This study aimed to identify whether gyrate atrophy of the choroid and retina (GACR) heterozygous individuals have possible clinical manifestations and to explore the potential pathogenic mechanism. In this retrospective study, we surveyed a two-generation pedigree of an individual diagnosed with GACR. Two family members underwent ophthalmological, hematologic, and genetic tests. An arginine-restricted diet with vitamin B6 supplementation was implemented; clinical assessments were repeated every 3 months during follow-up. Relative OAT mRNA expression was determined using real-time quantitative polymerase chain reaction. The 19-year-old compound heterozygous daughter (OAT: c.1186C>T; c.748C>T), had bilateral high myopia, posterior staphyloma, chorioretinal atrophy, macular abnormalities, and elevated hematologic ornithine. The 54-year-old heterozygous mother (OAT: c.1186C>T), presented with bilateral severe myopia, asymmetric posterior staphyloma, retina and choroidal capillary layer atrophy, retinal pigment epithelium abnormalities, and mildly elevated hematologic ornithine. Compared to normal individuals, the daughter and mother had 29% and 46% relative OAT mRNA expression, respectively (P<0.001). We believe that this is the first report of a carrier of one OAT variant allele with mild phenotypes, suggesting that family members should be aware of the possible involvement of autosomal recessive conditions. Additional data suggests nonsense mediated decay-initiated mRNA degradation may cause GACR.

This paper presents a system for identification of wind features, such as gusts and wind shear. These are of particular interest in the context of energy-efficient navigation of Small Unmanned Aerial Systems (UAS). The proposed system generates real-time wind vector estimates and a novel algorithm to generate wind field predictions. Estimations are based on the integration of an off-the-shelf navigation system and airspeed readings in a so-called direct approach. Wind predictions use atmospheric models to characterize the wind field with different statistical analyses. During the prediction stage, the system is able to incorporate, in a big-data approach, wind measurements from previous flights in order to enhance the approximations. Wind estimates are classified and fitted into a Weibull probability density function. A Genetic Algorithm (GA) is utilized to determine the shaping and scale parameters of the distribution, which are employed to determine the most probable wind speed at a certain position. The system uses this information to characterize a wind shear or a discrete gust and also utilizes a Gaussian Process regression to characterize continuous gusts. The knowledge of the wind features is crucial for computing energy-efficient trajectories with low cost and payload. Therefore, the system provides a solution that does not require any additional sensors. The system architecture presents a modular decentralized approach, in which the main parts of the system are separated in modules and the exchange of information is managed by a communication handler to enhance upgradeability and maintainability. Validation is done providing preliminary results of both simulations and Software-In-The-Loop testing. Telemetry data collected from real flights, performed in the Seville Metropolitan Area in Andalusia (Spain), was used for testing. Results show that wind estimation and predictions can be calculated at 1 Hz and a wind map can be updated at 0.4 Hz. Predictions show a convergence time with a 95% confidence interval of approximately 30 s.

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a U-Net framework. The U-Net architecture, commonly employed for biomedical image segmentation, is further enhanced with Depthwise Separable Convolutional Blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The Vision Transformer, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our U-Net model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient U-Net topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation.

Time series forecasting has been a challenging area in the field of Artificial Intel-ligence. Various approaches such as linear Neural Networks, Recurrent Linear Neural Networks, Convolutional Neural Networks and recently Transformers have been attempted for the time series forecasting domain. Although, Trans-former-based architectures have been outstanding in the Natural Language Pro-cessing domain, especially in autoregressive language modeling, the initial at-tempts to use transformers in the time series arena have met with mixed success. One of the recent papers demonstrated that modeling the multi-variate time se-ries problem as independent channels on a transformer architecture produced lower mean square and mean absolute errors on benchmarks, however, another recent paper claimed that a simple linear neural network out-performs previous approaches including transformer-based designs. We investigate this paradox in detail comparing the linear Neural Network and Transformer based designs, provide insights to why a certain approach may be better for a particular type of problem. We also improve upon the recently proposed simple linear Neural Network based architecture by using dual pipelines with batch normalization and reversible instance normalization. Our enhanced architecture outperforms all existing architectures for time series forecasting on majority of the popular benchmarks.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.

As the most serious of the many worse new pathological changes caused by diabetes, there are many risk factors for the occurrence and development of DR. It mainly includes hyperglycemia, hypertension, hyperlipidemia and so on. Among them, hyperglycemia is the most critical cause, which plays a key role in the pathological changes of DR.High-sucrose diets(HSDs) lead to elevated blood glucose levels in vivo, which, through oxidative stress, inflammation, the production of AGEs and VEGF, causes plenty of pathological damages to the retina and ultimately bring about loss of vision. The existing therapies for DR primarily target the terminal stage of the disease, when irreversible visual impairment has appeared. Therefore, early prevention is particularly critical. Early prevention of DR-related vision loss requires adjustments to dietary habits, mainly by reducing sugar intake. This article primarily discusses the risk factors, pathophysiological processes, and molecular mechanisms associated with the development of DR caused by HSDs. It aims to raise awareness of the crucial role of diet in the occurrence and progression of DR, promote timely changes in dietary habits, prevent vision loss, and improve the quality of life. The aim is to make people aware of the importance of diet in the occurrence and progression of DR. According to the dietary modification strategies we give, patients can change their poor eating habits timely, avoid the retinopathy that can be avoided theoretically, and obtain a excellent outcome.

Due to the influence of background conditions, lighting conditions, occlusion issues and the image resolution, how to extract robust person features is one of the difficulties in ReID research. Vision in Transformers (ViT) has achieved significant results in the field of computer vision. However, the existing problems still limit its application in ReID due to slow extraction of person features and difficulty in utilizing local features of people. To solve the mentioned problems, we utilize Pyramid Vision Transformer (PVT) as the backbone of feature extraction and propose a PVT-based ReID method in conjunction with other studies. Firstly, some improvements suitable for ReID are used on the PVT backbone, and we establish a basic model by using powerful methods verified on CNN-based ReID. Secondly, in an effort to further promote the robustness of the person features extracted by the PVT backbone, two new modules are designed. (1) The local feature clustering (LFC) is recommend to enhance the robustness of person features by calculating the distance between local features and global feature to select the most discrete local features and clustering them. (2) The side information embeddings (SIE) are used to encode non-visual information and send it into the network for training to reduce its impact on person features. Finally, the experiments show that PVTReID has achieved excellent results in ReID datasets and are 20% faster on average than CNN-based ReID methods.

Blood cell analysis is a crucial diagnostic process in medical practice. In particular, detecting white blood cells (WBCs) is essential for diagnosing of many diseases. The manual screening of blood films is a time-consuming and subjective process, which can lead to inconsistencies and errors. Therefore, automated detection of blood cells can improve the accuracy and efficiency of the screening process. In this study, an explainable Vision Transformer (ViT) model was proposed for the automatic detection of WBCs from blood films. The proposed model utilizes the self-attention mechanism to extract relevant features from the input images and leverages transfer learning by incorporating pre-trained model weights to improve its performance. The proposed model achieved a classification accuracy of 99.40% for five distinct types of WBCs and exhibited potential in reducing the time required for manual screening of blood films by pathologists. Upon examination of the misclassified test samples, it was observed that incorrect predictions were correlated with the presence or absence of granules in the cell samples. To validate this observation, the dataset was divided into two classes, namely Granulocytes and Agranulocytes, and a secondary training process was conducted. The resulting ViT model trained for binary classification achieved an accuracy of 99.70%, recall of 99.54%, precision of 99.32%, and F-1 score of 99.43% during the test phase. To ensure the reliability of the ViT model's multi-class classification of WBCs, the pixel areas that the model focuses on in its predictions are visualized through the Score-CAM algorithm.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

Deep Learning (DL) has made significant advances in computer vision with the advent of Vision Transformers (ViT). Unlike Convolutional Neural Networks (CNNs), ViTs use self-attention to extract both local and global features from image data, and then use residual connections to feed these features directly into a fully networked multilayer perceptron head. In hospitals, hematologists prepare peripheral blood smears (PBSs) and read them under a medical microscope to detect abnormalities in blood counts such as leukemia. However, this task is time-consuming and prone to human error. This study investigates the transfer learning process of Google ViT and ImageNet CNNs to automate the reading of PBSs. The study used two online PBS datasets, PBC and BCCD, and transferred them into balanced datasets to investigate the influence of data amount and noise immunity on both neural networks. The PBC results show that Google ViT is an excellent DL neural solution for data scarcity. The BCCD results show that Google ViT is superior to ImageNet CNNs in dealing with unclean, noisy image data because it is able to extract both global and local features and use residual connections, despite the additional time and computational overhead.

To accurately determine the refractive error of the eye, sufficient relaxation of eye accommodation is essential, either through the fogging technique or pharmacological cycloplegia. This study aimed to evaluate the clinical information revealed after cycloplegia and assess how age and non-cycloplegic refractive status influence the classification of eye refractive error. We analyzed the records of 472 non-population-based subjects aged 3–28 years (mean ± SD: 9.1 ± 4.6) who attended a private ophthalmology practice from January 2018 to December 2020. Cycloplegia was induced with one drop of cyclopentolate 1% in each eye, and refraction was measured 30 ± 5 min later using an objective autorefractometer. The average spherical equivalent (SE) difference (mean ± SD) induced by cycloplegia was 0.72 ± 0.73 D, with the highest difference observed in the 3-5 years age group (1.18 ± 0.85 D). Gender had no significant effect on the SE values before or after cycloplegia (p > 0.05). Cycloplegia caused a hyperopic refractive shift in 83% of participants, no shift in 12%, and a myopic refractive shift in 6%. This study highlights the importance of cycloplegia use in children and young adults.

Background: Visual acuity (VA) assessments are crucial in ophthalmology but traditionally rely on in-clinic evaluations. The emergence of telemedicine has spurred interest in creating dependable self-administered VA tests for use beyond standard clinical environments. This study evaluates the practicality and validity of a self-administered Near VA card test against traditional Snellen and Rosenbaum Pocket Vision Screener (RPVS) methods for home monitoring and enhancing clinical workflow. Methods: In a cross-sectional study a near VA card (Hadassah Self-Visual Acuity Screener-HSVA) was developed with written and videotaped instructions for self-use. Patients with a minimal best corrected VA (BCVA) of 1.0 LogMAR in at least one eye were recruited from Ophthalmology and Optometry clinics. Outcomes included mean BCVA difference between the self-administered and those obtained by the examiner, and correlations among BCVA values obtained by Snellen, RPVS, HSVA and previous distance BCVA according to the patient electronic medical records. Results: A total of 275 participants (mean age: 42.5±19.4 years, range: 18-89 years, 47% female) were included. Test-retest reliability analysis for the HSVA demonstrated very good correlation and repeatability (n=38 patients.; Rs=1.0, P

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual and textual features, and hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. Experimental results demonstrate that, compared to the current multimodal state-of-the-art methods, the proposed method achieves significant performance improvements in knowledge graph link prediction tasks. This proves that the proposed method effectively addresses the problem of multimodal feature fusion in knowledge graph link prediction tasks.

Purpose of research was to determine changes in optical quality for monthly disposable soft contact lenses (SCL) wearers with new and monthly worn SCL. Retinal straylight was assessed in SCL wearers using a C-Quant straylight meter. The study included 33 participants (age 22 ± 1.4 years) who wore monthly disposable silicone hydrogel contact lenses. Measurements were taken with month-old SCL that had been worn for no more than 4 hours. Participants then replaced the old lenses with new ones. After a 15-minute adaptation period, straylight measurements were taken with the new SCL. A questionnaire was administered to all participants, inquiring about vision complaints and the type of contact lens material used. The decimal logarithm of the stray-light parameter, log(s), was notably higher with month-old SCL (log(s) = 0.97±0.17) than with brand-new SCL (log(s) = 0.86±0.15), p < 0.001. The average increase in retinal straylight after a month of SCL use was log(s) = 0.11 ± 0.08. The questionnaire revealed that 35% of participants observed a reduction in visual quality after wearing the contact lenses for a month. Results showed that monthly disposable soft contact lenses could reduce visual quality when scheduled replacement time has been reached.

Integrating optical coherence tomography (OCT) into the pre-surgical stage of cataract management holds significant clinical and economic potential, particularly in low-to-middle-income countries like Kazakhstan. This study aimed to evaluate these impacts by prospectively recruiting 124 patients, aged 70±8 years, from two ophthalmology surgical centers in Almaty, Kazakhstan. Patients undergoing phacoemulsification of cataracts with monofocal intraocular lens (IOL) implantation between January and December 2022 were divided into two groups: the OCT group (n=75) received pre-operative OCT, while the Control group (n=49) did not. Visual acuity (VA) was measured pre- and post-surgery, and the cost-effectiveness of the surgical strategies was analyzed. The OCT group experienced a significantly greater improvement in VA (-0.647±0.232 logMAR) compared to the Control group (-0.543±0.244 logMAR), with a notable interaction between time and group (F(df) = 217.2, p &lt; 0.001). Additionally, pre-existing concomitant diseases were diagnosed in 25.3% of cases in the OCT group and 28.6% in the Control group. The economic analysis revealed that the integration of OCT facilitated multiple surgeries in one appointment, thereby reducing overall costs. These findings suggest that implementing OCT in the pre-surgical stage of cataract management can significantly enhance visual outcomes and decrease the cost of ophthalmology services in Kazakhstan.

U-Net, based on a deep convolutional neural network (CNN), has been clinically used to au-to-segment normal organs and potentially target volumes. However, CNNs with local geometric dependencies may limit the accuracy of segmentation. Additionally, the performance of CNNs can vary depending on the selection of network hyper-parameters, which was mitigated by the proposition of nnU-Net. We chose a vision transformer architecture called VT U-Net, which features a self-attention excluding the convolution layer, to overcome the limitations of CNNs by utilizing global geometric information of images. The VT U-Net v.2 became more powerful thanks to the adaptive hyper-parameter optimizer embedded in nnU-Net. However, despite leveraging the benefits of nnU-Net, VT U-Net v.2 still had additional network hyper-parameters that needed to be optimally chosen. Accordingly, among various hyper-parameters, this study attempted to find the optimal combination of the patch size and the embedded dimension regarding the transformer. From the 4-fold cross-validation, the modified VT U-Net v.2 showed the highest average performance for planning target volume (PTV) segmentation among the investigated networks. Though nnU-Net was based on convolution layers, the adaptive hyper-parameter optimizers turned out to enhance the performance. It was also confirmed that network hyper-parameters affected the segmentation accuracy of vision transformers.

In this work, we introduce the first pipeline that combines a refraction-aware Structure-from-Motion (SfM) method with a deep learning model specifically designed for airborne bathymetry. We accurately estimate the 3D positions of the submerged points by integrating refraction geometry within the SfM optimization problem. This way, no refraction correction as post-processing is required. Experiments with simulated data that approach the real-world capturing conditions demonstrate that SfM with refraction correction is extremely accurate, with submillimeter errors. We integrate our refraction-aware SfM within a deep learning framework that also takes into account radiometrical information, developing a combined spectral and geometry-based approach, with further improvements on accuracy and robustness to different seafloor types, both textured and textureless. We conducted experiments with real-world data at 2 locations in the southern Mediterranean Sea, with varying seafloor types which demonstrate the benefits of refraction correction for the deep learning framework. We open-source our refraction-aware SfM, providing researchers in airborne bathymetry with a practical tool to apply SfM in shallow water areas.

Color image binarization plays a pivotal role in image preprocessing work, significantly impacting subsequent tasks, particularly in text recognition. This paper concentrates on Document Image Binarization (DIB), aiming to separate a image into foreground (text) and background (non-text content). Through a thorough analysis of conventional and deep learning-based approaches, we conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields pre- and post-network training to underscore the Transformer model's advantages. Subsequently, we introduce a lightweight model based on the U-Net structure, enhanced with the Mobile ViT module to better capture global information features in document images. Given its adeptness at learning both local and global features, our proposed model exhibits superior performance on two standard datasets (DIBCO2012 and DIBCO2017) compared to state-of-the-art methods. Notably, our proposed DIB method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing. Moreover, its parameter count is less than a quarter of the HIP'23 model, which achives best results on three datasets(DIBCO2012, DIBCO2017 and DIBCO2018). Finally, two sets of ablation experiments were conducted to verify the effectiveness of the proposed binarization model.

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.

Against the background of the sky, imaging and perception of aircraft are cru- cial. Among these, the location of aircrafts is not a very difficult problem in general, because that deep learning algorithms and object detection models based on convolutional neural network(CNN) are ever-evolving. In order to have a better identification of various aircrafts, or to accurately locate different types of flying targets in the sky, it becomes significant to distinguish and recognize different types of aircrafts. One question is that, distinguishing and recognizing between sub-categories of aircrafts pose great challenges. Although fine-grained recognition focuses on exploring and studying such problems, aircrafts under different sub-categories and granularities lead us to rethink the application of features. We noticed that features in swin-transformer demonstrates the under- standing and processing of images, fully showcasing the encoding and indexing of information. Through this research and proposed approach, we discovered a better understanding of features encoding and use, which are inspired by the feature encoding and computation in swin-transformer. In our paper, our ap- proach has achieved effects on features encoded graphically, manifested from the architecture design and convolutional neural network computation, and outper- forms other famous fine-graiend classification models on this issue. Not only approach we proposed has demonstrated superior performance in fine-grained aicraft classification, but also the mechanisms of the feature encoding under different sample space partitions is revealed for this issue, which provides a re- search for the representation of aircraft fineness characteristics. The relationship between representation orientation of aircraft feature information under various grained divisions, shows that the recognition of different categories according to man-made, such as aircraft, can be achieved by means of the feature represen- tations studied in this paper, for more specific defined classification tasks and various man-made targets partition criteria, which may influences the princi- ple of design for calculation and feature extraction in fine-grained classification models.

Systematic reviews represent a powerful instrument to summarize the existing evidence in medical literature. However, articles for a systematic review are hard to identify, and mostly require a structured search of the literature through a number of databases, using keyword-based search strategies, followed by the painstaking manual selection of pieces of evidence that are pertinent to the query. A.I. algorithms may offer solutions to reduce the workload on investigators. We applied BERTopic, a newer and much-recognized transformer-based topic-modeling algorithm, to two datasets of 6137 and 5309 articles of newly published systematic reviews in the area of peri-implantitis and bone regeneration in implant dentistry. In the two datasets, BERTopic identified 14 and 22 clusters, respectively, and it automatically created labels describing the nature of the topics for each individual cluster based on semantic interpretation of their titles. Most themes regarded the query theme, but in both conditions, BERTopic also uncovered articles related to off-themes, which composed around 30% of the dataset—with sensitivity up to 0.79 and specificities of at least 0.99. Our results suggest that adding a topic-modeling step to the screening process could potentially save working hours for researchers involved in systematic reviews of the literature.

The reasons for the circular sense of human color perception generated by two sorts of color opponent neurons and three cone types are not well understood. Here we use geometrical analysis to examine the hypothesis that opponency, the recursive nature of color perception, and trichromacy arise as the most efficient ways of distinguishing spectrally different points on a plane using a minimum of color classes and receptor types.

A time-sequential working, spatially multiplexed autostereoscopic 3D display design consisting of a fast switchable RGB-color filter array is presented. The wavelength-selective filter barrier emits the light from a display over a larger active area than common autostereoscopic barrier displays. An optical modelling of wavelength-selective barriers has been used for instance to calculate the light ray distribution properties of that arrangement. To find well working display designs, automated searches by simulation and computational evaluation has been proceeded. Wavelength-selective filter barrier arrangements exhibit characteristics different from common barrier displays with similar barrier pitch and ascent. In particular, these constructions show strong angular luminance dependency under barrier inclination specified by correspondent slant angle. In time-sequential implementation it is important to avoid that quick eye or eyelid movement lead to visible color artifacts. In the millisecond regime tunable liquid crystal Fabry-Pérot color filters for the colors red, green and blue are presented. They consist of a sub-micrometer thick nematic layer sandwiched between dielectric mirrors and ITO-electrodes. These cells shall switch narrow-banding light of red, green or blue. An array for a glasses-free 3D display has to be equipped with several thousand switchable filter elements having different color apertures. The newly introduced design is usable as a multi user display as well as a single user system with user adaptive control.

This paper presents a comprehensive comparative analysis of four different computational vision algorithms for implementing an unpalleting system in a factory environment, under typical edge computing constraints. The primary objective is to automate the process of detecting and locating specific variable-shaped objects on a pallet, enabling a robotic system to accurately unstack them. The four algorithms evaluated are Pattern Matching, Scale-Invariant Feature Transform, Oriented FAST and Rotated BRIEF, and Haar cascade classifiers. Each technique is described in detail in this paper, and their implementations are outlined. Experimental results are thoroughly analyzed, assessing the algorithms’ performance based on accuracy, robustness to variability, computational speed, detection sensitivity, and resource consumption. The findings reveal the strengths and limitations of each algorithm, providing valuable insights for selecting the most appropriate technique based on the specific requirements of the unpalleting system. This research contributes to the advancement of automated object detection and localization in industrial environments, paving the way for more efficient and reliable unpalleting systems.

Ocean exploration is crucial for utilizing its extensive resources. Images captured by underwater robots suffer from issues such as color distortion and reduced contrast. To address the issue, we propose an innovative enhancement algorithm that integrates Transformer and Convolutional Neural Network (CNN) in a parallel fusion manner. Firstly, a novel transformer model is intro-duced to capture local features, employing peak-signal-to-noise ratio (PSNR) attention and linear operations. Subsequently, to extract global features, both temporal and frequency domain features are incorporated to construct convolutional neural network. Finally, the Fourier’s high and low-frequency information of the original image are utilized to fuse different features. To demon-strate the algorithm's effectiveness, underwater images with various levels of color distortion are selected for both qualitative and quantitative analyses. The experimental results demonstrate that our approach surpasses other mainstream methods, achieving superior PSNR and structural sim-ilarity index measure (SSIM) metrics and leading to a detection performance improvement of over ten percent.

Это исследование сосредоточено на разработке системы искусственного зрения для гибкого дельта-робота-манипулятора и ее интеграции с межмашинной связью для оптимизации взаимодействия устройств в реальном времени. Эта интеграция направлена ​​на увеличение скорости роботизированной системы и улучшение ее общей производительности. Предлагаемое сочетание системы искусственного зрения с межмашинной связью позволяет обнаруживать и распознавать цели с высокой точностью в режиме реального времени в ограниченном пространстве, предназначенном для позиционирования, дальнейшей локализации и выполнения производственных процессов, таких как сборка или сортировка деталей. . В данном исследовании RGB-изображения используются в качестве входных данных для алгоритма MASK-R-CNN, а результаты обрабатываются в соответствии с особенностями прототипа дельта-манипулятора робота. Данные, полученные от MASK-R-CNN, адаптированы для использования в системе управления дельта-роботом с учетом ее уникальных характеристик и требований к позиционированию. Технология M2M позволяет манипулятору робота быстро реагировать на изменения, например, на перемещение объектов или изменение их положения, что имеет решающее значение для задач сортировки и упаковки. Система была протестирована в условиях, близких к реальным, чтобы оценить ее производительность и надежность.

Non-toroidal shape primary pass through protection current transformers (CTs) are used to measure high currents. Their design provides them with a big airgap that allow passing several cables per phase though them, which is the main advantage versus toroidal types, as the number of CTs required to measure the whole phase current is drastically reduced. The cables pass through the transformer window can be in several positions. As the isolines of the magnetic field generated by the primary currents are centered in the cables, if these cables are not centered in the transformer window, the magnetic field will be non-uniform along the transformer core. Consequently, local saturations can appear if the cables are not properly disposed causing the malfunction of the CT. In this paper, the performance of a non-toroidal shape protection CT is studied. The research is focused on the cable position influence in possible partial saturations of the CT when it is operating near to its accuracy limit. Depending on the cable position, the ratio of the primary and secondary currents can depart from assigned ratio. The validation of this phenomenon has been carried out via Finite Element Analysis (FEA) showing that partial transformer core saturations appears in areas of the magnetic core close to the cable. Applying FEA, also the admissible accuracy region for cable positioning inside the CT is delimited. Finally, the simulation results are ratified with experimental tests performed in non-toroidal protection CTs varying the primary cables’ positions, which are subjected to currents up to 5 kA, achieving satisfactory results. From this analysis, installation recommendations are given.

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial amount of annotations for training in conventional object detection, which is very labor-intensive. However, existing few-shot methods achieve high precision with the sacrifice of time-consuming for exhaustive fine-tuning, or take poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose Few-Shot object detection via Correlation-RPN and Transformer Encoder-Decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a 4-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that, our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

Camouflage is a natural or artificially process to prevent an object from being detected while camouflage breaking is a countering process for the identification of the concealed object. We report that a perfectly camouflaged object in a two-dimensional scene can be retrieved and detected with stereo-vision assisted three-dimensional (3D) imaging perceived with stereopsis. The analysis is based on binocular energy model applied to general 3D settings. We show that a perfectly concealed object with random noise background can be retrieved with vision’s stereoacuity to resolve the hidden structures. The theoretical analysis is further tested and demonstrated with distant natural images taken by a drone-camera, processed with a computer and displayed in an autostereoscopy. The recovered imaging is presented with removal of the background interference to demonstrate the general applicability for camouflage breaking with stereo imaging and sensing.

The objective of person re-identification (ReID) tasks is to match a specific individual across different times, locations, or camera viewpoints. The prevalent issue of occlusion in real-world scenarios affects image information, rendering the affected features unreliable. The difficulty and core challenge lie in how to effectively discern and extract visual features from human images under various complex conditions, including cluttered backgrounds, diverse postures, and the presence of occlusions. Some works have employed pose estimation or human keypoint detection to construct graph-structured information to counteract the effects of occlusions. However, this approach introduces new noise due to issues such as the invisibility of keypoints. Our proposed module, in contrast, does not require the use of additional feature extractors. Our module employs multi-scale graph attention for the reweighting of feature importance. This allows features to concentrate on areas genuinely pertinent to the re-identification task, thereby enhancing the model's robustness against occlusions. To address these problems, a model that employs multi-scale graph attention to re-weight the importance of features is proposed in this study, significantly enhancing the model’s robustness against occlusions. Our experimental results demonstrate that, compared to baseline models, the method proposed herein achieves a notable improvement in mAP on occluded data sets, with increases of 0.5%, 31.5%, and 12.3% in mAP scores.

Within environmental perception, automatic navigation and object detection, computer vision is a crucial and demanding field with many applications in modern industries, such as multi-target long-term visual tracking in automated production, defect detection, and driverless robotic vehicles with sensing ability. The performance of computer vision has greatly improved recently thanks to developments in deep learning algorithms and hardware computing capabilities, which has spawned the creation of a large number of related applications. This paper presents the results of a detailed review of over 50 papers published over the course of two decades (1999–2024), with a primary focus on the technical advancement of computer vision. To elucidate the foundational principles, an examination of typical visual algorithms based on traditional correlation filtering was initially conducted. Subsequently, a comprehensive overview of the most recent advancements in deep learning-based computer vision techniques was compiled. Furthermore, a comparative analysis between conventional and novel algorithms was undertaken to discuss the future trends and directions of computer vision. Lastly, the feasibility of employing visual SLAM (Simultaneous Localization and Mapping) algorithms in the context of autonomous vehicles with sensing capability was explored. Furthermore, we explored a thorough and efficient architecture for utilizing these techniques in autonomous robotic vehicles into unmanned green and low-carbon smart factories, underlining novel advances as well as potential prospects for future research.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

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.

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.

The paper delineates the developed vision system of the UR5 cobot and the operating algorithm of the robotic quality control station. The hardware-software architecture of the developed robotic station was shown, consisting of a UR5 cobot equipped with a web camera and a stationary industrial camera with a lighting system. Image processing and analysis algorithms were described, the method of control and communication between the station components was discussed, and two operating scenarios were presented as a single robotic station and a robotic line. Based on the results obtained, the level of measurement noise, accuracy, and repeatability of the developed vision system were estimated.

Vision impairment may delay responses to hazards when driving. In a proof-of-concept driving simulator study, we evaluated a hazard warning device designed for vision impaired drivers. Three groups participated: 11 persons with central vision loss (CVL; median age 60 years), 12 with homonymous field loss (HFL; 52 years) and 11 with normal vision (NV; 60 years). CVL is characterised by impaired visual acuity and contrast sensitivity while HFL is a loss of vision in the same half of the visual field (blind side) in both eyes. Participants completed drives with and without the device which gave a directional vibro-tactile warning for an approaching pedestrian hazard when collision risk exceeded a pre-defined threshold. Warnings significantly (p< 0.001) reduced brake response times for CVL (∆= 0.54s) and HFL (∆= 0.30s), but not NV participants. For HFL participants, the reduction was greater (p = 0.02) for hazards on the blind (∆= 0.57s) than seeing side (∆= 0.10s). The warnings significantly reduced collision rates for CVL participants from 11 to 0% (all hazards) and for HFL participants from 30 to 1.7% (blind side hazards). Thus, hazard warnings may be beneficial in improving safety of vision impaired drivers; further research is warranted.

A Partial discharge (PD) occurrence in high-voltage (HV) and medium-voltage (MV) power assets is a warning sign of insulation system degradation or defective manufacturing/assembly, that may cause catastrophic damage and eventually lead to the breakdown of the power equipment. Ultra-high frequency (UHF) PD measurement technology has extensively been used to monitor the insulation health of the HV or MV equipment due to its high immunity against ambient noise and conducted disturbances. This paper presents experimental validation of a new design of a UHF planar rectangular microstrip antenna that can be used for PD monitoring of HV and/or MV power equipment, such as power transformers. The designed planar rectangular microstrip antenna has a compact size of 80mmx70mmx1.6mm. Laboratory experiments were performed to validate the antenna sensitivity to PD activity caused by insulation defects created inside an oil-filled transformer tank model. PD measurement results confirm that the proposed rectangular microstrip antenna has high sensitivity and high signal-to-noise ratio (SNR), thanks to its capability to suppress external noise disturbances, especially during online PD monitoring. Thus, the proposed UHF antenna seems to be a promising and alternative PD sensor that can be employed in UHF PD monitoring systems of HV or MV power equipment.

This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where for each matching pair there are always two possible non-matching patches; one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

Abstract: Colistin is a last-resort antimicrobial for treating multidrug-resistant Gram-negative bacteria. Phe-notypic colistin resistance is highly associated with plasmid-mediated mobile colistin resistance (mcr) genes. mcr-bearing Enterobacteriaceae have been detected in many countries, with the emergence of colistin-resistant pathogens a global concern. This study assessed the distribution of mcr-1, mcr-2, mcr-3, mcr-4, and mcr-5 genes with the phenotypic colistin resistance in isolates from diarrheal infants and children in Bangladesh. Bacteria were identified using the API-20E biochemical panel and 16s rDNA gene sequencing. Polymerase chain reac-tions detected mcr gene variants in the isolates. Their susceptibilities to colistin were determined by agar dilu-tion and E-test by minimal inhibitory concentration (MIC) measurements. Over 30.0% (69/225) of isolates showed colistin resistance by agar dilution assessment (MIC> 2.0 μg/mL). Overall, 15.5% of isolates carried mcr genes (7, mcr-1; 17, mcr-2; 13, mcr-3; and co-occurrence occurred in 2 isolates). Clinical breakout MIC val-ues (≥ 4 μg/mL) were associated with 91.3% of mcr-positive isolates. The mcr-positive pathogens include twenty Escherichia spp., five Shigella flexneri, five Citrobacter spp., two Klebsiella pneumoniae, and three Pseudo-monas parafulva. mcr-genes appeared to be significantly associated with phenotypic colistin resistance phe-nomena (p=0.000), with 100% colistin-resistant isolates showing MDR phenomena. Age and sex of patients showed no significant association with detected mcr variants. Overall, mcr-associated colistin-resistant bacte-ria have emerged in Bangladesh, which warrants further research to determine their spread and instigate ac-tivities to reduce resistance.

This article titled "AI and IoT in Automation and Security: A Vision for Next Generation Applications," explored the implications of marrying IoT with AI in the realms of automation and security; this piece goes further into what that entails. In this paper, we present innovative application descriptions arising from this technology convergence and its future-generation applications. We found that AI brings strong cyber security, predictive maintenance, and decision-making capabilities to the table due to its advanced algorithms and machine learning models. IoT has the potential to allow businesses to extract and generate big data, automate processes, and monitor in real-time thousands and even millions of businesses at once. For now, we believe some of the possible main conclusions will be that the smart city, stand-alone systems, and user experience will be quite consumer-friendly. Importantly, the study also assessed facets such as data protection, system interoperability, and a few others. Our vision underscores the essential of a strong structure to connect the full latent of AI and IoT, finally aiming to create more capable, protected, and approachable environments. Significant results include achieving 95.8% accuracy in anomaly detection and 93.4% accuracy in predictive maintenance. The showcasing results efficacy of AI models to enhance system reliability as well as operational efficiency. Vigorous encryption protocols performance ensures data security hence addressing issues of privacy. These culminations underscore the transformative potential of AI-IoT integration in next-generation automation and security applications.

Neutral facial expression recognition is of great importance in various domains and applications. This study introduces a data-centric approach for neutral facial expression recognition, presenting a comprehensive study that explores different methodologies, techniques, and challenges in the field to foster a deeper understanding. The results show that data augmentation plays a crucial role in improving dataset performance. Additionally, the study investigates different model architectures and training techniques to identify the most effective approach, with the InceptionV3 model achieving the highest accuracy of 72%. Furthermore, the research examines the influence of preprocessing methods on the performance of both InceptionV3 and a simplified CNN model. Interestingly, the results indicate that preprocessing techniques positively affect the performance of the simpler CNN model but negatively impact the InceptionV3 model. The implemented system, used to evaluate the findings, demonstrates promising results, correctly classifying 77% of neutral expressions. However, there are still areas for improvement. Creating a specialized dataset that includes both neutral and non-neutral expressions would greatly enhance the accuracy of the system. By addressing limitations and implementing suggested improvements, neutral facial expression recognition can be significantly enhanced, leading to more effective and accurate results.

Uveal melanoma (UM) poses a significant clinical challenge due to its high metastasis rate and poor prognosis. Melatonin, noted for its anti-cancer properties in various malignancies, including cutaneous melanoma, shows promise in UM treatment. This study aimed to evaluate melatonin receptor expression in primary UM and its association with UM-related mortality and prognostic factors. Immunohistochemical analysis of 47 primary UM tissues showed low expression of MTNR1A and MTNR1B receptors, with MTNR1A significantly higher in patients who succumbed to UM. Analysis of TCGA data from 80 UM patients revealed RNA expression for MTNR1A, RORα, and NQO2, but not MTNR1B or GPR50. Higher MTNR1A RNA levels were observed in patients with a BAP1 mutation, and higher NQO2 RNA levels were noted in patients with the epithelioid tumor cell type. However, Kaplan-Meier analysis did not show distinct survival probabilities based on receptor expression. The study concludes that UM clinical samples express melatonin receptors, suggesting a potential mechanism for melatonin's anti-cancer effects. Despite finding higher MTNR1A expression in patients who died of UM, no survival curve differences were observed. Further research is needed to explore additional mechanisms of melatonin’s oncostatic effects, including its antioxidant properties and immune modulation.

Computational animation of spatiotemporal models for 3-D shape and motion is considered as core of dynamic real-time vision. This is based on sets of features evaluated from multi-focal image streams. Subjects are defined as special objects capable of sensing environmental parameters and of initiating own actions in combination with stored knowledge. Object/subject recognition and scene understanding are achieved on different levels. Multiple objects are tracked individually for perceiving their actual state (‘here and now’). Fast saccadic jumps in gaze direction allow flexible concentration on objects or parts of actual interest. By analyzing motion of relevant objects/subjects over a larger time scale on the level of state variables and documenting them in the ‘scene tree representation’ (computer graphics), the situation with respect to decision making is assessed. Various behavioral capabilities of subjects are represented on an abstract level for characterizing their potential behaviors. These are generated by stereotypical feed-forward and feedback control applications on a separate level close to the actuator hardware with corresponding methods. This dual representation on one level for decision making and one on the implementation level allows for flexibility and easy adaptation or extension. Results are shown for road vehicle guidance based on three cameras on a gaze-controlled platform.

For centuries, Foeniculi fructus (F. fructus) has been used as a traditional herbal medicine in China and Europe and is widely used as a natural therapy for digestive disorders, including indigestion, flatulence, and bloating. The mechanism by which F. fructus alleviates functional dyspepsia was analyzed through network pharmacology, and its therapeutic effect on an animal model of functional dyspepsia was investigated. The compounds, targets, and related diseases of F. fructus were studied utilizing the traditional Chinese medicine systems pharmacology (TCMSP) database. Information on the target genes was classified using the UniProt database. A network was built using Cytoscape 3.9.1, and functional dyspepsia-related genes were checked using the Cytoscape string application. The efficacy of F. fructus on functional dyspepsia, including gastroparesis and gastrointestinal motility, was confirmed by treatment with its extract in a mouse model of loperamide-induced functional dyspepsia. Seven compounds targeted twelve functional dyspepsia-associated genes. In a functional dyspepsia mouse model, F. fructus significantly suppressed the symptoms when compared to that in the control group. Our animal studies showed that the mechanism of action of F. fructus is closely related to gastrointestinal motility. Based on animal experimental results, the results showed that F. fructus provides a potential means to treat functional dyspepsia, suggesting that its medical mechanism for functional dyspepsia can be described by the relationship between seven key compounds of F. fructus, including oleic acid and β-sitosterol, and 12 functional dyspepsia-related genes.

Many accidents, such as those involving collisions or trips, appear to involve failures of vision; but the association between accident risk and vision as conventionally assessed, is weak or absent. We addressed this conundrum by embracing the distinction inspired by neuroscientific research, between vision for perception and vision for action. A dual-process perspective predicts that accident vulnerability will be associated more strongly with vision for action than vision for perception. Older and younger adults, with relatively high and relatively low self-reported accident vulnerability (Accident Proneness Questionnaire), completed three behavioural assessments targeting: vision for perception (Freiburg Visual Acuity Test); vision for action (Vision for Action Test - VAT); and the ability to perform physical actions involving balance, walking and standing (Short Physical Performance Battery). Accident vulnerability was not associated with visual acuity or with performance of physical actions; but was associated with VAT performance. VAT assesses the ability to link visual input with a specific action –launching a saccadic eye movement as rapidly as possible, in response to shapes presented in peripheral vision. The predictive relationship between VAT performance and accident vulnerability was independent of age, visual acuity and physical performance scores. Applied implications of these findings are considered.

Traditional computer vision techniques aim to extract meaningful information from images but often depend on manual feature engineering, making it difficult to handle complex real-world scenarios. Fractional Calculus (FC), which extends derivatives to non-integer orders, provides a flexible way to model systems with memory effects and long-term dependencies, making it a powerful tool for capturing fractional rates of variation. Recently, Neural Networks (NNs) have demonstrated remarkable capabilities in learning complex patterns directly from raw data, automating computer vision tasks and enhancing performance. Therefore, the use of fractional calculus in neural network-based computer vision is a powerful method to address existing challenges by effectively capturing complex spatial and temporal relationships in images and videos. This paper presents a survey of Fractional Calculus Neural Network-based (FC NN-based) computer vision techniques for denoising, enhancement, object detection, segmentation, restoration, and NN compression. The survey compiles existing FFC NN-based approaches, elucidates underlying concepts, and identifies open questions and research directions. By leveraging FC's properties, FC NN-based approaches offer a novel way to improve the robustness and efficiency of computer vision systems.

The TRPV3 calcium ion channel is vital for maintaining skin health and has been associated with various skin-related disorders. Since TRPV3 is involved in the development of skin inflammation, inhibiting TRPV3 could be a potential treatment strategy. Alpha-mangostin isolated from Garcinia mangostana L. extract exhibits diverse positive effects on skin health; however, the underlying mechanisms remain obscure. This study investigated the TRPV3-inhibitory properties of alpha-mangostin on TRPV3 hyperactive mutants associated with Olmsted syndrome and its impact on TRPV3-induced cytokine secretion and cell death. Our findings demonstrate that alpha-mangostin effectively inhibits TRPV3, with an IC50 of 0.077 ± 0.013 μM, showing inhibitory effects on both wild-type and mutant TRPV3. TRPV3 inhibition with alpha-mangostin decreased calcium influx and cytokine release, protecting cells from TRPV3-induced death. These results indicate that alpha-mangostin reduced inflammation in TRPV3-activated skin keratinocytes, suggesting that alpha-mangostin could be potentially used for improving inflammatory skin conditions such as dermatitis.

A study of curvature along the contour provides important sources of information about the shape of an object. Knowledge of contour curvature allows for the perception of and interaction with 3D objects. In this review, we will explore the value of contour curvature in the field of neurophysiology, psychophysics, computer vision, and psychology. The serial consolidation of disjoint edges, oriented in a particular manner, into composited curves allows building of identifiable shapes in occluded natural environments [Hess1999, Wertheimer1923, Zucker1989, Feldman2001]. Examples are our ability to pick objects, sort and manage shapes otherwise hidden or confounded by occlusion in messy natural environments. Contour curvature has been intensively studied in psychology as it forms the first steps in 2D shape building which eventually becomes 3D object recognition in the human brain.

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.

Vertical Indoor Farming (VIF) with hydroponics offers a promising perspective for sustainable food production. Intelligent control of VIF system components plays a key role in reducing operating costs and increasing crop yields. Modern machine vision (MV) systems use Deep Learning (DL) in combination with camera systems for various tasks in agriculture, such as disease and nutrient deficiency detection, and flower and fruit identification and classification for pollination and harvesting. This study presents the applicability of MV technology with DL modelling to detect the growth stages of chilli plants using YOLOv8 networks. The influence of different bird’s eye and side view datasets and different YOLOv8 architectures was analysed. To generate the image data for training and testing the YOLO models, chilli plants were grown in a hydroponic environment and imaged throughout their life cycle using four camera systems. The growth stages were divided into growing, flowering and fruiting classes. All trained YOLOv8 models showed reliable identification of growth stages with high accuracy. The results indicate that models trained with data from both views show better generalisation. YOLO’s middle architecture achieved the best performance.

Neural decoding from spiking activity is an essential tool for understanding the information encoded in population neurons, especially in applications like brain-computer interface (BCI). Various quantitative methods have been proposed and have shown superiorities under different scenarios respectively. From the machine learning perspective, the decoding task is to map the high-dimensional spatial &amp; temporal neuronal activity to the low-dimensional physical quantities (e.g., velocity, position). Because of the complex interactions and the abundant dynamics among neural circuits, good decoding algorithms usually have the capability of capturing flexible spatiotemporal structures embedded in the input feature space. Recently, the Transformer-based models are widely used in processing natural languages and images due to its superior performances in handling long-range and global dependencies. Hence, in this work we examine the potential applications of Transformers in neural decoding and introduce two Transformer-based models. Besides adapting the Transformer to neuronal data, we also propose a data augmentation method for overcoming the data shortage issue. We test our models on three experimental datasets and their performances are comparable to the previous state-of-the-art (SOTA) RNN-based methods. In addition, Transformer-based models show increased decoding performances when the input sequences are longer, while LSTM-based models deteriorate quickly. Our research suggests that Transformer-based models are important additions to the existing neural decoding solutions, especially for large datasets with long temporal dependencies.

The purpose of this study is to show an automated laser vision correction (LVC) with the transep-ithelial refractive keratectomy (TransPRK) surgery technique. Since more surgical steps have been automated over the years, we have standardized the TransPRK technique. We have been using it since 2010. This paper aims to illustrate the processes that are readily applicable to automation. To meet the patient's expectations and ensure that the patient has uncorrected visual acuity at least equal to the preoperative corrected vision with glasses, patient selection is crucial in refractive surgical procedures. One major benefit of automating the surgery is that it can be performed in a similar way by each surgeon or laser correction centre, so once the standard and results are good, these can be per-formed by different surgeons.

As split learning (SL) becomes popular for addressing data privacy and resource limitation issues in edge model training process, it is crucial to pre-validate whether the extensive use of wireless and computing resources in SL can achieve the expected training latency and convergence. While digital twin network (DTN) can potentially estimate network strategy performance in pre-validation environments, they are still in their infancy for SL tasks, facing challenges like unknown non-i.i.d. data distributions, inaccurate channel states, and misreport resource availability across devices. To address these challenges, this paper proposes a TransNeural algorithm for DTN pre-validation environment to estimate SL latency and convergence. First, the TransNeural algorithm integrates transformers to efficiently model data similarities between different devices, considering different data distributions and device participate sequence greatly influence SL training convergence. Second, it leverages neural network to automatically establish the complex relationships between SL latency and convergence with data distributions, wireless and computing resources, dataset sizes, and training iterations. Deviations in user reports are also accounted for in the estimation process. Simulations show that the TransNeural algorithm improves latency estimation accuracy by 13.44% and convergence estimation accuracy by 116.74% compared to traditional equation-based methods.

In this paper, we introduce Syntax-Enhanced Transformer Model (SET), a groundbreaking approach in the realm of Transformer-based language modeling that seeks to redefine the boundaries of linguistic analysis and comprehension. SET innovatively combine (i) the well-established high-level performance, scalability, and adaptability of traditional Transformers with (ii) a sophisticated analysis of syntactic structures. This synergy is enabled by a novel attention mechanism tailored to parse syntactic nuances and a deterministic process adept at transforming linearized parse trees into meaningful linguistic representations. Our comprehensive experiments reveal that SET significantly advance the field by surpassing existing benchmarks in sentence-level language modeling perplexity. They exhibit exceptional proficiency in tasks that require an acute awareness of syntax, setting new standards for language models in understanding complex linguistic structures. Furthermore, SET demonstrate an enhanced capability to grasp nuanced linguistic patterns that have traditionally been challenging for standard Transformer models. However, our studies also uncover a unique aspect of SET: while they excel in sentence-level tasks, their representation of sentences as singular vectors—owing to the syntactic composition constraints intrinsic to their design—introduces certain limitations in document-level language modeling. This observation points to an intriguing area for future exploration; it suggests the potential need for an alternative or complementary memory mechanism within Transformer models, one that functions independently from, yet in harmony with, syntactic structures. Such a mechanism could be pivotal in enhancing the model's ability to comprehend and process long-form texts effectively. In conclusion, SET mark a significant stride in the journey towards more sophisticated, syntax-aware language models. They offer promising insights into the integration of deep linguistic knowledge with cutting-edge machine learning techniques, potentially opening doors to a new era of natural language understanding and processing.

The evolution of sentence representation learning, especially with parse tree encoders, has shown remarkable progress. Traditional approaches predominantly rely on recursive encoding of tree structures, which impedes parallel processing capabilities. Additionally, these methods often overlook the significance of dependency tree arc labels. To overcome these limitations, we introduce the Syntax-Enhanced Transformer (SET), incorporating a novel dual-attention mechanism that integrates relation-focused attention alongside traditional self-attention. This design effectively encodes both dependency and spatial positional relationships within sentence dependency trees. Our approach innovatively incorporates syntactic information into the Transformer framework without compromising its inherent parallelizability. The SET demonstrates superior or comparable performance to contemporary methods across various sentence representation tasks, significantly enhancing computational efficiency.

Recent advancements in neural language models, particularly attention-based architectures like the Transformer, have substantially surpassed traditional methods in various natural language processing tasks. These models adeptly generate nuanced token representations by considering contextual relations within a sequence. However, augmenting these models with explicit syntactic knowledge, such as part of speech tags, has been found to remarkably bolster their effectiveness, especially under constrained data scenarios. This study introduces the Linguistic Enhanced Transformer (LET), which integrates multiple syntactic features, showing a notable increase in translation accuracy, evidenced by an improvement of up to 1.99 BLEU points on subsets of the WMT '14 English-German dataset. Furthermore, this paper demonstrates that enriching BERT models with syntax-aware embeddings enhances their performance on several GLUE benchmark tasks.

With the development of agriculture, the complexity and dynamism of orchard environments pose challenges to the perception and positioning of inter row environments for agricultural machinery. The paper proposes a method for extracting navigation lines and measuring pedestrian obstacles. The improved YOLOv5 algorithm is used to detect tree trunks between left and right rows in orchards. The experimental results show that the average angle deviation of the extracted navigation lines is less than 5 degrees, verifying its accuracy. Due to the variable posture of pedestrians and ineffective camera depth, a distance measurement algorithm based on four zone depth comparison is proposed for pedestrian obstacle distance measurement. Experimental results show that within a range of 6m, the average relative error of distance measurement does not exceed 1%, and within a range of 9m, the maximum relative error is 2.03%. The average distance measurement time is 30 milliseconds, which can accurately and quickly achieve pedestrian distance measurement in orchard environments. On the publicly available TUM RGB-D dynamic dataset, YOLOD-SLAM2 significantly reduces the RMSE index of absolute trajectory error compared to ORB-SLAM2 algorithm, which is less than 0.05 m/s. In actual orchard environments, YOLOD-SLAM2 has a higher degree of agreement between the estimated trajectory and the true trajectory when the car is traveling in straight and circular directions. The RMSE index of the absolute trajectory error is less than 0.03m/s, and the average tracking time is 47ms, indicating that the YOLOD-SLAM2 algorithm proposed in this paper can meet the accuracy and real-time requirements of agricultural machinery positioning in orchard environments.

Computer vision is a fast-expanding discipline focusing on analyzing, altering, and comprehending images at a high level. Its goal is to figure out what's going on in front of a camera and use that knowledge to manage a computer or robotic system or to show people new visuals that are more instructive or attractive than the original camera photos. Video surveillance, biometrics, automotive, photography, movie production, Web search, medicine, augmented reality gaming, new user interfaces, and many other applications are all possible with computer vision technologies. This paper aims to describe how computer vision will be used to play a winning game of blackjack.

Computer vision is considered as an ally to solve business problems that require human intervention, intelligence and criteria. This topic of research has evolved in XXI century at faster peace, delivering various alternatives from open source until commercial platforms. With so many options and market growing, it result difficult to make a decision on which one to use, or even worse, realize it was not suited for different scenarios. In this paper we analyze five options selected arbitrarily and tested on a dataset of 755 images to detect persons in an image, using object detectors. We analyze elapsed time to process an image, error with observations by humans, number of persons detected, correlation of time and person density, object detected size and F1 Score, considering precision and recall. As we found there are score ties and similar behaviors among options available, we introduce a novel index that takes in consideration the number of persons and their pixel size, to propose the Vision Acuity Index of Computer Vision. The results demonstrate this is a good option to serve as indicator to make decisions. Also, this index proposed have a potential to be expanded for different business use cases, and to measure new proposed algorithms in the future along with the traditional metrics used previously.

This paper explores the application of machine learning (ML) in predicting functional recovery in patients with ischemic stroke. As technology advances, ML shows significant potential in the field of stroke medicine, especially in the areas of big data analytics and personalized medicine. Studies have shown that ML algorithms can improve the accuracy of stroke image analysis, subtype classification, risk assessment, treatment guidance, and prognosis prediction. However, the widespread use of ML still faces challenges such as data standardization, model validation, privacy, and bias. This paper reviews the current application status of ML in the field of stroke, discusses the challenges faced, and looks forward to the future development direction, aiming to promote the practical application of ML technology in the diagnosis and treatment of stroke to improve the prognosis and quality of life of patients.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

Heat transfer fluids are used in various industrial systems to maintain them in perfect operating conditions. Extensive research efforts have been dedicated to enhance the thermal properties of these heat transfer fluids to improve their efficiency. Developing nanofluids is a potential candidate for such enhancements. This study investigates the impact of incorporating TiO2 nanoparticles into two types of oils: transformer oil (NYTRO LIBRA) and virgin coconut oil (manufactured by Govi Aruna Pvt. Ltd.) at different temperatures and with varying volume fractions. The nanofluids were prepared using a two-step method by adding CTAB (Cetyltrimethylammonium bromide) surfactant. To minimize nanoparticle agglomeration, this study employed relatively low-volume fractions. Thermal properties by means of thermal conductivity, thermal diffusivity, and volumetric heat capacity were measured in accordance with ASTM (American Society for Testing and Materials) standard methods, using a multifunctional thermal conductivity meter (LAMBDA thermal conductivity meter). The measured thermal conductivity values were compared with theoretical models and previous research findings. It was confirmed that the modification of thermal properties was enhanced by doping TiO2 nanoparticles with different volume fraction.

This paper describes the successful application of the Transformer model used in the natural language processing and vision tasks as a means of processing the time series of signals from gyroscope and accelerometer sensors for the classification of human activities. The Transformer model is based on deep neural networks with many layers which can generalize well on signals. All measured signals come from a smartphone placed in a waist bag. Activity prediction is sequence-to-sequence, each time step of the signal is assigned a designation of the performed activity. Emphasis is placed on attention mechanisms, which express individual dependencies between signal values within a time series. In comparison with another recent result, the recognition precision was improved from 89.67 percent to 99.2 percent. The transformer model should in the future be included among the top options in machine learning methods for human activity recognition.

Agriculture is pivotal in national economies, with pest detection significantly influencing food quality and quantity. Pest classification remains challenging in automated agriculture monitoring systems, exacerbated by the non-uniform pest scales and the scarcity of high-quality datasets. In this study, we constructed a pest dataset by acquiring domain-agnostic images from the Internet and resizing them to a standardized 299x299 pixel format. Additionally, we employed diffusion models to generate supplementary data. While Convolutional Neural Networks (CNNs) are prevalent for prediction and classification, they often lack effective global information integration and discriminative feature representation. To address these limitations, we propose the RS Transformer, an innovative model that combines elements like the Region Proposal Network, Swin Transformer, and ROI Align. Additionally, we introduce the Randomly Generated Stable Diffusion Dataset (RGSDD) to augment the availability of high-quality pest datasets. Extensive experimental evaluations demonstrate the superiority of our approach compared to both two-stage models (SSD and Faster R-CNN) and one-stage models (YOLOv3, YOLOv4, YOLOv5m, YOLOv8, and DETR). We rigorously assess performance using metrics such as mean Average Precision (mAP), F1Score, Recall, and mean Detection Time (mDT). Our research contributes to advancing pest detection methodologies in automated agriculture systems, promising improved food production and quality.

Multi-view stereo (MVS) employs multi-point photography for image point positioning and three-dimensional reconstruction technology. Recently, this technology has been introduced into the monitoring of road slopes due to advances in photography and computing technology. In general, the various phases of post-image processing procedures are applied to various photographic data. In this study a novel, automated image-monitoring system is proposed to improve the ability of automatic processing. First, an Internet of things (IoT)-based digital photography system architecture was constructed to provide automatic control of camera photography and real-time transmission of image data. In addition, a visual SfM-MVS 3D reconstruction technique was used to develop related software and hardware interfaces based on the built-in Python computing framework of Photoscan Pro. The software integrates fully automatic photography, image transmission, monitoring of data processing and product release programs. The experimental results show that the system architecture can be applied to fully automatic three-dimensional monitoring of road slopes.

Estimating the Remaining Useful Life (RUL) of aircraft engines holds a pivotal role in enhancing safety, optimizing operations, and promoting sustainability, thus being a crucial component of modern aviation management. Precise RUL predictions offer valuable insights into an engine’s condition, enabling informed decisions regarding maintenance and crew scheduling. In this context, we propose a novel RUL prediction approach in this paper, harnessing the power of Bi-directional LSTM and Transformer architectures, known for their success in sequence modeling, such as natural languages. We adopt the encoder part of the full Transformer as the backbone of our framework, integrating it with a self-supervised denoising autoencoder that utilizes Bidirectional LSTM for improved feature extraction. Within our framework, a sequence of multivariate time series sensor measurements serves as the input, initially processed by the Bidirectional LSTM autoencoder to extract essential features. Subsequently, these feature values are fed into our Transformer encoder backbone for RUL prediction. Notably, our approach simultaneously trains the autoencoder and Transformer encoder, different from the naive sequential training method. Through a series of numerical experiments carried out on the C-MAPSS datasets, we demonstrate that the efficacy of our proposed models either surpasses or stands on par with that of other existing methods.

Indoor localization is an active area of research dominated by traditional machine-learning techniques. Deep learning-based systems have shown unprecedented improvements and have accomplished exceptional results over the past decade, especially the Transformer network within natural language processing (NLP) and computer vision domains. We propose the hyper-class Transformer (HyTra), an encoder-only Transformer with multiple classification heads (one per class) and learnable embeddings, to investigate the effectiveness of Transformer-based models for received signal strength (RSS) based WiFi fingerprinting. HyTra leverages learnable embeddings and the self-attention mechanism to determine the relative position of the wireless access points (WAPs) within the high-dimensional embedding space, improving the prediction of user location. From an NLP perspective, we consider a fixed order sequence of all observed WAPs as a sentence and the captured RSS value(s) for every given WAP at a given reference point from a given user as words. We test our proposed network on public and private datasets of different sizes, proving that the quality of the learned embeddings and overall accuracy improves with increments in samples.

In this research paper, a high gain transformer less inverter modeling which is used for the smart grid technology or as the stand alone for home appliances is proposed. The proposed transformer less topology provides a higher voltage gain, low cost, small size and simple control stand alone transformer less inverter for home appliances. The above inverter is modeled by using software which is known as MATLAB/ Simulimk.

We describe a vision for a national-scale heavy mineral (HM) map generated through automated mineralogical identification and quantification of HMs contained in floodplain sediments from large catchments covering most of Australia. The composition of the sediments reflects the dominant rock types in each catchment, with the generally resistant HMs largely preserving the mineralogical fingerprint of their host protoliths through the weathering-transport-deposition cycle. Heavy mineral presence/absence, absolute and relative abundance, and co-occurrence are metrics useful to map, discover and interpret catchment lithotype(s), geodynamic setting, magmatism, metamorphic grade, alteration or mineralization. Underpinning this vision is a pilot project, focusing on a subset of the national sediment sample archive, which is used to demonstrate the feasibility of the larger, national-scale project. We preview a bespoke, cloud-based mineral network analysis (MNA) tool to visualize, explore and discover relationships between HMs as well as between them and geological setting or mineral deposits. We envisage that the Heavy Mineral Map of Australia and MNA tool will contribute significantly to mineral prospectivity analysis and modeling here, particularly for technology critical elements and their host minerals, which are central to the global economy transitioning to a more sustainable, decarbonized paradigm.

Fatigue performance and self-repairing activity of asphalt binders are two properties that highly influence the fatigue cracking response of asphalt pavement. There are still numerous gaps of knowledge to fill linked with these two characteristics. For instance, current parameters fail to fully accommodate these two bitumen phenomena. This study aims to propose a new procedure to address this issue utilizing the linear amplitude sweep (LAS) test, LAS with rest period (RP) (LASH) test, and simplified viscoelastic continuum damage (S-VECD) model. This research work used four different types of asphalt binders: neat asphalt (NA), self-healing thermoplastic polyurethane (STPU)-modified bitumen (STPB), self-healing poly (dimethyl siloxane) crosslinked with urea bond (IPA1w)-modified bitumen (IPAB), and styrene–butadiene–styrene (SBS)-modified bitumen (SBSB). Before the testing process, all the materials were subjected to short-term and long-term aging. The new procedure showed a superior capacity to analyze and accommodate all bitumen fatigue performances and self-repairing activities compared to the current method. Another finding proved that asphalt binders with higher self-restoration behavior failed to show better fatigue performance. A breakthrough finding demonstrated that asphalt binder fatigue response augmented when the RP was applied at a higher damage intensity (S) value. STPBs and IPABs reached their highest increments of fatigue response, containing 1.0% of STPU and 0.5% of IPA1w, respectively. Those augmentations were 207.54% and 232.64%, respectively.

Visual object tracking is an important technology in camera based sensor networks, which has a wide range of practicability in auto drive system. A transformer is a deep learning model that adopts the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It makes such transformer-based applications be exposed to security threats. In this work, the security of the transformer model is investigated with the important component of autonomous driving, visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, so adversarial attacks are implemented as the security threats to conduct the investigation. First, adversarial examples are generated on top of video sequences to degrade tracking performance, and the frame-by-frame temporal motion is taken into consideration when generating perturbations over the predicted tracking results. Then, the influence of perturbations on performance is sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrate that the executed adversarial examples are effective on the performance drops of the transformer-based visual tracking.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges such as low imaging quality and high variability. There is a critical need to develop advanced automatic US image analysis methods to enhance diagnostic accuracy and objectivity. Vision transformer, a recent innovation in machine learning, has demonstrated significant potential in various research fields, including general image analysis and computer vision, due to its capacity to process large datasets and learn complex patterns. Its suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformer and discusses its applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in its application in medical US image analysis. Vision transformer has shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and is expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

This review paper provides a comprehensive overview of machine vision pose measurement algorithms. The paper focuses on the state-of-the-art algorithms and their applications. The paper is structured as follows: The introduction in Section 1 provides a brief overview of the field of machine vision pose measurement. Section 2 describes the commonly used algorithms for machine vision pose measurement. Section 3 discusses the factors that affect the accuracy and reliability of machine vision pose measurement algorithms. Section 4 presents the applications of machine vision pose measurement in various fields. The paper provides specific examples of how machine vision pose measurement is used in each of these fields. Finally, Section 5 summarizes the paper and provides future research directions. The paper highlights the need for more robust and accurate algorithms that can handle varying lighting conditions and occlusion. It also suggests that the integration of machine learning techniques may improve the performance of machine vision pose measurement algorithms. Overall, this review paper provides a comprehensive overview of machine vision pose measurement algorithms, their applications, and the factors that affect their accuracy and reliability. It provides a valuable resource for researchers and practitioners working in the field of computer vision.

The Avian retina is far less known than that of mammals such as mouse and macaque, and detailed study is overdue. The chicken (Gallus gallus) has potential as a model, in part because research can build on developmental studies of the eye and nervous system. One can expect differences between bird and mammal retinas simply because whereas most mammals have three types of visual photoreceptor birds normally have six. Spectral pathways and colour vision are of particular interest, because filtering by oil droplets narrows cone spectral sensitivities and birds are probably tetrachromatic. The number of receptor inputs is reflected in the retinal circuitry. The chicken probably has four types of horizontal cell, there are at least 11 types of bipolar cell, often with bi- or tri-stratified axon terminals, and there is a high density of ganglion cells, which make complex connections in the inner plexiform layer. In addition, there is likely to be retinal specialisation, for example chicken photoreceptors and ganglion cells have separate peaks of cell density in the central and dorsal retina, which probably serve different types of behaviour.

Vertebrate color vision is evolutionarily ancient. Jawless fish evolved four main spectral types of cone photoreceptor, almost certainly complemented by retinal circuits to process chromatic opponent signals. Subsequent evolution of photoreceptors and visual pigments are now documented for many vertebrate lineages and species, giving insight into evolutionary variation and ecological adaptation of color vision. We look at organization of the photoreceptor mosaic and the functions different types of cone in teleost fish, primates, and birds and reptiles. By comparison less is known about the underlying neural processing. Here we outline the diversity of vertebrate color vision and summarize our understanding of how spectral information picked up by animal photoreceptor arrays is adapted to natural signals. We then turn to the question of how spectral information is processed in the retina. Here, the quite well known and comparatively ‘simple’ system of mammals such as mice and primates reveals some evolutionarily conserved features such as the mammalian Blue^ON system which compares short and long wavelength receptors signals. We then survey our current understanding of the more complex circuits of fish, amphibians, birds and reptiles. Together, these clades make up more than 90% of vertebrate species, yet we know disturbingly little about their neural circuits for colour vision beyond the photoreceptors. Here, long-standing work on goldfish, freshwater turtles and other species is being complemented by new insights gained from the experimentally amendable retina of zebrafish. From this body of work, one thing is clear: The retinal basis of colour vision in non-mammalian vertebrates is substantially richer compared to mammals: Diverse and complex spectral tunings are established at the level of the cone output via horizontal cell feedforward circuits. From here, zebrafish use cone-selective wiring in bipolar cells to set-up color opponent synaptic layers in the inner retina, which in turn lead a large diversity of color-opponent channels for transmission to the brain. However, while we are starting to build an understanding of the richness of spectral properties in some of these species’ retinal neurons, little is known about inner retinal connectivity and cell-type identify. To gain an understanding of their actual circuits, and thus to build a more generalised understanding of the vertebrate retinal basis of color vision, it will be paramount to expand ongoing efforts in deciphering the retinal circuits of non-mammalian models.

Primate vision is an active process that constructs a stable internal representation of the 3D world based on 2D sensory inputs that are inherently unstable due to incessant eye movements. We present here a mathematical framework for processing visual information for a biologically-mediated active vision stereo system with asymmetric conformal cameras. This model utilizes the geometric analysis on the Riemann sphere developed in the group-theoretic framework of the conformal camera, thus far only applicable in modeling monocular vision. The asymmetric conformal camera model constructed here includes the fovea’s asymmetric displacement on the retina and the eye’s natural crystalline lens tilt and decentration, as observed in ophthalmological diagnostics. We extend the group-theoretic framework underlying the conformal camera to the stereo system with asymmetric conformal cameras. Our numerical simulation shows that the 1 theoretical horopter curves in this stereo system are conics that well approximate the empirical longitudinal horopters of the primate vision system.

Electrification of society, increasing renewable energy sources and mobility charging lead to new loading patterns for power transformers. Dynamic load conditions induce enhanced mechanical stress on the transformers’ windings, potentially causing degradation of the solid insulation over time and compromising the transformer's short-circuit withstand capability. Thermal expansion of the windings, caused by losses in the copper conductors, occurring as the transformer is load-ed, increases the stress. Conversely, magnetic losses in the core and tie plate expansion contribute to a reduction in stress. This paper presents the effect of step changes in core losses and copper losses by on-line measurements of the clamping pressure, to better understand the mechanical stresses acting upon the solid insulation cellulose materials.

Detection of partial discharge (PD) activities in high-voltage equipment can be done according to the several mechanisms of signal detection, which are electromagnetic wave signal detection, acoustic signal detection, chemical reactions, electrical signal detection, or optical emission detection. Recently, multiple methods of detection and localization of partial discharge activities occurred in power transformers and gas-insulated switchgear (GIS) have been proposed to monitor the health condition of high-voltage equipment, especially when the awareness regarding preventive maintenance has been emphasized at the industrial level and electrical providers. In aligning the needs of industrial and the improvement of PD detection methods, this manuscript focused on reviewing the current practice methods for the detection and localization of PD signals in high-voltage equipment and comparing their efficacy, in summarizing the future direction of research work-related methods of PD detection. The comparative reviews are discussed in terms of the mechanism of PD signal detection, indication parameters, calibration technique, advantages, and limitations of each method of PD measurement in detail.

Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Convolutional Transformer (DRCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCT model achieved an impressive average F1 score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Throughout 100 training epochs, the model exhibited strong generalization capabilities, achieving superior validation accuracy with minimal overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model's ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making.

Recommendation systems are crucial in navigating the vast digital market. However, user data’s dynamic and non-stationary nature often hinders their efficacy. Traditional models struggle to adapt to the evolving preferences and behaviours inherent in user interaction data, posing a significant challenge for accurate prediction and personalisation. Addressing this, we propose a novel theoretical framework, the Non-stationary Transformer, designed to capture and leverage the temporal dynamics within data effectively. This approach enhances the traditional transformer architecture by introducing mechanisms accounting for non-stationary elements, offering a robust and adaptable solution for recommendation systems. Our experimental analysis, encompassing deep learning and reinforcement learning paradigms, demonstrates the framework’s superiority over benchmark models. The empirical results confirm the efficacy of our proposed framework, which not only provides significant performance enhancements, approximately 8% in Logloss reduction and up to 2% increase in F1 score but also underscores its potential applicability across accumulative reward scenarios. These findings advocate adopting Non-stationary Transformer models to tackle the complexities of today’s recommendation tasks.

We propose Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes the 3×3 convolution in bottleneck of HRNet with Contextual Transformer (CoT) block, while reducing the complexity of the network. Specifically, CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on the query and contextualization keys, the dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for the multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module(AFAM). Technically, given an intermediate input, AFAM successively deduces attention maps along channel and spatial dimensions. Then, Adaptive refinement module(ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above studies, our lightweight network provides a powerful clue for detection of keypoints. Experiments are implemented on the COCO and MPII datasets. The model achieves 76.2 AP on the COCO val2017. Compared to other methods with the CNN as the backbone, CaFTNet reduces the number of parameters by 72.9 %. On the MPII, our method uses only 60.7% of the number of parameters, acquiring semblable results to other methods with the CNN as the backbone.

Structural magnetic resonance imaging (sMRI) is widely used in the clinical diagnosis of diseases due to its advantages: high definition and noninvasive. Therefore, computer-aided diagnosis based on sMRI images is broadly applied in classifying Alzheimer’s disease (AD). Due to the excellent performance of Transformer in computer vision, Vision Transformer (ViT) has been employed for AD classification in recent years. ViT relies on access to large datasets, while the sample size of brain imaging datasets is relatively insufficient. Moreover, the pre-processing procedures of brain sMRI images are complex and labor-intensive. To overcome the limitations mentioned above, we propose Resizer Swin Transformer (RST), a deep learning model that can extract information from brain sMRI images that are only briefly processed to achieve multi-scale and cross-channel features. In addition, we pre-trained our RST on a natural image dataset and obtained better performance. The experimental results of ADNI and AIBL datasets prove that RST can achieve better classification performance in AD prediction compared with CNN-based and Transformer models.

Long unpunctuated texts containing complex linguistic sentences are a stumbling block to processing any low-resource languages. Thus, approaches that attempt to segment lengthy texts with no proper punctuation into simple candidate sentences are a vitally important preprocessing task in many hard-to-solve NLP applications. In this paper, we propose (PDTS) a punctuation detection approach for segmenting Arabic text, built on top of a multilingual BERT-based model and some generic linguistic rules. Furthermore, we showcase how PDTS can be effectively employed as a text tokenizer for unpunctuated documents (i.e., mimicking the transcribed audio-to-text documents). Experimental findings across two evaluation protocols (involving an ablation study and a human-based judgment) demonstrate that PDTS is practically effective in both performance quality and computational cost.

Robotic odor source localization (OSL) is a technology that enables mobile robots or autonomous vehicles to find an odor source in unknown environments. An effective navigation algorithm that guides the robot to approach the odor source is the key to successfully locating the odor source. While traditional OSL approaches primarily utilize an Olfaction-only strategy, guiding robots to find the odor source by tracing emitted odor plumes, our work introduces a fusion navigation algorithm that combines both vision and olfaction-based techniques. This hybrid approach addresses challenges such as turbulent airflow, which disrupts olfaction sensing, and physical obstacles inside the search area, which may impede vision detection. In this work, we propose a hierarchical control mechanism that dynamically shifts the robot’s search behavior among four strategies: crosswind maneuver, Obstacle-avoid Navigation, Vision-based Navigation, and Olfaction-based Navigation. Our methodology includes a custom-trained deep-learning model for visual target detection and a moth-inspired algorithm for Olfaction-based navigation. To assess the effectiveness of our approach, we implemented the proposed algorithm on a mobile robot in a search environment with obstacles. Experimental results demonstrate that our Vision and Olfaction Fusion algorithm significantly outperforms Vision-only and Olfaction-only methods, reducing average search time by 54% and 30%, respectively.

The quality of yarn is essential in the control of the fabrics processes. There is some commercial equipment that measures the quality of yarn based on sensors, of different types, used for collecting data about some yarn characteristic parameters. The existing equipment, for the above-mentioned purpose, is characterized by its high size and cost, and for allowing the analysis of only few yarn quality parameters. Thus, this paper presents the development and results obtained with the design of a mechatronic prototype integrating a computer vision system that allows, among other parameters, the analysis and classification, in real time, of the hairs of the yarn using artificial intelligence techniques. The system also determines other characteristics inherent to the yarn quality analysis, such as: linear mass, diameter, volume, twist orientation, twist step, average mass deviation, coefficient of variation, hairiness coefficient, average hairiness deviation and standard hairiness deviation, as well as performs spectral analysis. A comparison of the obtained results with the designed system and a commercial equipment was performed validating the undertaken methodology.

Background: Retinal hemorrhages are an important ophthalmic diagnostic sign of underlying systemic vascular disorder. Capsaicin is a bioactive component of chili peppers used in most countries. Capsaicin crosses the blood–brain barrier in an efficient manner. Human exposure to capsaicinoids through diet is frequent and often substantial. Presumed lack of capsaicin toxicity in diet does not preclude rare adverse effects related to actions on the central neural system. Particularly on the retina, due to the reasons outlined in this case report. Methods: A case of a 34-year-old man, who reported sudden blurring of vision and micropsia in his left eye following ingestion of a considerable amount of red pepper. Results: The case study suggests that acute or chronic consumption of substantial amounts of hot red pepper in individuals with high reactivity towards TRPV1 agonists and/or higher expression of TRPV1 receptors in retinal ganglion cells causes retinal neovascularization. Conclusion: Acute consumption of red pepper may harm vision. This hypothesis can be easily evaluated retrospectively in larger sets of data.

Image classification in Remote Sensing and Geographic Information Systems (GIS) containing various land-cover classes is essential for efficient and sustainable land-use estimation, and other tasks like object detection, localization and segmentation. Deep Learning (DL) techniques have shown a tremendous potential in the GIS domain. While Convolutional Neural Networks (CNN) have dominated most of the image analysis domain, a new architecture called transformers have proved to be a unifying solution for several AI-based processing pipelines. Vision Transformers (ViT), a variant of transformers can have comparable and in some cases better accuracy than a CNN. However, they suffer from a significant drawback associated with an excessive use of training parameters. In this research we explore several modifications in the vision transformer architectures, especially MobileViT that can be optimized while boosting accuracy. To verify our proposed approach these new architectures are trained on four land-cover datasets AID, EuroSAT, UC-Merced, and WHU-RS19. Experiments reveal that combination of lightweight convolutional layers including ShuffleNet along with depthwise separable convolutions and average pooling can reduce the trainable parameters by 17.85% and yet achieve higher accuracy than the base MobileViT. It is also observed that utilizing a combination of convolution layers along with multi-headed self attention layers in MobileViT variants provide better performance in capturing local and global features unlike the standalone ViT architecture that utilizes almost 95% more parameters than the proposed MobileViT variant.

People with Down syndrome have more visual problems than general population. They experience a premature aging, and it would be expected they will also have an acceleration in worsening visual function. A prospective observational study which includes visual acuity, refractive error, accommodation, binocular and colour vision was performed to young adults with (n=69) and without (n=65) Down syndrome and to a senior group (n=55) without Down syndrome. Results showed significant differences in visual acuity between groups (p&lt;0.001) and it can be improved with a new prescription in 40% of the participants with Down syndrome. Regarding to accommodative state, no significant differences were found between groups of young people. Concerning binocular vision, 64.7% of strabismus was observed in the group with Down syndrome (p&lt;0.001). Visual abnormalities are significant in young adults with Down syndrome and are different from those of older people without Down syndrome, some of which can be improved by providing the optimal prescription as well as regular eye examinations.

Potholes on roads pose a major threat to motorists and autonomous vehicles. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

Introduction Color vision deficiency (CVD) constitutes one of the frequently observed eye disorders in all human populations. Color is a prominent sign utilized in the medical profession to study and identify histopathological specimens, lab instruments, and patient examination. Color deficiency affects the medical skills of students resulting in poor clinical examination and color appreciation. There is no effective screening of CVD at any level of the medical profession. Hence, this study was aimed to determine the prevalence of CVD among medical students. Materials and methods This was a cross-sectional study conducted from September 2019 to February 2020 over a period of six months in Karachi, Pakistan. All medical students aged 18-21 years of either gender enrolled in the first and second years of medical college were included in this study. The examination was performed during daylight. Ishihara plates were placed at a distance of 75 cm from the subject and tilted so that the plane of the paper lies perpendicular to the line of vision. Students were given five seconds to read the plate and one examiner was instructed to mark the checklist. A score of less than 12 out of 14 red/green test plates (not including the demonstration plate) was considered as a CVD. All statistical analysis was performed using Statistical Package for Social Sciences version 20.0 (Armonk, NY: IBM Corp). Results The mean age of the medical students was 19.61± 1.22 years. There were (n=123) 53.0% females and (n=111) 47.0% males. Most of the medical students (n=131, 56.0%) belonged to the upper-middle-class socioeconomic group. CVD was observed in (n=13) 6.0%of medical students. Age (p=0.001) and socioeconomic status (p=0.001) were the only demographic factors significantly associated with color deficiency. Conclusions Color deficiency, although an unnoticed concern, is fairly common among medical students. Medical students must be screened for CVD as this will enable them to be aware of their limitations in their future observational skills as a doctor and devise ways of overcoming them in clinical practice.

Autonomous aerial refueling technology is an effective solution to extend flight duration of unmanned aerial vehicles, and also a great challenge due to its high risk. For autonomous probe-and-drogue refueling tasks, relative navigation to provide relative position between the receiver aircraft and the refueling drogue is the first and essential step, and vision-based method is the most frequently used. A new monocular vision navigation sensor with image processing strategy consisting of the drogue detection method and the tracking method is developed for autonomous aerial refueling in this paper. In the drogue detection method, thresholding and mathematical morphology method are adopted to eliminate image interference, and contours extraction method is applied to obtain all contours, which are then subsequently checked to achieve target contour of drogue. In the tracking method, a rectangle of interest (ROI) of current frame image is determined by positioning results of last frame, and then processed by the previous drogue detection method. Finally, the proposed image processing strategy in monocular vision navigation sensor is validated using real flight images, which are captured from an autonomous aerial refueling testbed using a micro six-rotor aircraft as receiver aircraft.

With the development of human-computer interaction, the importance of emotion recognition is increasing. Emotion recognition technology provides practical benefits in various industries such as improving user experience, education, and organizational productivity. In education, emotion recognition can enable real-time understanding of students' emotional states and provide tailored feedback, and in the workplace, by monitoring employees' emotional states, it can improve work performance and job satisfaction. Therefore, multimodal-based research that combines text, speech, and video data for emotion recognition is being conducted in various industries. In this study, we propose an emotion recognition method that combines text and speech data, reflecting the characteristics of the Korean language. For text, KoELECTRA is used to perform embedding, and for speech, MFCC and pitch analysis are used to extract features. Finally, a multimodal transformer model is proposed that combines these two data types to perform emotion recognition. The multimodal transformer model processes text and speech data separately, and then learns the interaction between the two modalities through a Cross-Modal Attention mechanism. Through this, the complementary information from text and speech is effectively combined, improving emotion recognition performance. Experimental results show that the proposed model outperforms single-modality models, achieving a high accuracy of 73.13% and an F1-Score of 0.7344 in emotion classification. This study contributes to the advancement of emotion recognition technology by combining various language and modality data, and higher performance can be expected through the integration of additional modalities in the future.

In a densely populated country like Bangladesh, universities grapple with the challenge of efficiently addressing myriad queries from a large student body, leading to a heightened workload for university stakeholders. To tackle these challenges, we introduce PixieGPT, a tailor-made Generative Pre-Trained Transformer for Bangladeshi universities. PixieGPT significantly mitigates workload by adeptly handling common university-related queries, thereby enhancing user experience. The hierarchical structure plays a crucial role in managing diverse queries from thousands of students about the university system. The solution introduces a modular hierarchical knowledge base (KB) with simpler complexities, addressing the intricacies of efficiently managing large volumes of queries. PixieGPT is designed in a modular way so that the solution is also adaptable for the implementation of other universities worldwide based on the requirements of a particular administrative system. The modular nature facilitates easy adaptation with minor changes based on specific university requirements, ensuring a seamless integration process. This paper delves into the intricacies of PixieGPT's design, emphasizing its pivotal role in mitigating workload challenges for university stakeholders in Bangladesh. The incorporation of BERT for Natural Language Understanding(NLU) and GPT models for Natural Language Generation(NLG) enhances PixieGPT's capabilities, contributing to the scalability and efficiency of the system. The presented use case underscores the practical benefits of PixieGPT, positioning it as a promising solution for universities globally with similar operational frameworks.

The purpose of this study is to ​​explore the use of a custom Transformer model in brain-computer interfaces (BCIs) that translate the neural activity present when an individual with limited verbal and fine-motor skills attempts to handwrite. As found in previous studies, Transformers have performed better than recurrent neural networks (RNNs) in translation tasks which are similar to its usage here in decoding neural signals into intended handwritten text. Due to the known benefits of a Transformer, the hypothesis was that the Transformer would show promise in the context of a BCI through the recorded metrics. The neural signals of a tetraplegic individual, when they attempted to handwrite, were provided by existing research. Four trials were conducted using data with or without augmentation which the model used when training to separately minimize training loss and validation loss. When comparing the results of a BCI with the implementation of a Transformer model with the original RNN BCI (the original data source), the Transformer model performed less favorably across all four trials. Although the results do not indicate that the Transformer model currently outperforms an RNN BCI, it is important to note that further testing of the model's capabilities (such as training it with a larger and more preferable dataset and/or for longer, comparing training times between the RNN and Transformer, and/or seeing how the Transformer is improved with an offline autocorrect feature) is necessary before determining whether Transformers can enhance communication in this manner.

Safe, high-quality and economical electric energy transportation is the basic requirements of modern power system operation. Transformer, as one of the core equipment of power system and national grid system, has the characteristics of diverse types, variable models and wide deployment. It is the basic equipment for power system to realize voltage change and electric energy distribution. Because the power system transformer needs to operate with load for a long time, the probability of failure is usually higher than that of other power equipment in general. This paper starts from the transformer fault and fault diagnosis. Firstly, the transformer fault types, traditional transformer fault diagnosis techniques and the advantages of machine learning in transformer fault diagnosis are reviewed. Secondly, the application of information system theory and information entropy in transformer fault diagnosis is introduced. Then it introduces machine learning technology, feature selection and extraction technology in transformer fault diagnosis, and machine learning algorithms such as support vector machine and extreme learning machine for transformer fault diagnosis. Finally, the potential development trend of information system theory, information entropy and machine learning in transformer fault diagnosis is forecasted. The combination of transformer fault prediction and machine learning algorithm is helpful for power system maintenance personnel to accurately predict the running state of power equipment, and also provides a new method and technology for the safe and reliable operation and regular maintenance of power system.

UAV network operation enables gathering and fusion from disparate information sources for flight control in both manned and unmanned platforms. In this investigation, a novel procedure for detecting runways and horizons as well as enhancing surrounding terrain is introduced based on fusion of enhanced vision system (EVS) and synthetic vision system (SVS) images. EVS and SVS image fusion has yet to be implemented real-world situations due to signal misalignment. We address this through a registration step to align the EVS and SVS images. Four fusion rules combining discrete wavelet transform (DWT) sub-bands are formulated, implemented and evaluated. The resulting procedure is tested on real EVS-SVS image pairs and pairs containing simulated turbulence. Evaluations reveal that runways and horizons can be detected accurately even in poor visibility. Furthermore, it is demonstrated that different aspects of the EVS and SVS images can be emphasized by using different DWT fusion rules. The procedure is autonomous throughout landing, irrespective of weather. We believe the fusion architecture developed holds promise for incorporation into head-up displays (HUDs) and UAV remote displays to assist pilots landing aircraft in poor lighting and varying weather. The algorithm also provided a basis rule selection in other signal fusion applications.

With the emergence of autonomous functions in road vehicles, there has been an increased use of Advanced Driver Assistance Systems comprising various sensors to perform automated tasks. Light Detection and Ranging (LiDAR) is one of the most important types of optical sensor that detects the positions of obstacles, representing them as clusters of points in 3-dimensional space. LiDAR performance degrades significantly when driving in rain as raindrops adhere to the outer surface of the sensor assembly. The performance degradation behaviors include missing points and reduced reflectivity of the points. It was found that the extent of degradations is highly dependent on the interface material properties, which subsequently affects the shapes of the adherent droplets, causing different perturbations to the optical rays. A fundamental investigation is performed on the protective polycarbonate cover of the LiDAR assembly coated with four classes of materials – hydrophilic, almost-hydrophobic, hydrophobic, and superhydrophobic. Water droplets are controllably dispensed onto the cover to quantify the signal alteration due to each droplet of various sizes and shapes. To further understand the effects of droplet motion on LiDAR signals, sliding droplet conditions are simulated using numerical analysis and validated with physical optical tests using a 905 nm laser source and receiver to mimic the LiDAR detection mechanism. Comprehensive explanations are presented on LiDAR performance degradation in rain from both material and optical perspectives. These can aid component selection and the development of signal enhancing strategies for integrating LiDARs in vehicle designs to minimize the impact of rain.

The influence of the film thickness and the substrate’s refractive index on the surface mode at the superstrate is an important study step that may help clearing some of the misunderstandings surrounding their propagation mechanism. A single sub-wavelength slit perforating a thin metallic film is among the simplest nanostructure capable of launching Surface Plasmon Polaritons on its surrounding surface when excited by an incident field. Here, the impact of the substrate and the film thickness on surface waves is investigated. When the thickness of the film is comparable to its skin depth, SPP waves from the substrate penetrate the film and emerge from the superstrate, creating a superposition of two SPP waves, that leads to a beat interference envelope with well-defined loci which are the function of both the drive frequency and the dielectric constant of the substrate/superstrate. As the film thickness is reduced to the SPP’s penetration depth, surface waves from optically denser dielectric/metal interface would dominate, leading to volume plasmons that propagate inside the film at optical frequencies. Interference of periodic volume charge density with the incident field over the film creates charge bundles that are periodic in space and time.

A recently published article posited the use of polymer matrix composites (PMCs) as a replacement material for low-carbon steel (LCS) in large power transformer (LPT) tanks [1]. PMCs offer potential advantages such as weight reduction, corrosion prevention, and self-healing of the tank material which may not be achievable with traditional LCS. LCS can arrest ballistic projectiles at relatively low velocities, but at higher velocities, penetration can occur leading to a potential major transformer failure. Numerical simulations of steel projectile impacts upon LCS plates and glass and/or carbon fiber polymer composite laminates showed that with sufficient thickness both could prevent projectile penetration. This prevention was especially efficient when the plates were coated with a high strain rate sensitive material such as polyurea (PU). Our simulations show that the addition of a 3 mm coating of PU to a standard 10 mm thick LCS plate used in LPT tanks could prevent penetration of a 400 m/s steel projectile. For PMC plates, the simulations with the same projectile velocity showed three times faster deceleration with a 3 mm PU coating than without the coating. Thus, two realistic approaches to improving the ballistic protection of LPTs are presented. In addition to their other advantages, this research clearly shows that PMCs with the coating could provide significant ballistic protection for the next generation of LPT tanks.

In the realm of the five-category classification endeavor, there has been limited exploration into applied techniques for classifying Arabic text. These methods have primarily leaned on singletask learning, incorporating manually crafted features that lack robust sentence representations. Recently, the Transformer paradigm has emerged as a highly promising alternative. However, when these models are trained using single-task learning, they often face challenges in achieving outstanding performance and generating robust latent feature representations, especially when dealing with small datasets. This issue is particularly pronounced in the context of the Arabic dialect, which has a scarcity of available resources. Given these constraints, this study introduces an innovative approach to dissecting sentiment in Arabic text. This approach combines Inductive Transfer (INT) with the Transformer paradigm to augment the adaptability of the model and refine the representation of sentences. By employing self-attention SE-A and feed-forward sub-layers as a shared Transformer encoder for both the five-category and three-category Arabic text classification tasks, this proposed model adeptly discerns sentiment in Arabic dialect sentences. The empirical findings underscore the commendable performance of the proposed model, as demonstrated in assessments of the Hotel Arabic-Reviews Dataset, the Book Reviews Arabic Dataset, and the LARB dataset.