Search

ABSTRACT In this article, a neuroadaptive sliding mode control (NSMC) strategy based on recurrent neural network (RNN) for robustly and adaptively tracking the desired position and attitude of an uncertain tilting quadrotor unmanned aerial vehicle (TQUAV) with unknown controllers is presented. The main contribution of this article is the real‐time adjustment of unknown flight controllers using the approximation characteristics of RNN, in which the derived approximation errors of RNN are sufficiently estimated by adaptive control method that can reduce or eliminate the impact of error terms on the evolution of closed‐loop systems. Especially, Lyapunov stability analysis is greatly simplified compared to existing methods and does not require amplification or reduction. Finally, the superior performance of the NSMC strategy was verified by comparing simulation results. [ABSTRACT FROM AUTHOR]

ABSTRACT To fulfil the commitments of the Paris Agreement, China will strive to achieve carbon peak (CP) by 2030. It is necessary to identify the evolution characteristics of China's carbon emissions and provide a scientific path prediction for the formulation of reasonable emission reduction policies and measures. This study summarises and predicts the pathway of China's carbon peak (CP) using carbon emission intensity (CEI) and the percentage of non‐fossil energy consumption (NEC) as indicators, and combining MSIH(3)‐AR(2) model and recurrent neural network. The results show that: (1) China's CEI experiences a ‘low decline regime’ (LDR), a ‘medium decline regime’ (MDR) and a ‘high decline regime’ (HDR), while the share of NEC goes through a ‘low fluctuation regime’ (LFR), a ‘medium growth regime’ (MGR) and a ‘high growth regime’ (HGR). (2) For CEI, the switching probability from MDR to the HDR is 74.88%, illustrating a substantial improvement. For NEC, the switching probability from MGR to HGR is 28.92%, but the probability of returning to MGR is 61.76%, indicating an adjustment. (3) By 2030, CEI will reach 0.9896 tons/100 million CNY, decreased by 66.35% compared with 2005. While the percentage of NEC will rise to 26.61%. Based on these, policy suggestions such as strengthening the top‐level design, upgrading energy mix and accelerating green technological changes are proposed to break the bottlenecks of reaching CP and further zero carbon goal. This study is expected to provide theoretical support and empirical evidence for the achievement CP in China, and to provide empirical references for promoting the ‘dual carbon’ process in other countries. [ABSTRACT FROM AUTHOR]

Lithology classification is a fundamental aspect of reservoir classification. Due to the limited availability of core samples, computational modelling methods for lithology classification based on indirect measurements are required. The main challenge for standard clustering methods is the complex vertical dependency of sedimentological sequences as well as the spatial coupling of well logs. Machine learning methods, such as recurrent neural networks, long short‐term memory and bidirectional long short‐term memory, can account for the spatial correlation of the measured data and the predicted model. Based on these developments, we propose a novel approach using two distinct models: a self‐attention‐assisted bidirectional long short‐term memory model and a multi‐head attention‐based bidirectional long short‐term memory model. These models consider spatial continuity and adaptively adjust the weight in each step to improve the classification using the attention mechanism. The proposed method is tested on a set of real well logs with limited training data obtained from core samples. The prediction results from the proposed models and the benchmark one are compared in terms of the accuracy of lithology classification. Additionally, the weight matrices from both attention mechanisms are visualized to elucidate the correlations between depth steps and to help analyse how these mechanisms contribute to improved prediction accuracy. The study shows that the proposed multi‐head attention‐based bidirectional long short‐term memory model improves classification, especially for thin layers. [ABSTRACT FROM AUTHOR]

This paper explores the application of machine learning techniques, specifically deep learning, to the inverse problem of marine controlled‐source electromagnetic data. A novel approach is proposed that combines the convolutional neural network and recurrent neural network architectures to reconstruct layered electrical resistivity variation beneath the seafloor from marine controlled‐source electromagnetic data. The approach leverages the strengths of both convolutional neural network and recurrent neural network, where convolutional neural network is used for recognizing and classifying features in the data, and recurrent neural network is used to capture the contextual information in the sequential data. We have built a large synthetic dataset based on one‐dimensional forward modelling of a large number of resistivity models with different levels of electromagnetic structural complexity. The combined learning of convolutional neural network and recurrent neural network is used to construct the mapping relationship between the marine controlled‐source electromagnetic data and the resistivity model. The trained network is then used to predict the distribution of resistivity in the model by feeding it with marine controlled‐source electromagnetic responses. The accuracy of the proposed approach is examined using several synthetic scenarios and applied to a field dataset. We explore the sensitivity of deep learning inversion to different electromagnetic responses produced by resistive targets distributed at different depths and with varying levels of noise. Results from both numerical simulations and field data processing consistently demonstrate that deep learning inversions reliably reconstruct the subsurface resistivity structures. Moreover, the proposed method significantly improves the efficiency of electromagnetic inversion and offers significant performance advantages over traditional electromagnetic inversion methods. [ABSTRACT FROM AUTHOR]

Sentiment analysis, a method used to classify textual content into positive, negative, or neutral sentiments, is commonly applied to data from social media platforms. Arabic, an official language of the United Nations, presents unique challenges for sentiment analysis due to its complex morphology and dialectal diversity. Compared to English, research on Arabic sentiment analysis is relatively scarce. Transfer learning, which applies the knowledge learned from one domain to another, can address the limitations of training time and computational resources. However, the development of transfer learning for Arabic sentiment analysis is still underdeveloped. In this study, we develop a new hybrid model, RNN‐BiLSTM, which merges recurrent neural networks (RNN) and bidirectional long short‐term memory (BiLSTM) networks. We used Arabic bidirectional encoder representations from transformers (AraBERT), a state‐of‐the‐art Arabic language pre‐trained transformer‐based model, to generate word‐embedding vectors. The RNN‐BiLSTM model integrates the strengths of RNN and BiLSTM, including the ability to learn sequential dependencies and bidirectional context. We trained the RNN‐BiLSTM model on the source domain, specifically the Arabic reviews dataset (ARD). The RNN‐BiLSTM model outperforms the RNN and BiLSTM models with default parameters, achieving an accuracy of 95.75%. We further applied transfer learning to the RNN‐BiLSTM model by fine‐tuning its parameters using random search. We compared the performance of the fine‐tuned RNN‐BiLSTM model with the RNN and BiLSTM models on two target domain datasets: ASTD and Aracust. The results showed that the fine‐tuned RNN‐BiLSTM model is more effective for transfer learning, achieving an accuracy of 95.44% and 96.19% on the ASTD and Aracust datasets, respectively. [ABSTRACT FROM AUTHOR]

Precise and timely collision detection and warning are essential to ensure the safety of autonomous driving. However, existing collision detection systems based on image sensors and radars are prone to misjudgment in adverse environments such as darkness or rain. The lobula giant movement detector (LGMD) neuron found in locusts achieves potential collision detection in unpredictable environments without the need for object recognition algorithms. Existing artificial collision detectors inspired by LGMD suffer from complex device structures and sophisticated operating modes. Here, an LGMD‐inspired all‐optically triggered in‐sensor collision detector is presented by 2D complementary material devices (2D‐CMDs) composed of n‐type molybdenum disulfide (MoS2) and p‐type platinum diselenide (PtSe2) connected in series. The proposed 2D‐CMDs couple the positive photoconductivity of MoS2 and negative photoconductivity of PtSe2 in response to looming light, successfully mimicking the antagonism of excitatory and inhibitory responses in LGMD neurons to generate a nonmonotonic escape response. The 2D‐CMDs exhibit a simple device structure and all‐optically controlled operation mode, consuming only 1 nJ of energy for each collision detection. Furthermore, in‐sensor real‐time collision warning is realized by employing a Recurrent Neural Network (RNN) to predict alarm time based on the escape response of the proposed 2D‐CMDs. [ABSTRACT FROM AUTHOR]

Summary The noise that affects underwater acoustic communication (UWAC) is primarily characterised by its non‐stationary nature and is predominantly non‐Gaussian in distribution. The Minimum Mean Square Error (MMSE) criterion‐based receiver/equaliser is suboptimal for Underwater Acoustic Communication (UWAC). An underwater acoustic communication (UWAC) system that is resilient should have the capability to effectively manage a wide range of underwater noise patterns and complex multipath, non‐stationary channels with a high level of reliability. To address these challenges, we suggest the deployment of a robust receiver that autonomously handles the communication channel. This receiver would consist of two stages: the first stage would involve a prefilter based on the time‐reversal mirror (TRM), while the second stage would utilise a Recurrent Neural Network (RNN). Analysis of the proposed receiver in different scenarios unequivocally demonstrates its superiority over the conventional Decision Feedback Equalise (DFE) and Deep Neural Network (DNN) based receiver. [ABSTRACT FROM AUTHOR]

Introduction Material and Methods Results Conclusion Machine learning models have shown promising potential in individual‐level outcome prediction for patients with psychosis, but also have several limitations. To address some of these limitations, we present a model that predicts multiple outcomes, based on longitudinal patient data, while integrating prediction uncertainty to facilitate more reliable clinical decision‐making.We devised a recurrent neural network architecture incorporating long short‐term memory (LSTM) units to facilitate outcome prediction by leveraging multimodal baseline variables and clinical data collected at multiple time points. To account for model uncertainty, we employed a novel fuzzy logic approach to integrate the level of uncertainty into individual predictions. We predicted antipsychotic treatment outcomes in 446 first‐episode psychosis patients in the OPTiMiSE study, for six different clinical scenarios. The treatment outcome measures assessed at both week 4 and week 10 encompassed symptomatic remission, clinical global remission, and functional remission.Using only baseline predictors to predict different outcomes at week 4, leave‐one‐site‐out validation AUC ranged from 0.62 to 0.66; performance improved when clinical data from week 1 was added (AUC = 0.66–0.71). For outcome at week 10, using only baseline variables, the models achieved AUC = 0.56–0.64; using data from more time points (weeks 1, 4, and 6) improved the performance to AUC = 0.72–0.74. After incorporating prediction uncertainties and stratifying the model decisions based on model confidence, we could achieve accuracies above 0.8 for ~50% of patients in five out of the six clinical scenarios.We constructed prediction models utilizing a recurrent neural network architecture tailored to clinical scenarios derived from a time series dataset. One crucial aspect we incorporated was the consideration of uncertainty in individual predictions, which enhances the reliability of decision‐making based on the model's output. We provided evidence showcasing the significance of leveraging time series data for achieving more accurate treatment outcome prediction in the field of psychiatry. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial‐and‐error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ‐at‐risk (OAR) dose–volume histograms (DVHs) of left‐sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient‐specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning.This study aimed to develop a deep learning‐based framework for the prediction of organ‐specific dose–volume histograms (DVH) based on structures delineated for left‐sided breast cancer treatment.We used a dataset of 249 left‐sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice‐by‐slice DVHs for planning target volume (PTV) and organs‐at‐risk. The patients were divided into training (70%, n = 174), validation (10%, n = 24), and test (20%, n = 51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network.In the independent test set (n = 51), the point‐wise differences in the slice‐by‐slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10−4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference ± standard deviation of mean doses between the clinical and the predicted DVH were 0.08 ± 0.04 Gy, 0.24 ± 0.22 Gy, 0.73 ± 0.46 Gy, 0.07 ± 0.06 Gy, and 0.14 ± 0.14 Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively.The deep learning‐based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient‐specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning. [ABSTRACT FROM AUTHOR]

Summary Nowadays, wireless sensor networks (WSNs) have paid huge attention among researchers due to their wide applications. WSNs possess multiple sensor nodes that transmit data to each other by using constrained energy resources. The sensor nodes are highly affected by collision due to the transmission of packets over the network by one or two nodes at the same time. Collision detection is necessary to increase network security and enhance the lifetime of sensor nodes. In most of the previous research, efficiently implementing collision detection algorithms while minimizing resource usage remains a significant challenge. Thus, a hybrid deep learning model deep Kronecker recurrent neural network (DKRNN) is developed in this research. Here, the cluster head is selected using the chronological skill optimization algorithm (CSOA) algorithmic approach by considering multi‐objective parameters like energy, distance, delay, and trust. The network‐based parameters are then extracted from the network. Later, the collision is detected using the DKRNN approach and the collision is mitigated finally using a packet pre‐scheduling model named Dolphin Ant Lion Optimization (Dolphin ALO). Moreover, the detection performance of CSOA+ DKRNN is validated, and it achieved superior performance with a collision detection rate (CDR) of 0.940, packet delivery ratio (PDR) of 0.660, throughput of 0.850Mbps, and energy consumption of 0.110 J. [ABSTRACT FROM AUTHOR]

Summary: Employing mobile nodes or Sensor Nodes (SN) in the Wireless Sensor Networks (WSNs) is a critical task within the coverage area. However, these techniques produce huge errors in the evaluated distance between source nodes and unknown nodes, which increases the average NL error of the unknown node. The usage of a Global Positioning System (GPS) for all the SNs needs high cost for implementation in large‐scale WSNs. The designing of NL in WSN with less energy requirements and less cost is very significant. Enhanced NL is performed with deep learning techniques together with the heuristic strategy for performance enhancement. The developed localization model is mainly utilized for providing fast, scalable, and easily implementable results over heterogeneous and homogeneous networks. Moreover, it is applicable for sparse and dense deployment of nodes. Here, a hybridized deep structured approach is employed by integrating the Recurrent Neural Network (RNN) with a Gated Recurrent Unit (GRU) for calculating the distance among the source nodes to facilitate determining the optimal location for the unidentified node by analyzing the node information present in the received packets. Here, the optimization of constraints executed in the deep learning techniques with the Modified Exploration‐based Sandpiper Optimization Algorithm (ME‐SOA), and also it is utilized to find the optimal location of unknown nodes based on computed distance from the received packets that minimize the average localization error. The experimental results are validated and show the effectiveness of the proposed algorithm with a reduced error rate than other algorithms. [ABSTRACT FROM AUTHOR]

Summary Wireless sensor networks (WSNs) contain different sensors, which collect various data in the monitoring area. In general, one of the significant resources in WSNs is energy, which prolongs the network's lifetime. The energy‐efficient routing algorithms reduce energy consumption and enhance the survival cycle of WSNs. Thus, this work developed the optimization‐based WSN routing and deep learning (DL)–enabled energy prediction scheme for efficient routing in WSNs. Initially, the WSN simulation is carried out, and then, the node with minimum energy consumption is chosen as the cluster head (CH). Here, the proposed rat hawk optimization (RHO) algorithm is established for finding the best CH, and the RHO is the integration of rat swarm optimization (RSO) and fire hawk optimization (FHO). Furthermore, the routing is accomplished by the developed fractional rat hawk optimization (FRHO) using the fitness function includes delay, distance, link lifetime, and predicted energy of a network for predicting the finest route. Here, the fractional calculus (FC) is incorporated with the RHO to form the FRHO. The energy prediction is achieved by deep recurrent neural network (DRNN). The energy, delay, and throughput evaluation metrics are considered for revealing the efficiency of the proposed system, and the proposed system achieves the best results of 0.246 J, 0.190 s, and 67.13 Mbps, respectively. [ABSTRACT FROM AUTHOR]

Summary The Internet of Things (IoT) acts as a prevalent networking setup that plays a vital role in everyday activities due to the increased services provided through uniform data collection. In this research paper, a hybrid optimization approach for the construction of heterogeneous multi‐hop IoT wireless sensor network (WSN) network topology and data aggregation and reduction is performed using a deep learning model. Initially, the IoT network is stimulated and the network topology is constructed using Namib Beetle Spotted Hyena Optimization (NBSHO) by considering different network parameters and encoding solutions. Moreover, the data aggregation and reduction in the IoT network are performed using a Deep Recurrent Neural Network (DRNN)‐based prediction model. In addition, the performance improvement of the designed NBSHO + DRNN approach is validated. Here, the designed NBSHO + DRNN method achieved a packet delivery ratio (PDR) of 0.469, energy of 0.367 J, prediction error of 0.237, and delay of 0.595 s. [ABSTRACT FROM AUTHOR]

A long‐held tenet in computer science asserts that the training of deep learning is analogous to an alchemical furnace, and its "black box" signature brings forth inexplicability. For electromagnetic metasurfaces, the related intelligent applications also get stuck into such a dilemma. Although the past 5 years have witnessed a proliferation of deep learning‐based works across complex photonic scenarios, they neglect the already existing but untapped physical laws. Here, the intrinsic correlation between the real and imaginary parts of the spectra are revealed using Kramers–Kronig relations, which is then mimicked by bidirectional information flow in neural network space. Such consideration harnesses the missing spectral connection to extract crucial features effectively. The bidirectional recurrent neural network is benchmarked in metasurface inverse design and compare it with a fully‐connected neural network, unidirectional recurrent neural network, and attention‐based transformer. Beyond the improved accuracy, the study examines the intermediate information products and physically explains why different network structures yield different performances. The work offers explicable perspectives to utilize physical information in the deep learning field and facilitates many data‐intensive research endeavors. [ABSTRACT FROM AUTHOR]

Mechanical computing provides an information processing method to realize sensing‐analyzing‐actuation integrated mechanical intelligence and, when combined with neural networks, can be more efficient for data‐rich cognitive tasks. The requirement of solving implicit and usually nonlinear equilibrium equations of motion in training mechanical neural networks makes computation challenging and costly. Here, an explicit mechanical neuron is developed of which the response can be directly determined without the need of solving equilibrium equations. A training method is proposed to ensure the robustness of the neuron, i.e., insensitivity to defects and perturbations. The explicitness and robustness of the neurons facilitate the assembly of various network structures. Two exemplified networks, a robust mechanical convolutional neural network and a mechanical recurrent neural network with long short‐term memory capabilities for associative learning, are experimentally demonstrated. The introduction of the explicit and robust mechanical neuron streamlines the design of mechanical neural networks fulfilling robotic matter with a level of intelligence. [ABSTRACT FROM AUTHOR]

We proposed an online identification and adaptive control framework for the nonlinear dynamical systems using a novel hybrid‐feed‐forward recurrent neural network (HFRNN) model. The HFRNN is a combination of a feed‐forward neural network (FFNN) and a local recurrent neural network (LRNN). We aim to leverage the simplicity of FFNN and the effectiveness of RNN to capture changing dynamics accurately and design an indirect adaptive control scheme. To derive the weights update equations, we have applied the gradient‐descent‐based Back‐Propagation (BP) technique, and the stability of the proposed learning strategy is proven using the Lyapunov stability principles. We also compared the proposed method's results with those of the Jordan network‐based controller (JNC) and the local recurrent network‐based controller (LRNC) in the simulation examples. The results demonstrate that our approach performs satisfactorily, even in the presence of disturbance signals. [ABSTRACT FROM AUTHOR]

This study aimed to investigate the failure mechanism of Ti60 titanium alloy in the high cycle fatigue (HCF) and very high cycle fatigue (VHCF) at 500°C. Ti60 specimens were characterized before and after the 500°C VHCF test, and the fracture surfaces were observed. The results show that there are three different fatigue failure mechanisms at 500°C: (i) equiaxed primary α phase (αp) cleavage, forming small unsmooth facets and rough fracture area (RA), and fusion of non‐adjacent facets to grow into the main crack. (ii) αp grains gather into large grain with triple junction, and large grain slip to form large fusion facet. (iii) Oxide shedding and then cracks form. A dynamic recurrent neural network model is used to predict the fatigue life of Ti60 alloy, 91% of the overall predictions were within the scatter band of 3.0, and 100% were within the scatter band of 5.0. Highlights: Characterization yields three fatigue fracture mechanisms of Ti60 alloy at 500°C.Haigh diagrams evaluate the empirical formulas and constant life curves.Characterization reveals multiple triple junctions within the large αp grains after fatigue test.A dynamic recurrent neural network model predicts the fatigue life. [ABSTRACT FROM AUTHOR]

Current machine learning methods for discharge prediction often employ aggregated basin‐wide hydrometeorological data (lumped modeling) for parametric and non‐parametric training. This approach may overlook the spatial heterogeneity of river systems and their impact on discharge patterns. We hypothesize that integrating spatiotemporal hydrologic knowledge into the data modeling process (distributed/disaggregated modeling) can improve the performance of discharge prediction models. To test this hypothesis, we designed experiments comparing the performance of identical Long Short‐Term Memory Recurrent Neural Network (LSTM‐RNN) models forced with either lumped or distributed features. We gather meteorological forcing and static attributes for the Mackenzie basin in Canada‐ a large and unique basin. Importantly, discharge performance is assessed out‐of‐sample with k‐fold replication across gauges. Training LSTMs with disaggregated data significantly improved model accuracy. Specifically, there was a 9.6% increase in the mean Nash‐Sutcliffe Efficiency and a 4.6% increase in the mean Kling‐Gupta Efficiency, indicating a better agreement between predicted and actual observations in terms of mean, variability, and correlation. These experiments and results demonstrate the importance of integrating topologically guided geomorphologic and hydrologic information (distributed modeling) in data‐driven discharge predictions. Plain Language Summary: Accurate river discharge prediction is critical for sustainable water resource management and effective flood mitigation. Traditional methods often treat the entire river basin as a homogenous unit, neglecting crucial hydrologic and hydrometeorological variations that significantly impact water flow across different locations. This "lumped" approach can lead to inaccurate predictions. We propose a "distributed" modeling approach incorporating detailed information about the river basin's spatial heterogeneity. Applying this method to the Mackenzie River, a vast and complex river system in Canada, resulted in significantly more accurate discharge predictions compared to traditional lumped models. This confirms the critical importance of considering the river basin's spatial variability for better understanding and predicting water flow dynamics. Our work paves the way for enhanced water management strategies and improved flood preparedness by providing more precise and reliable discharge predictions. Key Points: Current Machine Learning models rely on aggregated hydrometeorological data, ignoring the spatial heterogeneity inherent in river systemsIncorporating topological‐guided spatiotemporal hydrologic data can improve understanding of discharge dynamics within the river basinTopologically guided river hierarchies help aggregate hydrological data at various scales, enhancing the accuracy of discharge predictions [ABSTRACT FROM AUTHOR]

Background and Aims: Alzheimer's disease (AD) is a degenerative neurological condition that worsens over time and leads to deterioration in cognitive abilities, reduced memory, and, eventually, a decrease in overall functioning. Timely and correct identification of Alzheimer's is essential for effective treatment. The systematic study specifically examines the application of deep learning (DL) algorithms in identifying AD using three‐dimensional (3D) imaging methods. The main goal is to evaluate these methods' current state, efficiency, and potential enhancements, offering valuable insights into how DL could improve AD's rapid and precise diagnosis. Methods: We searched different online repositories, such as IEEE Xplore, Elsevier, MDPI, PubMed Central, Science Direct, ACM, Springer, and others, to thoroughly summarize current research on DL methods to diagnose AD by analyzing 3D imaging data published between 2020 and 2024. We use PRISMA (Preferred Reporting Items for Systematic Reviews and Meta‐Analyses) guidelines to ensure the organization and understandability of the information collection process. We thoroughly analyzed the literature to determine the primary techniques used in these investigations and their findings. Results and Conclusion: The ability of convolutional neural networks (CNNs) and their variations, including 3D CNNs and recurrent neural networks, to detect both temporal and spatial characteristics in volumetric data has led to their widespread use. Methods such as transfer learning, combining multimodal data, and using attention procedures have improved models' precision and reliability. We selected 87 articles for evaluation. Out of these, 31 papers included various concepts, explanations, and elucidations of models and theories, while the other 56 papers primarily concentrated on issues related to practical implementation. This article introduces popular imaging types, 3D imaging for Alzheimer's detection, discusses the benefits and restrictions of the DL‐based approach to AD assessment, and gives a view toward future developments resulting from critical evaluation. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of generating clear image frames and minimizing the loss of keyframes by a robot engaging in rapid large viewing angle motion. These issues often lead to detrimental consequences such as trajectory drifting and loss during the construction of curved motion trajectories. To tackle this, we proposed a novel visual simultaneous localization and mapping (SLAM) algorithm, TKO‐SLAM, which is based on time‐delay feature regression and keyframe position optimization. TKO‐SLAM uses a multiscale recurrent neural network to rectify object deformation and image motion smear. This network effectively repairs the time‐delay image features caused by the rapid movement of the robot, thereby enhancing visual clarity. Simultaneously, inspired by the keyframe selection strategy of the ORB‐SLAM3 algorithm, we introduced a grayscale motion‐based image processing method to supplement keyframes that may be omitted due to the robot's rapid large viewing angle motion. To further refine the algorithm, the time‐delay feature regression image keyframes and adjacent secondary keyframes were used as dual measurement constraints to optimize camera poses and restore robot trajectories. The results of experiments on the benchmark RGB‐D data set TUM and real‐world scenarios show that TKO‐SLAM algorithm achieves more than 10% better localization accuracy than the PKS‐SLAM algorithm in the rapid large viewing angle motion scenario, and has advantages over the SOTA algorithms. [ABSTRACT FROM AUTHOR]

Summary: This paper presents a new method in the field of healthcare security that specifically targets cloud‐based wireless sensor networks (WSNs). The suggested method integrates a goal‐based artificial intelligent agent (GAIA) with an autoencoder (AE) architecture, yielding an autoencoder‐based agent (AE‐A). The main goal of this integrated system is to improve the efficiency of identifying botnet assaults, with a specific emphasis on the evolving security threats related to cloud computing. Our concept is around creating a meticulously calibrated, goal‐driven AI agent tailored explicitly for healthcare applications. The agent meticulously analyses network data and proficiently integrates autoencoder‐enhanced anomaly detection techniques to uncover intricate patterns indicative of botnet activities. The adaptability of the goal‐based AI agent is improved by ongoing real‐time learning, guaranteeing that its responses are in line with the primary goal of neutralizing threats. The autoencoder serves a vital role in the system by functioning as a tool for extracting features. This approach enables the AI Agent to navigate complex information and derive significant insights efficiently. Cloud computing resources greatly enhance the functionalities of a system, enabling scalability, real‐time analysis, and improved responsiveness. Utilizing goal‐driven AI and autoencoder together proves to be a successful strategy in safeguarding healthcare‐oriented WSNs against botnet attacks. This technique takes a proactive stance in ensuring the security of sensitive medical data. The suggested model is evaluated against various models, including the bidirectional long short‐term memory (BLSTM) method, the hybrid BLSTM with recurrent neural network (BLSTM‐RNN) algorithm, and the Random Forest algorithm. The models are evaluated using metrics such as Matthews correlation coefficient (MCC), prediction rate, accuracy, recall, precision, and F1 score analysis. The investigation demonstrates that the suggested model achieved the most significant values of 93% MCC, 94% prediction rate, 91% accuracy, 98% recall, 98% precision, and 98% F1 score, respectively when compared to the existing models. [ABSTRACT FROM AUTHOR]

Conversational assistants (CAs) and Task‐oriented ones, in particular, are designed to interact with users in a natural language manner, assisting them in completing specific tasks or providing relevant information. These systems employ advanced natural language understanding (NLU) and dialogue management techniques to comprehend user inputs, infer their intentions, and generate appropriate responses or actions. Over time, the CAs have gradually diversified to today touch various fields such as e‐commerce, healthcare, tourism, fashion, travel, and many other sectors. NLU is fundamental in the natural language processing (NLP) field. Identifying user intents from natural language utterances is a sub‐task of NLU that is crucial for conversational systems. The diversity in user utterances makes intent detection (ID) even a challenging problem. Recently, with the emergence of Deep Neural Networks. New State of the Art (SOA) results have been achieved for different NLP tasks. Recurrent neural networks (RNNs) and Transformer architectures are two major players in those improvements. RNNs have significantly contributed to sequence modelling across various application areas. Conversely, Transformer models represent a newer architecture leveraging attention mechanisms, extensive training data sets, and computational power. This review paper begins with a detailed exploration of RNN and Transformer models. Subsequently, it conducts a comparative analysis of their performance in intent recognition for Task‐oriented (CAs). Finally, it concludes by addressing the main challenges and outlining future research directions. [ABSTRACT FROM AUTHOR]

Summary Wireless sensor networks (WSNs) consist of numerous sensor nodes with limited battery life, computational power, and network capabilities. These sensors are deployed in specific areas to monitor environmental physical parameters. Once the data are collected, it is processed and transmitted to a base station (BS) via designated routes. The processes of sensing and transmitting consume significant energy, leading to rapid depletion of node batteries and the occurrence of hot spot problems. Consequently, relying on a single route for data transmission can result in network overhead issues. Enhancing the energy efficiency of WSNs is a persistent challenge. To address this, improvements in processes, such as routing and clustering are necessary. Implementing dynamic cluster head (CH) selection is a key approach for optimal path selection and energy conservation. Accordingly, in this work, a novel multiobjective CH selection and routing method for providing energy‐aware data transmission in WSN is presented. Here, CH selection is carried out using the proposed chronological wild geese optimization (CWGO) technique based on multiple constraints, such as delay, intercluster distance, intracluster distance, Link Life Time (LLT), and predicted energy. Further, the nodes' energy is determined by the deep recurrent neural network (DRNN). Then, the ideal path from the node to the BS is identified by the CWGO considering constraints, like predicted energy, delay, distance, and trust. Moreover, the proposed CWGO is examined considering metrics, like energy, trust, distance, and delay and is found to have attained superior values of 0.963 J, 0.700, 19.468 m, and 0.252 s, respectively. [ABSTRACT FROM AUTHOR]

Spatial‐temporal time series analysis and forecasting are crucial for understanding dynamic systems and making informed decisions. Recurrent neural networks (RNNs) have paved the way for reservoir computing (RC), a method enabling effective temporal information processing at low training costs. While software‐based RC performs well, physical RC systems face challenges like slow processing speed and limited state richness, leading to high hardware costs. This study introduces an innovative approach, i.e., the antiferroelectric field effect transistor‐based RC (AFeFET‐based RC) system for efficient temporal data processing. By exploiting the fading memory property inherent in hafnium oxide‐based antiferroelectric material, this system demonstrates promise for physical RC implementation. Moreover, it leverages the light sensitivity of 2D molybdenum disulfide (MoS2) channels for controllable temporal dynamics under electrical and optical stimuli. This dual‐mode modulation significantly enriches the reservoir state, boosting overall system performance. Experimental tests on standard benchmarking tasks using the AFeFET‐based RC system yielded impressive accuracy results (95.4%) in spoken‐digit recognition and a remarkable normalized root mean square error (NRMSE) of 0.015 in Mackey–Glass time series prediction. [ABSTRACT FROM AUTHOR]

The rapid advancement of neuromorphic computing demands innovative hardware solutions capable of efficiently mimicking the functionality of biological neural systems. In this context, dynamic memristors have emerged as promising candidates for realizing neuromorphic reservoir computing (RC) architectures. The dynamic memristors characterized by their ability to exhibit nonlinear conductance variations and transient memory behaviors offer unique advantages for constructing RC systems. Unlike recurrent neural networks (RNNs) that face challenges such as vanishing or exploding gradients during training, RC leverages a fixed‐size reservoir layer that acts as a nonlinear dynamic memory. Researchers can capitalize on their adaptable and efficient characteristics by integrating dynamic memristors into RC systems to enable rapid information processing with low learning costs. This perspective provides an overview of the recent developments in dynamic memristors and their applications in neuromorphic RC. It highlights their potential to revolutionize artificial intelligence hardware by offering faster learning speeds and enhanced energy efficiency. Furthermore, it discusses challenges and opportunities associated with integrating dynamic memristors into RC architectures, paving the way for developing next‐generation cognitive computing systems. [ABSTRACT FROM AUTHOR]

Summary: Passenger flow prediction is an important part of daily metro operation, and its accuracy affects the deployment of train resources management. Due to the complex spatiotemporal correlation characteristics of metro passenger flow, it is necessary to describe it to improve the accuracy of passenger flow prediction. However, the existing models mainly construct the weight matrix based on the static graph and the similarity between stations when describing the spatial correlation of station passenger flow but ignore the time‐varying characteristics of the spatial correlation of station passenger flow. To address this problem, this study introduces a dynamic multi‐graph and multidimensional attention spatiotemporal model. Specifically, the Graph Convolutional Neural Network combined with dynamic multigraph extracts spatial features and the Gated Recurrent Unit extracts temporal features of passenger flow. The multidimensional attention can obtain the spatiotemporal correlation of passenger flow data by assigning weights to them. Finally, this model has been used to conduct experiments on Beijing metro passenger flow datasets with time granularity of 10 and 15 min. The result indicates that the DGMANN model outperforms state‐of‐the‐art other deep learning methods in passenger flow prediction. In addition, the effectiveness of its key submodules has been verified through ablation experiments. [ABSTRACT FROM AUTHOR]

Soliton pulsations are ubiquitous feature of non‐stationary soliton dynamics in mode‐locked lasers and many other physical systems. To overcome difficulties related to a huge amount of necessary computations and low efficiency of traditional numerical methods in modeling the evolution of non‐stationary solitons, a two‐parallel bidirectional long short‐term memory recurrent neural network (TP‐Bi_LSTM RNN) is proposed, with the main objective to predict dynamics of vector‐soliton pulsations (VSPs) in various complex states, whose real‐time dynamics is verified by experiments. For two examples, viz., single‐ and bi‐periodic VSPs, with period‐21 and a combination of period‐3 and period‐43, the prediction results are better than provided by direct simulations – namely, deviations produced by the TP‐Bi_LSTM RNN results are 36% and 18% less than those provided by the simulations, respectively. This means that predicted results provided by the neural network are better than numerical simulations. Moreover, the prediction results for unstable VSP state with period‐9 indicate that the optimization of training sets and the number of training iterations are particularly important for the predictability. Besides, the scheme of coded information storage based on the TP‐Bi_LSTM RNN, instead of actual pulse signals, is realized too. The findings offer new applications of deep learning to ultrafast optics and information storage. [ABSTRACT FROM AUTHOR]

Modelling one‐to‐many type mappings in problems with a temporal component can be challenging. Backpropagation is not applicable to networks that perform discrete sampling and is also susceptible to gradient instabilities, especially when applied to longer sequences. In this paper, we propose two recurrent neural network architectures that leverage stochastic units and mixture models, and are trained with target propagation. We demonstrate that these networks can model complex conditional probability distributions, outperform backpropagation‐trained alternatives, and do not rapidly degrade with increased time horizons. Our main contributions consist of the design and evaluation of the architectures that enable the networks to solve multi‐model problems with a temporal dimension. This also includes the extension of the target propagation through time algorithm to handle stochastic neurons. The use of target propagation provides an additional computational advantage, which enables the network to handle time horizons that are substantially longer compared to networks fitted using backpropagation. [ABSTRACT FROM AUTHOR]

Generative artificial intelligence (AI) has developed as an effective tool for time series predicting, revolutionizing the typical methods of prediction. Different classical approaches that depend on existing approaches and assumptions, generative AI controls advanced deep learning (DL) approaches like generative adversarial networks (GANs) and recurrent neural networks (RNNs), to identify designs and connections in time series data. DL has accomplished major success in optimizing performances connected with AI. In the financial area, it can be extremely utilized for the stock market predictive, trade implementation approaches, and set of optimizers. Stock market predictive is the most important use case in this field. GANs with advanced AI approaches have become more significant in recent times. However, it can be utilized in image‐image‐translation and other computer vision (CV) conditions. GANs could not utilized greatly for stock market prediction because of their effort to establish the proper set of hyperparameters. This study develops an integrated spotted hyena optimization algorithm with generative artificial intelligence for time series forecasting (SHOAGAI‐TSF) technique. The purpose of the SHOAGAI‐TSF technique is to accomplish a forecasting process for the utilization of stock price prediction. The SHOAGAI‐TSF technique uses probabilistic forecasting with a conditional GAN (CGAN) approach for the prediction of stock prices. The CGAN model learns the data generation distribution and determines the probabilistic prediction from it. To boost the prediction results of the CGAN approach, the hyperparameter tuning can be performed by the use of the SHOA. The simulation result analysis of the SHOAGAI‐TSF technique takes place on the stock market dataset. The experimental outcomes determine the significant solution of the SHOAGAI‐TSF algorithm with other compared methods in terms of distinct metrics. [ABSTRACT FROM AUTHOR]

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free‐breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN‐based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN‐based method was compared with a dictionary‐matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN‐based method and the dictionary‐matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN‐based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60‐fold acceleration compared with the dictionary‐matching method. The RNN‐accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary‐matching method for the free‐breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications. [ABSTRACT FROM AUTHOR]

The article focuses on using recurrent neural networks (RNNs) and sensitivity analysis for estimating monthly evapotranspiration in Fez, Morocco. Topics include the comparison of various machine learning models for evapotranspiration estimation, the application of sensitivity analysis to understand environmental factors, and the performance evaluation of Long Short-Term Memory (LSTM) networks in improving water management strategies.

This paper examines the behavior of currencies' intraday exchange rates with mainly focuses on predicting these behaviors through deep learning models. The time series data are used in this study and comprise intraday exchange rate data for seven volatile currencies, recorded at two different frequency intervals: 1 h and 30 min. The data cover the time frame from January 1, 2018, to December 31, 2020. Firstly, wavelet maximal overlap discreet wavelet transform (MODWT) type "haar" is applied in order to identify the noise representing the volatile trend. Then learning models are applied to historical data that includes support vector regression (SVR), recurrent neural network (RNN), and long short‐term memory (LSTM). The main findings of the study provide strong evidence that the deep learning technique (i.e., LSTM) outperforms the other compatible models. This has been confirmed by the statistical measures for accuracy purposes. This study intends to address complex trends exhibited by volatile behavior of intraday exchange rates through non‐conventional learning techniques for the time of need‐based for the currency traders and other stakeholders. [ABSTRACT FROM AUTHOR]

Currency crises, recurrent events in the economic history of developing, emerging, and developed countries, have disastrous economic consequences. This paper proposes an early warning system for currency crises using sophisticated recurrent neural networks, such as long short‐term memory (LSTM) and gated recurrent unit (GRU). These models were initially used in language processing, where they performed well. Such models are increasingly being used in forecasting financial asset prices, including exchange rates, but they have not yet been applied to the prediction of currency crises. As for all recurrent neural networks, they allow for taking into account nonlinear interactions between variables and the influence of past data in a dynamic form. For a set of 68 countries including developed, emerging, and developing economies over the period of 1995–2020, LSTM and GRU outperformed our benchmark models. LSTM and GRU correctly sent continuous signals within a 2‐year warning window to alert for 91% of the crises. For the LSTM, false signals represent only 14% of the emitted signals compared with 23% for logistic regression, making it an efficient early warning system for policymakers. [ABSTRACT FROM AUTHOR]

This paper presents a promising approach using gated recurrent unit (GRU) network to predict bankruptcy based on the whole sequence of financial statements of the companies listed on an unregulated market. This approach contrasts with the traditional literature where default prediction is usually tackled with methods that do not fully account for a company's history. The GRU network can be used to model long‐term dependencies thanks to its update and reset gates, which prevent the vanishing gradient problem and decide how much of the past information is relevant for predicting a default. This aspect may be of utmost importance in alternative markets where the signal detection problem is particularly strong. The performance of the GRU network is compared against the performance of other standard machine learning methods including Cox proportional hazards, gradient‐boosted Cox proportional hazards model, extreme gradient boosting, random survival forest, and standard recurrent neural networks on the basis of a broad selection of performance metrics. The GRU network not only outperforms standard machine learning methods in out‐of‐sample forecasts but also seems to be more robust in terms of in‐ versus out‐of‐sample performance. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the influence of the confounding factors, direct water saturation (DWS), and magnetization transfer contrast (MTC) effects on measured Z‐spectra and amide proton transfer (APT) contrast in brain tumors. Methods: High‐grade glioma patients were scanned using an RF saturation‐encoded 3D MR fingerprinting (MRF) sequence at 3 T. For MRF reconstruction, a recurrent neural network was designed to learn free water and semisolid macromolecule parameter mappings of the underlying multiple tissue properties from saturation‐transfer MRF signals. The DWS spectra and MTC spectra were synthesized by solving Bloch‐McConnell equations and evaluated in brain tumors. Results: The dominant contribution to the saturation effect at 3.5 ppm was from DWS and MTC effects, but 25%–33% of the saturated signal in the gadolinium‐enhancing tumor (13%–20% for normal tissue) was due to the APT effect. The APT# signal of the gadolinium‐enhancing tumor was significantly higher than that of the normal‐appearing white matter (10.1% vs. 8.3% at 1 μT and 11.2% vs. 7.8% at 1.5 μT). Conclusion: The RF saturation‐encoded MRF allowed us to separate contributions to the saturation signal at 3.5 ppm in the Z‐spectrum. Although free water and semisolid MTC are the main contributors, significant APT contrast between tumor and normal tissues was observed. [ABSTRACT FROM AUTHOR]

We study the statistical properties of the Bitcoin return series and provide a thorough forecasting exercise. Also, we calibrate state‐of‐the‐art machine learning techniques and compare the results with econometric time series models. The empirical assessment provides evidence that the application of machine learning techniques outperforms econometric benchmarks in terms of forecasting precision for both in‐ and out‐of‐sample forecasts. We find that both deep learning architectures as well as complex layers, such as LSTM, do not increase the precision of daily forecasts. Specifically, a simple recurrent neural network describes a sensible choice for forecasting daily return series. [ABSTRACT FROM AUTHOR]

Summary: With the increase in internet connectivity worldwide, people have resorted to various video streaming applications for entertainment, education, healthcare, and so on. However, this has resulted in huge internet traffic, which is predominantly occurring due to the increased transmission of videos over wireless networks to mobile devices, Transmission of ultra‐high‐definition videos can be effortlessly carried out, although the video quality perceived by the users is normally lesser than the anticipated quality. In video streaming applications, it is a pre‐requisite to provide users with high quality of experience (QoE) but this is generally affected by the dynamic variations in the network conditions. This work presents a novel QoE‐based video delivery system in a collaborative e‐learning platform. Here, a novel deep learning structure recurrent neural network‐long short term memory (RNN‐LSTM) is developed for adaptive bit rate (ABR) selection, thereby providing users with videos of high QoE. Various network, time, and buffer‐based parameters are considered while selecting the bit rate. Additionally, the proposed RNN‐LSTM is assessed for its superiority in providing high QoE videos based on measures, like QoE, buffer size, and bit rate, and is observed to attain values of 0.975, 45.654, and 90.766 b/s, respectively. [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Positron emission tomography (PET) has been investigated for its ability to reconstruct proton‐induced positron activity distributions in proton therapy. This technique holds potential for range verification in clinical practice. Recently, deep learning‐based dose estimation from positron activity distributions shows promise for in vivo proton dose monitoring and guided proton therapy.This study evaluates the effectiveness of three classical neural network models, recurrent neural network (RNN), U‐Net, and Transformer, for proton dose estimating. It also investigates the characteristics of these models, providing valuable insights for selecting the appropriate model in clinical practice.Proton dose calculations for spot beams were simulated using Geant4. Computed tomography (CT) images from four head cases were utilized, with three for training neural networks and the remaining one for testing. The neural networks were trained with one‐dimensional (1D) positron activity distributions as inputs and generated 1D dose distributions as outputs. The impact of the number of training samples on the networks was examined, and their dose prediction performance in both homogeneous brain and heterogeneous nasopharynx sites was evaluated. Additionally, the effect of positron activity distribution uncertainty on dose prediction performance was investigated. To quantitatively evaluate the models, mean relative error (MRE) and absolute range error (ARE) were used as evaluation metrics.The U‐Net exhibited a notable advantage in range verification with a smaller number of training samples, achieving approximately 75% of AREs below 0.5 mm using only 500 training samples. The networks performed better in the homogeneous brain site compared to the heterogeneous nasopharyngeal site. In the homogeneous brain site, all networks exhibited small AREs, with approximately 90% of the AREs below 0.5 mm. The Transformer exhibited the best overall dose distribution prediction, with approximately 92% of MREs below 3%. In the heterogeneous nasopharyngeal site, all networks demonstrated acceptable AREs, with approximately 88% of AREs below 3 mm. The Transformer maintained the best overall dose distribution prediction, with approximately 85% of MREs below 5%. The performance of all three networks in dose prediction declined as the uncertainty of positron activity distribution increased, and the Transformer consistently outperformed the other networks in all cases.Both the U‐Net and the Transformer have certain advantages in the proton dose estimation task. The U‐Net proves well suited for range verification with a small training sample size, while the Transformer outperforms others at dose‐guided proton therapy. [ABSTRACT FROM AUTHOR]

Recurrent selection methods have been successful in generating superior Paspalum notatum families through the accumulation of favorable alleles. However, the effectiveness of these methods in producing apomictic hybrids with superior agronomic traits has not been thoroughly evaluated. The aim of this study was to characterize the reproductive behavior of P. notatum progenies obtained through recurrent selection based on combining ability (RSCA) and recurrent phenotypic selection (RPS) and assess the performance of the apomictic hybrids concerning various agronomic traits. The reproductive mode of 144 RSCA and 144 RPS hybrids was determined using a molecular marker tightly linked to the apospory trait (BCU243‐377). The expressivity of apospory was estimated observing mature embryo sacs. The apomictic hybrids were then evaluated for six agronomic traits. A segregation ratio of 5:1 between sexual and apomictic hybrids was observed for the RSCA progeny, while 4.3:1 was registered for the RPS progeny. Although apospory expressivity was variable among hybrids, 75% and 86% of the RSCA and RPS hybrids, respectively, exhibited a high expression (>81%). Non‐significant differences between breeding methods in the number of apomictic hybrids and the level of apospory expressivity were observed. Variations for all agronomic traits were observed among apomictic hybrids within each breeding method. However, no differences between methods in the performance of the highly apomictic hybrids were observed. This demonstrates that the reproductive behavior of P. notatum is not affected by the recurrent selection method. Therefore, the RPS method would be the most suitable since it was equally effective than RSCA but it is cheaper, faster, and easier to apply. Core Ideas: Highly apomictic hybrids with superior forage attributes were obtained by recurrent selection in Paspalum notatum.The proportion of apomictic hybrids was not affected by the recurrent selection method.Recurrent phenotypic selection would be the most suitable method for breeding Paspalum notatum. [ABSTRACT FROM AUTHOR]

A novel Modified Deep Fuzzy Clustering (MDFC) based classification model involves four major phases. They are preprocessing, segmentation, feature extraction and finally, detection and classification phase. To reduce noise and smooth the edges of the input image of the cotton crop, bilateral filtering is first used as a preprocessing approach. Next, a modified deep fuzzy clustering is suggested for the segmentation procedure that creates a collection of segments from the preprocessed image. The segmented image is then processed to extract relevant characteristics by using an enhanced Pyramid of Histogram Orientation Gradient (PHOG), Local Directional Ternary Pattern (LDTP), and statistical‐based features. In order to detect and classify cotton crop diseases more effectively, this paper proposes a hybrid system. Here, the features are put through a detection phase, after which the extracted features are trained in the Bidirectional Gated Recurrent Unit (Bi‐GRU) model to determine whether or not the cotton crop is infected. Once it is detected to be diseased, the type of disease is classified via an improved Recurrent Neural Network (RNN). In terms of several performance metrics, the proposed model is validated in comparison with the traditional approaches. The MDFC‐based classification model outperforms existing models with a specificity of 0.9687 at a learning rate of 90. In contrast, other models achieve lower specificities: Bi‐GRU (0.8436), RNN (0.8359), CNN (0.8654), LSTM (0.8769), SVM (0.7983), VGG16 (0.8619), DCNN (0.8725), BI‐RNN + BI‐LSTM (0.7869), and NN + CNN (0.85478). [ABSTRACT FROM AUTHOR]

Modern radar systems often face various interference signals in complex and rapidly changing electronic environments. The task of suppressing this interference in the radar echo signal to extract vital information is challenging. A radar interference suppression method is proposed based on a generative adversarial network (GAN). This method effectively recovers the target signal from the echo signal, which contains interference and noise, by leveraging the powerful fitting ability of GAN. Specifically, this method was tested using coherent suppression interference, smart noise interference, and noise frequency modulation suppression interference. We compared the proposed GAN method with recurrent neural network, short‐time Fourier transform time‐varying filtering, short‐time fractional Fourier transform time‐varying filtering algorithms and RNN approach. The results show that the interference suppression algorithm based on GAN is superior to the other three algorithms. [ABSTRACT FROM AUTHOR]

Fuel prices are rising, bringing attention to the utilization of alternative energy sources (RES). Even though load forecasting is more accurate at making predictions than wind power forecasting is. To address the operational challenges with the supply of electricity, wind energy forecasts remain essential. A certain kind of technology has recently been applied to forecast wind energy. On wind farms, a variety of wind power forecasting methods have been developed and used. The main idea underlying recurrent networks is parameter sharing across the multiple layers and neurons, which results in cycles in the network's graph sequence. Recurrent networks are designed to process sequential input. A novel hybrid optimization‐based RNN model for wind power forecasting is proposed in this research. Using the SpCro algorithm, a proposed optimization method, the RNN's weights are adjusted. The Crow Search Optimization (CSA) algorithm and the Sparrow search algorithm are combined to form the SpCro Algorithm (SSA). The suggested Algorithm was developed using the crow's memory traits and the sparrow's detecting traits. The proposed system is simulated in MATLAB, and the usefulness of the suggested approach is verified by comparison with other widely used approaches, such as CNN and DNN, in terms of error metrics. Accordingly, the MAE of the proposed method is 45%, 10.02%, 10.04%, 33.58%, 94.81%, and 10.01% higher than RNN, SOA+RNN, CSO+RNN, SSA+DELM, CFU‐COA, and GWO+RNN method. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is critical for power system planning and operations, and ensemble forecasting methods for electricity loads have been shown to be effective in obtaining accurate forecasts. However, the weights in ensemble prediction models are usually preset based on the overall performance after training, which prevents the model from adapting in the face of different scenarios, limiting the improvement of prediction performance. In order to improve the accurateness and validity of the ensemble prediction method further, this paper proposes an ensemble deep reinforcement learning approach using Q‐learning dynamic weight assignment to consider local behaviours caused by changes in the external environment. Firstly, the variational mode decomposition is used to reduce the non‐stationarity of the original data by decomposing the load sequence. Then, the recurrent neural network (RNN), long short‐term memory (LSTM), and gated recurrent unit (GRU) are selected as the basic power load predictors. Finally, the optimal weights are ensembled for the three sub‐predictors by the optimal weights generated using the Q‐learning algorithm, and the final results are obtained by combining their respective predictions. The results show that the forecasting capability of the proposed method outperforms all sub‐models and several baseline ensemble forecasting methods. [ABSTRACT FROM AUTHOR]

In the past three decades, proportional‐integral/PI‐differential (PI/PID) controllers and model predictive controller (MPCs) have predominantly governed complex chemical process control. Despite their advancements, these approaches have limitations, with PI/PID controllers requiring scenario‐specific tuning and MPC being computationally demanding. To tackle these issues, we introduce the long‐short‐term‐memory (LSTM)‐controller (LSTMc), a model‐free, data‐driven framework leveraging LSTM networks' robust time‐series prediction capabilities. The LSTMc predicts subsequent manipulated inputs by evaluating state evolution and error dynamics from both the current and previous time‐steps, which proved effective in our dextrose batch crystallization case study. Remarkably, the LSTMc achieves less than 2% set‐point deviation, three times better than MPCs, and retains robustness even with 10%–15% sensor noise. With these results, LSTMc emerges as a promising alternative for process control, adeptly adjusting to changing process conditions and set‐points, providing efficient computation for an optimal input profile, and effectively filtering out common industrial process noise. [ABSTRACT FROM AUTHOR]

The 2021-2022 surge in US inflation was unanticipated by the Survey of Professional Forecasters (SPF) and other macroeconomists and institutions. This study assesses whether nascent deep learning frameworks and methods more accurately project recent core personal consumption expenditures inflation. We create a recurrent neural network (RNN) to forecast long-term inflation, and after training on 60 years of quarterly data, the model outperforms the SPF and projects a spike in inflation similar to that of recent years. We compare the model's performance with and without COVID-19-specific data and discuss some implications of our findings for economic forecasting in global crises. [ABSTRACT FROM AUTHOR]

The gated structure of the long short‐term memory (LSTM) alleviates the defects of gradient disappearance and explosion in the recurrent neural network (RNN). It has received widespread attention in sequence learning such as text analysis. Although LSTM has good performance in handling remote dependencies, information loss often occurs in long‐distance transmission. We propose a new model called ELSTM based on the computational complexity and gradient dispersion in the traditional LSTM model. This model simplifies the input gate of LSTM, reduces some time complexity by reducing some components, and improves the output gate. By introducing the exponential linear unit activation layer, the problem of gradient dispersion is alleviated. Comparing the new model with multiple existing models, when predicting language sequences, the time used by the model has been greatly reduced, and the language confusion has been reduced, showing good performance. [ABSTRACT FROM AUTHOR]

Summary: The proposed antenna is a small wideband monopole with wideband circular polarization using heterogeneous bidirectional recurrent neural network for both narrow and wide band applications (NWB‐MAD‐HBRNN). The electromagnetic structure is designed, fabricated, and simulated with 1 mm thickness on FR4 substrate material along dielectric constant 4.3. The proposed antenna includes 4.3–8.85 GHz for ultrawideband applications; it contains reconfigurable narrow band for L‐band 1.27 GHz, LTE, and ultrawideband applications. To enhance the antenna impedance bandwidth (BW) along axial ratio bandwidth (ARBW), a slit is etched at the antenna patch, a rectangular stub is inserted into the ground plane, and semicircular stub is added to the top of antenna feed line. The better agreement is observed in the measured and simulated gain performance of 4.8 dB for LTE band applications. The proposed NWB‐MAD‐HBRNN design provides 13.50%, 18.91%, and 22.58% higher bandwidth and 18.36%, 20.38%, and 27.58% lower return loss than the existing designs, such as bio‐inspired wideband antenna for wireless applications based on perturbation technique (BWA‐WA‐PA), a compact circularly polarized modified printed monopole antenna for wireless applications (CCP‐MPMA‐WA), and new multiband monopole antenna for certain broadband wireless applications along wireless personal communications (PA‐MMA‐BWA), respectively. [ABSTRACT FROM AUTHOR]

In electronic warfare, radar signal deinterleaving is a critical task. While many researchers have applied deep learning and utilised known radar classes to construct interleaved pulse sequences training sets for deinterleaving models, these models face challenges in distinguishing between known and unknown radar classes in open‐set scenarios. To address this challenge, the authors propose a novel model, the Reconstruction Bidirectional Recurrent Neural Network (RBi‐RNN). RBi‐RNN utilises input reconstruction and employs a joint training strategy incorporating cross‐entropy loss, reconstruction loss, and centre loss. These strategies aim to maximise inter‐class latent representation distances while minimising intra‐class disparities. By incorporating an open‐set recognition method based on extreme value theory, RBi‐RNN adapts to open‐set scenarios. Simulation results demonstrate the superiority of RBi‐RNN over conventional models in both closed‐set and open‐set scenarios. In open‐set scenarios, it successfully discriminates between known and unknown radar signals within interleaved pulse sequences, deinterleaving known radar classes with high stability. The authors lay the foundation for future unsupervised deinterleaving methods designed specifically for unknown radar pulses. [ABSTRACT FROM AUTHOR]

Summary: In the presented study, the solution of the fuzzy nonlinear optimization problems (FNLOPs) is calculated using a recurrent neural network (RNN) model. Since there is a few research for solving FNLOP by RNN's, we give a new approach to solve the problem. By reducing the original program to an interval problem and then weighting problem, the Karush–Kuhn–Tucker (KKT) conditions are given. Moreover, we use the KKT conditions into a RNN as an important tool to solve the problem. Besides, the global convergence properties and the Lyapunov stability of the dynamic model are studied in this study. In the final step, some illustrative examples are considered to establish the obtained results. Reported results are compared with some others network models. [ABSTRACT FROM AUTHOR]

The quadruple tank (QT) system consists of four interacting tanks and can switch between the minimum and non‐minimum phase behavior with changes in the positions of pump valves and is considered a benchmark control problem. In the present study, long‐short term memory (LSTM), a type of recurrent neural networks (RNN) is designed for the benchmark QT system based on the model‐based control framework. Random input–output sequences are generated from the white box model of the QT system to train an LSTM network model. The LSTM network is tuned by adjusting its hyperparameters such as the number of hidden layers, hidden units, and epochs to minimize the prediction error on the test data. The trained model is cross validated both during and after training to avoid overfitting. Once a reasonably reliable model is obtained, another LSTM network is trained for use as a controller. The network architecture is constantly modified till the controller is able to track the test setpoints with minimum error. This procedure is repeated with a gated recurrent unit (GRU) network and the servo and regulatory response of both the network models and controller are evaluated in terms of standard performance measure namely root mean square error (RMSE), integral square error (ISE), and control effort (CE). It is observed that the controller designed based on RNN performs better than a conventional centralized controller. [ABSTRACT FROM AUTHOR]