Search

Stream mining, especially with concept drift, presents significant challenges across various domains. As data streams evolve over time, initial models become less effective. We present a novel approach using fuzzy ARTMAP's adaptability and neural networks' robustness to address concept drift. Our method dynamically updates models based on changing data distributions, enabling real-time adap- tation. By integrating fuzzy ARTMAP with backpropagation, it facilitates agile learning and accurate predictions in evolving scenarios. Through rigorous exper- iments, we demonstrate the effectiveness of our method in managing concept drift and achieving substantial performance improvements. The achieved accu- racy of 85.07% and F1 score of 72.47 demonstrate the effectiveness of the approach in real-time classification tasks. This research extends beyond just performance metrics. By leveraging the interpretability of fuzzy ARTMAP, we gain valuable insights into the mechanisms that enable our model to adapt to concept drift. This deeper understanding paves the way for further advancements in this area. [ABSTRACT FROM AUTHOR]

Featured Application: (1) The concept of trip assignment probability was used to simulate passenger behavior of selecting different HSR stations in a zone, unlike the existing all-or-nothing-based optimal strategy algorithm. (2) By optimizing the trip assignment probability using a backpropagation-based algorithm, the accuracy and time efficiency of long-term HSR demand forecasting were improved compared with the existing calibration process using a trial-and-error approach. (3) The estimation accuracy of the backpropagation-based algorithm was especially superior when applied to an area with multiple accessible HSR stations, such as the Seoul metropolitan area, as well as non-metropolitan areas with a single accessible HSR station. In Korea, decisions for high-speed railway (HSR) construction are made based on long-term demand forecasting. A calibration process that simulates current trip patterns is an important step in long-term demand forecasting. However, a trial-and-error approach based on iterative parameter adjustment is used for calibration, resulting in time inefficiency. In addition, the all-or-nothing-based optimal strategy algorithm (OSA) used in HSR trip assignment has limited accuracy because it assigns all trips from a zone with multiple accessible stations to only one station. Therefore, this study aimed to develop a backpropagation-based algorithm to optimize trip assignment probability from a zone to multiple accessible HSR stations. In this algorithm, the difference between the estimated volume calculated from the trip assignment probability and observed volumes was defined as loss, and the trip assignment probability was optimized by repeatedly updating in the direction of the reduced loss. The error rate of the backpropagation-based algorithm was compared with that of the OSA using KTDB data; the backpropagation-based algorithm had lower errors than the OSA for most major HSR stations. It was especially superior when applied to areas with multiple HSR stations, such as the Seoul metropolitan area. This algorithm will improve the accuracy and time efficiency of long-term HSR demand forecasting. [ABSTRACT FROM AUTHOR]

Copyright of Revista Brasileira de Engenharia Agricola e Ambiental - Agriambi is the property of Revista Brasileira de Engenharia Agricola e Ambiental and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The operation of power transformer in an electric system is the cause of noise in form of sound. At a certain level, this noise can be considered as pollution, interfering with the comfort and health of human hearing. The phenomenon shows the need to understand load noise that is generated during the design process of power transformer. However, a major related problem is the unavailability of an accurate load noise model capable of precise prediction during the design stage. Therefore, this research aimed to develop load noise model based on an artificial neural network for power transformer to predict the generated load noise value. The development process was carried out using a trained backpropagation neural network (BPNN) with the Levenberg-Marquardt algorithm. Before training for neural network, input parameters such as power, impedance, and winding geometry factors were selected and normalized. The linear regression method was used to assess the quality of neural network model training results. For performance comparison, the multiple linear regression (MLR) model and the Reiplinger method were also developed. The results showed that load noise model was developed based on BPNN with seven hidden layers and nine neurons for each layer. Model showed acceptable output variables, with mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (R) of 0.007, 0.464, 0.708, and 0.998, respectively. Furthermore, the prediction of load noise achieved through BPNN showed significantly high accuracy compared to the existing standard formulas.

Implicit neural networks and the related deep equilibrium models are investigated. To train these networks, the gradient of the corresponding loss function should be computed. Bypassing the implicit function theorem, we develop an explicit representation of this quantity, which leads to an easily accessible computational algorithm. The theoretical findings are also supported by numerical simulations. [ABSTRACT FROM AUTHOR]

A four‐degree‐of‐freedom upper limb exoskeleton rehabilitation robot system with a gravity compensation device is constructed. The objective is to address the rehabilitation training needs of patients with upper limb motor dysfunction. A BP neural network adaptive control method based on particle swarm optimization is proposed. First, the degrees of freedom of the human body are analyzed, and a Lagrange method is employed to construct a dynamic model. Second, a particle swarm optimization back propagation neural network adaptive control algorithm based on particle swarm optimization is presented. Subsequently, the range of motion of the upper limbs is analyzed with reference to muscle anatomy and a three‐dimensional motion capture system. And the robot structure design is analyzed in detail. Finally, simulation experiments were conducted, and the results demonstrated that the proposed method exhibited high effectiveness and accuracy. [ABSTRACT FROM AUTHOR]

In this study, we propose the CVMFCC-DR (Complex-Valued Mel-Frequency Cepstral Coefficients Dimensionality Reduction) algorithm as an efficient method for reducing the dimensionality of speech signals. By utilizing the complex-valued MFCC technique, which considers both real and imaginary components, our algorithm enables dimensionality reduction without information loss while decreasing computational costs. The efficacy of the proposed algorithm is validated through experiments which demonstrate its effectiveness in building a speech recognition model using a complex-valued neural network. Additionally, a complex-valued softmax interpretation method for complex numbers is introduced. The experimental results indicate that the approach yields enhanced performance compared to traditional MFCC-based techniques, thereby highlighting its potential in the field of speech recognition. [ABSTRACT FROM AUTHOR]

Almost every year, earthquakes threaten many lives, so not only do developing countries suffer negative effects from earthquakes on their economies but also developed ones that lose significant economic resources, suffer massive fatalities, and have to suspend businesses and occupancy. Existing buildings in earthquake-prone areas need structural safety assessments or seismic vulnerability assessments. It is crucial to assess earthquake damage before an earthquake to prevent further losses, and to assess building damage after an earthquake to aid emergency responders. Many models do not take into account the surveyor's subjectivity, which causes observational vagueness and uncertainty. Additionally, a lack of experience or knowledge, engineering errors, and inconspicuous parameters could affect the assessment. Thus, a consensus-based Likert–LMBP (the Levenberg–Marquardt backpropagation algorithm) model was developed to rapidly assess the seismic performance of buildings based on post-earthquake visual images in the devastating Kahramanmaraş earthquake, which occurred on 6 February 2023 and had magnitudes of 7.7 and 7.6 and severely affected 11 districts in Türkiye. Vulnerability variables for buildings are assessed using linguistic variables on a five-point Likert scale based on expert consensus values derived from post-earthquake visual images. The building vulnerability parameters required for the proposed model are determined as the top hill–slope effect, weak story effect, soft story effect, short column effect, plan irregularity, pounding effect, heavy overhang effect, number of stories, construction year, structural system state, and apparent building quality. Structural analyses categorized buildings as no damage, slight damage, moderate damage, or severe damage/collapse. Training the model resulted in quite good performance (mse = 7.26306 × 10−5). Based on the statistical analysis of the entire data set, the mean and the standard deviation of the errors were 0.00068 and 0.00852, respectively. [ABSTRACT FROM AUTHOR]

In this study, we investigate the classification of lung cancer CT scan images based on malignancy level using a backpropagation artificial neural network (ANN). Lung cancer is a deadly disease characterized by the growth of abnormal lung cells. The proposed method involves preprocessing to enhance image quality, followed by feature extraction using the Gray Level Co-occurrence Matrix (GLCM) method with angle variations of 0°, 45°, 90°, 135°, and d=1. The extracted features include energy, contrast, correlation, and homogeneity. The energy value range in malignant cancer is 0.27 to 0.81, while in benign cancer it is 0.26 to 0.73. The contrast in benign cancer ranges from 1.38 to 11.87, while in malignant cancer it is 1.47 to 13.67. The image correlation for malignant cancer is between 0.63 to 0.94, while for benign cancer it is 0.69 to 0.96. Homogeneity in malignant cancer has a value range between 0.67 to 0.91, while in benign cancer it ranges from 0.70 to 0.92. The classification of lung cancer malignancy is restricted to benign and malignant levels using a network architecture of [4 10 2], maximum iteration of 100000, and learning rate of 0.001. The accuracy of the testing data from the ANN is between 90% and 100%. These results demonstrate the effectiveness of the GLCM method and backpropagation algorithm in accurately classifying the malignancy level of lung cancer, which could aid in the early detection and treatment of the disease. [ABSTRACT FROM AUTHOR]

The spiking convolutional neural network (SCNN) is a kind of spiking neural network (SNN) with high accuracy for visual tasks and power efficiency on neuromorphic hardware, which is attractive for edge applications. However, it is challenging to implement SCNNs on resource-constrained edge devices because of the large number of convolutional operations and membrane potential (Vm) storage needed. Previous works have focused on timestep reduction, network pruning, and network quantization to realize SCNN implementation on edge devices. However, they overlooked similarities between spiking feature maps (SFmaps), which contain significant redundancy and cause unnecessary computation and storage. This work proposes a dual-threshold spiking convolutional neural network (DT-SCNN) to decrease the number of operations and memory access by utilizing similarities between SFmaps. The DT-SCNN employs dual firing thresholds to derive two similar SFmaps from one Vm map, reducing the number of convolutional operations and decreasing the volume of Vms and convolutional weights by half. We propose a variant spatio-temporal back propagation (STBP) training method with a two-stage strategy to train DT-SCNNs to decrease the inference timestep to 1. The experimental results show that the dual-thresholds mechanism achieves a 50% reduction in operations and data storage for the convolutional layers compared to conventional SCNNs while achieving not more than a 0.4% accuracy loss on the CIFAR10, MNIST, and FashionMNIST datasets. Due to the lightweight network and single timestep inference, the DT-SCNN has the least number of operations compared to previous works, paving the way for low-latency and power-efficient edge applications. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) have superior energy efficiency due to their spiking signal transmission, which mimics biological nervous systems, but they are difficult to train effectively. Although surrogate gradient-based methods offer a workable solution, trained SNNs frequently fall into local minima because they are still primarily based on gradient dynamics. Inspired by the chaotic dynamics in animal brain learning, we propose a chaotic spiking backpropagation (CSBP) method that introduces a loss function to generate brain-like chaotic dynamics and further takes advantage of the ergodic and pseudo-random nature to make SNN learning effective and robust. From a computational viewpoint, we found that CSBP significantly outperforms current state-of-the-art methods on both neuromorphic data sets (e.g. DVS-CIFAR10 and DVS-Gesture) and large-scale static data sets (e.g. CIFAR100 and ImageNet) in terms of accuracy and robustness. From a theoretical viewpoint, we show that the learning process of CSBP is initially chaotic, then subject to various bifurcations and eventually converges to gradient dynamics, consistently with the observation of animal brain activity. Our work provides a superior core tool for direct SNN training and offers new insights into understanding the learning process of a biological brain. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) are powerful data-oriented "black-box" algorithms capable of assessing and delineating linear and multifaceted non-linear correlations between the dependent and explanatory variables. Through the years, neural networks have proven to be effective and robust analytical techniques for establishing artificial intelligence-based tools for modelling, estimating, and projecting spatial and temporal variations in water bodies. Accordingly, ANN-based algorithms gained increased attention and have emerged as practical alternatives to traditional approaches for hydro-chemical analysis. ANNs are among the widely used computer systems for modelling surface water quality. Considering their wide recognition, resilience, flexibility, and accuracy, the current study employs a neural network-based methodology to construct a novel water quality index (WQI) model suitable for analysing South African rivers. The feed-forward, back-propagated multilayered perceptron model has three parallel-distributed neuron layers interconnected with seventy weighted links orientated laterally from left to right. First, the input layer includes thirteen neuro-nodes symbolising thirteen explanatory variables, including NH3, Ca, Cl, Chl-a, EC, F, CaCO3, Mg, Mn, NO3, pH, SO4, and turbidity (NTU). Second, the hidden layer consists of eleven neuro-nodes accountable for computational tasks. Lastly, the output layer features one neuron responsible for conveying network outcomes using a single-digit WQI rating extending from zero to one hundred, where zero represents substandard water quality and one hundred denotes exceptional water quality. The AI-based model was developed using water quality data obtained from six monitoring locations within four drainage basins under the management of the Umgeni Water Board in the KwaZulu-Natal Province of South Africa. The dataset comprises 416 samples randomly divided into training, testing, and validation sets using a proportional split of 70:15:15%. The Broyden–Fletcher–Goldfarb–Shanno (BFGS) technique was utilised to conduct backpropagation training and adjust synapse weights. The dependent variables are the WQI scores from the universal water quality index (UWQI) model developed specifically for South African river basins. The ANN demonstrated enhanced efficiency through an overall correlation coefficient (R) of 0.985. Furthermore, the neural network attained R-values of 0.987, 0.992, and 0.977 for the training, testing, and validation intervals. The ANN model achieved a Nash–Sutcliffe efficiency (NSE) value of 0.974 and coefficient of determination (R2) of 0.970. Sensitivity analysis provided additional validation of the preparedness and computational competence of the ANN model. The typical target-to-output error tolerance for the ANN model is 0.242, demonstrating an adequate predictive ability to deliver results comparable with the target UWQI, having the lowest and highest index ratings of 75.995 and 94.420, respectively. Accordingly, the three-layer neural network is scientifically sound, with index values and water quality evaluations corresponding to the UWQI results. The current research project seeks to document the processes used and the outcomes obtained. [ABSTRACT FROM AUTHOR]

This paper introduces a novel architecture—bidirectional optical neural network (BONN)—for providing backward connections alongside forward connections in artificial neural networks (ANNs). BONN incorporates laser diodes and photodiodes and exploits the properties of Köhler illumination to establish optical channels for backward directions. Thus, it has bidirectional functionality that is crucial for algorithms such as the backpropagation algorithm. BONN has a scaling limit of 96 × 96 for input and output arrays, and a throughput of 8.5 × 1015 MAC/s. While BONN's throughput may rise with additional layers for continuous input, limitations emerge in the backpropagation algorithm, as its throughput does not scale with layer count. The successful BONN-based implementation of the backpropagation algorithm requires the development of a fast spatial light modulator to accommodate frequent data flow changes. A two-mirror-like BONN and its cascaded extension are alternatives for multilayer emulation, and they help save hardware space and increase the parallel throughput for inference. An investigation into the application of the clustering technique to BONN revealed its potential to help overcome scaling limits and to provide full interconnections for backward directions between doubled input and output ports. BONN's bidirectional nature holds promise for enhancing supervised learning in ANNs and increasing hardware compactness. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is one of the most interesting application for machine learning models running on low-cost and low-power devices, such as microcontrollers (MCUs). As a matter of fact, MCUs are often dedicated to performing inference on their own acquired data, and any form of model training and update is delegated to external resources. We consider this mainstream paradigm a severe limitation, especially when privacy concerns prevent data sharing, thus model personalization, which is universally recognized as beneficial in HAR. In this letter, we present our HAR solution where MCUs can directly fine-tune a deep learning model using locally acquired data. In particular, we enable training functionalities for 1-D convolutional neural networks (CNNs) on STM32 microcontrollers and provide a software tool to estimate the memory and computational resources required to accomplish model personalization. [ABSTRACT FROM AUTHOR]

Spiking neural network (SNN) is broadly deployed in neuromorphic devices to emulate brain function. In this context, SNN security becomes important while lacking in-depth investigation. To this end, we target the adversarial attack against SNNs and identify several challenges distinct from the artificial neural network (ANN) attack: 1) current adversarial attack is mainly based on gradient information that presents in a spatiotemporal pattern in SNNs, hard to obtain with conventional backpropagation algorithms; 2) the continuous gradient of the input is incompatible with the binary spiking input during gradient accumulation, hindering the generation of spike-based adversarial examples; and 3) the input gradient can be all-zeros (i.e., vanishing) sometimes due to the zero-dominant derivative of the firing function. Recently, backpropagation through time (BPTT)-inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given spatiotemporal gradient maps. We propose two approaches to address the above challenges of gradient-input incompatibility and gradient vanishing. Specifically, we design a gradient-to-spike (G2S) converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a restricted spike flipper (RSF) to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all-zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer on the attack effectiveness. Extensive experiments are conducted to validate our solution. Besides the quantitative analysis of the influence factors, we also compare SNNs and ANNs against adversarial attacks under different attack methods. This work can help reveal what happens in SNN attacks and might stimulate more research on the security of SNN models and neuromorphic devices.

Voltage-gated sodium channels located in axon initial segments (AIS) trigger action potentials (AP) and play pivotal roles in the excitability of cortical pyramidal neurons. The differential electrophysiological properties and distributions of NaV1.2 and NaV1.6 channels lead to distinct contributions to AP initiation and propagation. While NaV1.6 at the distal AIS promotes AP initiation and forward propagation, NaV1.2 at the proximal AIS promotes the backpropagation of APs to the soma. Here, we show the small ubiquitin-like modifier (SUMO) pathway modulates Na+ channels at the AIS to increase neuronal gain and the speed of backpropagation. Since SUMO does not affect NaV1.6, these effects were attributed to SUMOylation of NaV1.2. Moreover, SUMO effects were absent in a mouse engineered to express NaV1.2-Lys38Gln channels that lack the site for SUMO linkage. Thus, SUMOylation of NaV1.2 exclusively controls INaP generation and AP backpropagation, thereby playing a prominent role in synaptic integration and plasticity.

Cancer is an invasive and malignant growth of cells and is known to be one of the most fatal diseases. Its early detection is essential for decreasing the mortality rate and increasing the probability of survival. This study presents an efficient machine learning approach based on the state vector machine (SVM) to diagnose and classify tumors into malignant or benign cancer using the online lymphographic data. Further, two types of neural network architectures are also implemented to evaluate the performance of the proposed SVM-based approach. The optimal structures of the classifiers are obtained by varying the architecture, topology, learning rate, and kernel function and recording the results' accuracy. The classifiers are trained with the preprocessed data examples after noise removal and tested on the unknown cases to diagnose each example as positive or negative. Further, the positive cases are classified into different stages including metastases, malign lymph, and fibrosis. The results are evaluated against the feed-forward and generalized regression neural networks. It is found that the proposed SVM-based approach significantly improves the early detection and classification accuracy in comparison to the experienced physicians and the other machine learning approaches. The proposed approach is robust and can perform sub-class divisions for multipurpose tasks. Experimental results demonstrate that the two-class SVM gives the best results and can effectively be used for the classification of cancer. It has outperformed all other classifiers with an average accuracy of 94.90%. [ABSTRACT FROM AUTHOR]

Spiking Neural Network (SNN) is one of the mainstream frameworks for brain-like computing and neuromorphic computing, which has the potential to overcome current AI challenges, for example, low-power learning dynamic processes. However, there is still a huge gap in performance between SNN and artificial neural networks (ANN) in traditional supervised learning. One solution for this problem is to propose a better spiking neuron model to improve its memory ability for temporal data. This paper proposed a leaky integrate-and-fire (LIF) neuron model with dynamic postsynaptic potential and a layer-span connecting method for SNN trained using backpropagation. The dynamic postsynaptic potential LIF model allows the neurons dynamically release neurotransmitters in an SNN model, which mimics the activity of biological neurons. The layer-span connecting method enhances the long-distance memory ability of SNN. We also first introduced a cosh-based surrogate gradient for the backpropagation training of SNNs. We compared the SNN with cosh-based surrogate gradient (CSNN), CSNN with dynamic postsynaptic potential (Dyn-CSNN), layer-span connecting CSNN (Las-CSNN), and SNN model with all the proposed methods (DlaCSNN-BP) in three image classification and one text classification datasets. The experimental results exhibited that proposed SNN methods could outperform most of the previously proposed SNNs and ANNs in the same network structure. Among them, the proposed DlaCSNN-BP got the best classification performance. This result indicates that our proposed method can effectively improve the effect of SNN in supervised learning and reduce the gap with deep learning. This work also provides more possibilities for putting SNN into practical application. [ABSTRACT FROM AUTHOR]

This paper proposes a particle swarm optimization (PSO) tuned novel proportional integral derivative (PID) like neural network (PSO-PID-NN), to control the temperature of a nonlinear jacketed continuous stirred tank reactor (CSTR). The nonlinear continuous stirred tank reactor (CSTR) plant is one of the most popular reactors in the chemical industry. The proposed structure is elegant in design, having only three neurons in the hidden layer and a single output neuron. The three weights in the neural network's output layer represent the PID controller's proportional, integral, and derivative gains. The suggested approach uses the PSO method to optimize the output layer weights, which corresponds to the PID gains. Mean square error is used as an objective function to optimize the weights. The performance of the proposed PSO-PID-NN controller is tested by comparing the time domain specifications of the output response, against the conventional Zeigler Nichols tuned PID controller and the back propagation-based NN-PID controller (BP-NN-PID). The overshoot in the proposed controller is 23.13%, while it is 26.33% in BP-NN-PID, and 44.13% in Zeigler Nichols tuned PID controller. In addition, the rise time is 0.1283 s, while it is 0.2727 s in the BP-NN-PID controller and 0.2813 s in Zeigler Nichols tuned PID controller. The proposed controller is also tested for disturbance rejection, it was found to be more efficient in rejecting disturbance signals as compared to BP-NN-PID and ZN-tuned PID controllers. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are essential in many areas, from healthcare to environmental monitoring. However, WSNs are vulnerable to routing attacks that might jeopardize network performance and data integrity due to their inherent vulnerabilities. This work suggests a unique method for enhancing WSN security through the detection of routing threats using feed-forward artificial neural networks (ANNs). The proposed solution makes use of ANNs' learning capabilities to model the network's dynamic behavior and recognize routing attacks like black-hole, gray-hole, and wormhole attacks. CICIDS2017 is a heterogeneous dataset that was used to train and test the proposed system in order to guarantee its robustness and adaptability. The system's ability to recognize both known and novel attack patterns enhances its efficacy in real-world deployment. Experimental assessments using an NS2 simulator show how well the proposed method works to improve routing protocol security. The proposed system's performance was assessed using a confusion matrix. The simulation and analysis demonstrated how much better the proposed system performs compared to the existing methods for routing attack detection. With an average detection rate of 99.21% and a high accuracy of 99.49%, the proposed system minimizes the rate of false positives. The study advances secure communication in WSNs and provides a reliable means of protecting sensitive data in resource-constrained settings. [ABSTRACT FROM AUTHOR]

Transformers are the cornerstone of natural language processing and other much more complicated sequential modelling tasks. The training of these models, however, requires an enormous number of computations, with substantial economic and environmental impacts. An accurate estimation of the computational complexity of training would allow us to be aware in advance about the associated latency and energy consumption. Furthermore, with the advent of forward learning workloads, an estimation of the computational complexity of such neural network topologies is required in order to reliably compare backpropagation with these advanced learning procedures. This work describes a mathematical approach, independent from the deployment on a specific target, for estimating the complexity of training a transformer model. Hence, the equations used during backpropagation and forward learning algorithms are derived for each layer and their complexity is expressed in the form of MACCs and FLOPs. By adding all of these together accordingly to their embodiment into a complete topology and the learning rule taken into account, the total complexity of the desired transformer workload can be estimated. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Central South University is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract A four‐degree‐of‐freedom upper limb exoskeleton rehabilitation robot system with a gravity compensation device is constructed. The objective is to address the rehabilitation training needs of patients with upper limb motor dysfunction. A BP neural network adaptive control method based on particle swarm optimization is proposed. First, the degrees of freedom of the human body are analyzed, and a Lagrange method is employed to construct a dynamic model. Second, a particle swarm optimization back propagation neural network adaptive control algorithm based on particle swarm optimization is presented. Subsequently, the range of motion of the upper limbs is analyzed with reference to muscle anatomy and a three‐dimensional motion capture system. And the robot structure design is analyzed in detail. Finally, simulation experiments were conducted, and the results demonstrated that the proposed method exhibited high effectiveness and accuracy.

Abstrak Peristiwa banjir di Kabupaten Sumbawa terjadi hampir setiap tahun. BNBP mencatat telah terjadi sebanyak 80 kali bencana banjir di Kabupaten Sumbawa sejak tahun 2009. Penelitian ini bertujuan untuk menganalisis potensi bencana banjir di Kabupaten Sumbawa berdasarkan data hasil prediksi curah hujan menggunakan metode Artificial Neural Network (ANN) backpropagation. Data historis curah hujan bulanan dari Juni 2009 sampai Mei 2024 digunakan untuk melatih dan menguji model ANN. Hasil prediksi menunjukkan periode kritis terjadi pada Februari 2025 yang mengindikasikan potensi banjir yang tinggi. Penelitian ini mengusulkan strategi mitigasi yang meliputi peningkatan sistem pemantauan cuaca, edukasi publik, reforestasi, dan pembangunan infrastruktur hijau. Kolaborasi antara pemerintah, masyarakat, dan lembaga penelitian ditekankan sebagai kunci untuk mengurangi risiko dan dampak banjir.

Electric power steering (EPS) poses significant control challenges in autonomous vehicles due to their inherent complexity and non-linearity. This study explores the application of artificial neural network (ANN) to address these limitations. Two approaches are proposed: 1) an ANN-based identifier utilizing the backpropagation (BP) algorithm to learn the system’s non-linear dynamics, and 2) an ANN-based controller leveraging the Levenberg-Marquardt (LM) algorithm to improve control performance. Our findings demonstrate the efficacy of the proposed ANN-based BP algorithm in EPS system identification achieving over 99.6% accuracy in predicting EPS system dynamics compared to the traditional approach. Additionally, the LM-learned ANN-based controller aiming a faster response and precise reference tracking compared to the traditional controller method. These advancements underscore the potential of employing ANN methodologies to optimize EPS performance in autonomous vehicles.

While backpropagation (BP) algorithm has been pivotal in enabling the success of modern deep learning technologies, it encounters challenges related to computational inefficiency and biological implausibility. Especially, the sequential propagation of error signals using forward weights in BP is not biologically plausible and prevents efficient parallel updates of learning parameters. To solve these problems, the direct feedback alignment (DFA) method is proposed to directly propagate the error signal from output layer to each hidden layer through random feedback weight, but the performance of DFA is still not competent to BP, especially in complicate tasks with large number of outputs and the convolutional neural network models. In this paper, we propose a method to adjust the feedback weights in DFA using additional local modules that are connected to the hidden layers. The local module attached to each hidden layer has a single-layer structure and learns to mimic the final output of the network. Then, the weights of a local module behave like a direct path connecting each hidden layer to the network output, which has an inverse relationship to the direct feedback weights of DFA. We use this relationship to update the feedback weight of DFA. From the experimental investigation, we confirm that the proposed adaptive feedback weights improve the alignment of the error signal of DFA with that of BP. Furthermore, comparative experiments show that the proposed method significantly outperforms the original DFA on well-known benchmark datasets. The code used for the experiments is available at https://github.com/leibniz21c/direct-feedback-learning-with-local-alignment-support.

Backpropagation neural networks are commonly utilized to solve complicated issues in various disciplines. However, optimizing their settings remains a significant task. Traditional gradient-based optimization methods, such as stochastic gradient descent (SGD), often exhibit slow convergence and hyperparameter sensitivity. An adaptive stochastic conjugate gradient (ASCG) optimization strategy for backpropagation neural networks is proposed in this study. ASCG combines the advantages of stochastic optimization and conjugate gradient techniques to increase training efficiency and convergence speed. Based on the observed gradients, the algorithm adaptively calculates the learning rate and search direction at each iteration, allowing for quicker convergence and greater generalization. Experimental findings on benchmark datasets show that ASCG optimization outperforms standard optimization techniques regarding convergence time and model performance. The proposed ASCG algorithm provides a viable method for improving the training process of backpropagation neural networks, making them more successful in tackling complicated problems across several domains. As a result, the information for initial seeds formed while the model is being trained grows. The coordinated efforts of ASCG’s Conjugate Gradient and ASCG components improve learning and achieve global minima. Our results indicate that our ASCG algorithm achieves 21 percent higher accuracy on the HMT dataset and performs better than existing methods on other datasets(DIR-Lab dataset). The experimentation revealed that the conjugate gradient has an efficiency of 95 percent when utilizing the principal component analysis features, compared to 94 percent when using the correlation heatmap features selection approach with MSE of 0.0678.