Expert Systems with Applications最新文献

筛选
英文 中文
PEGNN: Peripheral-Enhanced graph neural network for social bot detection
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-01 DOI: 10.1016/j.eswa.2025.127294
Qitian Guyan , Yaowen Liu , Jing Liu , Peng Zhang
{"title":"PEGNN: Peripheral-Enhanced graph neural network for social bot detection","authors":"Qitian Guyan ,&nbsp;Yaowen Liu ,&nbsp;Jing Liu ,&nbsp;Peng Zhang","doi":"10.1016/j.eswa.2025.127294","DOIUrl":"10.1016/j.eswa.2025.127294","url":null,"abstract":"<div><div>The development of social networks plays a stronger role in the increased importance of social bot detection. One of the most common existing graph-based detection methods is graph neural networks (GNNs). However, researchers mainly focus on the improvement of GNN architecture while neglecting the in-depth analysis of social network structure. In this paper, after in-depth analysis of the social graph structure, it demonstrate that there exists a graph stratification phenomenon, i.e., the social graph is divided into central and peripheral layers according to its topology. Based on this phenomenon, the idea that the social robot detection task should focus on the central node is proposed, and the existing detection task is adapted to a central node classification task. The task is then further investigated, and the Peripheral-Enhanced Graph Neural Network (PEGNN) framework is proposed to tackle the problem that existing frameworks cannot effectively utilize the information of peripheral networks. PEGNN effectively utilizes the information of peripheral networks via the synergistic effect of three losses. Eventually, the graph stratification phenomenon is verified on two datasets, and the original task is adjusted for central node classification to verify the enhancement effect of PEGNN. The experimental results exhibit that PEGNN obviously improves the model performance. On Twibot-20, the average improvement in accuracy is 1.30%, and the average improvement in F1 score is 1.37%; on Twibot-22, the average improvement in accuracy is 2.46%, the average improvement in F1 score is 5.91%; apparently, other metrics also show obvious improvement.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"278 ","pages":"Article 127294"},"PeriodicalIF":7.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A model-free and finite-time active disturbance rejection control method with parameter optimization
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-01 DOI: 10.1016/j.eswa.2025.127370
Zhen Zhang , Yinan Guo , Song Zhu , Feng Jiao , Dunwei Gong , Xianfang Song
{"title":"A model-free and finite-time active disturbance rejection control method with parameter optimization","authors":"Zhen Zhang ,&nbsp;Yinan Guo ,&nbsp;Song Zhu ,&nbsp;Feng Jiao ,&nbsp;Dunwei Gong ,&nbsp;Xianfang Song","doi":"10.1016/j.eswa.2025.127370","DOIUrl":"10.1016/j.eswa.2025.127370","url":null,"abstract":"<div><div>In the field of control, although active disturbance rejection control does not rely on the precise system models, it has not achieved completely model-free control. Moreover, this method also faces challenges such as complex structure and difficult parameter tuning. In view of this, a novel model-free and finite-time active disturbance rejection control method based on parameter optimization and filter is proposed in this paper. First, an improved second-order linear extended state observer is proposed based on the tracking error. The proposed observer can not only achieve complete model-free operation and a concise construction, but also synergistically improve the system tracking and estimation performance. Second, a feedback control law is presented based on the outputs of the proposed observer and the specifically designed filter. This control law reduces the computational complexity and avoids the high-frequency chattering phenomenon of the error-feedback control law based on transient process. Third, the system controller is constructed by compensating for the disturbance estimated by the proposed observer in the designed feedback control law. Following that, the finite-time convergence of the proposed observer and the system tracking error under the proposed controller is proven based on the Lyapunov stability theory. Fourth, the parameters of the proposed control method are tuned based on particle swarm optimization algorithm with the specifically designed objective function. Compared with the traditional trial-and-error method, this optimization strategy improves the efficiency and effectiveness of parameter tuning. Finally, simulation experiments have been carried on to compare the control performance among the proposed method and its four variants, as well as four state-of-art controllers. Also, the effectiveness and superiority of the newly-designed strategies are further verified.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"278 ","pages":"Article 127370"},"PeriodicalIF":7.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Cross-dataset EEG emotion recognition based on pre-trained Vision Transformer considering emotional sensitivity diversity
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-01 DOI: 10.1016/j.eswa.2025.127348
Fang Wang , Yu-Chu Tian , Xiaobo Zhou
{"title":"Cross-dataset EEG emotion recognition based on pre-trained Vision Transformer considering emotional sensitivity diversity","authors":"Fang Wang ,&nbsp;Yu-Chu Tian ,&nbsp;Xiaobo Zhou","doi":"10.1016/j.eswa.2025.127348","DOIUrl":"10.1016/j.eswa.2025.127348","url":null,"abstract":"<div><div>As a crucial task in brain–computer interfaces, emotion recognition helps develop a profound understanding of human behaviour and mental health. Despite the development of various methods for EEG (electroencephalograph) emotion recognition, designing a model for effective cross-dataset emotion recognition remains challenging. To tackle this challenge, a transfer learning framework is introduced, which is referred to as Pre-trained Encoder from Sensitive Data (PESD). It involves a pre-training model on subjects with the highest emotional sensitivity. The trained model is then transferred to other datasets and subjects through a combination of three data alignment strategies: Mixup, Triplet loss, and Domain discriminator. The model is evaluated on four public datasets (SEED, SEED-IV, DEAP, and FACED) to achieve cross-dataset emotion recognition across all these four datasets. The highest accuracy results are 93.14% (SEED), 83.18% (SEED-IV), 93.53% (DEAP), and 92.55% (FACED), respectively. These results demonstrate significant improvement of our approach over existing ones in cross-dataset emotion recognition. The source code of this work is publicly available at <span><span>https://github.com/fangwangeeg/PESD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"279 ","pages":"Article 127348"},"PeriodicalIF":7.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Semantic distillation and enhanced diagnostic alignment: A novel approach for depression detection in social media
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-01 DOI: 10.1016/j.eswa.2025.127346
Yu Su , Xiangyu Zheng , Junyu Lu , Yi Gong , Qijuan Gao , Shuanghong Shen , Qi Liu
{"title":"Semantic distillation and enhanced diagnostic alignment: A novel approach for depression detection in social media","authors":"Yu Su ,&nbsp;Xiangyu Zheng ,&nbsp;Junyu Lu ,&nbsp;Yi Gong ,&nbsp;Qijuan Gao ,&nbsp;Shuanghong Shen ,&nbsp;Qi Liu","doi":"10.1016/j.eswa.2025.127346","DOIUrl":"10.1016/j.eswa.2025.127346","url":null,"abstract":"<div><div>The growing prevalence of depression underscores the need for accessible detection methods. Social media provides an invaluable platform for identifying signs of depression, overcoming the limitations of traditional assessments. However, this task is fraught with challenges such as noisy data, insufficient labeled datasets, and limited integration of domain-specific knowledge, which hinder the effectiveness of existing models. To address these issues, we propose a novel framework consisting of three key components. First, the Unsupervised Multi-Layer Information Distillation Module employs unsupervised learning techniques to extract meaningful posts from noisy social media data. Second, the Domain Knowledge Enhancement Module with a Memory Update Mechanism addresses the challenge of sparse labeled data by incorporating continuous learning and integrating domain-specific knowledge. Finally, the mIRT-based User Depression Diagnosis Module utilizes multidimensional item response theory (mIRT) to assess symptom severity across multiple dimensions, enhancing the interpretability of the depression diagnosis. Experiments conducted on two real-world datasets demonstrate the effectiveness of our model, achieving accuracies of 97.45% and 94.54%. This framework improves both the accuracy and interpretability of social media-based depression detection, offering a promising solution for mental health monitoring.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"279 ","pages":"Article 127346"},"PeriodicalIF":7.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Asymmetrical siamese network for point clouds normal estimation
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-04-01 DOI: 10.1016/j.eswa.2025.127401
Wei Jin , Jun Zhou , Nannan Li , Haba Madeline , Xiuping Liu
{"title":"Asymmetrical siamese network for point clouds normal estimation","authors":"Wei Jin ,&nbsp;Jun Zhou ,&nbsp;Nannan Li ,&nbsp;Haba Madeline ,&nbsp;Xiuping Liu","doi":"10.1016/j.eswa.2025.127401","DOIUrl":"10.1016/j.eswa.2025.127401","url":null,"abstract":"<div><div>In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with different noise scales remains unexplored, resulting in poor performance in cross-domain scenarios. In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture. By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation. Moreover, we introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels. Evaluation of existing methods on this new dataset reveals their inability to adapt to different types of shapes, indicating a degree of overfitting. Extensive experiments show that the proposed dataset poses significant challenges for point cloud normal estimation and that our feature constraint mechanism effectively improves upon existing methods and reduces overfitting in current architectures.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"279 ","pages":"Article 127401"},"PeriodicalIF":7.5,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multimodal selective state space model-based time series classification for electricity theft detection
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-03-31 DOI: 10.1016/j.eswa.2025.127364
Wanghu Chen , Long Li , Jing Li
{"title":"Multimodal selective state space model-based time series classification for electricity theft detection","authors":"Wanghu Chen ,&nbsp;Long Li ,&nbsp;Jing Li","doi":"10.1016/j.eswa.2025.127364","DOIUrl":"10.1016/j.eswa.2025.127364","url":null,"abstract":"<div><div>In smart grids, electricity theft detection is essential for ensuring power system security and minimizing revenue losses, causing global annual losses of approximately USD 89.3 billion in the utility sector. While deep learning-based approaches have demonstrated effectiveness in utilizing users’ electricity consumption records, formulated as time series, challenges persist in balancing performance and time complexity when processing long time series. Meanwhile, the extraction of long-range temporal dependencies, especially with non-uniform sequence lengths, requires improvement. We propose a novel Multimodal Mamba Model-based Time Series Classification approach (MMM4TSC), which integrates the selective state space of Mamba with the Relative Position Matrix (RPM). This innovation transforms non-stationary time series data into two-dimensional images, thereby enhancing spatial feature and long-range temporal feature extraction. The proposed Multimodal Mamba Layer effectively extracts features from both the original time series and its 2D image representation through sub-channel splitting, while enhancing long-range temporal feature learning by incorporating channel dependencies and multi-scale context. Comprehensive evaluations are conducted on 128 public UCR datasets and a real-world electricity consumption dataset. Experiments demonstrate that MMM4TSC exhibits strong adaptability in handling time series classification tasks of varying lengths, achieving an accuracy of 96.9%, along with an AUC of 0.994 and an F1-score of 0.963 in electricity theft detection, outperforming state-of-the-art time series classification methods and existing electricity detection approaches. Furthermore, MMM4TSC strikes an excellent balance between classification accuracy and computational efficiency, with an 84.2% reduction in model parameters.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"278 ","pages":"Article 127364"},"PeriodicalIF":7.5,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimization control of spacecraft proximation based on r-domination adaptive bare-bones particle swarm optimization algorithm
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-03-31 DOI: 10.1016/j.eswa.2025.127269
Zhihao Zhu , Yu Guo , Zhi Gao
{"title":"Optimization control of spacecraft proximation based on r-domination adaptive bare-bones particle swarm optimization algorithm","authors":"Zhihao Zhu ,&nbsp;Yu Guo ,&nbsp;Zhi Gao","doi":"10.1016/j.eswa.2025.127269","DOIUrl":"10.1016/j.eswa.2025.127269","url":null,"abstract":"<div><div>This paper proposes a novel finite-time (FT) optimization control approach of spacecraft proximation based on a new r-domination adaptive bare-bones multi-objective particle swarm optimization scheme (r-ABBMOPSO). Specifically, a new adaptive particle update strategy is developed for bare-bones multi-objective particle swarm optimization algorithm (BBMOPSO) to enhance the robustness of the search. To make the search toward the desired point, r-ABBMOPSO applies r-domination to replace Pareto-domination. In addition, a new adaptive mutation algorithm is designed to strong the population search diversity. By virtue of r-ABBMOPSO to obtain the optimal control parameters, a FT six degrees of freedom (6-DOF) proximation controller with the adaptive update laws of the unknown parameters is proposed to regulate chaser spacecraft approach to target spacecraft. Finally, numerical comparison examples illustrate the performance of the proposed optimization controller.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"278 ","pages":"Article 127269"},"PeriodicalIF":7.5,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dynamic heterogeneous graph representation based on adaptive negative sample mining via high-fidelity instances and context-aware uncertainty learning
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-03-31 DOI: 10.1016/j.eswa.2025.127291
Wenhao Bai, Liqing Qiu, Weidong Zhao
{"title":"Dynamic heterogeneous graph representation based on adaptive negative sample mining via high-fidelity instances and context-aware uncertainty learning","authors":"Wenhao Bai,&nbsp;Liqing Qiu,&nbsp;Weidong Zhao","doi":"10.1016/j.eswa.2025.127291","DOIUrl":"10.1016/j.eswa.2025.127291","url":null,"abstract":"<div><div>Graph contrastive learning is a self-supervised learning method widely used in dynamic heterogeneous graph representation in recent years, demonstrating great potential and achieving excellent results. However, most graph contrastive learning methods randomly select negative samples and treat all negative samples as equally important to the model. This ignores that some negative samples can provide more information due to their closer proximity to positive samples in the feature space or higher semantic similarity. Therefore, this paper proposes a <strong>HCUAN</strong> model that aims to utilize <u><strong>h</strong></u>igh-fidelity anchor instances and corresponding positive and negative samples for <u><strong>c</strong></u>ontext-aware <u><strong>u</strong></u>ncertainty learning to <u><strong>a</strong></u>daptively mine prioritized <u><strong>n</strong></u>egative samples, which in turn improves the performance of graph contrastive learning. Specifically, the HCUAN first designs a new GNN encoder (LGE) for generating high-fidelity anchor instances and corresponding positive and negative samples, which efficiently fuses between local and global information to prevents the introduction of easy negative samples and enhance the model’s discriminative ability. Then, the HCUAN utilizes an uncertainty discriminator to perform an adaptive assessment of the correlation between each negative sample and the anchor instance, which provides more accurate references for graph contrastive learning, thus helping the model to distinguish the really prioritized negative samples more clearly. Next, the HCUAN designs an unified graph contrastive learning, which incorporates the modeling method of dynamic heterogeneous graphs in graph contrastive learning, the method of generating high-fidelity anchor instances and corresponding positive and negative samples, and the method of prioritized negative samples mining in the form of modules into the traditional processes of graph contrastive learning. Each module in the unified graph contrastive learning can be disassembled and updated according to the needs of the task, providing powerful flexibility and scalability for practical applications. Finally, numerous experiments on twelve datasets show that HCUAN can significantly improve the performance of graph contrastive learning.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"278 ","pages":"Article 127291"},"PeriodicalIF":7.5,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CAMAF: Context-Aware Multimodal Alignment Framework for explainable lung disease risk stratification
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-03-31 DOI: 10.1016/j.eswa.2025.127398
Subba Rao Dusari, Nagendra Panini Challa
{"title":"CAMAF: Context-Aware Multimodal Alignment Framework for explainable lung disease risk stratification","authors":"Subba Rao Dusari,&nbsp;Nagendra Panini Challa","doi":"10.1016/j.eswa.2025.127398","DOIUrl":"10.1016/j.eswa.2025.127398","url":null,"abstract":"<div><div>Lung disease remains a leading cause of morbidity and mortality worldwide, necessitating early and accurate risk stratification to improve patient outcomes. Existing approaches rely on either clinical data or imaging modalities independently, limiting their ability to capture the intricate interactions between structured and unstructured information. To overcome this limitation, we propose the Context-Aware Multimodal Alignment Framework (CAMAF), a novel AI-driven approach that dynamically integrates structured clinical data from the MIMIC-IV dataset and unstructured imaging data from the CheXpert dataset for context-aware and interpretable lung disease risk stratification. Unlike conventional multimodal fusion techniques, CAMAF introduces a Context-Gated Attention (CGA) mechanism, which adaptively aligns modality contributions based on patient-specific contexts. Additionally, CAMAF employs TabTransformer and Vision Transformer (ViT) for high-fidelity feature extraction and leverages a Transformer Encoder for enhanced multimodal fusion, ensuring superior predictive performance. Experimental results demonstrate the efficacy of CAMAF, achieving 92.78% accuracy and 0.9457 AUC-ROC, outperforming state-of-the-art machine learning baselines and traditional clinical risk scores (e.g., CURB-65, BODE Index). Robustness analysis highlights its ability to maintain performance under noisy and missing data conditions, while SHAP and Grad-CAM provide interpretable explanations for clinical decision-making. Despite its advantages, CAMAF faces challenges in handling rare pathologies, which can be addressed through data augmentation and transfer learning. This work establishes CAMAF as a novel, clinically viable AI framework, bridging the gap between multimodal data integration, interpretability, and real-world clinical applicability in lung disease risk stratification.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"279 ","pages":"Article 127398"},"PeriodicalIF":7.5,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A parallel approach to accelerate neural network hyperparameter selection for energy forecasting
IF 7.5 1区 计算机科学
Expert Systems with Applications Pub Date : 2025-03-31 DOI: 10.1016/j.eswa.2025.127386
D. Criado-Ramón , L.G.B. Ruiz , M.C. Pegalajar
{"title":"A parallel approach to accelerate neural network hyperparameter selection for energy forecasting","authors":"D. Criado-Ramón ,&nbsp;L.G.B. Ruiz ,&nbsp;M.C. Pegalajar","doi":"10.1016/j.eswa.2025.127386","DOIUrl":"10.1016/j.eswa.2025.127386","url":null,"abstract":"<div><div>Finding the optimal hyperparameters of a neural network is a challenging task, usually done through a trial-and-error approach. Given the complexity of just training one neural network, particularly those with complex architectures and large input sizes, many implementations accelerated with GPU (Graphics Processing Unit) and distributed and parallel technologies have come to light over the past decade. However, whenever the complexity of the neural network used is simple and the number of features per sample is small, these implementations become lackluster and provide almost no benefit from just using the CPU (Central Processing Unit). As such, in this paper, we propose a novel parallelized approach that leverages GPU resources to simultaneously train multiple neural networks with different hyperparameters, maximizing resource utilization for smaller networks. The proposed method is evaluated on energy demand datasets from Spain and Uruguay, demonstrating consistent speedups of up to 1164x over TensorFlow and 410x over PyTorch.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"279 ","pages":"Article 127386"},"PeriodicalIF":7.5,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信