Applied Soft Computing最新文献

{"title":"A multi-objective evolutionary algorithm with constraint-compliant initialization for energy transport and urban logistics in Electric Vehicle Routing","authors":"Yue Xie ,&nbsp;Kai-Fung Chu ,&nbsp;Albert Y.S. Lam ,&nbsp;Fumiya Iida","doi":"10.1016/j.asoc.2025.113624","DOIUrl":"10.1016/j.asoc.2025.113624","url":null,"abstract":"<div><div>Electric vehicles (EVs) offer a new opportunity to enhance the efficiency of both transportation logistics and energy distribution. Integrating these dual objectives introduces complex optimization challenges due to interdependent constraints. This paper addresses the Vehicle Routing Problem with Time Windows integrated with Energy Transport (VRPTW-ET), where a fleet of EVs is used to serve customer demands while simultaneously transporting energy to (dis)charging facilities. We formulate the problem as a multi-objective optimization problem and design an evolutionary algorithm based on NSGA-II, featuring constraint-aware initialization and problem-specific operators for routing, time windows, and energy logistics. Our approach operates under realistic simplification, including static energy demands and travel costs, which help isolate the core challenges of the problem. Experimental results on modified benchmarks show that the proposed integrated approach consistently outperforms decoupled baselines, achieving up to 30% reduction in energy costs and 20% fewer vehicles used. These findings demonstrate the effectiveness of coordinated logistics-energy strategies in promoting cost-efficient and sustainable urban mobility.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113624"},"PeriodicalIF":7.2,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714380","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}

{"title":"A selective memory attention mechanism for chaotic wind speed time series prediction with auxiliary variable","authors":"Ke Fu,&nbsp;Shengli Chen,&nbsp;Zhengru Ren","doi":"10.1016/j.asoc.2025.113579","DOIUrl":"10.1016/j.asoc.2025.113579","url":null,"abstract":"<div><div>Wind speed prediction is crucial for enhancing wind energy utilization and optimizing grid integration of wind power. Its chaotic nature and the lack of correlated variables make accurate prediction difficult. Most studies rely solely on past wind speed, limiting accuracy improvements. While wind power is highly correlated with wind speed, this correlation is reversely causal. The key challenge is effectively leveraging this reverse causality between wind power and wind speed to enhance prediction precision. This study proposed SMAMnet to address the challenge mentioned, a model that establishes its backbone network via proposed new attention mechanism. The convolution operation is employed to restructure features, besides, the frequency-domain transformation and selective state space model (SSM) serves for attention weights. The novelty of SMAMnet is characterized by the development of an adaptive frequency-domain selected attention weight operator to adaptively parse meaningful information in different frequency domain intervals. Taking 15 min and 1-hour mean absolute error as the standard, the actual wind speed prediction error is reduced by 68% and 49% compared with the classic LSTM algorithm. The feasibility of mining reverse causality to improve prediction accuracy was verified.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113579"},"PeriodicalIF":7.2,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711437","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}

{"title":"Disentangled Multi-view Graph Neural Network for multilingual knowledge graph completion","authors":"Bingbing Dong ,&nbsp;Chenyang Bu ,&nbsp;Ye Wang ,&nbsp;Yi Zhu ,&nbsp;Xindong Wu","doi":"10.1016/j.asoc.2025.113605","DOIUrl":"10.1016/j.asoc.2025.113605","url":null,"abstract":"<div><div>Multilingual knowledge graph completion (MKGC) uses limited seed pairs from diverse knowledge graphs (KGs) to enrich and complete a target KG. Unlike traditional knowledge graph completion (KGC) tasks that focus on a single KG, MKGC deals with multiple KGs described by diverse languages, imposing a higher level of heterogeneity due to the varying semantic meanings, syntactic structures, and regular expressions across different languages. Existing MKGC methods mainly rely on an end-to-end embedding function that maps multiple KGs into a shared latent space, using relation-aware graph neural networks (GNNs) to unify the contents of entities and relations with respect to their topological structures. However, such methods might not fully exploit the heterogeneity of multilingual KGs, as they overlook inherent details related to neighborhood entities and relations. To address these limitations, we propose a novel <strong>D</strong>isentangled <strong>M</strong>ulti-view <strong>G</strong>raph <strong>N</strong>eural <strong>N</strong>etwork (DMGNN) for MKGC. Specifically, our approach consists of two multi-view GNN modules: MKGC and multilingual KG alignment (MKGA) to facilitate knowledge transfer. Notably, DMGNN effectively captures the heterogeneity of multilingual KGs by learning graph features from three distinct views: entities, relations, and triples. Moreover, we introduce a disentangling mechanism wherein separate GNNs are employed to learn features from different views, mitigating feature interference. In addition, we incorporate an attention mechanism on each view GNN to distinguish the importance of neighborhood features. Extensive experiments on public multilingual datasets demonstrate the superiority of our proposed model over existing competitive baselines.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113605"},"PeriodicalIF":7.2,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703050","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}

{"title":"A soft sensor net based on the symplectic decomposition-global attention reconstruction architecture for biopharmaceutical industry","authors":"Simengxu Qiao,&nbsp;Yichen Song,&nbsp;Qunshan He,&nbsp;Shifan Chen,&nbsp;He Zhang,&nbsp;Xinggao Liu","doi":"10.1016/j.asoc.2025.113636","DOIUrl":"10.1016/j.asoc.2025.113636","url":null,"abstract":"<div><div>Non-linearity, time-varying properties, and high noise levels in biopharmaceutical process data have been recognized as critical factors affecting the accuracy of data-driven soft sensors. To address these issues and enhance prediction precision, we introduce BPSN, an innovative soft sensor framework grounded in the symplectic decomposition-global attention reconstruction architecture. Symplectic geometry mode decomposition effectively adapts to data complexity and reduces noise. A reconstruction module combines global attention mechanism and reversible instance normalization to enhance sharp signal features via Manhattan distance while addressing internal drift. Experiments show that the proposed soft sensor model outperforms state-of-the-art models in predicting key indicators: bacterial concentration, viscosity, and reducing sugar content in the erythromycin fermentation process. This illustrates its practical applicability and exceptional performance in biopharmaceutical industry. The source code is available at: <span><span>https://github.com/Joss0623/BioPharmaSoftNet.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113636"},"PeriodicalIF":7.2,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703051","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}

{"title":"Common neighbor-aware link weight prediction with simplified graph transformer","authors":"Lizhi Liu","doi":"10.1016/j.asoc.2025.113614","DOIUrl":"10.1016/j.asoc.2025.113614","url":null,"abstract":"<div><div>The link weight prediction holds significant importance in various fields, yet it has been less explored. Building a superior model faces two major challenges. First, the classic graph neural network can only propagate information along the adjacency connections due to the message-passing paradigm. When some edges are unobserved, learning better node representations is hindered. Second, existing methods often condense the local topological patterns into link representations by either graph pooling on enclosing subgraphs or handcrafted feature indices. The former incurs a heavy computational burden while the latter lacks flexibility. To address these challenges, we present a novel link weight prediction algorithm named CoNe. We design a simplified graph Transformer with linear complexity to simultaneously capture local and global topological structure information. Specifically, CoNe leverages a novel simplified global attention mechanism, allowing interactions to no longer be hardwired in static edges but to be flexibly and efficiently extended to arbitrary nodes. Furthermore, we propose self-attentive common neighbor aggregation to embed link heuristics into learnable pairwise representations. Experiments on real-world datasets demonstrate that CoNe outperforms state-of-the-art methods with 0.51%–14.67% improvements.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113614"},"PeriodicalIF":7.2,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694366","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}

{"title":"Change detection in remote sensing images based on multi-tree genetic programming","authors":"Ying Bi ,&nbsp;Tuo Zhang ,&nbsp;Jintao Lian ,&nbsp;Yaxin Chang ,&nbsp;Jing Liang","doi":"10.1016/j.asoc.2025.113609","DOIUrl":"10.1016/j.asoc.2025.113609","url":null,"abstract":"<div><div>Change detection in remote sensing images plays a crucial role in applications such as environmental monitoring, urban planning, and disaster management. Accurately identifying and distinguishing changed areas within complex image data poses significant challenges. Existing methods often struggle with high false-positive rates and limited adaptability. This paper introduces a novel approach using multi-tree genetic programming (GP) to automate the construction of ensembles for change detection in remote sensing images. The method employs a unique multi-tree GP representation comprising three distinct trees that utilize difference, spectral, and texture features to identify changes. These trees are combined into an ensemble using a majority voting strategy to make predictions. The approach integrates multi-tree crossover and mutation strategies to generate new individuals, which are evaluated based on a fitness function derived from classification accuracy. To validate its effectiveness, the proposed multi-tree GP approach is evaluated on four benchmark datasets (SZTAKI, EGY_BCD, LEVIR_CD+, and S2Looking) and compared with eight methods. In most cases, the proposed approach achieves higher maximum change detection accuracy. Notably, on the SZTAKI dataset (Img_10), it achieves an accuracy of 96.11%, representing a 5.55% improvement over the worst baseline (KNN) and a 0.55% gain over the best baseline (SpectralFormer). Experimental results demonstrate that the proposed approach outperforms standard GP, as well as several classic classifiers and neural network based methods, establishing it as an effective tool for remote sensing change detection. The method’s capability of to leverage diverse features and integrate them through ensemble learning underscores its potential in enhancing change detection accuracy using remote sensing imagery.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113609"},"PeriodicalIF":7.2,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714382","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}

{"title":"Enhancing EEG-based individual-generic emotion recognition through invariant sparse patterns extracted from ongoing affective processes","authors":"Yiwen Zhu ,&nbsp;Jiehao Tang ,&nbsp;Hongjuan Wei ,&nbsp;Kaiyu Gan ,&nbsp;Jianhua Zhang ,&nbsp;Zhong Yin","doi":"10.1016/j.asoc.2025.113659","DOIUrl":"10.1016/j.asoc.2025.113659","url":null,"abstract":"<div><div>Emotional responses to stimuli produce distinct brain activity patterns that are often sparse in time and spatial distribution across the cortex. These neural signals also contain individual-specific features, complicating emotion recognition across diverse populations. Current approaches rarely address the dual challenge of capturing sparse emotional patterns while minimizing identity-related biases in individual-generic emotion analysis. To bridge this gap, we propose a graph-based emotion-enhancing network framework that isolates emotion-specific neural signatures by amplifying sparse temporal-spatial features and suppressing person-specific biomarkers. Evaluated on two benchmark databases for binary emotion classification, our model achieved state-of-the-art performance in individual-dependent scenarios with accuracies of 65.76 % and 65.39 % for the arousal scale, and 57.75 % and 66.74 % for the valence scale. In the individual-generic condition, the accuracies were 56.11 % and 61.02 % for arousal, and 55.21 % and 66.17 % for valence. Notably, the model’s temporal and spatial enhancement modules provide interpretable insights into emotion-related neural sparsity through learned feature weights. This framework advances emotion recognition systems by reliably identifying universal emotional patterns across individuals while improving computational generalizability.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113659"},"PeriodicalIF":7.2,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711436","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}

{"title":"A double-convolution-double-attention Transformer network for aircraft cargo hold fire detection","authors":"Hai Li ,&nbsp;Zhen-Song Chen ,&nbsp;Sheng-Hua Xiong ,&nbsp;Peng Sun ,&nbsp;Hai-Ming Zhang","doi":"10.1016/j.asoc.2025.113622","DOIUrl":"10.1016/j.asoc.2025.113622","url":null,"abstract":"<div><div>Traditional smoke and gas detection systems in aircraft cargo compartments tend to have high false-alarm rates, and deep learning models reliant on video imagery tend to entail substantial computation. This paper introduces a transfer learning approach, FE-DCDA-Transformer-TL. Color features are used to enhance fire images, so as to improve the recognition of fire smoke and flame targets. The Transformer network is simplified and combined with dual convolution and dual attention mechanism modules. Dual convolution reduces the number of structural parameters of the Transformer network, and dual attention enhances the features of fire smoke and flame. FE-DCDA-Transformer-TL is trained and evaluated on a custom aircraft cargo compartment fire dataset, and tested on a similar dataset. In experiments, the proposed model achieves 97.69% accuracy, 98% precision, 96.7% recall, an F1-score of 97.34%, 0.98 AUC, 3.44G FLOPS, 21.54M Params, and 0.61 FPS. Compared with state-of-the-art methods, the proposed model improves accuracy, precision, and recall by at least 32.91%, 28.60%, and 16.94%, respectively. FE-DCDA-Transformer-TL effectively solves the accuracy problem of aircraft cargo hold fire detection, providing strong support for fire detection.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"183 ","pages":"Article 113622"},"PeriodicalIF":7.2,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703049","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}

{"title":"Enhancing long-tailed software vulnerability type classification via adaptive data augmentation and prompt tuning","authors":"Long Zhang ,&nbsp;Xiaolin Ju ,&nbsp;Lina Gong ,&nbsp;Jiyu Wang ,&nbsp;Zilong Ren","doi":"10.1016/j.asoc.2025.113612","DOIUrl":"10.1016/j.asoc.2025.113612","url":null,"abstract":"<div><div>Software vulnerability type classification (SVTC) is essential for efficient and targeted remediation of vulnerabilities. With the rapid increase in software vulnerabilities, the demand for automated SVTC approaches is becoming increasingly critical. However, the SVTC is significantly affected by the long-tailed issues, where the distribution of vulnerability types is highly unbalanced. Specifically, a small number of head classes contain a large volume of samples, while a substantial portion of tail classes consists of only a limited number of samples. This imbalance poses a significant challenge to the classification accuracy of existing approaches. To alleviate these challenges, we propose an innovative approach VulTC-LTPF, which integrates prompt tuning with long-tailed learning to enhance the effectiveness of SVTC. Within VulTC-LTPF, an adaptive error-rate-based data augmentation strategy is developed. This strategy allows the SVTC model to dynamically augment data for tail classes types with limited sample size during training, thereby mitigating the impact of the long-tailed problem. Furthermore, VulTC-LTPF employs a hybrid prompt tuning strategy, aligning the training process more closely with pre-training, which enhances adaptability to downstream tasks. Unlike existing approaches that rely solely on either vulnerability description or source code, VulTC-LTPF leverages both sources of information. By incorporating a combination of hard and soft prompts, it facilitates a more comprehensive and effective classification strategy. Experimental results demonstrate that VulTC-LTPF achieves substantial performance improvements over four state-of-the-art SVTC baselines, with gains ranging from 26.1% to 55.1% in MCC. Ablation studies further validate the effectiveness of the adaptive data augmentation, prompt tuning, the integration of two types of vulnerability information, and the use of hybrid prompts. These findings highlight that VulTC-LTPF represents a promising advancement in the field of SVTC, offering significant potential for further progress in addressing software vulnerability type classification challenges.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113612"},"PeriodicalIF":7.2,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694365","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}

{"title":"Denoising diffusion spatial-temporal residual multi-graph convolutional network for traffic flow prediction","authors":"Yinxin Bao ,&nbsp;Qinqin Shen ,&nbsp;Jinghan Xue ,&nbsp;Weiping Ding ,&nbsp;Quan Shi","doi":"10.1016/j.asoc.2025.113656","DOIUrl":"10.1016/j.asoc.2025.113656","url":null,"abstract":"<div><div>Real-world traffic flow prediction remains a significant challenge in intelligent transportation systems. Current methods rely heavily on preprocessed noisy data for model training, yet models trained on such smoothed data often fall short in real-world prediction accuracy. This limitation stems from the overly smoothing effect of interpolation and other preprocessing techniques, which lead to the loss of crucial historical features in the noisy data. To address this challenge, a novel <u>D</u>enoising d<u>iff</u>usion <u>S</u>patial-<u>T</u>emporal residual <u>M</u>ulti-<u>G</u>raph convolutional network (DiffSTMG) is proposed for traffic flow prediction. Specifically, DiffSTMG consists of Information Encoding (IE) module, Gated Causal Convolution (GCC) module, Multi-Graph Convolution (MGC) module, Fully Connected (FC) layer and residual connection. The core of the IE module consists of the Denoising Diffusion (DeDiff) module, which is designed to recover the latent features of the noisy data based on diffusion convolution, and the GCC module, which is designed to enhance the temporal features of the noiseless data based on the gating mechanism and the causal convolution. The output of the IE module, after the further enhancement of the temporal features by the GCC module, is passed through the MGC module to obtain the dynamic spatial features. The MGC module is based on the graph convolution network of static and dynamic graphs to further enhance the dynamic spatial features under the influence of historical patterns, locations, and holidays. Extensive experiments on six real-world datasets validate that the DiffSTMG prediction accuracy outperforms state-of-the-art models.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"182 ","pages":"Article 113656"},"PeriodicalIF":7.2,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686385","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}