The accurate forecasting of solar power output is essential for ensuring the stable and efficient operation of grid-connected photovoltaic (PV) systems, especially when faced with variable weather patterns. This research focuses on the integration of Machine Learning (ML) methodologies and climatic parameters to predict solar panel energy generation, with a specific emphasis on addressing consumption-production imbalances. Leveraging a dataset sourced from the Kaggle platform, the study is conducted in the context of Estonia, aiming to optimize solar energy utilization in this geographic region. The dataset, obtained from Kaggle, encompasses comprehensive information on climatic variables, including sunlight intensity, temperature, and humidity, alongside corresponding solar panel energy output. Leveraging machine learning algorithms, including XGBoost regression and neural networks, our model aims to identify complex patterns and relationships within the datasets. By tailoring the model to Estonia's climatic nuances, we seek to enhance the accuracy of energy production forecasts and, consequently, better manage the challenges associated with consumption-production imbalances. Furthermore, the research investigates the adaptability of the proposed model to diverse climatic conditions, ensuring its applicability for similar endeavors in other geographical locations. The performance of the forecasting model will be evaluated using error metrics like mean absolute error (MAE) and root mean squared error (RMSE). This study leverages a comprehensive dataset from Kaggle and utilizes advanced machine learning techniques to generate valuable insights. These insights can inform the development of sustainable energy policies and practices, ultimately leading to a more efficient and reliable renewable energy infrastructure.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.

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

In this review, we summarize recent progress in crystal growth and understanding the influence of crystal structure on the superconductivity in pure and Pb-doped Bi2Sr2CuOy (Bi-2201) materials belonging to the overdoped region of high temperature cuprate superconductors. The crystal growth of Bi-2201 superconductors faces challenges due to intricate materials chemistry and lack of knowledge of corresponding phase diagrams. Historically, a crucible-free floating zone method has emerged as the most promising growth approach for these materials, resulting in high-quality single crystals. This review outlines the described in the literature and the authors' synthesis endeavors, encompassing Pb-doped Bi-2201 crystals, detailed structural characterization of as-grown and post-growth annealed samples, and highlights optimal growth conditions that yield large-size, single-phase, and compositionally homogeneous Bi-2201 single crystals.

Dynamic optical structural color is always desired in various display applications and usually involves active materials. Full-color generation, especially bi-directional full-color generation in both reflective and transmissive modes, without any active materials included has been rarely investigated. Herein, we demonstrate a scheme of bi-directional full-color generation based on a plasmonic metasurface modulated by rotation of the polarization angle of the incident light without varying the geometry and the optical properties of the materials and the environment where the metasurface resides. The metasurface unit cell consists of plasmonic modules aligning in three directions and is patterned in a square array. The metasurface structural color device generates full colors in both reflection and transmission. Based on the proposed polarization-dependent structural color, information encoding of three multiplexed animal images and quick-responsive (QR) codes is demonstrated to verify the efficient information encoding and decoding of the proposed scheme. The animals can be seen under different polarization incidence and the QR codes can be successfully decoded by the polarization rotation in transmission. The proposed bi-directional full-color generation metasurface has great potential in applications such as kaleidoscope generation, anti-counterfeiting, dynamic color display, and optical information encoding.

Alcohol use disorder (AUD) is a chronically relapsing disease characterized by loss of control in seeking and consuming alcohol (ethanol) driven by recruitment of brain stress systems. However, AUD differs among the sexes: men are more likely to develop AUD, but women progress from casual to binge drinking and heavy alcohol use more quickly. The central amygdala (CeA) is a hub of stress and anxiety, with corticotropin releasing factor (CRF)-CRF1 receptor and GABAergic signaling dysregulation occurring in alcohol dependent male rodents. However, we recently showed that GABAergic synapses in female rats are less sensitive to the acute effects of ethanol. Here, we used patch clamp electrophysiology to examine the effects of alcohol dependence on the CRF-modulation of rat CeA GABAergic transmission of both sexes. We found that GABAergic synapses of naïve female rats were unresponsive to CRF application compared males, although alcohol dependence induced a similar CRF responsivity in both sexes. In situ hybridization revealed that females had less CeA neurons containing mRNA for the CRF1 receptor (Crhr1) than males, but in dependence, the percentage of Crhr1-expressing neurons in females increased, unlike males. Overall, our data provide evidence for sexually dimorphic CeA CRF system effects on GABAergic synapses in dependence.

In this study, we evaluated the antibacterial effect against Staphylococcus aureus and Salmonella Typhimurium in fried fish paste using floating electrode-dielectric barrier discharge (FE-DBD) plasma (1.1 kV, 43 kHz, N2 1.5 m/s, 1-60 min). In addition, quality evaluation (pH, VBN) of fried fish paste was conducted after FE-DBD plasma treatment. When FE-DBD plasma was treated for 1, 5, 10, 20, 30 and 60 min, S. aureus decreased by 0.16-1.13 log10 CFU/g, and S. Typhimurium decreased 0.25-1.13 log10 CFU/g. Both decreased > log10 CFU/g at 60 min. The D-value was 58.92 and R2 was 0.97 for S. aureus using first-order kinetics, and the D-value was 43.60 and R2 was 0.97 for S. Typhimurium using the Weibull model. There was no significant difference in pH after FE-DBD plasma treatment (p > 0.05). However, volatile basic nitrogen (VBN) significantly decreased as the treatment time increased (p < 0.05), and it was the lowest at 60 min to 3.46. Therefore, FE-DBD plasma treatment could be considered as a technology for preserving the quality of processed foods.

The Giant Babax, an endemic bird in China and a nationally protected wildlife species of Class Ⅱ, is primarily distributed in southern and southeastern Tibet. To investigate the factors influencing nesting site selection, this study conducted research on nest characteristics and nesting site preferences at four sample sites around Lhasa from March to October 2023y, using systematic search methods, tracking methods, and sampling methods. The research findings are as follows: (1) The average nest depth was (7.70±1.47)cm, nest height was (19.58±2.97)cm, inner diameter was (10.64±1.73)cm, outer diameter was (24.65±4.8)cm, average weight was (162.3±13.5)g, and average nest spacing within the plot was 396.93m. (2) The nests of Giant Babax were predominantly found on vegetation such as Salix longistamina (38%), Hippophae gyantsensis (20%), Rosa sericea Lindl. (14%), and Populus szechuanica Schneid(11%). They showed a preference for artificial secondary forests as nesting sites. (3) Giant Babax exhibited a preference for habitats with robust trees that had high canopies while being distant from houses and roads, but close to water sources; moreover, the canopy of the nesting tree played a crucial role in their choice of nesting sites. (4) The reproductive success rate reached 76%, with key factors affecting it being the canopy coverage of the nesting tree and the number of helpers. These research results provide fundamental data support for population conservation efforts and ecological resource management strategies concerning the Giant Babax.

In this study, we introduce a new class of bi-univalent functions using q-Janowski Function. We derive the Fekete-Szegö functional problems for functions in this new subclass, as well as estimates for the Taylor-Maclaurin coefficients |α2| and |α3|. Furthermore, a collection of fresh outcomes are3 presented by customizing the parameters employed in our initial discoveries.

When analyzing user geospatial information through deep learning methods, it is typically necessary to annotate existing geospatial data. Currently, manual annotation methods are commonly employed, suffering from issues related to low efficiency and accuracy. This design is based on the TensorFlow deep learning framework and first realizes the BiLSTM+CRF+AGG deep learning model. Among the models, AGG is the aggregation layer, which is introduced to solve the problem of solid particle size equilibrium. Secondly, based on the characteristics of original data and professional data, an automatic labeling algorithm is proposed. The algorithm first preprocesses the acquired original data set and professional data set, The most valuable unlabeled data set which can make the training model converge quickly is selected from the original data set as the target data set. Sort the target data set based on preset rules and set annotation parameters for the sorted target data set. Based on the set annotation parameters, the corpus is synthesized and used as the annotation result. Thirdly, based on the active learning strategy, a manual annotation auxiliary scheme is proposed, and an Excel generation module that is convenient for manual annotation correction is designed and developed to further improve the efficiency and quality of annotation through iterative processing. The combination of the BiLSTM+CRF+AGG deep learning model and high-quality annotation can accurately identify non-standard, incomplete, or even incorrect geographical information entities. This annotation method has found successful practical application within the context of the research project and has been granted an invention patent.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Accurate classification of objects in 3D point clouds is a significant problem in several applications, such as autonomous navigation and augmented/virtual reality scenarios, which has become a research hot spot. In this paper, we presented a deep learning strategy for 3D object classification in augmented reality. The proposed approach is a combination of the GRU and LSTM. LSTM networks learn longer dependencies well, but due to the number of gates, it takes longer to train; on the other hand, GRU networks have a weaker performance than LSTM, but their training speed is much higher than GRU, which is The speed is due to its fewer gates. The proposed approach used the combination of speed and accuracy of these two networks. The proposed approach achieved an accuracy of 0.99 in the 4,499,0641 points dataset, which includes eight classes (unlabeled, man-made terrain, natural terrain, high vegetation, low vegetation, buildings, hardscape, scanning artifacts, cars). Meanwhile, the traditional machine learning approaches could achieve a maximum accuracy of 0.9489 in the best case.

Bicyclic peptides have attracted the interest of pharmaceutical companies because of their remarkable properties putting them on a new path in medicine. Their conformational rigidity that improves proteolytic stability, leads to rapid penetration into tissues via any possible route of administration and elimination, occurring by renal metabolism, is of great importance for people with a history of liver diseases. In addition, each ring can function independently, making them extremely versatile molecules for further optimization. In this paper we compared the potentiometric and spectroscopic properties studied by UV-Vis, MCD, and EPR, of four synthetic analogues of the bi-cyclic peptide c(PKKHP-c(CFWKTC)-PKKH). In particular we correlated the structural and spectral properties of complexes with coordinating abilities toward Cu(II) ions of MCL (Ac-PKKHPc(CFWKTC)PKKH-NH2) that contains the unbinding cycle and N- and C-terminal linear parts, with two histidine residues, one per part; two monocyclic ligands containing one histidine residue, both in the N-terminal position i.e., MCL2 (Ac-PKKHPc(CFWKTC)PKKS-NH2) and in the C-terminal position i.e., MCL3 (Ac-PKKSPc(CFWKTC)PKKH-NH2), respectively, and the linear structure LNL (Ac-PKKHPSFWKTSPKKH-NH2).

The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.

This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.

This study focuses on the reasoning of symptoms of TCM internal diseases. Taking cough as an example, the BERT-BiLSTM-CRF model is used for entity recognition. Experiments show that the model has the best entity recognition effect on three types of texts, including teaching cases, clinical cases and literature data, and the F1 value is up to 0.967. It can effectively identify symptoms, course of disease, tongue condition and pulse condition in TCM diagnosis and treatment texts, which lays a solid foundation for intelligent assisted syndrome differentiation and treatment of TCM. By constructing four types of entity corpora and using three mainstream entity recognition models for experiments, it is found that the BERT-BiLSTM-CRF model has a good entity recognition effect in three types of data: teaching cases, clinical cases and literature data. Experimental results show that the F1 values of the BERT-bilSTM-CRF model in teaching cases, clinical cases and literature data are 0.967, 0.82 and 0.91, respectively, which provides an effective method for information extraction in the field of TCM syndrome differentiation diagnosis and treatment, and lays a foundation for further research on knowledge reasoning.

This paper describes a stochastic clustering architecture that is used in the paper for making predictions over energy data. The design is discrete, localised optimisations based on similarity, followed by a global aggregating layer, which can be compared with the recent random neural network designs, for example. The topic relates to the IDEAS Smart Home Energy Project, where a client-side Artificial Intelligence component can predict energy consumption for appliances. The proposed data model is essentially a look-up table of the key energy bands that each appliance would use. Each band represents a level of consumption by the appliance. This table can replace disaggregation from more complicated methods, usually constructed from probability theory, for example. Results show that the table can accurately disaggregate a single source to a set of appliances, because each appliance has quite a unique energy footprint. As part of predicting energy consumption, the model could possibly reduce costs by 50% and more than that if the proposed schedules are also included. The hyper-grid has been changed to consider rows as single units, making it more tractable. A second case study considers wind power patterns, where the grid optimises over the dataset columns in a self-similar way to the rows, allowing for some level of feature analysis.

Responsible, efficient, and environmentally conscious energy consumption practices are increasingly essential for ensuring the reliability of the modern electricity grid. This study focuses on leveraging time series analysis to improve forecasting accuracy, crucial for various application domains where real-world time series data often exhibit complex, non-linear patterns. Our approach advocates for utilizing Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models for precise time series forecasting. To ensure a fair evaluation, we compare the performance of our proposed approach with traditional neural networks, time-series forecasting methods, and conventional decline curves. Additionally, individual models based on LSTM, Bi-LSTM, and other machine learning methods are implemented for a comprehensive assessment. Experimental results consistently demonstrate that our proposed model outperforms all benchmarking methods in terms of mean absolute error (MAE) across most datasets. Addressing the imbalance between activations by consumer and prosumer groups, our predictions show superior performance compared to several traditional forecasting methods, such as the Autoregressive Integrated Moving Average model (ARIMA) and Seasonal Autoregressive Integrated Moving Average model (SARIMA). Specifically, the root mean square error (RMSE) of Bi-LSTM is 5.35%, 46.08%, and 50.6% lower than LSTM, ARIMA, and SARIMA, respectively, on the May test data.

Aluminum profile surface defects can greatly affect the performance, safety and reliability of products. Traditional human-based visual inspection is low accuracy and time consuming, and machine vision-based methods depend on hand-crafted features which need to be carefully designed and lack robustness. To recognize the multiple types of defects with various size on aluminum profiles, a multiscale defect detection network based on deep learning is proposed. Then, the network is trained and evaluated using aluminum profile surface defects images. Results show 84.6%, 48.5%, 96.9%, 97.9%, 96.9%, 42.5%, 47.2%, 100%, 100%, 43.3% average precision(AP) for the ten defect categories, respectively, with a mean AP of 75.8%, which illustrate the effectiveness of the network in aluminum profile surface defects detection. In addition, saliency maps also show the feasibility of the proposed network.

Detection of formaldehyde is very important in terms of life protection, as it can cause serious injury to eyes, skin, mouth and gastrointestinal function if indirectly inhaled and hence researchers are putting effort in developing novel and sensitive device. In this work, we have fabricated an electro-chemical sensor in the form of a field effect transistor (FET) to detect formaldehyde over wide range (10 nM to 1 mM). For this, ZnO nanosheets (NS) were first synthesized by hydrothermal method with in-situ deposition on cleaned SiO₂ coated Si (100) substrate. The synthesized materials were characterized for morphology and purity and surface area (31.718 m²/g). The developed device was tested for formaldehyde detection at room temperature that resulted in a linear response with concentration (96%), sensitivity value of 0.27 mA/M/cm² and a low detection limit of 210 nM, and a high 0.93194 return.

In this study, the effect of NaOCl (10–200 ppm of Cl2) on the inactivation of human norovirus (HuNV) GII.4 and hepatitis A virus (HAV) in groundwater was investigated using PMA/RT­qPCR. Initially, 4.00 log copies/μL of HuNV GII.4 or 5.50 log copies/μL of HAV were artificially inoculated in ground water. The titers of HuNV GII.4 and HAV decreased significantly (p < 0.05) with increasing Cl2 concentrations. Ground water was treated with 10, 30, 50, 100, 150, and 200 ppm of Cl2, and the viable HuNV GII.4 was significantly (p < 0.05) reduced to 3.28 (0.21 log reduction), 3.18 (0.31 log reduction), 3.01 (0.48 log reduction), 2.75 (0.74 log reduction), 2.54 (0.95 log reduction), and 2.34 (1.15 log reduction) log copies/μL, respectively. The viable HAV was also significantly (p < 0.05) reduced to 4.99 (0.23 log reduction), 4.76 (0.46 log reduction), 4.55 (0.67 log reduction), 4.21 (1.01 log reduction), 3.89 (1.33 log reduction), and 3.64 (1.58 log reduction) log copies/μL, respectively. The decimal reduction time (D-value) (1-log reduction) of HuNV GII.4 and HAV infectivity in ground water was predicted as 116.7 and 98.9 ppm of Cl2, respectively using the first-order kinetics model (HuNV GII.4 ; y = - 0.0054x + 3.3585, R2= 0.97, HAV ; y = - 0.0091x + 5.0470, R2= 0.97). The result specifically suggests that 150–200 ppm Cl2 can potentially be used for the inactivation of > 1 log copies/μL HuNV GII.4 and HAV in ground water.

Cognitive neuroscience is the study of how the human brain functions on tasks like decision making, language, perception and reasoning. Deep learning is a class of machine learning algorithms that use neural networks. They are designed to model the responses of neurons in the human brain. Learning can be supervised or unsupervised. Ngram token models are used extensively in language prediction. Ngrams are probabilistic models that are used in predicting the next word or token. They are a statistical model of word sequences or tokens and are called Language Models or Lms. Ngrams are essential in creating language prediction models. We are exploring a broader sandbox ecosystems enabling for AI. Specifically, around Deep learning applications on unstructured content form on the web.

This study developed Makgeolli (Korean traditional alcoholic beverage) by adding raw 20% Codium fragile (Cf), a green seaweed, to a mixed base consisting of rice and oats (1:1 ratio) (COM) and analyzed its quality characteristics and antioxidant activity. The rice based Makgeolli supplemented with raw 20% Cf was designated as control (CRM). The physicochemical (pH, acidity), microbiological (yeast, lactic acid bacteria), antioxidant (DPPH, ABTS), and sensory properties (7-henodonic scale) of CRM and COM were investigated during 7 days of fermentation. The pH/acidity levels of CRM and COM reached 3.66/0.68 and 3.69/0.95 after 7 days of fermentation, respectively. Compared to CRM, COM had lower alcohol and sugar contents (P < 0.05) (CRM: 14.5%/9.8 Brix, COM: 11.2%/7.4 Brix). However, COM contained more yeast and lactic acid bacteria (P < 0.05) (CRM: 1.30/4.28 log, COM: 6.04/6.09 log) compared to CRM. The antioxidant activity of DPPH/ABTS (P < 0.05) in COM was approximately 1.5 times that of CRM (CRM: 40.00/51.57%, COM: 56.76/70.91%). In addition, COM had an excellent sensory preference score (P < 0.05) due to its overall fresh flavor and savory taste (CRM: 4.93, COM: 6.06). Therefore, COM was shown to be Makgeolli with enhanced antioxidant function, with yeast and lactic acid bacteria, and improved flavor, suggesting the possibility of commercializing this Makgeolli.

This article presents the implementation of a model to estimate the future price of commodities in the Brazilian market from time series of short-term technical evaluation. For this, data from two databases were used, one referring to the foreign market (opening values, maximum, minimum, closing, closing adjustment and volume) and the other, from the Brazilian market (the price of the day), considering commodities, sugar, cotton, corn, soybean and wheat. Subsequently, the technical indicators were calculated from the TA-Lib technical analysis library. Pearson’s correlation coefficient was applied, records with low correlation were removed, and then the database was consolidated. From the pre-processed data, Long Short-Term Memory (LSTM) recurrent neural networks were used to perform data prediction at the one and three day interval. These models were evaluated using the mean square error (MSE), obtaining results between 0.00010 and 0.00037 on test data one day ahead, and from 0.00017 to 0.00042 three days ahead. However, based on the results obtained, it was observed that the developed model obtained a promising forecasting performance for all the commodities evaluated. As a main contribution, there is the consolidation of databases that can be used in future scientific research. Furthermore, based on its interpretation, it can assist in decision making regarding the buying and selling of commodities to increase financial gains.

Sign language recognition technology can help people with hearing impairments to communicate with those who are hearing impaired. At present, with the rapid development of society, deep learning technology also provided certain technical support for sign language recognition work. In sign language recognition tasks, the use of traditional convolutional neural networks to extract spatio-temporal features from sign language videos suffers from insufficient feature extraction, resulting in low recognition rates. Nevertheless, video-based sign language datasets are very large and require a lot of computational resources for training and generalisation must be ensured, which poses a challenge for recognition. In this paper, we have presented a video-based sign language recognition method based on resnet and lstm. As the number of network layers increases, the ResNet network can effectively solve the granularity explosion problem and obtain better time series features. We use the Resnet convolutional network as the backbone model. At the initialisation stage, we obtain sign language features using ResNet; then, the learned feature space is used as the input of LSTM network to obtain long sequence features. The experimental results show that the accuracy of the above model is better than the mainstream model, and it can effectively extract the spatio-temporal features in sign language videos and improve the recognition rate of sign language actions.

We investigate the power of time series analysis based on a variety of information-theoretic approaches from statistics (AIC, BIC) and machine learning (Minimum Message Length) - and we then compare their efficacy with traditional time series model and with hybrids involving deep learning. More specifically, we develop AIC, BIC and Minimum Message Length (MML) ARMA (autoregressive moving average) time series models - with this Bayesian information-theoretic MML ARMA modelling already being new work. We then study deep learning based algorithms in time series forecasting, using Long Short Term Memory (LSTM), and we then combine this with the ARMA modelling to produce a hybrid ARMA-LSTM prediction. Part of the purpose of the use of LSTM is to seek capture any hidden information in the residuals left from the traditional ARMA model. We show that MML not only outperforms earlier statistical approaches to ARMA modelling, but we further show that the hybrid MML ARMA-LSTM models outperform both ARMA models and LSTM models.

Network Embedding (NE) is an important method to learn the representations of network via a low-dimensional space. Conventional NE models focus on capturing the structure information and semantic information of vertices while neglecting such information for edges. In this work, we propose a novel NE model named BimoNet to capture both the structure and semantic information of edges. BimoNet is composed of two parts, i.e., the bi-mode embedding part and the deep neural network part. For bi-mode embedding part, the first mode named add-mode is used to express the entity-shared features of edges and the second mode named subtract-mode is employed to represent the entity-specific features of edges. These features actually reflect the semantic information. For deep neural network part, we firstly regard the edges in a network as nodes, and the vertices as links, which will not change the overall structure of the whole network. Then we take the nodes' adjacent matrix as the input of the deep neural network as it can obtain similar representations for nodes with similar structure. Afterwards, by jointly optimizing the objective function of these two parts, BimoNet could preserve both the semantic and structure information of edges. In experiments, we evaluate BimoNet on three real-world datasets and task of relation extraction, and BimoNet is demonstrated to outperform state-of-the-art baseline models consistently and significantly.

"Finding fresh water in the ocean of data." is a challenge that all deep learning domains struggle with, especially in the area of hyperspectral image analysis. As hyperspectral remote sensing technology advances by leaps and bounds, there are increasing amounts of hyperspectral images(HSIs) can be available. Whereas in fact, these unlabeled HSIs are powerless to be used as material to driven a supervised learning task due to the extremely expensive labeling costs and some unknown regions. Although learning-based methods have achieved remarkable performance due to their superior ability to represent features, at the cost, these methods are complex, inflexible and tough to carry out transfer learning. In this paper, we propose the "Instructional Mask AutoEncoder"(IMAE), which is a simple and powerful self-supervised learner for HSI classification that uses a transformer-based mask autoencoder to extract the general features of HSIs through a self-reconstructing agent task. Moreover, we utilize the metric learning to perform an instructor which can direct the model focus on the human interested region of the input so that we can alleviate the defects of transformer-based model such as local attention distraction, lack of inductive bias and tremendous training data requirement. In downstream forward propagation, instead of global average pooling, we employ a learnable aggregation to put the tokens into fullplay. The obtained results illustrate that our method effectively accelerates the convergence rate and promotes the performance in downstream task.

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

Breast Cancer diagnosis is one of the most studied problems in the medical domain. In the medical domain, cancer diagnosis has been studied extensively which instantiates the need of early prediction of cancer disease. For obtaining advance prediction, health records are exploited and given as input to an automated system. This paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining possibility of being affected by breast cancer. Proposed model is compared against other baseline classifiers such as stacked Simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that stacked GRU-LSTM-BRNN yield better classification performance for predictions related to breast cancer disease.

With an explosion of data in the nearly every domain, from physical and environmental sciences to econometrics and even social science, we have entered a golden era of time-domain data science. In addition to ever increasing data volumes and varieties of time-series, there's a plethora of techniques available to analyses them. Unsurprisingly, machine learning approaches are very popular. In environmental sciences (ranging from climate studies to space weather/solar physics), machine learning (ML )and deep learning (DL) approaches complement the traditional data assimilation approaches. In solar and astrophysics, multiwavelength time-series or lightcurves along with observations of other messengers like gravitational waves provide a treasure trove of time-domain data for ML/DL approaches for modeling and forecasting. In this regard, deep learning algorithms such as recurrent neural networks (RNNs) should prove extremely powerful for forecasting as it has in several other domains. Such methods agnostic of the physics can only predict transient flares that are represented in the original distribution trained on (eg. coloured noise fluctuations) and not special, isolated episodes (eg. a one-off outburst like a major coronal mass ejection) potentially distinguishing them. Therefore it is vital to test robustness of these techniques ; here we attempt to make a small contribution to this by exploring sensitivity of RNNs with some rudimentary experiments. We test the performance of a very successful class of RNNs, the Long Short Term Memory (LSTM) algorithms with simulated lightcurves. As an example, we focus on univariate forecasting of time-series (or lightcurves) characteristic certain variable astrophysical objects (eg. active galactic nuclei or AGN). Specifically, we explore the sensitivity of training and test losses to key parameters of the LSTM network and data characteristics namely gaps and complexity measured in terms of number of Fourier components. We find that typically, the performances of LSTMs are better for pink or flicker noise type sources. The key parameters on which performance is dependent are batch size for LSTM and the gap percentage of the lightcurves. While a batch size of $10-30$ seems optimal, the most optimal test and train losses are under $10 \%$ of missing data for both periodic and random gaps in pink noise. The performance is far worse for red noise. This compromises detectability of transients. Thus, we show that generative models (time-series simulations) are excellent guides for use of RNN-LSTMs in building forecasting systems

Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

Stability considerations play a central role in structural dynamics to determine states that are robust against perturbations during the operation. Linear stability concepts, such as the complex eigenvalue analysis, constitute the core of analysis approaches in engineering reality. However, most stability concepts are limited to local perturbations, i.e. they can only measure a state’s stability against small perturbations. Recently, the concept of basin stability has been proposed as a global stability concept for multi-stable systems. As multi-stability is a well-known property of a range of nonlinear dynamical systems, this work studies the basin stability of bi-stable mechanical oscillators that are affected and self-excited by dry friction. The results indicate how the basin stability complements the classical binary stability concepts for quantifying how stable a state is given a set of permissible perturbations.

South Korea proposed reducing greenhouse gas emissions by 37% compared to the expected emissions by 2030 as the POST-2020 greenhouse gas reduction target. Electric vehicle distribution in the public sector is essential to achieve the carbon dioxide reduction target for transportation. In particular, when buses with internal combustion engines, which travel long distances and contribute substantially to greenhouse gas emissions, are replaced with electric buses, it is expected that greenhouse gas emissions will be significantly reduced. There are three types of electric buses with different power supply systems: a plug-in type in which power is supplied when a plug is inserted, a battery-swapping type in which a battery mounted on top of the vehicle is swapped at a swapping station, and a wireless type in which the battery is wirelessly charged through self-induction at a charging facility installed on the road. Vehicles of each charging type have different advantages and disadvantages. The performance, charging type, battery capacity, and operating environment of electric buses are mutually related parameters that must be considered when introducing such vehicles. Therefore, the optimal charging type must be selected according to the operating environment to enable the widespread use of electric buses. As such, this report proposes the optimal charging type according to the operating environment of public-sector electric vehicles.

This work addresses the intricate task of predicting the prices of diverse financial assets, including stocks, indices, and cryptocurrencies, each exhibiting distinct characteristics and behaviors under varied market conditions. To tackle the challenge effectively, a novel hybridized architecture, AE-GRU, integrating the encoder-decoder principle with GRU is designed. The experimentation involves multiple activation functions and hyperparameter tuning. With extensive experimentation and enhancements applied to AE-LSTM, the proposed AE-GRU architecture still demonstrates significant superiority in forecasting the annual prices of volatile financial assets from multiple sectors mentioned above. Thus, the novel AE-GRU architecture emerges as a superior choice for price prediction across diverse sectors and fluctuating market scenarios by extracting important non-linear features of financial data and retaining the long-term context from past observations.

Caring for dolphins is a delicate process that requires experienced caretakers to pay close attention to their behavioral characteristics. However, caretakers may sometimes lack experience or not be able to give their full attention, which can lead to misjudgment or oversight. To address these issues, a dolphin behavior analysis system has been designed to assist caretakers in making accurate assessments. The study utilized image preprocessing techniques to reduce sunlight reflection in the pool and enhance the outline of dolphins, making it easier to analyze their movements. The dolphins were divided into 11 keypoints using an open-source tool called DeepLabCut, which helped accurately mark various body parts for skeletal detection. The AquaAI Dolphin Decoder (ADD) was then used to analyze six dolphin behaviors. To improve behavior recognition accuracy, the Long Short-Term Memory (LSTM) neural network was introduced. The ADD and LSTM models were integrated to form the ADD-LSTM system. Several classification models, including unidirectional and bidirectional LSTM, GRU, and SVM, were compared. The results showed that the ADD module combined with a double-layer bidirectional LSTM method achieved high accuracy in dolphin behavior analysis. The accuracy rates for each behavior were over 90%.

Predicting the prices of cryptocurrency owing to its volatility, instability, and other factors has been challenging; investors and traders especially in Nigeria have been on a constant look for a more reliable way of knowing market trends and prices and while there has been so many research conducted using deep learning, the results for which has fall short of what investors could called a strong predictor. This research reviewed the results of many works that had been done and proposed two types of recurrent neural network (RNNs) namely Long Short-Term Memory and Gated Recurrent Unit (GRU) for predicting the future prices of two of the most common crypto assets namely Bitcoin (BTC) and Ethereum (ETH), these two were selected based on their popularity, the volume traded and their market capitalization. The experiment was conducted in a GPU Jupyter Notebook environment and the performance of our experiment was evaluated on a test set using root mean square error (RMSE) and based on its values, the LSTM presented a better performance with rsme scores of 654.66, and 80.30 respectively for BTC and ETH as compared to GRU. The paper proceeds further to compare the results of this experiment with other related works and we discovered that its performance is a great improvement.

Coastal wave modeling and forecasting are essential in oceanography, sustainable marine energy, and ocean engineering. Precise forecasting of wave speed and direction are crucial for offshore operations, marine energy, risk management, environmental management, coastal and sustainable maritime management. The coastline of Brunei Darussalam can generate between 15 and 126 Giga Watt of wave energy. In this experimental research, we used two numerical approaches, the finite difference, and spectral element methods, to model and simulate wave speed and direction. We calculated the mean error between numerical and analytical solutions. We proposed a novel, promising, univariate time series forecasting model by combining the Long Short-Term (LSTM) with KerasTuner hyperparameters tuning and optimization techniques. This method helps us to improve the accuracy and efficiency of time-series forecasting.. The experimental data was computed from high-precision Acoustic Doppler Current Profiler (ADCP) sensor data. This research is part of the preliminary feasibility analysis of wave energy production in Brunei Darussalam and net zero commitment for a sustainable environment. Seven independent forecast experiments were performed for wave speed and direction in degree and radian units for 1, 3, 6, 8, 10, 12, and 24 hours. Mean squared error (MSE) was adopted as a metric for both training and testing. The experimental results reveal that the wave speed forecast has the lowest MSE compared to direction, regardless of the unit of measure, but has a longer duration. In addition, the direction forecast in the degree unit has the lowest errors compared to the unit of radians; the latter has a longer running time than the former. The model has delivered optimal results throughout the experiments with minor training and test errors. We conducted a thorough evaluations on two benchmark time series datasets, which include the study dataset and air quality index dataset, to validate the performance of the proposed model with other models. The proposed model outperforms cutting-edge forecasting models, such as the conventional LSTM, ARIMA, and Prophet. The model has the slightest forecast error compared to the existing literature’s result.

The choice of holiday destinations is highly depended on climate considerations. Nowadays, since the effects of climate crisis are being increasingly felt, the need of accurate weather and climate services for hotels is crucial. Such a service could be beneficial for both the future planning of tourists’ activities and destinations and for hotel managers as it could help in decision making about the planning and expansion of the touristic season, due to a prediction of higher temperatures for a longer time span, thus causing increased revenue for companies in the local touristic sector. The aim of this work is to calculate predictions on climatic variables using statistical techniques as well as Artificial Intelligence (AI) for a specific area of interest utilising data from in situ meteorological station, and produce valuable and reliable localised predictions with the most cost-effective method possible. This investigation will answer the question of the most suitable prediction method for time series data from a single meteorological station that is deployed in a specific location. As a result, an accurate representation of the microclimate in a specific are is achieved. To achieve this high accuracy in situ measurements and prediction techniques are used. As prediction techniques, Seasonal Auto Regressive Integrated Moving Average (SARIMA), AI techniques like the Long-Short-Term-Memory (LSTM) Neural Network and hybrid combinations of the two are used. Variables of interest are divided in the easier to predict temperature and humidity that are more periodic and less chaotic, and the wind speed as an example of a more stochastic variable with no known seasonality and patterns. Our results show that the examined Hybrid methodology performs the best at temperature and wind speed forecasts, closely followed by the SARIMA whereas LSTM perform better overall at the humidity forecast, even after the correction of the Hybrid to the SARIMA model.

The synergistic efficacy of combined treatment mild heat (MH) and dielectric barrier discharge (DBD) plasma in Bacillus cereus-contaminated red pepper powder was tested. A cocktail of three strains of B. cereus (NCCP 10623, NCCP 14579, ATCC 11778) was inoculated onto red pepper powder and then treated with MH (60 ℃ for 5-20 min) and DBD plasma (5-20 min). Treatment with MH and DBD plasma alone for 5~20 min resulted in reductions of 0.23~1.43 and 0.12~0.96 log CFU/g, respectively. Combined treatment with MH and DBD plasma was the most effective at reducing B. cereus counts on red pepper powder and resulted in log-reductions of ≥ 6.0 log CFU/g. The largest synergistic values (4.24-4.42 log) against B. cereus in red pepper powder were obtained by the combination of 20 min MH and 5~15 min DBD plasma. Hunter color ‘‘L’’, ‘‘a’’, and ‘‘b’’ values of the combination-treated samples were not significantly different from those of non-treated samples. Also, no significant (p > 0.05) differences in pH values between samples were observed. Therefore, these results suggest that the combination of MH treatment and DBD plasma can be potentially utilized in the food industry to effectively inactivate B. cereus without incurring quality deterioration of red pepper powder.

This paper presents the automation of the thin-layer chromatography technique whose separation and identification of molecules present in a mixture are currently done manually and laboriously [1]. We have therefore found an interest in automating this technique. In this part, the method implemented comprises 2 steps. First we proceeded to the segmentation of the spots obtained on the chromatographic plate. We then developed a program to identify families of molecules such as coumarins, terpenes, tannins, flavonoids, polyphenols, etc. by calculating segmentation parameters such as standard deviation, entropy, average pixel intensity from an algorithm on the matlab software. Finally our results have been compared to the results obtained by the traditional identification technique in laboratories. Some similarity between the two results obtained shows the reliability and the robustness of our technique.

In this paper, a special recurrent neural network (RNN) called \emph{Long Short-Term Memory (LSTM)} is used to design a virtual load sensor that estimates the mass of heavy vehicles. The estimation algorithm consists of a two-layer LSTM network, with the two layers based on sequence-to-sequence and sequence-to-one logic, respectively. The network estimates the vehicle mass based on the vehicle speed, longitudinal acceleration, engine speed, engine torque, and the accelerator pedal position. The network is trained and tested with a data set collected in a high-fidelity simulation environment called Truckmaker. Training data is generated in acceleration maneuvers in a range of speeds whereas test data is obtained by simulating the vehicle in a Worldwide harmonized light vehicles test cycle (WLTC). Preliminary results show that, with the proposed approach, the heavy-vehicle mass can be estimated as accurately as commercial load sensors in a range of load mass as wide as four tons.

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.

Fluctuating stock prices make it difficult for investors to see investment opportunities. One tool that can help investors overcome this is forecasting techniques. Long Short-Term Memory (LSTM) is one of deep learning methods used in forecasting time series. The training and success of deep learning is strongly influenced by the selection of hyperparameters. This research uses a hybrid method between the Genetic Algorithm (GA) and LSTM to find a suitable model for predicting stock prices. GA is used in optimizing the architecture such as the number of epochs, window size, and the number of LSTM units in the hidden layer. Tuning optimizer is also carried out using several optimizers to achieve the best value. From method that has been applied, it shows that the method has a good level of accuracy with MAPE values below 10% in every optimizer used. The error rate generated is quite low, in case-1 with a minimum RMSE value of 93.03 and 94.40, & in case-2 with an RMSE value of 104.99 and 150.06 during training and testing. A fairly stable and small value is generated by setting it using the Adam Optimizer.

We have successfully synthesized a series of Bi doped BaFe2As2 high quality single crystals for the first time. The x-ray diffraction (XRD) patterns show an expansion of lattice parameter c with Bi doping, indicating a negative pressure effect. By investigating the resistivity, a Fermi liquid (FL) to non-Fermi liquid (NFL) crossover is observed from normal state to antiferromagnetic order state, accompanied by three superconducting transitions labeled as SC I, SC II and SC III which are supposed to be induced from three superconducting realms with various Bi concentration. Thus, the NFL behavior is proposed to be closely related with the presence of superconductivity. The magnetic susceptibility measurements further speculates that the SC I and SC III phases should be filamentary superconductivity while the SC II be a possible bulk superconductivity with TC 7 K.

Nanopowders are continuously under investigation as they open new perspectives in numerous fields. There are two main challenges to stimulate their development: sufficient low-cost high throughput synthesis methods leading to a production with well-defined and reproducible properties, and for ceramics, conservation of their nanostructure after sintering. In this context, this paper presents the synthesis of a pure nanosized powder of ZnO (dv₅₀ ~ 60 nm, easily redispersable) by using a continuous Segmented Flow Tubular Reactor (SFTR), which has previously shown its versatility and its robustness, ensuring a high powder quality and reproducibility over time. A higher scale of production can be achieved based on a “scale-out” concept by replicating the tubular reactors. The sinterability of ZnO nanopowders synthesized by the SFTR was studied, by natural sintering at 900 °C and 1100 °C, and Spark Plasma Sintering (SPS) at 900 °C. The performances of the synthesized nanopowder were compared to a commercial ZnO nanopowder of high quality. The samples obtained from the synthesized nanopowder could not be densified at low temperature by traditional sintering, whereas SPS led to a fully dense material after only 5 minutes at 900 °C, while limiting the grain growth and thus leading to a nanostructured material.

Abstract: To describe the feeder topology and information exchange between intelligent electronic devices (IEDs) for Internet of Things (IoT), it is necessary to extend IEC 61850 and add a logical model. The feeder model described in IEC 61970 is then extended in IEC 61850 to serve as a container for the equipment along the distribution line. For the physical connections in the electrical equipment, both terminal and connectivity node logical models are added. Taking logical node XCBR as the example, its attributes for the terminals are added to the electrical equipment. The logical node LCNN is then further added in order to describe the connectivity node. By next adding the logical node LTPN to describe the topological node, and FTPA to describe the results of the topology analysis, we can efficiently describe the topology analysis results. Based on these new logical nodes, the exchange of topology information between intelligent terminals no longer relies on configuration files, but only requires logical nodes. Through the above expansion, the topology description and information exchange of medium and low voltage feeders are realized.

Fire outbreaks continue to cause damage despite the improvements in fire-detection tools and algorithms. It is still challenging to implement a well performing and optimized approach, which is sufficiently accurate, and has tractable complexity and low false alarming rate. Small amount of fire and identification of fire from a long distance is also a challenge in previously proposed techniques. In this study, we propose a novel hybrid model based on Convolutional Neural Networks (CNN) to detect and analyze fire intensity. 21 convolutional layers, 24 Rectified Linear Unit (ReLU) layers, 6 pooling layers, 3 fully connected layers, 2 dropout layers, and a softmax layer are included in the proposed 57-layer CNN model. Our proposed model performs instance segmentation in order to distinguish between fire and non-fire events. To reduce the intricacy of the proposed model, we also propose a key-frame extraction algorithm. The proposed model uses Internet of Things (IoT) devices to alert the relevant person by calculating the severity of fire. Our proposed model is tested on a publicly available dataset having fire and normal videos. The achievement of 95.25 % classification accuracy, 0.09% False Positive Rate (FPR), 0.65 percent False Negative Rate (FNR), and a prediction time of 0.08 seconds validates the proposed system.

This study explores the properties and behavior of bi-close-to-convex functions, introducing new subclasses defined by their relationship with fractional differential operator and bi-univalent functions. Using the Faber polynomial technique, we derive upper bounds for the n^{th} coefficient of functions in these classes. We also investigate the erratic behavior of initial coefficients in bi-close-to-convex functions, as characterized by the (λ,q)-fractional differintegral operator. Furthermore, we address Fekete-Szegö problems and present notable findings from our investigation, contributing to the continued growth and refinement of geometric function theory, yielding new insights and practical uses.

In current study we have obtained Co2FeSi-glass coated microwires with different geometrical aspect ratio, ρ = d/Dtot (diameter of metallic nucleus, d and total diameter, Dtot). The structure and magnetic properties are investigated at a wide range of temperature. XRD analysis illustrates a notable changing in the microstructure by increasing the aspect ratio of Co2FeSi glass coated microwires. Amorphous structure is detected for the sample with the lowest aspect ratio (ρ = 0.23), whereas a growth of crystalline structure is observed in the other samples (aspect ratio ρ = 0.30 and 0.43). This change at the microstructure properties correlates with dramatic changing in magnetic properties. For the sample with the lowest ρ -ratio, non-perfect square loops are obtained with low normalized remanent magnetization. A notable enhancement in the squareness and coercivity are obtained by increasing ρ -ratio. Changing the internal stresses strongly affects the microstructure, resulting in a complex magnetic reversal process. The thermomagnetic curves show large irreversibility for the Co2FeSi with low ρ -ratio. Meanwhile, if we increase the ρ -ratio, the sample shows perfect ferromagnetic behavior without irreversibility. The current result illustrates the ability to control the microstructure and magnetic properties of Co2FeSi-glass-coated microwires by changing only their geometric properties without performing any addition heat treatment. The modification of geometric parameters of Co2FeSi glass-coated microwires allows to obtain microwires which exhibit an unusual magnetization behavior that offers opportunities to understand the phenomena of various types of magnetic domain structures, which is essentially helpful for designing sensing devices based on thermal magnetization switching.

Graphene foam prepared by chemical vapor deposition method is a promising thermal interfacial material. However, the thermal properties of graphene foam highly depend on the experimental fabrication conditions during the chemical vapor deposition process. Aiming to reveal how to prepare the appropriate graphene foam for the various thermal management scenarios, the influence of experimental conditions on thermal properties of graphene foam is investigated. Furthermore, the contribution of thermal conductivity and thermal radiation to the effective thermal coefficient of graphene foam is carried out for comparison. Research results show that, the porosity and the cross-section shape of struts of growth template are two critical factors to affect the thermal transport of graphene foam, especially with the increase of temperature. In addition, the deposition time of graphene determines the wall thickness and affects the thermal conductivity directly. The thermal radiation contributes more than thermal conductivity when the temperature climbs continuously. Comparatively, the effective thermal coefficient of graphene foam composite with high porosity and circular shape struts is much superior to others at high temperature. The research findings can provide important guidance for the graphene foam fabrication and its applications in the field of thermal management.

With the disruption of digital technologies, customers have emerged as co-producers in order to reduce costs and enhance productivity. Customer-driven business logic recognizes customer capabilities and sustainable innovation as key factors in the performance of customized manufacturing enterprises. The potential relationship between customers and producers has become a new area of inquiry. Existing research rarely delves into the impact of customer predictive ability on the process of customized production activities, particularly in relation to sustainable innovation, which remains inadequately characterized. Ships serve as a typical representation of customized enterprises. This study explores the underlying drivers of sustainable innovation through customer demand orientation by examining 20-year historical patterns in the global shipping and shipbuilding markets, considering the environmental dependency and temporal correlation characteristics of the shipbuilding market (producers) and the shipping market (consumers). By employing time series and panel data in a machine learning algorithm, specifically the random forest model, the study reveals a strong and statistically significant correlation between new ship deliveries and the Baltic Dry Index (BDI), with larger value ships having a more pronounced impact on the consumer market. The correlation analysis confirms that these two variables, in combination, can comprehensively reflect customer predictive ability and serve as crucial decision criteria for customer investment in new ship production. Furthermore, based on principal component analysis of customer predictive ability and ship innovation levels, as well as Granger causality tests, the study demonstrates that customer predictive ability is a Granger cause of sustainable innovation in customized production. Customer predictive ability influences sustainable innovation in customized enterprises to varying degrees. This research provides valuable insights for shipbuilding companies in terms of engaging in sustainable innovation in international markets and understanding the value of international market customers.

Fresh water springs are unique natural resources in Florida, currently under threat from increasing groundwater pumping and pollution resulting from a variety of sources. This paper estimates current recreation benefits from visiting springs using the travel cost method and elicits residents’ willingness to contribute for springs restoration using the contingent valuation method. It further compares the performance of count data models correcting for endogenous stratification and truncation, and finds that the annual consumer surplus per person per trip is between $20 and $43. Furthermore, visitors are willing to contribute $12 to $14 per person per trip for springs restoration without reducing trip demand.

Exploring for green and affordable protection of perishable fruit like cherry tomato is of significance. Here the protective efficacy and its underpinnings of coating with oleaster gum, alone or incorporated with cuminal, on cherry tomatoes stored at ambient temperature were investigated. The composite coating of oleaster gum with 0.1% cuminal reduced decay, respiration rate, weight loss, and softening of the fruit and decelerated their decreases of total soluble solids, titratable acidity, and soluble proteins, and therefore maintained their marketability. Furthermore, it reduced the accumulation of O•− 2and H2O2 in fruit, and mitigated cell membrane lipid oxidation and permeabilization, thereby retarding their senescence. Instrumentally, it elevated the activities of superoxide dismutase, catalase, peroxidase, and ascorbate peroxidase and the levels of ascorbic acid and glutathione. This potentiation of the fruit antioxidant system makes the composite coating a promising approach to keeping the postharvest quality of perishable fruit.

This research investigates the application of deep learning in sentiment analysis of Canadian maritime case law. It offers a framework for improving maritime law and legal analytics policy-making procedures. The automation of legal document extraction takes center stage, underscoring the vital role sentiment analysis plays at the document level. Therefore, this study introduces a novel strategy for sentiment analysis in Canadian maritime case law, combining sentiment case law approaches with state-of-the-art deep learning techniques. The overarching goal is to systematically unearth hidden biases within case law and investigate their impact on legal outcomes. Employing Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) based models, this research achieves a remarkable accuracy of 98.05% for categorizing instances. In contrast, Conventional Machine Learning techniques such as Support Vector Machines (SVM) yield an accuracy rate of 52.57%, Naive Bayes at 57.44 %, and Logistic Regression at 61.86%. The superior accuracy of the CNN and STM model combination underscores its usefulness in legal sentiment analysis, offering promising future applications in diverse fields like legal analytics and policy design. These findings mark a significant choice for AI-powered legal tools, presenting more sophisticated and sentiment-aware options for the legal profession.

: Innovative solutions are now being researched to manage the ever-increasing amount of data required to optimize the performance of internal combustion engines. Machine Learning ap-proaches have shown to be a valuable tool for signal prediction due to their real-time and cost-effective deployment. Among them, the architecture consisting of Long Short-Term Memory (LSTM) and one-dimensional Convolutional Neural Networks (1DCNN) has emerged as a highly promising and effective option for replacing the role of physical sensors. The architecture com-bines the capacity of LSTM to detect patterns and relationships in smaller segments of the signal with the ability of 1DCNN to detect patterns and relationships in larger segments of the signal. The purpose of this work is to assess the feasibility of substituting a physical device dedicated to calculating the torque supplied by a spark-ignition engine. The suggested architecture was trained and tested using signals from the field during a test campaign conducted under transient operating conditions. The results reveal that LSTM+1DCNN is particularly well suited for signal prediction with considerable variability. It constantly outperforms other architectures used for comparison, with average error percentages of less than 2%, proving the architecture's ability to replace physical sensors.

THz radiation has assumed a great importance thanks to the efforts in the development of technological tools used in this versatile band of the electromagnetic spectrum. Here we propose a reflecting bi-mirror axicon-like device with wavelength-independent long focusing performances in the THz band, by exploiting the high thermo-mechanical deformation of the elastomer polydimethylsiloxane (PDMS). This deformation permits to achieve significant optical path modulations in the THz band and effective focusing. The surface of a PDMS layer is covered with a gold thin film, acting as heater thanks to its absorption for wavelengths below ~500 nm . An invariance property of the Fresnel integral has been exploited to verify experimentally the THz performances of the device with an ordinary visible laser source, finding excellent agreement with the theoretical predictions at 1 and 3 THz. The same property allowed also to verify experimentally that the axicon focus has a longitudinal extension much greater than that one exhibited by a benchmark cylindrical mirror with the same optical power. The axicon is thermo-mechanically stable up to a heating power of 270 mW, although it might be potentially exploited at higher powers with a minor degradation of the optical performances.

In the present paper we introduce three new classes of bi-univalent functions connected with Gregory coefficients. For functions in each of these three bi-univalent function classes we have derived the estimates of the Taylor--Maclaurin coefficients $\left|a_{2}\right|$ and $\left|a_{3}\right|$ and Fekete-Szeg\H{o} functional problems for functions belonging to these new subclasses. We defined three subclasses of the class of the bi-univalent functions $\Sigma$, namely $\mathfrak{HG}_{\Sigma}$, $\mathfrak{GM}_{\Sigma}(\mu)$ and $\mathfrak{G}_{\Sigma}(\lambda)$ by using the subordinations with the function whose coefficients are Gregory's numbers. First, we proved that these classes are not empty, i.e. contains other functions than the identity one. Using the well-known Carath\'eodory Lemma for the functions with real positive parts in the open unit disk, together with an estimation due to P. Zaprawa (see https://doi.org/10.1155/2014/357480) and another one of Libera and Zlotkiewicz, we gave upper bounds for the above mentioned initial coefficients and for the Fekete-Szeg\H{o} functionals. The main results are followed by some particular cases, and the novelty of the definitions and the proofs could involve further studies for such type of similarly defined subclasses.

With the rapid development of science and technology, many new concepts and terms appear, especially in English. Other languages try to express these concepts with words from their own vocabulary. In the specific case of Arabic, there are many ways to find a counterpart for a particular new concept, such as using an existing word to denote the new concept, derivation, and blending. When these methods fail, the new concepts are simply phonetically transliterated. This has the disadvantage that most of the transliterated terms do not conform to the rules of the Arabic language and lead to a distortion of the language. Some modern linguists call for using the generation strategy to translate the new terms into Arabic by using the unused Arabic roots. Therefore, it is necessary to provide a resource that contains all Arabic roots with a categorization of what is used, what is available for use, and what is rejected according to the phonetic system. This work provides a comprehensive lexicon that contains all possible Arabic triliteral roots, determines the status of each root in terms of usage and acceptability, and provides a mechanism for giving preference to roots when there is more than one root that indicates the desired meaning.

With the rapid development of science and technology, many new concepts and terms appear, especially in English. Other languages try to express these concepts with words from their own vocabulary. In the specific case of Arabic, there are many ways to find a counterpart for a particular new concept, such as using an existing word to denote the new concept, derivation, and blending. When these methods fail, the new concepts are simply phonetically transliterated. This has the disadvantage that most of the transliterated terms do not conform to the rules of the Arabic language and lead to a distortion of the language. Some modern linguists call for using the generation strategy to translate the new terms into Arabic by using the unused Arabic roots. Therefore, it is necessary to provide a resource that contains all Arabic roots with a categorization of what is used, what is available for use, and what is rejected according to the phonetic system. This work provides a comprehensive lexicon that contains all possible Arabic triliteral roots, determines the status of each root in terms of usage and acceptability, and provides a mechanism for giving preference to roots when there is more than one root that indicates the desired meaning.

This article puts forward the bi-matrix games with crisp parametric payoffs based on interval value function approach. We conclude that the equilibrium solution of the game model can converted into optimal solutions of the pair of the non-linear optimization problem. Finally, experiment results show the efficiency of the model.

To solve the problem of low efficiency of source seeking in implicit information field, this paper presents an autonomous souring method based on balanced searching strategy is enlighten by biological homing behaviors. At the beginning of the research, the source seeking task come down to a multi-objective convergence issue. By taking the feasibility search behaviors as the individual sample of the evolutionary population drawing on the thought of evolutionary algorithms, then combine motion searching with population evolution, so the carrier can be guide to complete source seeking task by solving the multi-objective problem. Furthermore, the distribution entropy is also considerated d to measure the searching bias in the process of source seeking. Combined with the demand of the source seeking process, a new source seeking method of balanced searching strategy is designed. Ultimately, through theoretical analysis and simulation verification confirm the effectiveness and rationality of the proposed method.

Increasing clinical and preclinical evidences implicate gut microbiome (GM) dysbiosis as a key susceptibility factor for neurodegenerative disorders, including Alzheimer’s disease (AD) and Parkinson’s diseases (PD). In recent years, neurodegenerative diseases have not been viewed as driven solely by defects in brain, and the role of GM in modulating the central nervous system function via gut-brain axis has attracted considerable interest. Encouraged by GM researches, the next-generation probiotics may lead to tangible impacts on the treatment of neurodegenerative disorders. This review summarizes the current understandings of GM composition and characteristics associated with neurodegenerative diseases, and the demonstrations of molecules from GM affecting neurodegeneration. Particularly, applications of next-generation probiotics such as Clostridium butyricum, Akkermansia muciniphila, Faecalibacterium prausnitzii, and Bacteroides fragilis for remediation of neurodegenerative diseases are discussed.

Phospholipid fatty acids (PLFAs) can be used as biomarkers for qualitative and quantitative analyses of soil microbial community diversity. In this study, we collected soil samples at 10-cm intervals to a depth of 1 m from Robinia pseudoacacia plantations of four different ages (10, 15, 25 and 40 years) in a loess area and analysed the soil microbial community structure by PLFA analysis. A total of 97 PLFAs were detected in soils of R. pseudoacacia plantations of different ages. The individual PLFA contents gradually decreased in the 0- to 40-cm soil layers, with little variation in the 40- to 100-cm soil layers. The individual PLFAs were similarly distributed in the soils of R. pseudoacacia plantations of different ages, and there was a clear variation with stand age and soil depth. The individual PLFA contents in the 0- to 20-cm soil layers were highest for the 25-year-old plantation, while those in the 20- to 40-cm soil layers were relatively high for the 25- and 40-year-old plantations; the 16:0 content was the highest among individual PLFAs. The total PLFA content and the PLFA contents of different microbial groups [bacteria, fungi, Gram-positive bacteria (G⁺), Gram-negative bacteria (G^-) and actinomycetes] initially increased before decreasing in the soils of R. pseudoacacia plantations with increasing stand age, whereas these contents gradually decreased with increasing soil depth; the highest PLFA contents was found in the 25-year-old plantation. The total PLFA content and the contents of fungal, G^- and actinomycete PLFAs in the soils of R. pseudoacacia plantations differed significantly among stands of different ages in the 0- to 10-cm, 10- to 20-cm and 30- to 40-cm soil layers, while no significant differences were found in the 20- to 30-cm soil layers; the G⁺ and bacterial PLFAs contents in each of the 0- to 40-cm soil layers were significantly different. The PLFA ratios between different microbial groups differed among the stands of different ages. The fungi/bacteria ratio showed a “decrease-increase-decrease” trend with stand age, while the G⁺/G^- ratio showed an “increase-decrease” trend. The saturated/monounsaturated PLFA ratio initially decreased before plateauing, while the opposite trend was observed for the cyclopropyl/precursor ratio. The PLFA contents of different microbial groups were ranked as follows: bacteria > G^- > G⁺ > actinomycetes > fungi. In the principle component analysis, 18:1ω9c, 10Me18:0, i17:0, a17:0, 18:1ω7c, 18:1ω5c and 18:0 made the greatest contribution to principal component 1, and a14:0, i14:0 3OH, i14:0, i14:1ω7c and 14:0 made the greatest contribution to principal component 2. In conclusion, soil nutrient status and other soil eco-environmental stress factors should be considered in 10- to 25-year-old (particularly ~15-year-old) plots for the management of R. pseudoacacia plantations to prevent forest soil degradation and improve forest stand quality, thereby achieving better soil and water conservation and environmental improvement in R. pseudoacacia plantations.

Hepatitis E virus (HEV) is a common cause of acute hepatitis worldwide, accounting for approximately 25% of deaths among pregnant women. We previously reported that pregnancy serum facilitates HEV replication in vitro. However, the differences in host cells with HEV infection induced by pregnancy serum and fetal bovine serum (FBS) are unclear. In this study, differentially expressed proteins were identified in HEV-infected hepatoma cells (HepG2) supplemented with different sera by using isobaric tags for relative and absolute quantitation. Proteomic analysis indicated that HEV infection significantly induced 1014 differentially expressed proteins in HEV-infected HepG2 cells when supplemented with FBS compared with pregnancy serum. Further validation by Western blot confirmed that filamin A, heat-shock proteins 70 and 90, Cytochrome c, and Thioredoxin were associated with HEV infection. This comparative analysis provides an important basis to further investigate HEV pathogenesis in pregnant women and HEV replication.

Cooperative localization under complex urban environments has become a solution to replace the Global Navigation Satellite System (GNSS) positioning. Due to utilizing distance measured and information exchanged between vehicles, cooperative localization results in high computational complexity and heavy communication overhead. This paper proposes a cooperative localization method based on evolutionary coalitional game theory, which implements vehicles' location estimation with less communication cost. We select the neighboring vehicles to form a coalition based on the node's square position error bound and communication cost. The location is obtained via exchanging information between vehicles. It is evident from the simulations and results that the proposed method holds low communication overhead while maintaining localization accuracy.

Complementary Metal-Oxide-Semiconductor (CMOS) is a typical image sensor that has a wide range of applications. However, considering the limitations of the weather condition and hardware cost, it is hard to capture high-resolution images by CMOS sensor. Recently, Super-Resolution (SR) techniques for image restoration has been gaining attentions due to its excellent performance. Under the powerful learning ability, Generative Adversarial Networks (GANs) have been proved to achieve great success. In this paper, we propose the Advanced Generative Adversarial Networks (AGAN) to efficiently correct these issues; 1) we design a Laplacian pyramid framework as pre-trained module, which is beneficial to provide multi-scale features for our input. 2) at each feature block, a convolutional skip-connections network, which may contain some latent information, is significant for generative model to reconstruct a plausible-looking image; 3) considering that edge details usually play an important role in image generation, a novel perceptual loss function is defined to train and seek optimal parameters. It is effective to achieve excellent and compelling quality captured by CMOS sensor. Quantitative and qualitative evaluations have been demonstrated that our algorithm not only fully takes advantage of Convolutional Neural Networks (CNNs) to improve the image quality, but also performs better than previous GAN algorithms for super-resolution task.

Compared to tin lead alloys, lead-free tin alloys have lower toxicity, making them more widely used. In this study, Sn-20Bi-0.3Al-xY solders alloys were prepared. The effects of the addition of Y on its microstructure, micro-hardness, wettability and mechanical properties was investigated. The result showed that the addition of Y had significant effect on the refinement of Sn-20Bi-0.3Al-xY. From the spreading tests results, Y increased the wettability of the solders, however when the fraction of Y gradually increased, the wettability reduced. The ultimate tensile and hardness of Sn-20Bi-0.3Al-xY solders alloys were increased as the content of Y increasing.

In recent years, the management of health systems is a main concern of governments and decision makers. Home health care is one of the newest methods of providing services to patients in developed societies that can respond to the individual lifestyle of modern age and the increase of life expectancy. The home health care routing and scheduling problem is a generalized version of the vehicle routing problem, which is extended to a complex problem by adding special features and constraints of health care problems. In this problem, there are multiple stakeholders such as nurses for which an increase of their satisfaction level is very important. In this study, a mathematical model is developed to expand traditional home health care routing and scheduling models to downgrading cost aspects by adding the objective of minimizing the difference between the actual and potential skills of the nurses. Downgrading can lead to a dissatisfaction of the nurses. In addition, skillful nurses have higher salaries and high-level services increase equipment costs and need more expensive trainings and nursing certificates. Therefore, downgrading can enforce hidden huge costs to the managers of a company. To solve the bi-objective model, an -constraint based approach is suggested and the model applicability and its ability to solve the problem in various sizes are discussed. A sensitivity analysis on the Epsilon parameter is conducted to analyze the effect of this parameter on the problem. Finally, some managerial insights are presented to help the managers in this field, and some directions for future studies are mentioned as well.

The main aim of this work is to report an alternative energy efficient technique of fabricating flexible thermoelectric generators (TEGs) using printable ink. In this process, we have fabricated thermoelectric (TE) composite thick film and we are experimenting several ways to overcome the challenges of conventional and additive manufacturing methods. Two different mesh sizes of n-type bismuth particle, various binder to thermoelectric (TE) material weight ratio, and two different pressure (200 MPa and 300 MPa) were employed for optimizing the thermoelectric properties of TE composite films. We are also exploring naturally occurring chitosan as a binder. Dimethyl sulfoxide (DMSO) dissolved chitosan was used for the binder and less than 0.2 wt% of chitosan was sufficient for the fabrication of TE inks and composite films. Low energy intensive curing process was employed to evaporate the solvent from the drop casted inks. External uniaxial pressure not only eliminated high energy intensive curing processes but also increased the packing density of the film by removing pores and voids in the chitosan-bismuth composite film. The microstructure analysis reveals that bulk-like structure, which rarely has voids, pores and grain boundaries, was observed in the composite films pressed at sufficiently high pressures. The highest performing composite film was obtained with the conditions of 1:2000 binder to bismuth weight ratio, 100 mesh of particle size, and 300 MPa of pressure. The best performing bismuth chitosan composite film pressed at 300 MPa had the power factor as 4009 ± 391 μW/m·K² with high electrical conductivity value of 7337 ± 522 S/cm. The measured thermal conductivity of the best performing chitosan-bismuth composite film was 4.4 ± 0.7 W/m·K and the figure of merit calculated from the thermal conductivity was 0.27 at room temperature.

The escalating reliance on revolutionary online web services has introduced heightened security risks, with persistent challenges posed by phishing despite extensive security measures. Traditional phishing systems, reliant on machine learning and manual features, struggle with evolving tactics. Recent advances in deep learning offer promising avenues for tackling novel phishing challenges and malicious URLs. This paper introduces a two-phase stack generalized model named AntiPhishStack, designed to detect phishing sites. The model leverages the learning of URLs and character-level TF-IDF features symmetrically, enhancing its ability to combat emerging phishing threats. In Phase I, features are trained on a base machine learning classifier, employing K-fold cross-validation for robust mean prediction. Phase II employs a two-layered stacked-based LSTM network with five adaptive optimizers for dynamic compilation, ensuring premier prediction on these features. Additionally, the symmetrical predictions from both phases are optimized and integrated to train a meta-XGBoost classifier, contributing to a final robust prediction. This work's significance lies in advancing phishing detection with AntiPhishStack, operating without prior phishing-specific feature knowledge. Experimental validation on two benchmark datasets, comprising benign and phishing or malicious URLs, demonstrates the model's exceptional performance, achieving a notable 96.04% accuracy. This research adds value to the ongoing discourse on symmetry and asymmetry in information security and provides a forward-thinking solution for enhancing network security in the face of evolving cyber threats.

Cultural Tourism (CT), which enhances the economic development of a region, aids a country in reinforcing its identities, enhancing cross-cultural understanding, and preserving the heritage culture of an area. Designing a proper tourism model assists the tourists in understanding the point of interest without the help of a local guide. However, owing to the need for the analysis of different factors, designing such a model is a complex process. Therefore, this article proposes a CT model for Riyadh for peak visitor time. Primarily, the map data and cultural event dataset are processed for location, such as grouping with Kriging Interpolation-based Chameleon (KIC), tree forming, and feature extraction. After that, the event dataset’s attributes are processed with word embedding. Meanwhile, the Social Network Sites (SNS) data like reviews and news are extracted with an external Application Programming Interface (API). The review data is processed with keyword extraction and word embedding, whereas the news data is processed with score value estimation. Lastly, the data are fused corresponding to a historical site and given to the Multi-Quadratic-Long Short Term Memory (MQ-LSTM) Recommendation System (RS); also, the recommended result with the map is stored in a database. Lastly, the database security is maintained with Locality Sensitive Hashing (LSH); moreover, by attaining higher performance values, the proposed model is experimentally verified.

This paper introduces a multi-class hand gesture recognition model developed to identify a set of defined hand gesture sequences in two-dimensional RGB video recordings. The work presents an action detection classifier that looks at both appearance and spatiotemporal parameters of consecutive frames. The classifier utilizes a convolutional-based network combined with a long-short-term memory unit. To leverage the need for a large-scale dataset, the model uses an available dataset to then adopt a technique known as transfer learning to fine-tune the model on the hand gestures of relevance. Validation curves performed over a batch size of 64 indicate an accuracy of 93.95% (± 0.37) with a mean Jaccard index of 0.812 (± 0.105) for 22 participants. The presented model illustrates the possibility of training a model with a small set of data (113,410 fully labelled frames). The proposed pipeline embraces a small-sized architecture that could facilitate its adoption.

Speech/music classification that facilitates optimized signal processing from classification results has been extensively adapted as an essential part of various electronics applications, such as multi-rate audio codecs, automatic speech recognition, and multimedia document indexing. In this paper, a new technique to improve the robustness of speech/music classifier for 3GPP enhanced voice service (EVS) using long short-term memory (LSTM) is proposed. For effective speech/music classification, feature vectors implemented with the LSTM are chosen from the features of the EVS. Experiments show that LSTM-based speech/music classification produces better results than conventional EVS under a variety of conditions and types of speech/music data.

Characteristics of artificial waveguide lines composed of finite size artificial cells are analyzed and discussed with relation to designing the travelling wave parametric amplifiers. From this point of view, flux driven amplifier suggested recently can be considered as the most successful amplifier design. To increase dynamic range of the amplifier, dc SQUID cells of the artificial line in use can be substituted for bi-SQUID cells. The 1-dB compression points of the amplifier gain are calculated and compared for both types of the cells.

The purpose of the present paper is to introduce and investigate new subclasses of analytic function class of bi univalent function defined in open unit disk connected with a linear q-convolution operator, which are associated with the quasi-subordination. We find coefficients estimate |h_2 |,|h_3 | for functions in these subclasses. Several known and new consequences of these results are also pointed out.

Sustainable agricultural production is endangered by several ecological factors such as drought, extreme temperatures, excessive salts, parasitic ailments, and insect pest infestation. These challenging environmental factors may have adverse effects on future agriculture production in many countries. In modern agriculture, conventional crop breeding techniques alone are inadequate for achieving the increasing population’s food demand on a sustainable basis. The advancement of molecular genetics and related technologies are promising tools for the selection of new crop species. Gene pyramiding through marker assisted selection (MAS) and other techniques have accelerated the development of durable resistant/tolerant lines with high accuracy in the shortest possible period of time for agricultural sustainability. Gene stacking has not been fully utilized for biotic stress resistance development and quality improvement in most of the major cultivated crops. This review emphasizes on gene pyramiding techniques that are being successfully deployed in modern agriculture for improving crop tolerance to abiotic and biotic stresses for sustainable crop improvement.

Anomaly occurrences in hydraulic machinery may lead to massive systems shut down, jeopardizing the safety of the machinery and its surrounding human operator(s) and environment, and the severe economic implications succeeding the faults and their associated damage. Hydraulics are mostly placed in ruthless environments, where they are consistently vulnerable to many faults. Hence, not only the machines and their components are prone to anomalies, but also the sensors attached to them, which monitor and report their health and behavioral changes. In this work, a comprehensive applicational analysis of anomalies in hydraulic systems extracted from a hydraulic test rig is thoroughly achieved. Firstly, we provided a combination of a new architecture of LSTM autoencoders and supervised machine and deep learning methodologies to perform two separate stages of fault detection and diagnosis. The two phases are condensed by: the detection phase using the LSTM autoencoder. Followed by the fault diagnosis phase represented by the classification schema. The previously mentioned framework is applied to both component and sensor faults in hydraulic systems, deployed in the form of two in-depth applicational experiments. Moreover, a thorough literature review of the past decade related work for the two stages separately is successfully conducted in this paper.

This paper proposed emotion recognition methods for consecutive facial images, and implements the inference of neural network model on a field-programmable gate array (FPGA). The proposed emotion recognition methods are based on a neural network model architecture that combines convolution neural networks (CNNs), long short-term memory (LSTM), and fully connected neural networks (FCNNs), called CLDNN or ConvLSTM-FCN. This type of neural network mod-el can analyze the local feature sequences obtained through convolution of data, making it suita-ble for processing time-series data such as consecutive facial images. In this paper, sequences of facial images are sampled from videos corresponding to various emotional state of subjects. The sampled images are then pre-processed with the processes includes facial detection, greyscale conversion, resize, and data augmentation if necessary. The 2-D CNN in ConvLSTM-FCN is used for feature extraction for these pre-processed facial images. These sequences of facial im-age features are time sequences with dependent properties between the elements within them. The LSTM is then used to model these time sequences followed by fully connected neural net-works (FCNNs) for classification. The proposed consecutive facial emotion recognition method achieves an average recognition rate of 99.51% on RAVDESS dataset, 87.80% on BAUM-1s dataset and 96.82% on eNTERFACE’05 data set, using 10-fold cross-validation on the PC. Some com-parisons of recognition accuracies between the proposed method and the other existing related works are conducted in this paper. According to the comparisons, the proposed emotion recog-nition methods outperform the existing related researches. The proposed emotion recognition methods are then implemented on an FPGA chip using the neural network model inference algo-rithms in this paper, and the accuracies of the experiments conducted on the FPGA chip are iden-tical to those obtained on the PC. This verifies that the proposed neural network model imple-mented on the FPGA chip performs well.

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to hu-man error. Recognizing this limitation, the rise of deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time-frequency domain alongside pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time-frequency (CWT) images processed using auto-encoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: remarkable 100% accuracy in most of the binary classifications, impressive performance exceeding 95% for three-class and four-class challenges, and a commendable rate exceeding 93.5% for the five-class classification.

Radiator reliability is crucial in environments characterized by high temperatures and friction, where prompt interventions are often required to prevent system failures. This study introduces a proactive approach to radiator fault diagnosis, leveraging the integration of Gaussian Mixture Model (GMM) and Long-Short Term Memory (LSTM) autoencoders. Vibration signals from radiators were systematically collected through randomized durability vibration bench tests, resulting in four operating states—two normal, one unknown, and one faulty. Time-domain statistical features of these signals were extracted and subjected to Principal Component Analysis (PCA) to facilitate efficient data interpretation. Subsequently, this study discusses the comparative effectiveness of GMM and LSTM in fault detection. GMMs are deployed for initial fault classification, leveraging their clustering capabilities, while LSTM autoencoders excel in capturing time-dependent sequences, facilitating advanced anomaly detection for previously unencountered faults. This alignment offers a potent and adaptable solution for radiator fault diagnosis, particularly in challenging high-temperature or high-friction environments. Consequently, the proposed methodology not only provides a robust framework for early-stage fault diagnosis but also effectively balances diagnostic capabilities during operation. Additionally, this study presents the foundation for advancing reliability life assessment in accelerated life testing, achieved through dynamic threshold adjustments using both the absolute log-likelihood distribution of the GMM and the reconstruction error distribution of the LSTM autoencoder model.

Photovoltaic(PV) power generation is highly nonlinear and stochastic. Accurate prediction of PV power generation plays a crucial role in grid connection as well as the operation and scheduling of power plants. To predict the PV power combination model, this paper suggests a method based on Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Nonlinear Auto-Regressive Neural Networks with Exogenous Input (NARXNN), Long Short Term Memory (LSTM) Neural Network, and Light Gradient Boosting Machine (LightGBM) algorithms. To attempt to reduce the non-smoothness of PV power, the weather variable features with the greatest effect on PV power are first identified by correlation analysis. Following this, the PV power modal decomposition is split and reorganized into a new feature matrix. Finally， a NARX is used to obtain preliminary PV power components and residual vector features， and the PV power is predicted by combining three models of LightGBM， LSTM, and NARX and then the final prediction results are obtained by combining the PV power prediction results using error inverse method weighted optimization. The prediction results demonstrate that the model put forth in this paper outperforms those of other models and validate the model's validity by utilizing real measurement data from Andre Agassi College in the United States.

Deep neural networks (DNNs) have made a huge impact in the field of machine learning by providing unbeatable humanlike performance to solve real-world problems such as image processing and natural language processing (NLP). Convolutional neural network (CNN) and recurrent neural network (RNN) are two typical architectures that are widely used to solve such problems. Time sequence-dependent problems are generally very challenging, and RNN architectures have made an enormous improvement in a wide range of machine learning problems with sequential input involved. In this paper, different types of RNN architectures are compared. Special focus is put on two well-known gated-RNN’s Long Term Short Memory (LSTM) and Gated Recurrent Unit (GRU). We evaluated these models on the task of force estimation system in pouring. In this study, four different models including multi-layers LSTM, multi-layers GRU, single-layer LSTM and single-layer GRU) were created and trained. The result suggests that multi-layer GRU outperformed other three models.

The rapid development of electrochemical CO2 reduction offers a promising route to convert in-termittent renewable energy into products of high value-added fuels or chemical feedstocks. However, low faradaic efficiency, low current density, and a narrow potential range still limited the large-scale application of CO2RR electrocatalyst. Herein, monolith 3D bi-continuous nano-porous Bismuth (np-Bi) electrodes are fabricated via a simple one-step electrochemical dealloying strategy from Pb-Bi binary alloy. The unique bi-continuous porous structure ensures highly effective charge transfer, meanwhile the controllable millimeter-size geometric porous structure enables easy catalyst adjustment to expose highly suitable surface curvatures with abundant reactive sites. This results in a high selectivity of 92.6% and superior potential window (400 mV, selectivity >88%) for electrochemical reduction of carbon dioxide to formate. Our scalable strategy provides a feasible pathway for mass-producing high-performance and versatile CO2 electrocatalysts.

This study aimed to evaluate contrast-enhanced mammography (CEM) and compare breast lesions on CEM and breast magnetic resonance imaging (MRI) using 5 features. We propose to create a flowchart for BI-RADS classification of breast lesions on CEM based on the Kaiser score (KS) flowchart for breast MRI. Included were 68 subjects (women and men; median age 61.4 ± 11.6 years) who were suspected of having a malignant process in the breast based on digital mammography (MG) findings. The patients underwent breast ultrasound (US), CEM, MRI, and biopsy of the suspicious lesion. There were 47 patients with malignant lesions confirmed by biopsy and 21 patients with benign lesions, for each of which a KS was calculated. In the patients with malignant lesions, the MRI-derived KS was 9 (IQR 8-9), its CEM equivalent was 9 (IQR 8-9), and BI-RADS was 5 (IQR 4-5). In patients with benign lesions, MRI-derived KS was 3 (IQR 2-3), its CEM equivalent was 3 (IQR 1.7-5), and BI-RADS was 3 (IQR 0-4). There was no significant difference between the ROC-AUC of CEM and MRI (P=0.749). In conclusion, there were no significant differences in KS results between CEM and breast MRI. The KS flowchart is useful for evaluating breast lesions on CEM.

Transparent conducting oxides (TCO) with high electrical conductivity and at the same time high transparency in the visible spectrum are an important class of materials widely used in many devices requiring a transparent contact such as light-emitting diodes, solar cells and display screens. Since the improvement of electrical conductivity usually leads to degradation of optical transparency, a fine-tuning sample preparation process and a better understanding of the correlation between structural and transport properties is necessary for optimizing the properties of TCO for use in such devices. Here we report a structural and magnetotransport study of tin oxide (SnO₂), a well-known and commonly used TCO, prepared by a simple and relatively cheap Atmospheric Pressure Chemical Vapour Deposition (APCVD) method in the form of thin films deposited on soda-lime glass substrates. The thin films were deposited at two different temperatures (which were previously found to be close to optimum for our setup), 590 °C and 610 °C, and with (doped) or without (undoped) the addition of fluorine dopants. Scanning Electron Microscopy (SEM) and Grazing Incidence X-ray Diffraction (GIXRD) revealed the presence of inhomogeneity in the samples, on a bigger scale in form of grains (80–200 nm), and on a smaller scale in form of crystallites (10–25 nm). Charge carrier density and mobility extracted from DC resistivity and Hall effect measurements were in the ranges 1–3 × 10²⁰ cm⁻³ and 10–20 cm²/Vs, which are typical values for SnO₂ films, and show a negligible temperature dependence from room temperature down to -269 °C. Such behaviour is ascribed to grain boundary scattering, with the interior of the grains degenerately doped (i.e., the Fermi level is situated well above the conduction band minimum) and with negligible electrostatic barriers at the grain boundaries (due to high dopant concentration). The observed difference for factor 2 in mobility among the thin-film SnO₂ samples most likely arises due to the difference in the preferred orientation of crystallites (texture coefficient).

Given the significant role of the Ningxia Urban Agglomeration along the Yellow River in reshaping the urban network and promoting coordinated development in the upper Yellow River region of China, this paper takes enterprise flow as the explicit manifestation of the regional urban network. Based on the data of registered enterprises from 2005 to 2021, combined with the interlocking network model, social network analysis method, and spatial panel econometric model, this paper interprets the evolution of the regional urban network structure and its influencing mechanisms through the different types of enterprise flow. The results indicate the following: (1) The external network is primarily focused on outflow investments towards North China, East China, and Northwest China. The overall inflow sources form a multi-origin structure dominated by North China and East China. The Jinfeng and Xingqing serve as core hubs for enterprise exports in the external network and destinations for incoming enterprises. However, in the Productive manufacturing connections, a spatial organizational pattern driven by multiple cities has formed. (2) In the internal network, a concentric connection structure centered around the Jinfeng and Xingqing has formed. The Productive service connections are relatively active, while the Productive manufacturing connections are relatively concentrated between the Jinfeng, Xingqing, Ningdong, and Lingwu. However, there is an imbalance in the spatial connections within the urban agglomeration network and an incomplete hierarchical system of network nodes. (3) In the external network, the main feature is the absorption of external elements to foster development momentum. In the internal network, the Jinfeng and Xingqing serve as contact and radiation sources, influencing various nodes. However, their driving capacity is weak. (4) The market demand and coordinated development both demonstrate significant promoting effects on the connections within the external and internal networks. The sluggish adjustment and transformation of regional industrial structure have resulted in a temporary negative inhibitory effect on the development of transformation. The negative impact of urban investment activities and the positive impact of government management are reflected within the internal network. (5) The improvement of urban management and service functions, as well as external borrowing, can promote the connection in different network. However, the borrowing economic activity can have a negative impact in different networks. (6) Industrial agglomeration can promote enterprises connections in different networks and generate significant spatial spillover effects.

Neuroinflammation and brain oxidative stress are recognized as significant contributors to hypertension including salt sensitive hypertension. Extracellular vesicles (EVs) play an essential role in intercellular communication in various situations, including physiological and pathological ones. Based on this evidence, we hypothesized that EVs derived from the brains of hypertensive rats with salt sensitivity could trigger neuroinflammation and oxidative stress during hypertension development. To test this hypothesis, we compared the impact of EVs isolated from the brains of hypertensive Dahl Salt Sensitive rats (DSS) and normotensive Sprague Dawley (SD) rats on inflammatory factors and mitochondrial reactive oxygen species (mtROS) production in primary neuronal cultures and brain cardiovascular relevant regions, including the hypothalamic paraventricular nucleus (PVN) and lamina terminalis (LT). We found that brain-derived DSS-EVs significantly increased mRNA levels of proinflammatory cytokines (PICs) and chemokines, including TNFα, IL1β, CCL2, CCL5, and CCL12, as well as the transcriptional factor NF-κB in neuronal cultures. DSS-EVs also induced oxidative stress in neuronal cultures, as evidenced by elevated NADPH oxidase subunit CYBA coding gene mRNA levels and persistent mtROS elevation. When DSS-EVs were injected into the brains of normal SD rats, mRNA levels of PICs, chemokines, and the chronic neuronal activity marker FOSL1 were significantly increased in the PVN and LT. Furthermore, DSS-EVs caused mtROS elevation in brain PVN and LT, particularly in neurons. Our study reveals a novel role for brain-derived EVs from hypertensive rats in triggering neuroinflammation, upregulating chemokine expression, and inducing excessive ROS production. These findings provide insight into the complex interactions between EVs and hypertension-associated processes, offering potential therapeutic targets for hypertension-linked neurological complications.

Body-centered cubic bismuth (Bi) is considered an enticing pressure marker, and therefore it is highly desirable to command its accurate equation of state (EOS). However, significant discrepancies are noted among the previous experimental EOSs. In the present work, the EOS up to 300 GPa is theoretically obtained by direct solving the partition function via a direct integral approach (DIA). The calculated results nearly reproduce the hydrostatic experimental measurements below 75 GPa, and the deviations from the measurements gradually get larger with increasing pressure. Based on the ensemble theory of equilibrium state, DIA works with high precision particularly in high-pressure conditions, so the hydrostatic EOS presented in this work is expected to be a reliable pressure standard.

The dual-station Interferometric Synthetic Aperture Radar (InSAR) system can overcome the physical limitations imposed by the baseline of single-station dual-antenna InSAR. It provides greater flexibility and can enhance elevation measurement accuracy through a well-designed baseline configuration.Unmanned aerial vehicles (UAV) equipped with dual-station InSAR, with relatively low cost and high flexibility, are useful for mapping and land resource exploration. However, due to challenges including spatiotemporal synchronization and motion errors, there are limited reports on UAV-borne dual-station InSAR. This paper proposes a comprehensive method for processing data from small UAV-borne dual-station InSAR by integrating two-way synchronization chain signals. The proposed method includes compensation for time and phase synchronization errors, trajectory refinement with synchronized chain and Position and Orientation System (POS) data, high-precision dual-station InSAR imaging and interferometric processing. Height inversion results based on the proposed method is also provided, demonstrating the effectiveness of the proposed method and improving interferometric accuracy at calibration points from 0.66 meters to 0.42 meters.

In this paper, we give all non splitting bi-unitary superperfect polynomials divisible by one or two irreducible polynomials over the prime field of two elements. We prove the nonexistence of odd bi-unitary superperfect polynomials over F2.

The current COVID19 pandemic has raised huge concerns for outdoor air quality due to expected lungs deterioration. These concerns include the challenges in the scalable prediction of harmful gases like carbon dioxide, iterative/repetitive inhaling due to mask and environmental temperature harshness. Even in the presence of air quality sensing devices, these challenges lead to failed planning and strategy against respiratory diseases, epidemics, and pandemics in severe cases. In this work, a dual time-series with bi-cluster sensor data-stream-based novel optimized regression algorithm was proposed with optimization predictors and optimization responses that use automated iterative optimization of the model based on the similarity coefficient index. The algorithm was implemented over SeReNoV2 sensor nodes data, i.e. multi-variate dual time-series of environmental and US Environmental Protection Agency standard sensor variables for air quality index measured from air quality sensors with geospatial profiling. The SeReNoV2 systems were placed at four locations that were 3 km apart to monitor air quality and their data was collected at Ubidots IoT platform over GSM. Results have shown that the proposed technique achieved a root mean square error (RMSE) of 1.0042 with a training time of 469.28 seconds for normal and RMSE of 1.646 in the training time of 28.53 seconds for optimization. The estimated R-Squared error of 0.03 with Mean-Square Error for temperature 1.0084 ᵒC and 293.98 ppm for CO2 was observed. Furthermore, the Mean-Absolute Error (MAE) for temperature 0.66226 ᵒC and 10.252 ppm for CO2 at a prediction speed of ~5100 observations/second for temperature 45000 observations/second for CO2 due to iterative optimization of the training time 469.28 seconds for temperature and 28.53 seconds for CO2 was very promising in forecasting COVID19 countermeasures before time.

The relationship between the host and the microbiome, or the assemblage of microorganisms (including bacteria, archaea, fungi, and viruses), has been proven crucial for its health and disease development. The high dimensionality of microbiome datasets has often been addressed as a major difficulty for data analysis, such as the use of Machine Learning (ML) and Deep Learning (DL) models. Here we present BiGAMi, a bi-objective genetic algorithm fitness function for feature selection in microbial datasets to train high-performing phenotype classifiers. The proposed fitness function allowed us to build classifiers that outperformed the baseline performance estimated by the original studies by using as few as 0.04% to 2.32% features of the original dataset. In 19 out of 21 classification exercises, BiGAMi achieved its results by selecting 6-68% fewer features than the highest performance of a Sequential Forward Feature Selection algorithm. This study showed that the application of a bi-objective GA fitness function against microbiome datasets succeeded in selecting small subsets of bacteria whose contribution to understood diseases and the host state was already experimentally proven. Applying this feature selection approach to novel diseases is expected to quickly reveal the microbes most relevant to a specific condition.

Autonomous mobile robots are essential to the industry, and human-robot interactions are becoming more common nowadays. These interactions require that the robots navigate scenarios with static and dynamic obstacles in a safely manner, avoiding collisions. This paper presents a physical implementation of a method for dynamic obstacle avoidance using a Long Short-Term Memory (LSTM) neural network that obtains information from the mobile robot’s LiDAR for it to be capable of navigating through scenarios with static and dynamic obstacles while avoiding collisions and reaching its goal. The model is implemented using a TurtleBot3 mobile robot within an OptiTrack Motion Capture (MoCap) system for obtaining its position at any given time. The user operates the robot through these scenarios, recording its LiDAR readings, target point, position inside the MoCap system, and its linear and angular velocities, all of which serve as the input for the LSTM network. The model is trained on data from multiple user-operated trajectories across five different scenarios, outputting the linear and angular velocities for the mobile robot. Physical experiments prove that the model is successful in allowing the mobile robot to reach the target point in each scenario while avoiding the dynamic obstacle, with a validation accuracy of 98.02%.

This paper investigates nonverbal communication in human interactions, with a specific focus on facial expressions. Employing a Long Short-Term Memory (LSTM) architecture and a custom-ized facial expression framework, our approach aims to improve virtual agent interactions by incorporating subtle nonverbal cues. The paper contributes to the emerging field of facial expres-sion generation, addressing gaps in current research and presenting a novel framework within Unreal Engine 5. The model's architecture, trained on the CANDOR corpus, captures temporal dynamics, and refines hyperparameters for optimal performance. During testing, the trained model showed a cosine similarity of -0.95. This enables the algorithm to accurately respond to non-verbal cues and interact with humans in a way that is comparable to human-human interac-tion. Unlike other approaches in the field of facial expression generation, the presented method is more comprehensive and enables the integration of a multi-modal approach for generating facial expressions. Future work involves integrating blendshape generation, real-world testing, and the inclusion of additional modalities to create a comprehensive framework for seamless hu-man-agent interactions beyond facial expressions.

In industrial settings, gears play a crucial role by assisting various machinery functions such as speed control, torque manipulation, and altering motion direction.The malfunction or failure of these gear components can have serious repercussions, resulting in production halts and financial losses. As a result, there is an increasing requirement to monitor the state of these components in order to avoid such issues from occurring. To address this need, research efforts have focused on early defect detection in gears in order to reduce the impact of possible failures. This study focused on analyzing vibration and thermal datasets from two extruder machine gearboxes using an autoencoder Long Short-Term Memory (LSTM) model. The major goal is to implement an outlier detection approach to detect and classify defects. The results of this study highlighted the extraordinary performance of the Autoencoder LSTM model, which achieved an impressive accuracy rate of 94.42% in recognizing malfunctioning gearboxes within the extruder machine system. Furthermore, the study used a thorough global metrics evaluation methodology to further test the model’s dependability and efficacy, consequently substantiating the proposed approach’s validity.

Raindrop size distribution (RSD) is an index for reflecting precipitation characteristics. Analyzing the differences of RSD plays an important role in understanding the precipitation microphysical processes and improving quantitative precipitation prediction of radar. In this paper, the RSD data of Dafang (57708) station, Majang (57828) station, and Luodian (57916) station (with an altitude of 1722.7m, 985.0m, and 441.5m, respectively) in Guizhou are analyzed according to the precipitation microphysical characteristics. First,Particles with particle size less than 1mm contributes the highest value to the density of particle number , and decrease with the descending altitude. Second, the GAMMA distribution fit shows a better fit compare to M-P distribution fit, and GAMMA distribution fit increases with the ascending altitude. Third, the mass-weighted average diameter is not sensitive enough to the change of precipitation intensity with correlation coefficients of 54.84%, but there is a obvious relationship between the average volume diameter and the precipitation intensity with correlation coefficients of 69.15%. Then, the precipitation prediction model is established using LSTM neural network after fusing the representative microphysical characteristics of RSD with radar and rain gauge data. The precipitation prediction model is applied to the Dafang (57708) site to predict precipitation for time range of 0-180 minutes, and it is found that for the prediction of convective cloud and stratiform cloud precipitation, the 60-minute prediction results are the most consistent with the actual precipitation, where the correlation coefficients are 92.87% and 92.57%, respectively. Conclusively, the results demonstrate that combining with the RSD base data could improve the reliability of precipitation forecasting.

Activated sludge process is a well known method to treat municipal and industrial waste water. In this complex process, the oxygen concentration in the reactors plays a critical role in the plant efficiency. This paper proposes the use of a Long Short-Term Memory (LSTM) network to identify an input-output model suitable for the design of an oxygen concentration controller. The model is identified from easy-accessible measures collected from a real plant. This dataset covers almost a month. The performances achieved with the proposed LSTM model are compared with the ones obtained with a standard AutoRegressive model with eXogenous input (ARX). Both models catch the oscillation and the overall behaviour (ARX ρ=0.833 , LSTM ρ=0.921), but, while the ARX model fails in reaching the correct amplitude (FIT=41.20%), the LSTM presents satisfactory performance (FIT=60.56%).

This paper realizes early bearing fault warning through bearing fault time series prediction, and proposes a bearing fault time series prediction model based on optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to ensure bearings operation reliability. The model is based on lifecycle vibration signal of the bearing, to begin, the cuckoo search (CS) is utilized to optimize the parameter filter length L and deconvolution period T of MCKD, taking into account the influence and periodicity of the bearing time series, the fault impact component of the optimized MCKD deconvolution time series is improved. Then select the LSTM learning rate α depending on deconvolution time series. Finally, the dataset obtained through various preprocessing approaches are used to train and predict the LSTM model. The average prediction accuracy of the optimized MCKD-LSTM model is 26 percent higher than that of the original time series, proving the efficiency of this method, and the prediction results track the real fault data well, according to the XI'AN JIAOTONG University XJTU-SY bearing dataset.

In cognitive radio systems, identifying spectrum opportunities is fundamental to efficiently use the spectrum. Spectrum occupancy prediction is a convenient way of revealing opportunities based on previous occupancies. Studies have demonstrated that usage of the spectrum has a high correlation over multidimensions which includes time, frequency, and space. Accordingly, recent literature uses tensor-based methods to exploit the multidimensional spectrum correlation. However, these methods share two main drawbacks. First, they are computationally complex. Second, they need to re-train the overall model when no information is received from any base station for any reason. Different than the existing works, this paper proposes a method for dividing the multidimensional correlation exploitation problem into a set of smaller sub-problems. This division is achieved through composite two-dimensional (2D)-long short-term memory (LSTM) models. Extensive experimental results reveal a high detection performance with more robustness and less complexity attained by the proposed method. The real-world measurements provided by one of the leading mobile network operators in Turkey validate these results.