Search

The pulp and paper industry is critical to global industrial and economic development. Recently, India's pulp and paper industries have been facing severe competitive challenges. The challenges have impaired the environmental performance and resulted in the closure of several operations. Assessment and prediction of the performance of the Indian pulp and paper industry using various parameters is a critical task for researchers. This study proposes a framework for performance assessment and prediction based on Data Envelopment Analysis (DEA), Artificial Neural Networks, and Deep Learning (DL) to assist industry administration and decision-making. We presented a case study based on eight industries to demonstrate the methodology's applicability. This study analyses and predicts industry performance based on sample data observations over 30 years. The result suggests the DEA-DL-based efficiency prediction has an overall MSE of 0.08 compared with the actual efficiency. Furthermore, the efficiency rankings are compared between the three techniques. The results suggest that the integrated DEA-DL method is primarily accurate in most scenarios with the actual values. The findings of this study provide a comprehensive analysis of environmental performance for policymakers. [ABSTRACT FROM AUTHOR]

This study investigates the impact of air pollution on health outcomes in Middle Eastern countries, a region facing severe environmental challenges. As such, these are important in an effort to add up to policy-level as well as interventional changes that can be put in practice in the area of public health. Numeration analysis and association with health parameters was carried out by using Analytical tools such as, AIR Data, ARIMA,ANN, SVM and Exponential smoothing. Amongst the models, Support Vector Machine came again on top, with high accuracy yielding Mean Absolute Percentage Error of approximately 1%. Mortality of Air pollution in Qat from the case of Mortality of Air Pollution in Qatar is 959 while Auto regressive Integrated Moving average is 11.096, Exponential Smoothing 9.892 and Artificial Neural Networks are the source of inspiration for the development of this paper 4.61. The above perceptions indicate that there is need to adapt modeling strategies depending on the context and establish that it is possible to implement ML models in public health planning basket. This paper publishes the methodological frameworks for the purpose of modeling and analysis of the EHDs and serves as policy prescription for the policy makers to intending to reduce the effects of air borne pollution on health. [ABSTRACT FROM AUTHOR]

This paper introduces a novel design for a universal DC-DC and DC-AC converter tailored for DC/AC microgrid applications using Approximate Dynamic Programming and Artificial Neural Networks (ADP-ANN). The proposed converter is engineered to operate efficiently with both low-power battery and single-phase AC supply, utilizing identical side terminals and switches for both chopper and inverter configurations. This innovation reduces component redundancy and enhances operational versatility. The converter's design emphasizes minimal switch usage while ensuring efficient conversion to meet diverse load requirements from battery or AC sources. A conceptual example illustrates the design's principles, and comprehensive analyses compare the converter's performance across various operational modes. A test bench model, rated at 3000W, demonstrates the converter's efficacy in all five operational modes with AC/DC inputs. Experimental results confirm the system's robustness and adaptability, leveraging ADP-ANN for optimal performance. The paper concludes by outlining potential applications, including microgrids, electric vehicles, and renewable energy systems, highlighting the converter's key advantages such as reduced complexity, increased efficiency, and broad applicability. [ABSTRACT FROM AUTHOR]

This document provides a summary of eight research papers presented at the British Machine Vision Conference. The papers cover a range of topics in machine vision, machine learning, and deep learning. Each paper introduces a new approach or technique and presents experimental evidence of its effectiveness. The topics include denoising, image rendering, human head editing, gaze estimation, reconstruction, video hashing, object tracking, and head/face reenactment. The papers collectively showcase the diverse and evolving nature of research in the field of computer vision. [Extracted from the article]

With the establishment of the "double carbon" goal, various industries are actively exploring ways to reduce carbon emissions. Cloud data centers, represented by cloud computing, often have the problem of mismatch between load requests and resource supply, resulting in excessive carbon emissions. Based on this, this paper proposes a complete method for cloud computing carbon emission prediction. Firstly, the convolutional neural network and bidirectional long-term and short-term memory neural network (CNN-BiLSTM) combined model are used to predict the cloud computing load. The real-time prediction power is obtained by real-time prediction load of cloud computing, and then the carbon emission prediction is obtained by power calculation. Develop a dynamic server carbon emission prediction model, so that the server carbon emission can change with the change of CPU utilization, so as to achieve the purpose of low carbon emission reduction. In this paper, Google cluster data is used to predict the load. The experimental results show that the CNN-BiLSTM combined model has good prediction effect. Compared with the multi-layer feed forward neural network model (BP), long short-term memory network model (LSTM), bidirectional long short-term memory network model (BiLSTM), modal decomposition and convolution long time series neural network model (CEEMDAN-ConvLSTM), the MSE index decreased by 52 % , 50 % , 34 % and 45 % respectively. [ABSTRACT FROM AUTHOR]

De-mining operations are of critical importance for humanitarian efforts and safety in conflict-affected regions. In this paper, we address the challenge of enhancing the accuracy and efficiency of mine detection systems. We present an innovative Deep Learning architecture tailored for pulse induction-based Metallic Mine Detectors (MMD), so called DL-MMD. Our methodology leverages deep neural networks to distinguish amongst nine distinct materials with an exceptional validation accuracy of 93.5%. This high level of precision enables us not only to differentiate between anti-personnel mines, without metal plates but also to detect minuscule 0.2-g vertical paper pins in both mineralized soil and non-mineralized environments. Moreover, through comparative analysis, we demonstrate a substantial 3% and 7% improvement (approx.) in accuracy performance compared to the traditional K-Nearest Neighbors and Support Vector Machine classifiers, respectively. The fusion of deep neural networks with the pulse induction-based MMD not only presents a cost-effective solution but also significantly expedites decision-making processes in de-mining operations, ultimately contributing to improved safety and effectiveness in these critical endeavors. [ABSTRACT FROM AUTHOR]

To investigate how the petroleum industry evaluates and selects powerful cloud service providers, first, an evaluation index system including 25 indices such as scalability and private data protection is built. This index system can systematically examine the comprehensive strengths of cloud service providers. Aiming to solve the problems that the traditional expert evaluation method has high requirements on expert experience and is easily affected by subjective factors, a novel artificial intelligence evaluation model named TentISSA-BPNN is proposed. The objective evaluation ability of this model can be effectively used in evaluation research on cloud service providers for petroleum enterprises. In this model, the SSA algorithm is optimized by Tent chaotic mapping and adaptive inertia weight; an algorithm, TentISSA, that has good stability and fast convergence speed is designed and proposed; and the BPNN is improved with TentISSA to obtain more accurate evaluation results. To evaluate the performance of the TentISSA algorithm, nine unimodal and multimodal functions are selected in this paper to test the convergence accuracy. Then, seven models are selected as the control groups to validate the effectiveness and performance of the TentISSA-BPNN evaluation model proposed in this paper. Finally, the preprocessed data of the candidate cloud service providers are input into the trained neural network model proposed in this paper for evaluation. Based on the ranking of the evaluation scores, the comprehensive strengths of the cloud service providers are obtained to provide a decision-making reference for managers of petroleum enterprises in the process of choosing cloud service providers. [ABSTRACT FROM AUTHOR]

Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data. Recent efforts have utilized pre-trained contrastive image-text models like CLIP, adapting them for medical use by fine-tuning the model with chest X-ray images and corresponding reports for zero-shot pathology classification, thus eliminating the need for pathology-specific annotations. However, most studies continue to use the same contrastive learning objectives as in the general domain, overlooking the multi-labeled nature of medical image-report pairs. In this paper, we propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. We aim to improve the performance of zero-shot pathology classification without relying on external knowledge. Our method can be applied to any pre-trained contrastive image-text encoder and easily transferred to out-of-domain datasets without further training, as it does not use external data. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models, with an average macro AUROC increase of 4.3%. Additionally, our method outperforms the state-of-the-art and marginally surpasses board-certified radiologists in zero-shot classification for the five competition pathologies in the CheXpert dataset. [ABSTRACT FROM AUTHOR]

Due to the complex structure of most frame structure, a large amount of sensor data needs to be processed for damage diagnosis, which increases the computational cost of diagnosis models and poses a serious challenge to their fast, accurate, and efficient damage diagnosis. In order to address this issue, this paper proposes a novel lightweight damage diagnosis method of frame structure for mobile devices based on convolutional neural networks. This method first uses mean filtering to process the vibration data collected by sensors, and then innovatively combines two convolutional neural network models, ShuffleNet and GhostNet, to form a new lightweight convolutional neural network model called SGNet, thereby reducing the computational cost of the model while ensuring diagnosis accuracy. In order to test the performance of the method proposed in this article, experimental research on damage degree diagnosis and damage type diagnosis is conducted by taking the frame structure provided by Columbia University as the research object, and comparative experiments of performance are conducted with MobileNet, GhostNet, and ShuffleNet. The experimental results show that the lightweight damage diagnosis method for frame structure proposed in this article not only has high damage diagnosis accuracy, but also has fewer computational parameters, when the highest accuracy is 99.8%, the computational parameters are only 1 million. At the same time, it is superior to MobileNet, GhostNet, ShuffleNet in terms of diagnosis accuracy and computational cost, so it is an effective high-precision lightweight damage diagnosis method for frame structure. [ABSTRACT FROM AUTHOR]

Multimodal aspect-level sentiment analysis (MALSA) aims to predict the sentiment polarity of each given aspect in multimodal contexts. The previous studies usually developed deep neural networks to capture the impacts that a given aspect brings to text and images. However, the dynamic interaction between the intra-modality and inter-modality relations is seldom investigated before fusing the textual and visual representations. This paper presents a conditioned joint-modality attention fusion approach for the MALSA task, which can iteratively deliver useful information flow between and across textual and visual modalities under the guidance of aspect information for sentiment polarity prediction. The point is the dual conditioned-attention mechanism, which calculates intra-modality attention flows dynamically modulated by the other modality. Experiments are conducted on three public datasets including Twitter-2015, Twitter-2017 and Multi-ZOL. Results show that the proposed model outperforms the state-of-the-art models, and demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Forecasting mortality is challenging. In general, mortality rate forecasting exercises have been based on the supposition that predictors' residuals are random noise. However, issues regarding model selection, misspecification, or the dynamic behavior of the temporal phenomenon lead to biased or underperformed single models. Residual series might present temporal patterns that can still be used to improve the forecasting system. This paper proposes a new recursive direct multi-step Hybrid System for Mortality Forecasting (HyS-MF) that combines the Autoregressive Integrated Moving Average (ARIMA) with Neural Basis Expansion for Time Series Forecasting (N-BEATS). HyS-MF employs (i) ARIMA to model and forecast the mortality rate time series with a recursive approach and (ii) N-BEATS with the direct multi-step approach to learn and forecast the residuals of the linear predictor. The final output is generated by summing ARIMA with the N-BEATS forecasts in each time horizon. HyS-MF achieved an average Mean Absolute Percentage Error (MAPE) less than 1.34% considering all prediction horizons, beating statistical techniques, machine learning, deep learning models, and hybrid systems considering 101 different time series from the French population mortality rate. [ABSTRACT FROM AUTHOR]

Objects in the visual field are perceived to have an inherent structure that is seen in the way that they are constructed from their components. For example, a face requires its parts to be arranged in a certain spatial configuration. This property, of having such a structure, is termed as compositionality. For deep neural networks to preserve these structures of their inputs in their representations, the capsule network model was proposed. However, there is no empirical evidence to confirm if capsule networks do indeed learn compositional representations. Here, we propose a novel task for the experimental analysis of this property. This task, termed MeasureComp, tests the unsupervised learning of unannotated part-whole structures in a classification setting. Our results show that capsule networks that use dynamic routing are unable to learn pose-aware representations. In an effort to improve upon this, and as an initial direction towards compositional capsule models, we propose a novel compositional loss-function termed EntrLoss. Experimental results on MeasureComp show that the use of this loss function improves the compositionality of capsule networks. Further, we also present a simple capsule network model that uses our EntrLoss and outperforms several other recent capsule networks. The code for our paper is available at https://github.com/codesubmissionforpaper/entropy_regularised_capsule. [ABSTRACT FROM AUTHOR]

Email phishing is a social engineering scheme that uses spoofed emails intended to trick the user into disclosing legitimate business and personal credentials. Many phishing email detection techniques exist based on machine learning, deep learning, and word embedding. In this paper, we propose a new technique for the detection of phishing emails using word embedding (Word2Vec, FastText, and TF-IDF) and deep learning techniques (DNN and BiLSTM network). Our proposed technique makes use of only four header based (From, Returnpath, Subject, Message-ID) features of the emails for the email classification. We applied several word embeddings for the evaluation of our models. From the experimental evaluation, we observed that the DNN model with FastText-SkipGram achieved an accuracy of 99.52% and BiLSTM model with FastText-SkipGram achieved an accuracy of 99.42%. Among these two techniques, DNN outperformed BiLSTM using the same word embedding (FastText-SkipGram) techniques with an accuracy of 99.52%. [ABSTRACT FROM AUTHOR]

In computer vision, an important challenge to deep neural networks comes from adjusting the varying properties of different image domains. To study this problem, researchers have been investigating a practical setting in which the deep neural networks are trained on a labeled source domain and then transferred to an unlabeled or even unseen target domain. The major difficulty lies in the potential domain gap, which essentially arises from the overfitting in the source domain. Hence, it is important to introduce generalized priors to alleviate the issue. From this perspective, this paper presents a novel framework that forces visual features to align with domain-agnostic priors (DAP). Specifically, we study two kinds of priors, (i) language-guided embedding and (ii) class-level relationship, and we believe that more such priors can be constructed. Our framework, referred to as DAP, is evaluated on both unsupervised domain adaptation (UDA) and domain generalization (DG) where the target domain is unlabeled and even unseen, respectively. We use the standard benchmark that performs transfer semantic segmentation on synthesized datasets (i.e., GTAv and SYNTHIA) and a real dataset (i.e., Cityscapes). Experiments validate the effectiveness of DAP with competitive accuracy in all tasks. In particular, language-guided priors work sufficiently well for UDA, while class-level priors serve as useful complements for DG. The proposed frameworks shed light that domain transfer benefits from better proxies, possibly from other modalities. [ABSTRACT FROM AUTHOR]

This paper addresses a relevant problem in Forensic Sciences by integrating radiological techniques with advanced machine learning methodologies to create a non-invasive, efficient, and less examiner-dependent approach to age estimation. Our study includes a new dataset of 12,827 dental panoramic X-ray images representing the Brazilian population, covering an age range from 2.25 to 96.50 years. To analyze these exams, we employed a model adapted from InceptionV4, enhanced with data augmentation techniques. The proposed approach achieved robust and reliable results, with a Test Mean Absolute Error of 3.1 years and an R-squared value of 95.5%. Professional radiologists have validated that our model focuses on critical features for age assessment used in odontology, such as pulp chamber dimensions and stages of permanent teeth calcification. Importantly, the model also relies on anatomical information from the mandible, maxillary sinus, and vertebrae, which enables it to perform well even in edentulous cases. This study demonstrates the significant potential of machine learning to revolutionize age estimation in Forensic Science, offering a more accurate, efficient, and universally applicable solution. [ABSTRACT FROM AUTHOR]

In ophthalmology, artificial intelligence methods show great promise due to their potential to enhance clinical observations with predictive capabilities and support physicians in diagnosing and treating patients. This paper focuses on modelling glaucoma evolution because it requires early diagnosis, individualized treatment, and lifelong monitoring. Glaucoma is a chronic, progressive, irreversible, multifactorial optic neuropathy that primarily affects elderly individuals. It is important to emphasize that the processed data are taken from medical records, unlike other studies in the literature that rely on image acquisition and processing. Although more challenging to handle, this approach has the advantage of including a wide range of parameters in large numbers, which can highlight their potential influence. Artificial neural networks are used to study glaucoma progression, designed through successive trials for near-optimal configurations using the NeuroSolutions and PyTorch frameworks. Furthermore, different problems are formulated to demonstrate the influence of various structural and functional parameters on the study of glaucoma progression. Optimal neural networks were obtained using a program written in Python using the PyTorch deep learning framework. For various tasks, very small errors in training and validation, under 5%, were obtained. It has been demonstrated that very good results can be achieved, making them credible and useful for medical practice. [ABSTRACT FROM AUTHOR]

As computer image processing and digital technologies advance, creating an efficient method for classifying sports images is crucial for the rapid retrieval and management of large image datasets. Traditional manual methods for classifying sports images are impractical for large-scale data and often inaccurate when distinguishing similar images. This paper introduces an SE module that adaptively adjusts the weights of input feature mapping channels, and a Res module that excels in deep feature extraction, preventing gradient vanishing, multi-scale processing, and enhancing generalization in image recognition. Through extensive experimentation on network structure adjustments, the SE-RES-CNN neural network model is applied to sports image classification. The model is trained on a sports image classification dataset from Kaggle, alongside VGG-16 and ResNet50 models. Training results show that the proposed SE-RES-CNN model improves classification accuracy by approximately 5% compared to VGG-16 and ResNet50 models. Testing revealed that the SE-RES-CNN model classifies 100 out of 500 sports images in 6 s, achieving an accuracy rate of up to 98% and a single prediction time of 0.012 s. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency. [ABSTRACT FROM AUTHOR]

Network slicing is crucial to the 5G architecture because it enables the virtualization of network resources into a logical network. Network slices are created, isolated, and managed using software-defined networking (SDN) and network function virtualization (NFV). The virtual network function (VNF) manager must devise strategies for all stages of network slicing to ensure optimal allocation of physical infrastructure (PI) resources to high-acceptance virtual service requests (VSRs). This paper investigates two independent network slicing frameworks named as dual-slice isolation and management strategy (D-SIMS) and recommends the best of the two based on performance measurements. D-SIMS places VNFs for network slicing using self-sustained resource reservation (SSRR) and master-sliced resource reservation (MSRR), with some flexibility for the VNF manager to choose between them based on the degree to which the underlying physical infrastructure has been sliced. The present research work consists of two phases: the first deals with the creation of slices, and the second with determining the most efficient way to distribute resources among them. A deep neural network (DNN) technique is used in the first stage to generate slices for both PI and VSR. Then, in the second stage, we propose D-SIMS for resource allocation, which uses both the fuzzy-PROMETHEE method for node mapping and Dijkstra's algorithm for link mapping. During the slice creation phase, the proposed DNN training method's classification performance is evaluated using accuracy, precision, recall, and F1 score measures. To assess the success of resource allocation, metrics such as acceptance rate and resource effectiveness are used. The performance benefit is investigated under various network conditions and VSRs. Finally, to demonstrate the importance of the proposed work, we compare the simulation results to those in the academic literature. [ABSTRACT FROM AUTHOR]

This paper investigated the global attractive set for quaternion-valued neural networks (QVNNs) with leakage delay, time-varying delay, and neutral items. Based on various basic conditions of activation function, the global attractive set and global exponential attractive set of QVNNs are given combined with novel analytical techniques and Lyapunov theory. The QVNNs are studied by a direct method, without any decomposition. The time delay can be non-differential, which makes the results more pragmatic. Restrictions on the activation function of the neutral item are relaxed. The neutral activation function can be bounded or unbounded, which makes the results more practical. Two simulation examples are given to verify the validity of the theory results. [ABSTRACT FROM AUTHOR]

Deep neural network (DNN) architectures such as recurrent neural networks and transformers display outstanding performance in modeling sequential unstructured data. However, little is known about their merit to model customer churn with time-varying data. The paper provides a comprehensive evaluation of the ability of recurrent neural networks and transformers for customer churn prediction (CCP) using time-varying behavioral features in the form of recency, frequency, and monetary value (RFM). RFM variables are the backbone of CCP and, more generally, customer behavior forecasting. We examine alternative strategies for integrating time-varying and non-variant customer features in one network architecture. In this scope, we also assess hybrid approaches that incorporate the outputs of DNNs in conventional CCP models. Using a comprehensive panel data set from a large financial services company, we find recurrent neural networks to outperform transformer architectures when focusing on time-varying RFM features. This finding is confirmed when time-invariant customer features are included, independent of the specific form of feature integration. Finally, we find no statistical evidence that hybrid approaches (based on regularized logistic regression and extreme gradient boosting) improve predictive performance—highlighting that DNNs and especially recurrent neural networks are suitable standalone classifiers for CCP using time-varying RFM measures. [ABSTRACT FROM AUTHOR]

This paper is about the opposite of judgement and calculation. This opposition has been a traditional anchor of critiques concerned with the rise of AI decision making over human judgement. Contrary to these approaches, it is argued that human judgement is not and cannot be replaced by calculation, but that it is human judgement that contextualises computational structures and gives them meaning and purpose. The article focuses on the epistemic structure of algorithms and artificial neural networks to find that they always depend on human judgement to be related to real life objects or purposes. By introducing the philosophical concept of judgement, it becomes clear that the property of judgement to provide meaning and purposiveness is based on the temporality of human life and the ambiguity of language, which quantitative processes lack. A juxtaposition shows that calculations and clustering can be used and referred to in more or less prejudiced and reflecting as well as opaque and transparent ways, but thereby always depend on human judgement. The paper clearly asserts that the transparency of AI is necessary for their autonomous use. This transparency requires the explicitness of the judgements that constitute these computational structures, thereby creating an awareness of the conditionality of such epistemic entities. [ABSTRACT FROM AUTHOR]

Accurate prediction of sea level height is critically important for the government in assessing sea level risk in coastal areas. However, due to the nonlinear, time-varying and highly uncertain characteristics of sea level change data, sea level prediction is challenging. To improve the accuracy of sea level prediction, this paper uses a new swarm intelligence algorithm named the sparrow search algorithm (SSA), which can imitate the foraging behavior and antipredation behavior of sparrows, to determine optimal solutions. To avoid the algorithm falling into a local optimal situation, this paper integrates the sine–cosine algorithm and the Cauchy variation strategy into the SSA to obtain an algorithm named the SCSSA. The SCSSA is used to optimize the parameter values of the CNN-BiLSTM (convolutional neural network combined with bidirectional long short-term memory neural network) model; finally, a combined neural network model (named SCSSA-CNN-BiLSTM) is proposed. In this paper, the time series data of seven tidal stations located in coastal China are used for experimental analysis. First, the SCSSA-CNN-BiLSTM model is compared with the CNN-BiLSTM model to predict the time series data of SHANWEI Station. With respect to the training and test sets of data, the SCSSA-CNN-BiLSTM model outperforms the other models on all the evaluation metrics. In addition, the remaining six tide station datasets and five neural network models, including the SCSSA-CNN-BiLSTM model, are used to further study the performance of the proposed prediction model. Four evaluation indices including the root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R2) are adopted. For six stations, the RMSE, MAE, MAPE and R2 of SCSSA-CNN-BiLSTM model are ranged from 20.9217 ~ 27.8427 mm, 9.4770 ~ 17.8603 mm, 0.1322% ~ 0.2482% and 0.9119 ~ 0.9759, respectively. The experimental analysis results show that the SCSSA-CNN-BiLSTM model makes effective predictions at all stations, and the prediction performance is better than that of the other models. Even though the combination of SCSSA algorithm may increase the complexity of the model, indeed the proposed model is a new prediction method with good accuracy and robustness for predicting sea level change. [ABSTRACT FROM AUTHOR]

The paramount concern of highly accurate energy-efficient computing in machines with significant cognitive capabilities aims to enhance the accuracy and efficiency of bio-inspired Spiking Neural Networks (SNNs). This paper addresses this main objective by introducing a novel spatial power spike-timing-dependent plasticity (Spatial-Pow-STDP) learning rule as a digital block with high accuracy in a bio-inspired SNN model. Motivated by the demand for precise and accelerated computation that reduces high-cost resources in neural network applications, this paper presents a methodology based on COordinate Rotation DIgital Computer (CORDIC) definitions. The proposed designs of CORDIC algorithms for exponential (Exp CORDIC), natural logarithm (Ln CORDIC), and arbitrary power function (Pow CORDIC) are meticulously detailed and evaluated to ensure optimal acceleration and accuracy, which respectively show average errors near 10–9, 10–6, and 10–5 with 4, 4, and 6 iterations. The engineered architectures for the Exp, Ln, and Pow CORDIC implementations are illustrated and assessed, showcasing the efficiency achieved through high frequency, leading to the introduction of a Spatial-Pow-STDP learning block design based on Pow CORDIC that facilitates efficient and accurate hardware computation with 6.93 × 10–3 average error with 9 iterations. The proposed learning mechanism integrates this structure into a large-scale spatiotemporal SNN consisting of three layers with reduced hyper-parameters, enabling unsupervised training in an event-based paradigm using excitatory and inhibitory synapses. As a result, the application of the developed methodology and equations in the computational SNN model for image classification reveals superior accuracy and convergence speed compared to existing spiking networks by achieving up to 97.5%, 97.6%, 93.4%, and 93% accuracy, respectively, when trained on the MNIST, EMNIST digits, EMNIST letters, and CIFAR10 datasets with 6, 2, 2, and 6 training epochs. [ABSTRACT FROM AUTHOR]

Genetic and agronomic advances consistently lead to an annual increase in global barley yield. Since abiotic stresses (physical environmental factors that negatively affect plant growth) reduce barley yield, it is necessary to predict barley resistance. Artificial intelligence and machine learning (ML) models are new and powerful tools for predicting product resilience. Considering the research gap in the use of molecular markers in predicting abiotic stresses, this paper introduces a new approach called GenPhenML that combines molecular markers and phenotypic traits to predict the resistance of barley genotypes to drought and salinity stresses by ML models. GenPhenML uses feature selection algorithms to determine the most important molecular markers. It then identifies the best model that predicts atmospheric resistance with lower MAE, RMSE, and higher R2. The results showed that GenPhenML with a neural network model predicted the salinity stress resistance score with MAE, RMSE and R2 values of 0.1206, 0.0308 and 0.9995, respectively. Also, the NN model predicted drought stress scores with MAE, RMSE and R2 values of 0.0727, 0.0105 and 0.9999, respectively. The GenPhenML approach was also used to classify barley genotypes as resistant and stress-sensitive. The results showed that the accuracy, accuracy and F1 score of the proposed approach for salinity and drought stress classification were higher than 97%. [ABSTRACT FROM AUTHOR]

In this work, we propose a novel single-end morphing capacitive sensing method for shape tracking, FxC, by combining Folding origami structures and Capacitive sensing to detect the morphing structural motions using state-of-the-art sensing circuits and deep learning. It was observed through embedding areas of origami structures with conductive materials as single-end capacitive sensing patches, that the sensor signals change coherently with the motion of the structure. Different from other origami capacitors where the origami structures are used in adjusting the thickness of the dielectric layer of double-plate capacitors, FxC uses only a single conductive plate per channel, and the origami structure directly changes the geometry of the conductive plate. We examined the operation principle of morphing single-end capacitors through 3D geometry simulation combined with physics theoretical deduction, which deduced similar behavior as observed in experimentation. Then a software pipeline was developed to use the sensor signals to reconstruct the dynamic structural geometry through data-driven deep neural network regression of geometric primitives extracted from vision tracking. We created multiple folding patterns to validate our approach, based on folding patterns including Accordion, Chevron, Sunray and V-Fold patterns with different layouts of capacitive sensors using paper-based and textile-based materials. Experimentation results show that the geometry primitives predicted from the capacitive signals have a strong correlation with the visual ground truth with R-squared value of up to 95% and tracking error of 6.5 mm for patches. The simulation and machine learning constitute two-way information exchange between the sensing signals and structural geometry. By embedding part of the origami surface with morphing single-end capacitive sensors, FxC presents a unique solution that leverages both the mechanical properties of origami and sensing properties of capacitive sensing. [ABSTRACT FROM AUTHOR]

Accurate prediction of regional terrestrial water storage change (TWSA) is of great significance for water resources planning and management, and early warning of extreme climate disasters. Aiming at the problem that the conventional methods on prediction of TWSA time series are difficult to be accurate, the six typical regions are selected in China as examples, including the upper reaches of the Yangtze River (UYR), the southwest region (SWR), the Liaohe River Basin (LRB), the North China Plain (NCP), the Qinghai-Tibet Plateau (QTP), and the Pearl River Basin (PRB). The mascon product from GRACE/GRACE-FO provided by CSR is used to extract TWSA time series in six typical areas. The improved Back Propagation (BP) neural network, Long Short-Term Memory (LSTM) neural network and the latest Bidirectional LSTM (BiLSTM-attention) neural network model based on attention mechanism are proposed to predict and analyze the regional TWSA. In the experiment, the selection of the optimal model parameters such as the number of hidden layer nodes and the number of hidden units of the neural network model is tested and analyzed in detail. Meanwhile, the model prediction results are compared with the traditional least squares method and random forest (RF) prediction method. The root mean square error (RMSE), determination coefficient (R2), Nash–Sutcliffe efficiency coefficient (NSE) and mean absolute percentage error (MAPE) were used to evaluate the accuracy of the predicted results. The results show that the improved BP, LSTM and Bi-LSTM-attention neural network models all achieve higher prediction accuracy in UYR and SWR areas. RMSE is less than 2.641 cm, R2 is as high as 0.8 or more, NSE is above 0.6, and MAPE is within 0.1. Compared with the least square method, the RMSE of the predicted results from three neural network decreased by 0.998 cm, 0.700 cm and 0.7563 on average, and the R2 increased by 81.75%, 69.89% and 72% on average. Compared with RFML method, the RMSE from three neural network is reduced by 0.601 cm, 0.316 cm and 0.360, and R2 is increased by 38.20%, 24.60% and 27.06% on average. NSE and RMSE are improved to varying degrees in the above regions. It shows that the improved BP, LSTM and BiLSTM-attention model used can effectively predict TWSA. The research methods and results in this paper can provide important reference for the rational utilization of regional water resources and disaster risk assessment. [ABSTRACT FROM AUTHOR]

Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binary classification of extreme concentration levels. Finally, we investigate probabilistic regression approaches and explore uncertainty estimates for enhanced clinical usefulness. Our results show that DNNs outperform traditional models but model performance varies significantly across different electrolytes. While discretization leads to good classification performance, it does not address the original problem of continuous concentration level prediction. Probabilistic regression has practical potential, but our uncertainty estimates are not perfectly calibrated. Our study is therefore a first step towards developing an accurate and reliable ECG-based method for electrolyte concentration level prediction—a method with high potential impact within multiple clinical scenarios. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved remarkable success in various fields. However, training an effective deep neural network still poses challenges. This paper aims to propose a method to optimize the training effectiveness of deep neural networks, with the goal of improving their performance. Firstly, based on the observation that parameters (weights and bias) of deep neural network change in certain rules during training process, the potential of parameters prediction for improving training efficiency is discovered. Secondly, the potential of parameters prediction to improve the performance of deep neural network by noise injection introduced by prediction errors is revealed. And then, considering the limitations comprehensively, a deep neural network Parameters Linear Prediction method is exploit. Finally, performance and hyperparameter sensitivity validations are carried out on some representative backbones. Experimental results show that by employing proposed Parameters Linear Prediction method, as opposed to SGD, has led to an approximate 1% increase in accuracy for optimal model, along with a reduction of about 0.01 in top-1/top-5 error. Moreover, it also exhibits stable performance under various hyperparameter settings, shown the effectiveness of the proposed method and validated its capacity in enhancing network's training efficiency and performance. [ABSTRACT FROM AUTHOR]

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections. This results in scan times of several days to acquire hundreds of hyperspectral projections, during which end users have minimal feedback. To address these challenges, a golden ratio scanning protocol combined with model-based image reconstruction algorithms have been proposed. This novel approach enables high quality real-time reconstructions from streaming experimental data, thus providing feedback to users, while requiring fewer yet a fixed number of projections compared to the filtered back projection method. In this paper, we propose a novel machine learning criterion that can terminate a streaming neutron tomography scan once sufficient information is obtained based on the current set of measurements. Our decision criterion uses a quality score which combines a reference-free image quality metric computed using a pre-trained deep neural network with a metric that measures differences between consecutive reconstructions. The results show that our method can reduce the measurement time by approximately a factor of five compared to a baseline method based on filtered back projection for the samples we studied while automatically terminating the scans. [ABSTRACT FROM AUTHOR]

Highlights: Transient response plays a crucial role as a performance indicator for organic electrochemical transistors (OECTs), particularly in their application in high-speed logic circuits and neuromorphic computing systems. This review presents a systematic overview on the fundamental principles underlying OECT transient responses, emphasizing the essential roles of transient electron and ion dynamics, as well as structural evolution, in both volatile and non-volatile behaviors. We also discuss the materials, morphology, device structure strategies on optimizing transient responses. The rapid development of organic electrochemical transistors (OECTs) has ushered in a new era in organic electronics, distinguishing itself through its application in a variety of domains, from high-speed logic circuits to sensitive biosensors, and neuromorphic devices like artificial synapses and organic electrochemical random-access memories. Despite recent strides in enhancing OECT performance, driven by the demand for superior transient response capabilities, a comprehensive understanding of the complex interplay between charge and ion transport, alongside electron–ion interactions, as well as the optimization strategies, remains elusive. This review aims to bridge this gap by providing a systematic overview on the fundamental working principles of OECT transient responses, emphasizing advancements in device physics and optimization approaches. We review the critical aspect of transient ion dynamics in both volatile and non-volatile applications, as well as the impact of materials, morphology, device structure strategies on optimizing transient responses. This paper not only offers a detailed overview of the current state of the art, but also identifies promising avenues for future research, aiming to drive future performance advancements in diversified applications. [ABSTRACT FROM AUTHOR]

Current challenges in the field of luminescent materials are concerned with designing efficient material to meet the rapidly rising demands of industry. Luminescent material excitation and emission are highly complex phenomena driven by the combination of atomic-level properties such as valence electron, inter-atomic radius, ionic radius, etc., and physical properties such as crystal structure, symmetry, etc. The current research paper focuses on the development of a machine-learning algorithm based on simple luminescent materials to predict the excitation to the closest possible accuracy using easily accessible key attributes by the CatBoost regressor, multiple linear regression (MLR), and an artificial neural network (ANN) approach. These selected features likely correlate with the excitation of the material. In comparison, the ANN and MLR algorithms have higher mean absolute error values in both the training and test datasets. The CatBoost algorithm outperforms the other algorithms in terms of mean of the absolute percentage difference, achieving a value of 0.302136% in the training dataset. The CatBoost algorithm exhibits the lowest root mean squared error value of 1.680768 nm in the training dataset, indicating that its predictions have a smaller average deviation from the actual values. The style for studying the material property has the potential to reduce the cost and time involved in an Edisonian approach to the lengthy laboratory experiment to identify excitation. [ABSTRACT FROM AUTHOR]

In this paper, a new type of auxetic honeycomb is designed, which introduces arc walls into the concave hexagonal honeycomb cells and has higher specific energy absorption. The deformation modes and energy absorption of the designed honeycomb are analyzed by using three methods including finite element, compression experiment and machine learning methods. A fully connected two-hidden layer backpropagation deep neural network (BP-DNN) is developed to predict the energy absorptions of the honeycomb with different geometric parameters. It is found that the error of the validation set is low, and the average correlation coefficient of the validation set is 99.2%, which indicates that the neural network can obtain good predictions. The sensitivity analysis of the input parameters shows that the thickness t has the highest sensitivity, and the ratio of the length of the straight wall to the height has the lowest sensitivity to the energy. In addition, the neural network developed can also predict the mechanical properties of the honeycombs outside the parameter range of the training set and the results are consistent with that of the sensitivity analysis. The DNN provides a fast and accurate method for the energy absorption of honeycombs, which is expected to speed up the optimization and design process of honeycomb structures. [ABSTRACT FROM AUTHOR]

In recent years, vector-to-vector mapping-based raw waveform biosignal enhancement methods have gained significant attention in remote health monitoring system. In this paper, a novel end-to-end convolutional encoder–decoder (CED) model with stacked gated recurrent unit (SGRU) is proposed to learn sequential information of biosignal for signal enhancement. The proposed model CED-SGRU employs convolutional neural network to capture the spatial features and SGRU to capture temporal distributions of the biosignal layer by layer which increases the robustness of the proposed model. This work applies mean absolute error as a loss function for CED-SGRU-based vector-to-vector model. The proposed method has been evaluated on three foremost required biosignals, namely electrocardiogram, photoplethysmography and heart rate signals for diagnosing cardiovascular diseases. Experimental result shows outstanding denoising capability of the proposed CED-SGRU model on three biosignals which yields significantly higher reconstruction signal-to-noise ratio value and lower average absolute error, root mean square error and percent root mean square difference values when compared with state-of-the-art-methods. Moreover, the simple architecture of SGRU lowers the complexity of the model; thereby, reducing the inference time for denoising and restoring compressed biosignal tasks is fairly compared with baseline models, namely recurrent neural network model and long short-term memory model. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of spatially-varying illumination-aware indoor harmonization. Existing image harmonization works either focus on extracting no more than 2D information (e.g., low-level statistics or image filters) from the background image or rely on the non-linear representations of deep neural networks to adjust the foreground appearance. However, from a physical point of view, realistic image harmonization requires the perception of illumination at the foreground position in the scene (i.e., Spatially-Varying (SV) illumination), especially for indoor scenes. To solve indoor harmonization, we present a novel learning-based framework, which attempts to mimic the physical model of image formation. The proposed framework consists of a new neural harmonization architecture with four compact neural modules, which jointly learn SV illumination, shading, albedo, and rendering. In particular, a multilayer perceptron-based neural illumination field is designed to recover the illumination with finer details. Besides, we construct the first large-scale synthetic indoor harmonization benchmark dataset in which the foreground focuses on humans and is rendered and perturbed by SV illuminations. An object placement formula is also derived to ensure that the foreground object is placed in the background at a reasonable size. Extensive experiments on synthetic and real data demonstrate that our proposed approach achieves better results than prior works. [ABSTRACT FROM AUTHOR]

One of the focal points in the field of intelligent transportation is the intelligent control of traffic signals (TS), aimed at enhancing the efficiency of urban road networks through specific algorithms. Deep Reinforcement Learning (DRL) algorithms have become mainstream, yet they suffer from inefficient training sample selection, leading to slow convergence. Additionally, enhancing model robustness is crucial for adapting to diverse traffic conditions. Hence, this paper proposes an enhanced method for traffic signal control (TSC) based on DRL. This approach utilizes dueling network and double q-learning to alleviate the overestimation issue of DRL. Additionally, it introduces a priority sampling mechanism to enhance the utilization efficiency of samples in memory. Moreover, noise parameters are integrated into the neural network model during training to bolster its robustness. By representing high-dimensional real-time traffic information as matrices, and employing a phase-cycled action space to guide the decision-making of intelligent agents. Additionally, utilizing a reward function that closely mirrors real-world scenarios to guide model training. Experimental results demonstrate faster convergence and optimal performance in metrics such as queue length and waiting time. Testing experiments further validate the method's robustness across different traffic flow scenarios. [ABSTRACT FROM AUTHOR]

Spectroscopic techniques generate one-dimensional spectra with distinct peaks and specific widths in the frequency domain. These features act as unique identities for material characteristics. Deep neural networks (DNNs) has recently been considered a powerful tool for automatically categorizing experimental spectra data by supervised classification to evaluate material characteristics. However, most existing work assumes balanced spectral data among various classes in the training data, contrary to actual experiments, where the spectral data is usually imbalanced. The imbalanced training data deteriorates the supervised classification performance, hindering understanding of the phase behavior, specifically, sol-gel transition (gelation) of soft materials and glycomaterials. To address this issue, this paper applies a novel data augmentation method based on a generative adversarial network (GAN) proposed by the authors in their prior work. To demonstrate the effectiveness of the proposed method, the actual imbalanced spectral data from Pluronic F-127 hydrogel and Alpha-Cyclodextrin hydrogel are used to classify the phases of data. Specifically, our approach improves 8.8%, 6.4%, and 6.2% of the performance of the existing data augmentation methods regarding the classifier's F-score, Precision, and Recall on average, respectively. Specifically, our method consists of three DNNs: the generator, discriminator, and classifier. The method generates samples that are not only authentic but emphasize the differentiation between material characteristics to provide balanced training data, improving the classification results. Based on these validated results, we expect the method's broader applications in addressing imbalanced measurement data across diverse domains in materials science and chemical engineering. [ABSTRACT FROM AUTHOR]

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843. [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) are widely utilized in neural network research to capture spatiotemporal features in video data. However, their effectiveness heavily relies on the spatial features upon which they trained. This paper introduces innovative ensembles of features for constructing frame-wise structures by employing impactful neural network models with innovative training pipelines. These features are designed to enhance the recognition of hand gesture videos using RNN by leveraging temporal information. Recognizing hand gestures from videos is a complex task that presents considerable challenges. One notable challenge is the overlap in gesture motion, where different gesture categories exhibit similar hand poses within a single video clip. To overcome this issue, we were motivated to develop extensive and diverse features that offer a more comprehensive description of the gesture video clips, thereby mitigating recognition problems caused by images overlapping. Overall, our efforts to generate diverse features have yielded promising results in enhancing the recognition of hand gestures from videos, particularly in scenarios where overlap poses a significant challenge. We have combined the extracted features from a deep neural network trained from scratch with features obtained from various standard neural networks (Self-Organizing Map, Radial Base Function) that are trained to enhance the deep-trained features. The mutual arrangement for combining the shared features has configured new frame-wise image features. Furthermore, we have provided a performance comparison of the newly constructed frame-wise features through time-sharing to train RNN for recognition. The proposed models have been evaluated on two-hand gesture video datasets, where a preserving gesture sequence is crucial due to overlapping motions. Our work demonstrates a significant improvement in performance for both datasets. [ABSTRACT FROM AUTHOR]

Rock strength parameters such as uniaxial compressive strength and modulus of elasticity are crucial parameters in designing rock engineering structures. Owing to the importance of the aforementioned parameters, in this paper, image processing technique is coupled with artificial neural network (ANN) method for assessing the uniaxial compressive strength and modulus of elasticity of sandstones. For this reason, 102 core sandstone samples were prepared. Subsequently petrographic analyses and imaging operation for 102 images were performed. Principal component analysis was then conducted for feature reduction purposes. At last, an ANN model, which received its input data from image processing technique, was constructed for assessing the UCS and E of sandstone samples. Overall, the best performance of the network was obtained when 10 hidden nodes were used. The correlation coefficient (R) values of 0.9722 and 0.97062 for UCS and E, respectively, suggest the feasibility of the proposed model. [ABSTRACT FROM AUTHOR]

Safe and efficient navigation is critical for a mobile robot in a highly constrained workspace. Autonomous navigation is to be performed safely and robustly in the environment map with obstacles of various geometric shapes, sizes and colors positioned at random locations. In this paper, we present an approach to perform autonomous navigation by detecting the obstacles in the map and by generating auxiliary collision-free waypoints in obstacle-free space map. In achieving this, the object detection is done using SSDMobileNetV2 model and auxiliary collision-free navigation waypoints are generated using the Deepway neural network model. Further, the RRT path planner is applied to analyze the waypoints generated and to find the a global path between start and goal locations. An optimal local path is achieved using the A* path planner. Extensive simulations of various scenarios are performed and the proposed model is evaluated. The results reveal that the proposed model achieves significant improvements in terms of time, distance and F1-score. [ABSTRACT FROM AUTHOR]

In recent years, Model Predictive Torque Control (MPTC) has gained popularity as a powerful method of controlling Induction Motors (IMs). There are, however, some factors such as the weighted coefficient that must be taken into account to attain satisfactory performance at different operation points for stator flux. As of now, an empirical procedure has been used for tuning the weighting factor in MPTC, which is not as effective. Model Predictive Flux Control (MPFC) is proposed in this paper, which eliminates complicated process of predicting the stator current by using the flux vectors as control variables. In order to get over these obstacles, a novel Model Predictive Control (MPC) method utilizing a Cascaded Artificial Neural Network (ANN) is proposed in this research. As a result, the control complexity is diminished and weighting factor in standard MPTC is eliminated. In-depth evaluations and comparisons of MPTC and MPFC are conducted, covering low-speed function, dynamic response, and steady-state performance. In contract to traditional approaches, the preferred method has much lower computational cost, virtuous dynamic response, and superior steady-state performance. The overall proposed work is simulated using MATLAB/SIMULINK platform and experimental tests performed on 3Φ VSI fed IM drives are used to verify the efficacy of proposed approach. [ABSTRACT FROM AUTHOR]

This paper presents improved single- and multi-objective algorithms based on the original moth flame optimizer (MFO) to tackle the dynamic economic emission dispatch (DEED) problem that affects power systems operations. The DEED problem is a multi-objective optimization problem that is strongly constrained, multi-dimensional, nonlinear, and non-convex. It comprises several optimization criteria, many of which are in direct opposition to one another; therefore, no one solution is optimal with regard to all of those criteria. Firstly, an enhanced flame generation strategy is incorporated into the MFO algorithm to improve performance. Then, the improved MFO is combined with the crowding distance mechanism and non-dominated sorting framework to enhance the convergence rate and the quality of the results. This helps improve the convergence pace. Firstly, the proposed multi-objective moth flame optimizer (MOMFO) algorithm is validated using 15 ZDT and UF benchmark multi-objective test functions. Then, the nonlinear DEED problem is also solved by determining the feasible optimal solution using the MOMFO algorithm. The implementation of the MOMFO on 10-unit systems and the IEEE 30-bus test system is being done to display the ability to solve a nonlinear, non-convex, and constrained DEED optimization problem. The DEED problem is solved using the MOMFO algorithm and other state-of-the-art algorithms, such as the non-dominated sorting genetic algorithm-II (NSGA-II), the multi-objective teaching–learning-based optimization (MOTLBO) algorithm, and multi-objective reptile search algorithm (MORSA). The selection of the control parameters of the MOMFO can be decided from the algorithm's findings on different IEEE bus systems. This study also introduces a new technique for incorporating loss predictions using artificial neural networks into the DEED model. During each phase of the dispatch time, the trained neural network can make only a single forecast of the transmission loss. The performance of MOMFO is compared with NSGA-II, MOTLBO, and MORSA, and the results obtained for both benchmarks and DEED proved the superiority of the proposed algorithm in solving the DEED of the power systems. [ABSTRACT FROM AUTHOR]

This research paper aims to ensure the reliable and efficient operation of grid-connected solid-state transformers (SSTs) by detecting and evaluating various undesirable operating conditions. The study considers different types of faults, including internal faults like open switches and open capacitors, external faults such as symmetrical and asymmetrical faults occurring at various locations of the SST, and abnormalities on the grid side known as sympathetic inrush conditions. To analyze these operating conditions, the secondary current of the high-frequency transformer is normalized and decomposed using the discrete wavelet transform (DWT) and wavelet packet transform (WPT). From the DWT and WPT decomposition at multiple levels, several statistical parameters are calculated. These statistical parameters are carefully selected from different decomposition levels to enhance the effectiveness of the detection algorithm utilizing DWT and WPT. In order to quickly identify and classify all operating conditions that impact the performance of the grid-connected SST, a three-layer feedforward artificial neural network (ANN) is employed, using the selected statistical features. The accuracy and efficiency of the ANN-based classification approach are evaluated by assessing the effectiveness of the statistical features obtained from DWT and WPT. Simulation results have been altered by introducing various noise levels to systematically assess the performance of the proposed algorithms. The average accuracy of the DWT-ANN algorithm stands at 97.89%, while the WPT-ANN algorithm achieves a slightly elevated accuracy level of 98.01%. This notable similarity in accuracy curtails from the careful selection of the wavelet function, decomposition level, and feature sets. [ABSTRACT FROM AUTHOR]

There has been extensive evidence demonstrating that deep neural networks are vulnerable to adversarial examples, which motivates the development of defenses against adversarial attacks. Existing adversarial defenses typically improve model robustness against individual specific perturbation types (e.g., ℓ ∞ -norm bounded adversarial examples). However, adversaries are likely to generate multiple types of perturbations in practice (e.g., ℓ 1 , ℓ 2 , and ℓ ∞ perturbations). Some recent methods improve model robustness against adversarial attacks in multiple ℓ p balls, but their performance against each perturbation type is still far from satisfactory. In this paper, we observe that different ℓ p bounded adversarial perturbations induce different statistical properties that can be separated and characterized by the statistics of Batch Normalization (BN). We thus propose Gated Batch Normalization (GBN) to adversarially train a perturbation-invariant predictor for defending multiple ℓ p bounded adversarial perturbations. GBN consists of a multi-branch BN layer and a gated sub-network. Each BN branch in GBN is in charge of one perturbation type to ensure that the normalized output is aligned towards learning perturbation-invariant representation. Meanwhile, the gated sub-network is designed to separate inputs added with different perturbation types. We perform an extensive evaluation of our approach on commonly-used dataset including MNIST, CIFAR-10, and Tiny-ImageNet, and demonstrate that GBN outperforms previous defense proposals against multiple perturbation types (i.e., ℓ 1 , ℓ 2 , and ℓ ∞ perturbations) by large margins. [ABSTRACT FROM AUTHOR]

This paper presents an analysis and prediction of the shear strength of wide-shallow reinforced concrete beams, utilizing Finite Element Analysis (FEA) and machine learning techniques. The methodology involves validating a detailed Finite Element Model (FEM) against experimental results, conducting a parametric study, and developing three Machine Learning prediction equations. The FEM captures concrete and steel behaviors, including cracking and crushing for concrete and linear isotropic properties for steel reinforcement. Loading and boundary conditions are defined for accuracy and validated against 13 experimental specimens, exhibiting a maximum 8% and 12% difference in loads and deflections, respectively. A parametric study generates a dataset of 77 wide beam configurations, exploring variations in beam widths, concrete strengths, compression rebars, and shear reinforcement. This dataset is used to develop machine learning models, including "Genetic Programming (GP)", "Evolutionary Polynomial Regression (EPR)", and "Artificial Neural Network (ANN)". Comparative analysis reveals GP and EPR models with over 95% correlation, while the ANN model outperforms with 99% accuracy. Sensitivity analysis underscores the significant influence of concrete strength and beam aspect ratio on shear strength. In conclusion, the study demonstrates the potential of FEA and machine learning models to predict shear strength in wide-shallow reinforced concrete beams, providing valuable insights for architectural design and engineering practices and emphasizing the role of concrete strength and beam geometry in shear behavior. [ABSTRACT FROM AUTHOR]

The health management of railway signal equipment in the high-speed railway is a key link between intelligent operation and maintenance. Accurately predicting the health state of compensation capacitors is of great significance to ensure the reliable work of track circuits. This paper proposes an improved deep neural network algorithm focusing on the problem of long-term accurate health forecasts for compensation capacitors. First, establishing a transmission state model for degradation mechanism mining, the difference function that can quantitatively evaluate features is defined by piecewise processing cab signaling receiving voltage. Introducing the degradation model, predictive driving under both model and data is implemented. Then, the convolutional neural networks and bidirectional long–short-term memory are combined and improved to construct a novel artificial intelligence combination strategy, while parameters are optimized based on the sparrow search algorithm. Finally, facing the conditional repair of compensation capacitors, we set a reasonable threshold for the occurrence of hidden dangers to complete fault warning. This novel and practical approach effectively explores the procedure of prognosis and health management, while the refined maintenance will better utilize current monitoring information, helping the intelligence and accuracy of safety control decision-making. [ABSTRACT FROM AUTHOR]

The application of deep neural network has achieved remarkable success in object detection. However, the network structures should be still evolved consistently and tuned finely to acquire better performance. This gears to the continuous demands on high performance in those complex scenes, where multi-scale objects to be detected are located here and there. To this end, this paper proposes a network structure called Multi-Scale Coupled Attention (MSCA) under the framework of self-attention learning with methodologies of importance assessment. Architecturally, it consists of a Multi-Scale Coupled Channel Attention (MSCCA) module, and a Multi-Scale Coupled Spatial Attention (MSCSA) module. Specifically, the MSCCA module is developed to achieve the goal of self-attention learning linearly on the multi-scale channels. In parallel, the MSCSA module is constructed to achieve this goal nonlinearly on the multi-scale spatial grids. The MSCCA and MSSCA modules can be connected together into a sequence, which can be used as a plugin to develop end-to-end learning models for object detection. Finally, our proposed network is compared on two public datasets with 13 classical or state-of-the-art models, including the Faster R-CNN, Cascade R-CNN, RetinaNet, SSD, PP-YOLO, YOLO v3, YOLO v5, YOLO v7, YOLOX, DETR, conditional DETR, UP-DETR and FP-DETR. Comparative experimental results with numerical scores, the ablation study, and the performance behaviour all demonstrate the effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

Artificial Neural Networks (ANNs) have been used in a multitude of real-world applications given their predictive capabilities, and algorithms based on gradient descent, such as Backpropagation (BP) and variants, are usually considered for their optimisation. However, these algorithms have been shown to get stuck at local optima, and they require a cautious design of the architecture of the model. This paper proposes a novel memetic training method for simultaneously learning the ANNs structure and weights based on the Coral Reef Optimisation algorithms (CROs), a global-search metaheuristic based on corals' biology and coral reef formation. Three versions based on the original CRO combined with a Local Search procedure are developed: (1) the basic one, called Memetic CRO; (2) a statistically guided version called Memetic SCRO (M-SCRO) that adjusts the algorithm parameters based on the population fitness; (3) and, finally, an improved Dynamic Statistically-driven version called Memetic Dynamic SCRO (M-DSCRO). M-DSCRO is designed with the idea of improving the M-SCRO version in the evolutionary process, evaluating whether the fitness distribution of the population of ANNs is normal to automatically decide the statistic to be used for assigning the algorithm parameters. Furthermore, all algorithms are adapted to the design of ANNs by means of the most suitable operators. The performance of the different algorithms is evaluated with 40 classification datasets, showing that the proposed M-DSCRO algorithm outperforms the other two versions on most of the datasets. In the final analysis, M-DSCRO is compared against four state-of-the-art methods, demonstrating its superior efficacy in terms of overall accuracy and minority class performance. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative electrocardiogram (ECG ) denoising technique based on stationary wavelet transform ( S W T) and wavelet/total variation (WATV). In this technique, we also use two different artificial neural networks ( ANNs ) to determine two ideal thresholds, t h r 1 and t h r 2 . The latter is used for the soft thresholding of a noisy details coefficient, c d b 2 , to obtain a denoised coefficient, c d d 2 . The threshold t h r 1 is used for the soft thresholding of a noisy details coefficient, c d b 1 , yielding a denoised coefficient, c d d 1. The coefficient c d b 1 and a noisy approximation coefficient, c a b 1 , are obtained by applying SWT to the noisy ECG signal. The coefficient c d b 2 and another noisy approximation coefficient, c a b 2 , are obtained by applying SWT to c a b 1 . In this proposed ECG denoising system, we also apply a WATV-based denoising technique to c a b 2 to obtain a denoised approximation coefficient, c a d 2 . This WATV-based denoising technique requires the estimation of the level of the noise corrupting the clean ECG signal. This noise is additive Gaussian white noise (AGWN) and its level is denoted as σ , which is estimated from c d b 1 . After that, the inverse of SWT ( S W T - 1 ) is applied to c d d 2 and c a d 2 to obtain a denoised approximation coefficient, c a d 1 . Subsequently, we apply S W T - 1 to c d d 1 and c a d 1 to finally obtain the denoised ECG signal. The performance of this proposed ECG denoising technique is proven by the results obtained after computing the signal-to-noise ratio ( SNR ), the peak SNR ( PSNR ), the mean square error ( MSE ), the mean absolute error ( MAE ) and the cross-correlation ( CC ). [ABSTRACT FROM AUTHOR]