate ROIs in each slice. Further, the framework performs the multi-view analysis, i.e., in sagittal and coronal views, to improve the segmentation performance. The proposed scheme has been rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset and an extensive analysis of results have been performed. The quantitative analysis shows that the proposed method not only improves the existing state-of-the-art in term of dice score but also, significantly robust against the different types, shape and dimensions of lung nodules.

Prostate cancer is the second leading cause of death in males in America, with advanced prostate cancers exhibiting a 5-year survival rate of only 32%. Castration-resistance is often developed during the course of treatment, though its influences require further understanding. This study explores the human microbiome for its implications in castration-resistance and metastasis in prostate cancer. RNA sequencing data was downloaded for bone and soft tissue biopsies of patients with metastatic castration-resistant prostate cancer. These sequences were mapped to bacterial sequences to yield species-level abundance approximations. Numerous species were found to correlate to the expression of known markers of castration-resistance, including AR, PI3K, and AKT. Castration-resistance-associated signaling pathways were also enriched with these species, including PI3K-AKT signaling and endocrine resistance. For their implications in cancer aggression and metastasis, cancer stem cell markers were further explored for relation to these species. EGFR and SLC3A2 were widely downregulated with greater abundance of most species. Our results suggest that the microbiome is heavily associated with castration-resistance and stemness in prostate cancer. By considering the microbiome’s importance in these factors, we may better understand the highly aggressive and highly invasive nature of prostate cancer, allowing for needed improvement in the treatment of this disease.

：Non-Euclidean data, such as social networks, and citation relationships between documents, has node information and structural information. Graph Convolutional Network(GCN) can automatically learn node features and association information between nodes. The core ideology of the graph convolutional network is to aggregate node information by using edge information, thereby generating a new node feature. In the process of updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node, the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the Adaptive Attention Mechanism(AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution(MHGC). Finally, we adopt cross-entropy(CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on AAM, MHGC and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). Experiments show that the classification accuracy has achieved outstanding performances on Cora, Citeseer and Pubmed datasets.

To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.

Purpose: Early glottic cancer is a highly curable malignancy. Disease control is achieved by resec-tion or external beam radiation with similar long-term results according survival. Surgery is predominantly performed by transoral endoscopic approach, due to reduced complication rates when compared to open cordectomy. Open cordectomy might still be warranted in cases of inad-equate surgical accessibility. Aim of the present study was to compare endoscopic versus open approach in relation to complications and outcome in an up-to-date patient group. Methods: 219 patients underwent primary tumor resection in early glottic cancer (UICC stages I-II). 168 opera-tions were performed endoscopically, 51 operations were open transcervical cordectomies. We compared survival data with non-parametric methods and functional outcome according to need of tracheostomy, feeding tube and voice functional outcome following ELS protocol. Results: There were no significant differences in overall survival (OS). 2 years OS after endoscopic surgery was 90.5% vs 95.3% after transcervical resection. As expected, OS in T1b and T2 tumors was worse than in T1a tumors. We found a statistically significant difference in disease free survival (DFS) within the T1a and T1b/T2 group (Log rank test: p=0.006) but no relevant difference be-tween the two surgical modalities, even when the data was stratified by T-categories performing a Cox regression (hazard ratio 1.21, p=0.712). Patients who underwent open surgery had a sig-nificantly worse peri- and postoperative course with longer hospital stay, higher frequency of tracheotomies and longer need for nasogastric tubes. Functional results were comparable within the two patient groups while higher tumor size / stage was an unfavorable predictor for voice re-habilitation. Conclusion: Open cordectomy leads to more complications but offers comparable oncological and functional outcome when compared to transoral endoscopic approach in early glottic cancer. Open surgery therefore continues to be a valid treatment option when endoscopic resection is not possible.

Multimodal emotion classification (MEC) involves analyzing and identifying human emotions by integrating data from multiple sources, such as audio, video, and text. This approach leverages the complementary strengths of each modality to enhance the accuracy and robustness of emotion recognition systems. However, one significant challenge is effectively integrating these diverse data sources, each with unique characteristics and levels of noise. Additionally, the scarcity of large, annotated multimodal datasets in Bangla limits the training and evaluation of models. In this work, we unveiled a pioneering multimodal Bangla dataset, MAViT-Bangla (Multimodal Audio Video Text Bangla dataset). This dataset, comprising 1002 samples across audio, video, and text modalities, is a unique resource for emotion recognition studies in the Bangla language. It features emotional categories such as anger, fear, joy, and sadness, providing a comprehensive platform for research. Additionally, we developed a framework for emotion recognition that employs a cross-modal attention mechanism among unimodal features. This mechanism fosters the interaction and fusion of features from different modalities, enhancing the model’s ability to capture nuanced emotional cues. The effectiveness of this approach was demonstrated by achieving an F1-score of 0.64, a significant improvement over unimodal methods.

Being forced to live in an area following a catastrophic landslide may adversely impact people's mental well-being. Unprivileged communities such as Adivasis, Dalits, plantation workers, and people with low incomes in Kerala's hilly districts are forced to live in landslide-affected areas despite their fear. This paper examines the fears and concerns of landslide survivors from the marginalized sections of society from a broader framework of the political economy of mental health. This approach aligns with the assertion made by the World Health Organisation that individual factors do not solely determine mental health but are intricately linked to broader social, political, and economic circumstances. Data were collected through in-depth interviews with fatal landslide survivors and key informants [ ]. The study employed thematic data analysis from in-depth interviews of various fatal landslide survivors since 2018. The three major themes unveiled in the analysis are: 1. post-disaster fears, 2. The factors that triggered fear and concern and 3. Socio-economic marginality and mental health. The study asserts that individuals who are poor and unprivileged are highly susceptible to mental health issues associated with landslides.

With the development of deep learning, several Graph Neural Networks (GNN)-based approaches have been utilized for text classification. However, GNNs encounter challenges in capturing contextual text information within a document sequence. To address this, a novel text classification model RB-GAT is proposed by combining RoBERTa-BiGRU embedding and a multi-head Graph ATtention Network (GAT). First, the pre-trained RoBERTa model is exploited to learn word and text embeddings in different contexts. Second, the Bidirectional Gated Recurrent Unit (BiGRU) is employed to capture long-term dependencies and bidirectional sentence information from the text context. Next, the multi-head graph attention network is applied to analyze this information, which serves as a node feature for the document. Finally, the classification results are generated through a Softmax layer. Experimental results on three benchmark datasets demonstrate that our method can achieve an accuracy of 71.48%, 98.45%, and 80.32% on Ohsumed, R8, and MR, which is superior to the existing nine text classification approaches.

In the last decades we have experienced great social, cultural, and educational changes, spending more time performing tasks in near vision and less hours in outdoor activities, having more overexposure to digital screens, especially the youngest and increasingly from younger ages. It is common to see cases when performing tasks in near vision the posture or position of the head is not adequate, especially the youngest, being essential to have a correct posture of the head to avoid visual, muscular, or articular problems. We present a procedure to try to control the correct position of the head in real time when performing close-up activities. The aim is to detect the inclination of the head and to know if a bad position is adopted due to a visual problem or simply to inadequate visio-postural habits, warning us of the postural anomaly to correct it.

The aim of the present study was to predict the response of non-small cell lung cancer (NSCLC) patients to immune checkpoint inhibitors (ICIs) by leveraging computed tomography (CT) images using deep learning techniques. Retrospectively, 624 sequential CT images were gathered from 156 patients at Jiangsu Province Hospital, along with their clinical data. The dataset was subsequently partitioned into three groups: training (n=547), validation (n=64), and test (n=64). Moreover, an external validation cohort included 37 CT images from patients at Nanjing Pukou Peoples' Hospital, accompanied by comprehensive clinical data. An advanced Video Vision Transformer (ViViT) model incorporating global self-attention was utilized to analyse patients treated with ICIs and predict their response. The ViViT model's efficacy was evaluated using a confusion matrix and a receiver operating characteristic curve (ROC). Notably, the ViViT model demonstrated predictive prowess for ICIs response, yielding respective areas under the receiver operating characteristic curve (AUC) of 0.74 (95% CI: 0.69-0.78), 0.74 (95% CI: 0.61-0.86), 0.76 (95% CI: 0.62-0.88), and 0.69 (95% CI: 0.5-0.87) in the training, validation, test, and external validation cohorts. The present study illustrates how a deep learning model can provide a non-invasive means to predict clinical outcomes in NSCLC patients undergoing ICIs, potentially transforming personalized treatment approaches for individuals with NSCLC.

Researchers achieved high torque volume ratios in magnetorheological (MR) fluid braking devices by introducing multiple layers and multiple poles concepts. The number of magnetic poles, pole geometry and placement have a significant effect on these multi-pole MR brake performances. This research work focused on the effect of the pole head geometry in a multi-pole dual-disc MR brake for the enhancement of braking torque. The magnetic field generated by the electromagnetic coil has to penetrate through pole heads and travel orthogonally through the rotor and MR fluid layers to achieve maximum brake torque. This flow depends on the profiles of the magnetic pole head area and corresponding core dimensions. This study considered pentagon, square, hexagon, trapezoid and ellipse pole head profiles in place of the conventional circular pole and the best possible core dimensions were used for each geometry. A three-dimensional electromagnetic analysis of the MR brake is conducted to simulate the brake performance. Results showed that the hexagonal and elliptical pole heads are having better magnetic field area, magnetic intensity distribution and higher magnetic flux lines piercing through the MR fluid perpendicularly than the circular and square pole heads. An increment of 3.88% for braking torque performance is obtained, and the braking torque is significantly enhanced.

With the development of deep learning, the Super-Resolution (SR) reconstruction of microscopic images has improved significantly. However, the scarcity of microscopic images for training, the underutilization of hierarchical features in original Low Resolution (LR) images, and the high-frequency noise unrelated with the image structure generated during reconstruction process are still challenges in the Single Image Super-Resolution (SISR) field. Faced with these issues, we first collected sufficient microscopic images through Motic, a company engaged in the design and production of optical and digital microscopes, to establish a dataset. Secondly, we proposed a Residual Dense Attention Generative Adversarial Network (RDAGAN). The network comprises a generator, an image discriminator, and a feature discriminator. The generator includes a Residual Dense Block (RDB) and a Convolutional Block Attention Module (CBAM), focusing on extracting the hierarchical features of the original LR image. Simultaneously, the added feature discriminator enables the network to generate high-frequency features pertinent to the image’s structure. Finally, we conducted experimental analysis and compared our model with six classic models. Compared with the best model, our model improved PSNR and SSIM by about 1.5dB and 0.2, respectively.

An application of CO2/HCO3--free solution (Zero-CO2) did not increase intracellular pH (pHi) in ciliated human nasal epithelial cells (c-hNECs), leading to no increase in the beating frequency (CBF) or bend distance (CBD, an index of amplitude). This study demonstrated that the pHi of the c-hNECs expressing carbonic anhydrase IV (CAIV) is high (7.64), while that of the ciliated human bronchial epithelial cells (c-hBECs) expressing no CAIV is low (7.10). Upon applying Zero-CO2, an extremely high level of pHi caused the pHi, CBF and CBD to decrease, while a low level of pHi caused them to increase. The high pHi was generated by a high rate of HCO3- influx via interac-tions between CAIV and Na+/HCO3- cotransport (NBC) in c-hNECs. An NBC inhibitor (S0859) decreased the pHi and CBF, and Zero-CO2 application increased the CBF in S0859-treated c-hNECs. In conclusion, the interactions of CAIV and NBC maximize the HCO3- influx to increase the pHi in c-hNECs. This novel mechanism causes the pHi to decrease, leading to no increase in CBF and CBD in c-hNECs upon Zero-CO2 application, and appears to play a crucial role in maintaining pHi, CBF and CBD in c-hNECs periodically exposed to air (0.04% CO2) with respiration.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.

The RPL protocol is a routing protocol for low power and lossy networks. In such a network, energy is a very scarce resource; so many studies are focused on minimizing global energy consumption. End-to-end latency is another important performance indicator of the network, but existing research tends to focus more on energy consumption and ignore the end-to-end delay of data transmission. In this paper, we propose a kind of energy equalization routing protocol to maximize the surviving time of the restricted nodes so that the energy consumed by each node is close to each other. At the same time, a multi-path forwarding route is proposed based on the cache utilization. The data is sent to the sink node through different parent nodes at a certain probability, not only by selecting the preferred parent node, thus avoiding buffer overflow and reducing end-to-end delay. Finally, the two algorithms are combined to accommodate different application scenarios. The experimental results show that the proposed three improved schemes improve the reliability of the routing, extend the lifetime of the network, reduce the end-to-end delay, and reduce the number of DAG reconfiguration.

Background: The laryngeal mask airway Vision Mask (LMA VM) is a supraglottic airway device (SAD) with vision guidance system. The ideal head and neck position for direct laryngoscopy is known, but the ideal position for placing a LMA is not. The objective of this study is to evaluate and compare the optimal position for placement of a video laryngeal mask airway. Methods: This was a prospective observational, transversal and analytical study of 72 consecutive patients. In the same patient, laryngeal vision was first assessed with the head and neck in the sniffing position and then with the head in the neutral position. Procedures were filmed and performed by the same investigator. Assessment of the laryngeal view was performed using two classifications: modified Cormack-Lehane classification and Brimacombe classification. Device placement was considered adequate when the Cormack-Lehane rating was scored from 1 to 2 and the Brimacombe rating was from 2 to 4. Results: 72 patients were included in this study. In the assessment of the glottis using the Cormack Lehane classification for fiberoptic view, laryngeal visibility was adequate in 64 (88.89%) patients in the neutral position and in 65 (90,28%) patients in the sniffing position (p>0,05). In the fiberoptic view of the glottis, assessed using the Brimacombe classification, laryngeal visibility was adequate in 68 (93%) patients in the neutral position and in 69 (95%) patients in the sniffing position, (p>0,05). There was no statistically significant difference in the rate of success between the sniffing position (70 patients, 97.22% success rate) and the neutral position (67 patients, 93.06% success rate) during the first insertion attempt. Two patients required a second attempt in the sniffing position, while five patients required a second attempt in the neutral position. Conclusion: An adequate sniffing position did not result in a better glottic view than neutral position, and the number and type of additional maneuvers were equal in both positions.

Insulin-like Growth Factor 2 mRNA binding Protein 1 (IGF2BP1) is a promising candidate gene for influencing economic traits in livestock and poultry. The second intronic region of IGF2BP1 is closely related to growth traits, although the exact mechanism remains unclear. The preliminary resequencing results of goats in our laboratory demonstrated that the IGF2BP1 gene region was subject to strong selection, then we selected multiple single nucleotide polymorphisms (SNPs) to identify. Seven SNPs were located in the conserved region of the second intron, and their functions and relationship with growth traits require further clarification. This study selected 348 Nanjiang Yellow goats as experimental subjects, and chose Time of Flight Mass Spectrometer (MALDI-TOF) as the main method. Our results showed that six SNPs were significantly correlated with the growth traits of the Nanjiang yellow goat by association analysis. Among them, the rs652062749(A>G) was identified as the primary locus affecting the later stage of growth traits of Nanjiang yellow goat. Moreover, there was a strong linkage among three SNPs, and the rs638185407 (T>A) mutant type was observed to increase the luciferase activity in H293T cells extremely significantly. The TTAACT, TTCCCC, and ATCACT combination genotypes were dominant combination genotypes, which provided theoretical references for further genetic co-breeding. The results of our study demonstrate the potential role of the IGF2BP1 gene as a functional genetic marker in the breeding programs of Nanjiang Yellow goats.

This article describes the history of research and development of surface-penetrating radar, starting from the 60s in the USSR, and ending today in Russia and neighboring states formed after the collapse of the USSR. The outstanding role played in the initial period of this technology development by Prof. M.I. Finkelstein and his colleagues is highlighted. Their research had a significant impact on subsequent developments in modern Russia and the neighboring countries.

In recent years, electroencephalogram (EEG) emotion recognition has emerged as a research hotspot in the field of artificial intelligence (AI). Despite advancements in EEG-based emotion recognition, room for enhancing performance persists due to EEG signal redundancy and limitations in feature extraction, leading to inefficient models and emotional information loss. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification, and 97.69% and 98.05% in ternary classification, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

With the rapid developments that have been made in computer vision and computer technology, semantic segmentation of high-resolution images has emerged as a mainstream and challenging task. The, segmentation of water areas remains a complex task due to the similar features between water areas or between water areas and other land objects. Meanwhile, since coastlines and riverbanks are typically presented in irregular shapes, it is difficult to obtain the categories of pixels at boundaries. This paper proposed the use of a Water-Land Boundary Attention Network (WLBANet) to improve the accuracy of pixels at boundaries between water and land. This network also reinforced the performance of contextual information extraction into distinguishing between water areas and other land objects. To prove the validity of this proposed network, WLBANet was performed on the Water Land Dataset (WLD), which is also by this paper, and which contains water areas and other land objects categories. The results demonstrates that the proposed method has significant effectiveness.

The electric vehicle (EV) industry is experiencing rapid growth, accompanied by continuous advancements in charging infrastructure to satisfy the rising need for fast and reliable charging. Particularly, the focus has shifted towards EV fast charging (EVFC) and its impact on the power grid. This paper presents a comprehensive analysis and survey of scholarly literature and projects conducted in this field over the past decade. The findings highlight the rising demand for EVFC and the need to address its potential adverse effects on the power grid. However, there is a noticeable lack of clear research guidance regarding charging time. To tackle these challenges and pave the way for future solutions, extensive research on DC fast charging, ultra-fast charging, and the integration of vehicle-to-grid (V2G) systems is required. This review paper thoroughly investigates the development of fast charging technology for electric vehicles (EVs), including its advantages and comparative analyses from various perspectives. Furthermore, it delves into the advancements in DC fast charging infrastructure, emphasizing charging standards and control modes. The study also investigates different categories of battery chargers for both on-board and off-board charging. Additionally, it explores the classification of DC-DC converters in the context of DC fast charging stations, discusses control strategies for EV systems, identifies existing challenges, and outlines future trends in EV fast charging.

Background: In most cases, intra-labyrinthine schwannoma (ILS) occurs in patients with unilateral hearing deterioration or neurofibromatosis type II (NF II). The pattern of localization of these tumors is various but affects mostly the cochlea. Extirpation of the ILS, if hidden by the cochlea modiolus, is difficult under the aspect of complete removal. Therefore, a tissue removal device (TRD) was designed and tested in temporal bones. The principle of handling the new device is a pushing and pipe cleaner handling inside the cochlea. This present study aimed to describe the first in vivo experience with the newly developed TRD for removing cochlear intra-labyrinthine schwannoma. Methods: In three patients, the TRD was used for the tumor removal of ILS. In two patients with a cochlear schwannoma in combination with a cochlea implantation and one patient suffering from NF II, a cochlear schwannoma was removed with the TRD. The access was performed with a posterior tympanotomy, an enlarged round window approach, and an additional second-turn access. The device was inserted and extracted gradually from the second turn access until the rings were visible in the second turn access. By pushing and pipe cleaner handling, the tumors were removed. An MRI control was performed on the day postoperatively with a T1 GAD sequence. Results: Tumor removal with the TRD was performed in a 15-minute procedure. MRI control confirmed a complete removal on the postoperative day in both cases. Conclusion: In vivo handling of the device confirmed a straightforward handling for tumor removal. MRI scanning showed a complete removal of the tumor by the TRD.

From the existing millions of fungal species only a few cause disease. In this study, we investigated invasive fungal infections in the head and neck over a 19-year period (2005 to 2024) at a large academic healthcare system. Among 413 cases, 336 were noninvasive, and 77 were invasive. The highest incidence of invasive infections occurred in the sinonasal cavities, with a 15-fold difference compared to other sites. Most infections affected adults over 40 years old. The most common organisms were Mucorales (51%), hyaline molds (29%), and Candida (11%). Risk factors included malignancy, transplant, diabetes, and illicit drug use. Mortality was high in patients with malignancy and/or transplant. Infections affecting the mandible were usually a complication of osteoradionecrosis and were associated with coinfection of Candida and Actinomyces. At other sites, infections were rare and were usually the result of penetrating injuries or immunosuppression. Treatment typically involved a combination of antifungals and surgical procedures.

To enhance the safety of power grid operations, this study proposes a high-precision short-term photovoltaic power prediction method that integrates information from surrounding pho-tovoltaic stations and the Conv-LSTM-ATT model. In the deep learning prediction model, not only is numerical weather prediction (NWP) data from the target photovoltaic station used as input features, but also highly correlated features from nearby photovoltaic stations are incor-porated. The research begins by analyzing the correlation between irradiance and power se-quences, along with distance factors, to calculate a composite similarity index between the target and other regional photovoltaic stations. Stations with high similarity indices are then selected as data sources. Subsequently, Bayesian optimization techniques are employed to find the optimal data fusion ratios. Ultimately, using the selected data, power prediction mod-eling is conducted via the Conv-LSTM-ATT deep neural network. Experimental results con-firm the superiority of the proposed model, which demonstrates higher predictive accuracy compared to three other classical models. The data fusion strategy determined by Bayesian optimization significantly enhances prediction accuracy, reducing the root mean square error (RMSE) of the test set by 20.04%, 28.24%, and 30.94% for three weather types, respectively.

The mortality of birds resulting from collisions and electrocutions with overhead lines, such as power lines, and phone line among others, has been implicated in the decline of various avian species globally. Specifically, overhead line collisions pose a significant threat to the conserva-tion of the Canarian houbara bustard (Chlamydotis undulata fuertaventurae), an endangered sub-species endemic to the Canary Islands. This study centres on the postmortem findings of Canarian houbara bustards that have collided with overhead lines, providing insights into the post-collision outcomes for these birds. A com-plete standardized necropsy of nine Canarian houbara bustards revealed that polytrauma was the cause of death in all cases. The most notable gross lesions associated with trauma included bone fractures, soft tissue lacerations, haemorrhages, luxations, and hemocoelom, with certain body regions being more frequently affected. Histopathology, immunohistochemistry, and en-tomology analysis confirmed that numerous birds survived the initial trauma, exhibiting varia-ble survival intervals before succumbing to their injuries. We concluded that when a houbara bustard collide with an overhead line it frequently survives the initial trauma. The histopathology, immunohistochemistry, or entomologic analysis may be helpful to approximate the timing interval between trauma and death.

The learning equations of an ANN are presented, giving an extremely concise derivation based on the principle of backpropagation through the descendent gradient. Then, a reflection is developed on the dual attention network that applies the learning equations and coordinates subnetworks toward purposeful behaviors. Speculation is made on possible developments of functionalities that could provide additional skills and at the same time shed light on competencies typical of ``natural intelligence".

Background Gingivitis can develop without mechanical cleaning within three weeks. The first clinical sign is bleeding on positive probing. The accumulation of dental biofilm generates an inflammatory gingival response. In the past decade, attention has focused mainly on the interproximal areas and the use of customsized interproximal toothbrushes.The aim of the study was to evaluate the effectiveness of individualized oral hygiene education and its role in dental prevention among patients with dental problems. Methods Before treatment, patients were clinically and radiologically examined, full mouth plaque score (FMPS), full mouth bleeding score (FMBS), and bleeding on brushing (BOB) were recorded, and matrix-metalloproteinase-8 (MMP-8) was measured by using a chair-side MMP-8 measuring system. Patients in group A had gingivitis, but no periodontal damage and patients in group B had periodontal damage. Patients in both groups A and B were identified in to four subgroups based on their toothbrushing habits and the oral health education they received. The three months after initial examination, each patient was examined three more times (2, 4 and 12 weeks later). Results It was concluded that subjects in groups A1 and B1 showed significant reduction in BOB, MMP-8, FMBS and FMPS levels after two weeks. Solo Prophylaxis (A1and B1) remained as a well-constructed protocol with hte complete resolution of interdental inflammation after two weeks. Other subgroups achieved significant reductions only after 12 weeks. Conclusions BOB and MMP-8 are valuable complements in preventive dentistry, and are able to detect potential pathological processes in interproximal spaces. The clinical relevance of BOB, in addition to FMBS, FMPS and gingival inflammation can be demonstrated to patients, which may increase compliance.

(1) Background: The interplay between coronavirus disease 2019 (COVID-19) and laryngeal cancer represents a substantial challenge for both patients and healthcare. To garner information on recent mortality data for laryngeal cancer, including during the COVID-19 pandemic, we analyzed real-world data from the US Centers for Disease Control and Prevention (CDC). (2) Methods: We searched the CDC WONDER on-line database 2018-2022 using with the ICD-10 code for laryngeal cancer (C32; malignant neoplasm of larynx). We also performed a sub-analysis between genders, and across ten-year age groups. Data were analyzed with one-way analysis of variance (ANOVA) and Tukey post-hoc test. (3) Results: The trend of age-adjusted mortality ×100,000 did not change significantly between 2018-2022 (p=0.553). Males had higher age-adjusted mortality rates (M/F ratios between 4.6 and 5.0), but no significant variation was found in both genders (males: p=0.676; females: p=0.596). Although the mortality rate remained unchanged in people aged 35-84 years, the variation reached statistical significance in those aged 85 or older (p=0.004), displaying significant increase in 2021 compared to 2018 (p=0.006) and 2019 (p=0.039). (4) Conclusions: The impact of the COVID-19 pandemic on mortality for laryngeal cancer seemed to be relatively modest in the general US population. Nevertheless, closer attention must be paid to older people, in whom the unfavorable consequences of misdiagnosis or mistreating can be exacerbated.

Alzheimer’s disease (AD) and the therapies of AD with anti-amyloid1-42 (Aβ) monoclonal antibodies are associated with the vascular complications of brain edema, hemorrhage, and cerebral amyloid angiopathy (CAA) termed amyloid-related imaging abnormalities (ARIAs). The neuropathology of normal and AD brains demonstrates that monocyte/macrophages (MMs) are critical in successful brain clearance in healthy brain by up-loading, transporting, and degrading Aβ but fail degradation and clearance in AD patients by releasing Aβ into vessels at the blood-brain barrier, causing vasculitis and ARIAs. The naturally-formed epoxides (EpFAs) of polyunsaturated fatty acids (PUFA’s), including arachidonic, docosahexaenoic, and eicosapentaenoic fatty acids, may repair degradation of Aβ by regulating Aβ-degrading enzymes, inflammatory cytokines, and unfolded protein response (UPR) to endoplasmic reticulum stress in a homeostatic fashion. EpFAs are, however, degraded by the soluble epoxide hydrolase enzyme (sEH) but are protected by the sEH inhibitor (sEHI) TPPU. In the cultures of AD patients’ macrophages, TPPU with the epoxide EEQ, and the cGAS/STING inhibitor H-151 increased uptake of Aβ at 2 hours and degradation of Aβ at 24 hours. In conclusion, the soluble epoxide hydrolase inhibitor TPPU with omega-3 fatty acids and the cGAS/STING inhibitor H-151 increase Aβ uptake and degradation in macrophages of AD patients, and potentially enhancing Aβ clearance in the AD brain.

Head and neck cancers arise from mucosa lining the oral cavity, oropharynx, hypopharynx, larynx, sinonasal tract, and nasopharynx and the etiology of head and neck cancers is complex and involves many factors, among which oncogenic viruses are also enumerated. Nevertheless, this type of cancers are among the most common cancers around the world. The thorough knowledge of the pathogenesis of viral infection is needed to fully understand its impact on cancer development.

Antimicrobial peptides (AMPs) are a promising alternative to antibiotics to combat drug resistance in pathogenic bacteria. However, the development of AMPs with high potency and specificity remains a challenge, and new tools to evaluate antimicrobial activity are needed to accelerate the discovery process. As a step toward direct prediction of the experimental minimum inhibitory concentration (MIC) of AMPs, we proposed MBC-Attention, a combination of a multi-branch CNN architecture and attention mechanism. Using a curated dataset of 3929 AMP against Escherichia coli, the optimal MBC-Attention model achieved an average Pearson correlation coefficient of 0.775 and an RMSE of 0.533 (log μM) in three independent tests of 393 sequences each. This results in a 5–12% improvement in PCC and 7–13% improvement in RMSE compared with RF and SVM models. Ablation studies confirmed that both attention mechanisms contributed to performance improvement.

Attention deficit hyperactivity disorder (ADHD) is the most common childhood-onset neurodevelopmental disorder characterized by difficulty maintaining attention, impulsivity and hyperactivity. Although the cause of this disorder is still unclear, recent studies state that heredity is important in the development of ADHD. This is linked to a few comorbidities: depression, criminal behavior and anxiety. Although genetic factors play a major role in the pathogenesis of ADHD, there are also non-genetic factors, one of which would be oxidative stress (OS) that are associated with ADHD. OS is implicated in the pathogenesis of ADHD, through lower levels of antioxidant enzymes such as glutathione peroxidase (GPx), catalase (CAT), and superoxide dismutase (SOD), as well as a lower total antioxidant status (TOS) compared to control groups. Moreover, there is a close bidirectional connection between the nervous system and the intestinal microbiota, and the communication between the two systems is carried out through the gut-brain axis (GBA). A thorough review of diet, OS implications, mechanism of action, pharmacokinetics, and drug-drug interactions are reviewed here, with a special focus on treatment in adults with comorbid conditions.

In today’s fast paced, attention-demanding society, executive functions and attentional resources are often taxed. Individuals need ways to sustain and restore these resources. We first review the concepts of attention and restoration, as instantiated in Attention Restoration Theory (ART). ART emphasizes the role of nature in restoring attention. We then discuss essentials of experiments on the causal influences of nature. Next, we expand the concept of ART to include modern, designed environments. We propose a wider perspective termed attentional ecology, in which attention behavior is viewed within a larger system involving the human and their interactions over time with environmental demands. When the ecology is optimal, mental functioning can be a positive “flow” that is productive, sustainable for the individual, and sometimes creative.

Laser Photoacoustic Spectrometers (LPAS), which provide photoacoustic spectra for detecting food frauds or adulteration, and fluorescence-based systems for recognition of contamination by heavy metal ions in water are two important families of sensors for health and environmental purposes. Both sensor families require one or more low-frequency Lock-In Amplifiers (LIAs) to extract the signal of interest from background noise. In the cited applications, the required LIA frequency is quite low (up to 1kHz), and this leads to a simplification of the hardware with consequent good results in portability, economy, reduced size, weight and low-cost characteristics. The present system, called ENEA DSP Box Due, is based on a very inexpensive microcontroller proto-board and can replace four commercial LIAs, resulting in significant savings in both cost and space. Furthermore, it incorporates a dual-channel oscilloscope and a sinusoidal function generator. This article outlines the architecture of the ENEA DSP Box Due, its electrical characterization and its applications within a project concerning laser techniques for food and water safety.

Unmanned aerial vehicles (UAVs)-based communication system is a promising solution to meet coverage and capacity requirements of future wireless networks. However, UAV-enabled communications is constrained with its coverage, energy consumption, and flying regulations, and the number of works focusing on the sustainability aspect of UAV-assisted networking has been limited in the literature so far. In this paper, we propose a solution to this limitation; particularly, we design a $Q$-learning-based UAV positioning scheme for sustainable wireless connectivity considering key constraints, that are, altitude regulations, non-flight zones, and transmit power. The objective is to find the optimal position of the UAV base station (BS) and minimize the energy consumption while maximizing the number of users covered. Moreover, a weighting mechanism is developed, where the energy consumption and number of users covered can be prioritized according to network/battery conditions. The proposed Q-learning-based solution is compared to the baseline k-means clustering method, where the UAV BS is positioned at the centroid location that minimizes the cumulative distance between the UAV BS and the users. The results demonstrate that the proposed solution outperforms the baseline k-means clustering-based method in terms of the number of users covered while achieving the desired minimization of the energy consumption.

By introducing environmental mediator, for avoiding randomness in selecting indicators and subjectivity in deciding interaction path coefficients to reveal interaction mechanism among forest industry, ecology and environmental capacity, structural Pressure–State–Impact–Response (PSIR) and quantitative Structural Equation Modeling (SEM) are utilized with data on thirty–one provinces of China. We can find that: (i) forest industry has a negative influence on ecology, whereas ecology has a positive influence on industry; (ii) the destructive influence that industry has on ecology is much greater than the positive effect ecology has on industry; and (iii) environmental capacity plays a partial mediating role between industry and ecology. According to these results we can conclude that: (i) forest industry and ecology are not in a symbiotic relationship and have not reached a level of ecological security; (ii) the interaction between industry and ecology is in a period of transition from antagonistic to beneficial; and (iii) industry dominates ecology. However, we prospect the following advice: (i) methods of forest industry should be changed; (ii) new modes of industrial integration and circular economy should be developed; and (iii) the ability of the environment to sustain itself should be enhanced. The level of forest ecological security to discuss the symbiotic mechanism of industry and ecology will propose to be measured in future.

Revealing the spatial distribution mechanism of the coupling effect between soil water and salt is essential for managing saline-alkali farmland. This study utilized the multifractal method to analyze soil water and salt under varying water content levels in arid saline-alkali farmland. Soil samples were collected on the second (S1), fifth (S2), eighth (S3), eleventh (S4), and fourteenth (S5) days after a rainfall event. The findings showed that a significant decrease in soil water content, contrasting with an increase in soil salt content throughout the soil layers post-rainfall. As water content decreased, the spatial variability of soil water initially increased from S1-3 and then decreased, while the spatial variability of soil salt decreased. The spatial distribution between soil water and salt exhibited a high correlation at S3-4 (with relative water content of soil ranging from 0.52 to 0.75) due to their coupling effect. However, soil salt was unevenly leached by rainfall at high water content levels (S1-2) and precipitated at low water content levels (S5), resulting in low spatial variability correlations between soil water and salt. This study elucidated the coupling process of soil water and salt, identifying their spatiotemporal distribution mechanism in dryland agricultural areas.

Piperine, an active plant alkaloid from black pepper (Piper nigrum), has several pharmacological effects: antioxidant, anti-inflammatory and immunomodulatory, which involves inhibiting molec-ular events associated with various stages of cancer development. The aim of this study was to investigate the molecular mechanisms of action of piperine in relation to its potential anticancer effect on head and neck cancer cells. Parameters related to neoplastic potential, analysis of cyto-kine, protein and gene expression were investigated in the head and neck cancer cell lines (HEp-2 and SCC-25) treated with piperine. The results of the tests indicated that piperine modified mor-phology, inhibited viability and the formation of cell colonies. Piperine promoted genotoxicity by triggering apoptosis and cell cycle arrest in G2/M and S. A decrease in cell migration was also observed, and decreased expression of MMP2/9 genes. Piperine also reduced the expression of inflammatory molecules (PTGS2 and PTGER4), regulated the secretion of cytokines (IF-y and IL-8) and modulated the expression of ERK and p38. These results suggest that piperine exerts anti-cancer effects on tumor cells, and could be a promising natural treatment by regulating signaling pathways associated with head and neck cancer.

We propose a deep learning algorithm that directly compensates for luminance degradation owing to the deterioration of organic light emitting diode (OLED) devices to address the burn-in phenomenon of OLED displays. Conventional compensation circuits are encumbered by a high cost of development and manufacturing processes owing to their complexity. However, given that deep learning algorithms are typically mounted on a system on chip (SoC), the complexity of the circuit design is reduced, and the circuit can be reused by re-learning only the changed characteristics of the new pixel device. The proposed approach comprises deep feature generation and multi-stream self-attention, which decipher the importance of the variables, and the correlation between burn-in-related variables. It also utilizes a deep neural network that identifies the nonlinear relationship between the extracted features and luminance degradation. Thereafter, the luminance degradation is estimated from the burn-in-related variables, and the burn-in phenomenon can be addressed by compensating for the luminance degradation. The experimental results revealed that compensation was successfully achieved within an error range of 4.56%, and demonstrate the potential of a new approach that can mitigate the burn-in phenomenon by directly compensating for pixel-level luminance deviation.

As a new plant slope protection technology, living stumps can effectively improve slope stability. The current study attemptes to investigate the mechanical characteristics of the root system of living stumps and their reinforcement mechanism on slopes by carrying out a three-dimensional living stump slope modeling test. Using ABS materials, a 3D model of a living elm stump was created by 3D printing and a slope model test was carried out. The reinforcement mechanism of the living stump was studied through a combination of model testing and numerical simulation. The results indicate that, due to the presence of living stumps in the lower and middle parts of the slope, the maximum shear stress area of the soil moved to a deeper direction. The stress state of the soil around the living stump was effectively improved due to the existence of the lateral root system.Living stumps in the lower part of the slope cross the potential sliding surface and transferred the soil shear stress gradually to the root system through root-soil interaction. Moreover, the tap roots and lateral roots of living stumps form a robust spatial structure that bears the shear stress of soil together, thus increasing the stability of the slope.

This paper studies the maximum reliability of multi-hop relay UAV, in which UAV provides wireless services for remote users without direct communication link on the ground as a coded cooperative relay. In this paper, the analytical expressions of total power loss and total bit error rate are derived as reliability measures. Firstly, based on the environmental statistical parameters, a LOS probability model is proposed. Then the problem of minimizing the bit error rate of static and mobile UAVs is studied. The goal is to minimize the total bit error rate by jointly optimizing the height, elevation, power and path loss, and subject to the maximum allowable path loss con-straints, transmission power allocation constraints and UAV height and elevation constraints. At the same time the total path loss is minimized to achieve maximum ground communication cov-erage. However, the formulated joint optimization problem is non-convex and generally difficult to solve. Therefore, we decomposed the problem into two subproblems and proposed an effective joint optimization iteration algorithm. Finally, the simulation results are given, and the analysis shows that the optimal height of different reliability measures is slightly different, and using the mobility of UAVs can improve the reliability of communication performance.

Underwater image often exhibit detail blurring and color distortion due to light scattering, impurities, and other influences, obscuring essential textures and details. This presents a challenge for existing super-resolution techniques in identifying and extracting effective features, making high-quality reconstruction difficult. This research aims to innovate underwater image super-resolution technology to tackle this challenge. Initially, an underwater image degradation model was created by integrating random subsampling, Gaussian blur, mixed noise, and suspended particle simulation to generate a highly realistic synthetic dataset, thereby training the network to adapt to various degradation factors. Subsequently, to enhance the network's capability to extract key features, improvements were made based on the symmetrically structured Blind Super-Resolution Generative Adversarial Network (BSRGAN) model architecture. An attention mechanism based on energy functions was introduced within the generator to assess the importance of each pixel, and a weighted fusion strategy of adversarial loss, reconstruction loss, and perceptual loss was utilized to improve the quality of image reconstruction. Experimental results demonstrate that the proposed method achieved significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Underwater Image Quality Measure (UIQM) by 0.85 dB and 0.19, respectively, significantly enhancing the visual perception quality and indicating its feasibility in super-resolution applications.

Glioblastoma (GB) is the most aggressive and prevalent glioma within the Central Nervous System. GB exhibit a dismal 5-year survival rate (~6%) due to unfavorable prognosis and lack of viable treatment options. Therefore, novel therapies with plant-derived compounds emerge as very promising. This study aims to investigate the antitumor activity of 7α-acetoxy-6β-hydroxyroyleanone (Roy) in GB cell lines. Roy was isolated from Plectranthus hadiensis Schweinf. and its antitumor mechanism was assessed in a panel of five GB cell lines to mimic tumor heterogeneity. Metabolic activity was evaluated by Alamar Blue® assay, while cell death, cell cycle regulation, mitochondrial membrane potential, and activated caspase-3 were evaluated by flow cytometry. mRNA levels of target genes were measured by qPCR and protein expression was assessed by Western blotting. Cell uptake and impact on mitochondrial morphology were evaluated by confocal microscopy. Roy induced G2/M cell cycle arrest, mitochondrial fragmentation, and apoptosis by inhibiting the expression of anti-apoptotic proteins and increasing activated caspase-3 levels with concentration 6-9 fold lower than those of temozolomide, the first-line treatment. Roy demonstrated a robust antitumor activity against GB cells, without affecting non tumoral cells (microglia and astrocytes), being a promising natural lead compound for the development of novel chemotherapeutic approaches.

The existing methods of oil palm Fresh Fruit Bunch (FFB) evacuation from in-field to temporary collection point which typically apply medium to large tractors, often result in unexpected soil compaction. Meanwhile, smaller size equipment indicates low working capacity and unable to perform direct unloading to collection bin. This paper addresses the challenge of FFB evacuation by focusing on preventing soil compaction, increasing working capacity and enabling direct unloading to collection bin. For this purpose, a 6x6WD transporter prototype with a scissor lift mechanism was developed. With the design, the transporter could evacuate FFB in both steep mineral terrain and low ground pressure peatland, able to carry FFB with capacity of 750 kg and provide direct unloading into collection bin. The average field working capacity of the transporter was found to be 15 tons day-1. This research offers insights for future designs of medium-sized FFB transporters with advanced unloading mechanisms.

Cutaneous squamous cell carcinoma is a prevalent malignancy with a rising incidence and notably high mutational load. Exploring the genetic nuances of cSCC and investigating molecular approaches stands as a potential avenue for improving outcome in high-risk patients. This retrospective case-control study involved two cohorts of 14 patients (“discovery cohort”) and 12 patients (“validation cohort”) with cSCC located in head-neck anatomical district and diagnosed at pT2 stage. Overall, cases developed early local relapse of the disease whereas controls never re-lapsed during the entire follow-up period. Next generation sequencing (NGS) approach conducted on histological samples revealed that TP53 and CDKN2A were the most frequently mutated genes in our series. No specific mutation was identified as potential prognostic or therapeutic targets. Controls exhibited a tendency toward a higher mutational rate compared to cases. It is possible that an increased number of mutations could prompt the cSCC to expose more antigens, becoming more immunogenic and facilitating the recognition by the immune system. This could enhance and sustain immunological response, potentially preventing future recurrences.

A method for accurately determining the chemical composition of deposits at the bottom of pores during the electrocoloring (e-coloring) of aluminum anodic oxide (AAO) layers in tin-based solutions is developed. The aluminum samples were AC e-colored after DC sulfuric anodization. Free-standing, tin e-colored aluminum oxide film was obtained by selective dissolution of the metallic aluminum from the AAO in copper chloride solution to access the deposit directly at the bottom of the pore. This allowed us to take XPS analysis directly from the deposits at pore bottoms without any interference from the base material or insulating barrier layer. The results revealed the presence of a mixture of tin oxide and metal in the deposits, which were richer in oxide content. Furthermore, a cyclic voltammetry experiment mimicking real polarization conditions during AC conditions was optimized and used to gain a deeper understanding of the electrochemical reactions that occur during AC electrocoloring. The comparison of CV results in tin-free and tin-containing electrolytes indicated that the tin deposited during a cathodic cycle is oxidized in the anodic cycle. The formation of tin based deposits radically changed the CV behavior. The XPS and cyclic voltammetry results consistently show that the deposits formed during e-coloring comprised a mixture of metallic and oxidic tin species richer in oxide content.

With the advancement of technology, signal modulation types are becoming increasingly diverse and complex. The phenomenon of signal time-frequency overlap during transmission poses significant challenges for the classification and recognition of mixed signals, including poor recognition capabilities and low generality. This paper presents a recognition model for fine-grained analysis of mixed signal characteristics, proposing a Geometry Coordinate attention mechanism and introducing a low-rank bilinear pooling module to more effectively extract signal features for classification. The model employs a residual neural network as its backbone architecture and utilizes the Geometry Coordinate attention mechanism for time-frequency weighted analysis based on information geometry theory. This analysis targets multiple-scale features within the architecture, producing time-frequency weighted features of the signal. These weighted features are further analyzed through a low-rank bilinear pooling module, combined with the backbone features, to achieve fine-grained feature fusion. This results in a fused feature vector for mixed signal classification. Experiments were conducted on a simulated dataset comprising 39,600 mixed signal time-frequency plots. The model was benchmarked against a baseline using a residual neural network. The experimental outcomes demonstrated an improvement of 9% in the exact match ratio and 5% in the Hamming score. These results indicate that the proposed model significantly enhances the recognition capability and generalizability of mixed signal classification.

In recent years, graph neural networks (GNNs) have become a promising method for analyzing data structured in graph format. By considering connections between entities in a graph, GNNs are able to extract valuable insights. One notable variation of GNN is the graph attention network (GAT), which employs the attention mechanism and has demonstrated promising performance in various applications. However, its ability to incorporate feature information from nodes beyond the immediate neighborhood is limited, leading to degraded performance on heterophilic data. To address this limitation, this thesis proposes a novel attention-based model, namely the Directional Graph Attention Network (DGAT). This model combines the feature-based attention with the global directional information extracted from the graph topology, as inspired by the Directional Graph Network (DGN). A new class of Laplacian matrices is proposed and an existing theoretical result on DGN is extended. This extension bridges a gap in the literature. The experimental results presented in the thesis, based on nine real-world benchmarks and ten synthetic data sets, demonstrate the superiority of the proposed DGAT model compared to the GAT baseline model. Particularly on heterophilic data sets, DGAT showed a notable average increase of approximately 35% in node classification tasks across all heterophilic real-world data sets. In addition, DGAT outperforms GAT by an average margin of around 51% in all ten synthetic data sets with various levels of heterophily

Banana wilt caused by Fusarium oxysporum f. sp. cubense tropical race 4 (Foc TR4) is a devastating fungal disease. Biocontrol strategies owned immense potential in inhibiting the spread of Foc TR4. Here, thirty actinobacteria were isolated from soils and screened for their antagonistic activity against Foc TR4. Strain SCA4-21T exhibited broad-spectrum antifungal activity against nine phytopathogenic fungi including Foc TR4. The strain was identified as the genus Streptomyces according to phenotypic characteristics and 16S rRNA gene phylogenetic analysis. Multi-locus sequence analysis based on five house-keeping gene alleles (atpD, gyrB, recA, rpoB, and trpB) revealed that strain SCA4-21T clustered into S. hygroscopicus subsp. hygroscopicus NBRC 13472T with 100% of bootstrap value. Average nucleotide identity and dDDH were 98.49% and 44.30% above the threshold of novel species. Hence, strain SCA 4-21T represented a novel species within the genus Streptomyces, named as Streptomyces luomodiensis sp. nov.. The type strain is SCA4-21T (=GDMCC4.340T= JCM36555T). By the CAZymes analysis, 348 carbohydrate-active enzymes were detected, including 15 chitinases and 8 β-1,3-glucanases. The fermentation broth of strain SCA4-21T showed high activities of chitinase and β-1,3-glucanase, contributing to the antifungal activity. Our results showed an innovative potential biocontrol agent for managing plant fungal diseases, specifically banana fusarium wilt.

Dysferlinopathies comprise a spectrum of muscular dystrophies characterized by progressive muscle weakness and degeneration due to mutations in the DYSF gene, which encodes the dysferlin protein critical for muscle membrane repair. This review delves into the clinical spectra of dysferlinopathies, their molecular mechanisms, and the spectrum of emerging therapeutic strategies. We explore the phenotypic heterogeneity of dysferlinopathies, highlight the incomplete understanding of genotype-phenotype correlations, and discuss the implications of various DYSF mutations. Furthermore, we examine the utility of animal models in elucidating disease mechanisms and the potential of symptomatic, pharmacological, molecular, and genetic therapies in mitigating the disease's progression. We also consider the roles of diet and metabolism in managing dysferlinopathies, as well as the impact of clinical trials on treatment paradigms. By culminating the complexities inherent in dysferlinopathies, this article emphasizes the need for multidisciplinary approaches, precision medicine, and extensive collaboration in research and clinical trial design to advance our understanding and treatment of these challenging disorders.

Nutrition therapy is the best solution to human chronic diseases, especially beer and barley which play an important role in human health and civilization. We demonstrated the actional mechanism of functional ingredients in beer and barley to combat chronic diseases, based on PubMed, google, CNKI, and ISI Web of Science databases from 1997 to 2024. Beer is rich in functional ingredients that is a complex of barley malt and hops; the health effect of beer against 26 chronic diseases is highly similar to that of barley, due to molecular mechanism of polyphenols (phenolic acids, flavonoids), melatonin, minerals, bitter acids, vitamins, and peptides. The ancient German Beer Purity Law provides much scientific basis today, especially indirectly supporting the human one cell disease theory. Low purine beer can be produced by enzymatic and biological degradation and adsorption of purines as well as dandelion addition. Functional beer with low purine and high active ingredients made from Beer Purity and barley malt as well as functional foods addition will be the key and important development direction, such as ginger beer and ginseng beer, especially coix-lily beer at the ancestors ca. 9000 years ago. This review paper not only reveals the actional mechanism of beer overcoming human chronic diseases, but also provides scientific basis for the development of functional beer for the prevention and treatment of human chronic diseases.

The North China Plain is among the regions most afflicted by ground fissure disasters in China. Recent urbanization has accelerated ground fissure activity in the three counties of the northern North China Plain, posing significant threats to both the natural environment and socioeconomic sustainability. Despite the increased attention, a lack of comprehensive understanding persists due to delayed recognition and limited research. This study conducted field visits and geological surveys across 43 villages and 80 sites to elucidate the spatial distribution patterns of ground fissures in the aforementioned counties. By integrating these findings with regional geological data, we formulated a causative model to explain ground fissure formation. Our analysis reveals a concentration of ground fissures near the Niuxi and Rongxi faults, with the former exhibiting the most extensive distribution. The primary manifestations of ground fissures include linear cracks and patch-shaped collapse pits, predominantly oriented in east-west and north-south directions, indicating tensile failure with minimal vertical displacement. Various factors contribute to ground fissure development, including fault activity, ancient river channel distribution, bedrock undulations, rainfall, and ground settlement. Fault activity establishes a concealed fracture system in shallow geotechnical layers, laying the groundwork for ground fissure formation. Additionally, the distribution of ancient river channels and bedrock undulations modifies regional stress fields, further facilitating ground fissure emergence. Rainfall and differential ground settlement serve as triggering mechanisms, exposing ground fissures at the surface. This research offers novel insights into the causative mechanisms of ground fissures in the northern North China Plain, providing valuable scientific evidence for mitigating ground fissure disasters during the urbanization process in the region.