{"title":"Thinking Innovation Strategy (TIS): A novel mechanism for metaheuristic algorithm design and evolutionary update","authors":"Heming Jia, Xuelian Zhou, Jinrui Zhang","doi":"10.1016/j.asoc.2025.113071","DOIUrl":"10.1016/j.asoc.2025.113071","url":null,"abstract":"<div><div>The metaheuristic optimization algorithm(MHS) is a global optimization method inspired by natural phenomena, demonstrating superior performance in specific application scenarios. Traditional optimization algorithms utilize two main concepts: exploration, to expand the search range, and exploitation, to enhance solution accuracy. However, as problem complexity and application scenarios increase, MHS struggles to balance exploration and exploitation to find the optimal solution. Therefore, this paper introduces innovative characteristics of individual thinking and proposes a new Thinking Innovation Strategy (TIS). TIS does not aim for an optimal solution but seeks global optimization based on successful individuals, enhancing algorithm performance through survival of the fittest. This paper applies TIS strategies to improve various MHS algorithms and evaluates their performance on 57 engineering problems and the IEEE CEC2020 benchmarks. Experimental results indicate that the TIS-enhanced algorithms outperform the original versions across 57 engineering problems, according to Friedman ranking and Wilcoxon rank-sum test results. Some algorithms show significant improvement, demonstrating the feasibility and practicality of TIS for optimization problems. The TIS (LSHADE_SPACMA) of the source code can be accessed through the following ways: https://github.com/LIANLIAN-Serendipity/TIS-</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113071"},"PeriodicalIF":7.2,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724233","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":"Nested deep learning with learned network embeddings for software defect prediction","authors":"Sweta Mehta , Lov Kumar , Sanjay Misra , K.Sridhar Patnaik , Vikram Singh","doi":"10.1016/j.asoc.2025.113057","DOIUrl":"10.1016/j.asoc.2025.113057","url":null,"abstract":"<div><div>Existing software (SW) defect prediction approaches and the models are majorly based on features extracted from the code of the software to build defect datasets for predictive modeling. However, these models fail to sufficiently capture the complex, latent dependencies within the software components, which acts as a hindrance in achieving higher predictive accuracy. This study introduces an improved defect prediction model, the Nested Deep Learning (NDL) model, that leverages network embeddings from call graphs for enhanced representation of intricate hierarchical class dependencies and interactions. This work evaluates six network-embedding algorithms by applying them to call graphs of 10 real software projects, generating embeddings of dimensions 32 and 128. A total of 50 NDL models—with and without dropout layers—are developed, and a comparative evaluation of these models is conducted against traditional classifier-based models. This evaluation demonstrated the superiority of the NDL model with dropout, achieving a mean AUC of 0.87, an 8.98 % improvement over the traditional classifier-based models. Among the evaluated embedding methods, LINE embeddings outperformed others, and integrating network embeddings with software metrics led to a 15.85 % AUC improvement over using software metrics alone. The optimal configuration—combining software metrics with LINE embeddings (dimension 128) in an NDL model with three deep learning layers and dropout—achieved a mean AUC of 0.93, surpassing all other configurations by 3.33–14.81 %<strong>.</strong> This study is the first to validate the effectiveness of a nested deep learning framework for modeling call graph dependencies through network embeddings, providing a scalable and robust approach for improving software defect prediction.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113057"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724712","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}
{"title":"Cancelable binary biometric template generation scheme based on partial walsh transformation and MinHash algorithm","authors":"Shuaichao Song, Yeming Yang, Miao Yu, Yuming Liao, Weilai Guo, Jiyuan Li, Songhui Guo","doi":"10.1016/j.asoc.2025.113049","DOIUrl":"10.1016/j.asoc.2025.113049","url":null,"abstract":"<div><div>With the widespread use of biometrics, biometric templates stored in biometric systems are at serious risk of security and privacy breaches. Cancelable biometric scheme is an effective remedy when many unprotected biometric templates are compromised. We propose a cancelable binary biometric template generation scheme based on the partial Walsh transformation and the MinHash algorithm to improve recognition accuracy and generation efficiency. Firstly, the partial Walsh matrix transforms the high-dimensional original biometric feature into a low-dimensional space. Then, protected cancelable binary biometric templates are generated based on the proposed sliding window grouping minimum hash algorithm SWG-MinHash. Our scheme demonstrates superior recognition accuracy and generation efficiency on fingerprint and face databases compared to existing schemes. Meanwhile, our scheme satisfies the properties of non-invertibility, revocability, and unlinkability, and is resistant to common security and privacy attacks. Therefore, our scheme effectively mitigates the problem of balancing recognition accuracy, security, and generation efficiency of cancelable biometric schemes and is more practical for biometric systems. The source code of our scheme is available at <span><span>https://github.com/sscwrx/cbef</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113049"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724229","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 performance-driven multi-stage KNN approach for local adaptive classification","authors":"Che Xu , Zhenhua Fan","doi":"10.1016/j.asoc.2025.113070","DOIUrl":"10.1016/j.asoc.2025.113070","url":null,"abstract":"<div><div>A key issue of the K-Nearest Neighbors (KNN) algorithm is determining the optimal neighborhood size <em>K</em>, which limits the widespread applicability of KNN. To address this, a performance-driven multi-stage KNN (PMKNN) approach is proposed in this paper. Given a set of alternative <em>K</em> values, the traditional KNN algorithm is initially employed in the PMKNN approach to identify the optimal <em>K</em> values for all known samples. A convex optimization model is then constructed based on the least squares loss function to learn the correlation between known samples and query samples. After the learned correlation is used to evaluate the performances of all candidate <em>K</em> values in classifying query samples, a weighted majority voting process is designed to generate the final classification results. Unlike existing KNN approaches, the proposed PMKNN approach considers multiple optimal <em>K</em> values for each query sample, enhancing classification stability and reliability. The proposed approach also reduces the negative impact of inappropriate <em>K</em> values on classification performance. An experimental study is conducted using twenty real-world classification datasets collected from two public data repositories to assess the effectiveness of the proposed PMKNN approach. The relevant results highlight the high classification performance of the proposed PMKNN approach compared to seven state-of-the-art KNN methods and underscore its predictive stability compared to the traditional KNN algorithm using all possible <em>K</em> values.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113070"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724091","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}
Ahmad Hashemi , Hamed Gholami , Xavier Delorme , Kuan Yew Wong
{"title":"A multidimensional fitness function based heuristic algorithm for set covering problems","authors":"Ahmad Hashemi , Hamed Gholami , Xavier Delorme , Kuan Yew Wong","doi":"10.1016/j.asoc.2025.113038","DOIUrl":"10.1016/j.asoc.2025.113038","url":null,"abstract":"<div><div>The set covering problem (SCP) is a conventional integer programming challenge in combinatorial optimization, with applications spanning fields such as transportation, logistics, and location problems. Solving SCPs efficiently is crucial for optimizing operations in these domains, particularly in location problems, where traditional algorithms often struggle with multidimensional objective spaces. To address such challenges, this study proposes a novel problem-dependent heuristic algorithm to solve SCPs, featuring a new multi-dimensional fitness function, which was evaluated by benchmarking against other heuristic and metaheuristic algorithms. A collection of reproduced and selected OR-library problems of various scales were chosen as benchmark instances to assess the performance of the algorithm. The performance of the algorithm was confirmed as it constructs solutions by leveraging a novel fitness function to address the limitations of time complexity, applicability, and scalability. Computational results demonstrate that the developed algorithm offers competitive solutions for SCPs, showing improvements of up to 88 % and 20 % in terms of time compared to simulated annealing and a preliminary heuristic algorithm, respectively. In terms of quality, the developed algorithm achieved cost reductions of up to 21 % and 11 % compared to these algorithms, respectively.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113038"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687321","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":"Data preprocessing techniques and neural networks for trended time series forecasting","authors":"Ana Lazcano , Miguel A. Jaramillo-Morán","doi":"10.1016/j.asoc.2025.113063","DOIUrl":"10.1016/j.asoc.2025.113063","url":null,"abstract":"<div><div>Research on time series forecasting continues to attract significant attention, particularly in the use of Artificial Neural Networks (ANN) due to their ability to model nonlinear behaviors. However, forecasting economic time series with steep upward trends presents challenges, often leading to poorly fitting predictions. This study addresses the issue by applying differentiation as a preprocessing step. Three real-world time series exhibiting this behavior were analyzed and forecasted using two neural network models—Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP)—with and without preprocessing. The differentiated series were further processed using techniques such as Empirical Mode Decomposition (EMD) and trend-fluctuation decomposition via Moving Average of Wavelet Transform. The results demonstrate that differentiation significantly enhances forecasting accuracy across all tested models, reducing errors by up to 30 % compared to models without preprocessing. This approach effectively mitigates trend-related distortions, leading to more reliable predictions in complex economic time series.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113063"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687320","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}
Fardin Rezaei Zeynali , Mohammad Parvin , Ali Akbar ForouzeshNejad , Emaad Jeyzanibrahimzade , Mohssen Ghanavati-Nejad , AmirReza Tajally
{"title":"A heuristic-based multi-stage machine learning-based model to design a sustainable, resilient, and agile reverse corn supply chain by considering third-party recycling","authors":"Fardin Rezaei Zeynali , Mohammad Parvin , Ali Akbar ForouzeshNejad , Emaad Jeyzanibrahimzade , Mohssen Ghanavati-Nejad , AmirReza Tajally","doi":"10.1016/j.asoc.2025.113042","DOIUrl":"10.1016/j.asoc.2025.113042","url":null,"abstract":"<div><div>This study addresses the reverse supply chain configuration problem for the agri-food sector with agility, resilience, and sustainability aspects. To do this, this article proposes a heuristic-based multi-stage machine learning-based model to design a corn reverse logistics based on agility, resilience, and sustainability features. In this way, at the first stage, the performance of the potential recycling partners is evaluated by combining the Categorical Boosting Algorithm (CatBoost) method. In the next stage, a multi-objective model is suggested to configure the corn reverse logistics in which the resilience, agility, and sustainability dimensions are incorporated. Afterwards, we deal with uncertainty by developing a data-driven method based on the chance-constrained fuzzy programming method and the seasonal autoregressive integrated moving average approach. Finally, by choosing a real-world case study, the suggested model is solved by developing a heuristic-based solution procedure. The obtained results showed that the developed heuristic-based solution approach able to find optimal and near-optimal solution in a reasonable time. Based on the achieved outputs, increasing the capacity parameter has a positive impact in the efficiency of the supply chain. Also, results show that when the amount of the initial waste increases, the total profit and environmental impacts of the supply chain have increased, too. Also, the achieved outputs confirm the robustness and efficiency of the developed machine learning-based approach. Then, several sensitivity analyses are presented to examine the role of the key parameters in the research problem. Finally, the managerial insights are provided.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113042"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698028","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 quantum entanglement-based optimization method for complex expensive engineering problems","authors":"Fengling Peng, Xing Chen","doi":"10.1016/j.asoc.2025.113019","DOIUrl":"10.1016/j.asoc.2025.113019","url":null,"abstract":"<div><div>Due to the computational costliness and time-consuming nature of complex and expensive engineering (CEE) problems, this paper proposes a genetic algorithm based on quantum entanglement to address these challenges. This method encodes individuals into quantum genes, where each gene bit stores not 0 or 1, but a superposition state of both. By leveraging the uncertainty of the superposition state during the collapse, this method effectively preserves population diversity even with a very small population size. A smaller population size implies fewer calls to time-consuming simulations. Additionally, quantum entangled states are created for parts of an individual's gene, utilizing the characteristic that entangled states instantly affect each other upon collapse, to achieve parallel evolution of parts of the genes in multiple individuals. This parallel evolution significantly increases the search speed of the algorithm, thereby reducing the number of iterations. Fewer iterations also mean fewer calls to simulations. Benchmark function experiments demonstrate that the proposed method is significantly superior to other similar algorithms in a 30D solution space with a population size of 20 and also has certain advantages in a 100D solution space.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113019"},"PeriodicalIF":7.2,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687318","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":"Multi-reference super-resolution reconstruction of remote sensing images based on hierarchical similarity mapping","authors":"Fuzhen Zhu , Qi Zhang , Bing Zhu , Chen Wang","doi":"10.1016/j.asoc.2025.113027","DOIUrl":"10.1016/j.asoc.2025.113027","url":null,"abstract":"<div><div>To make full use of the details from multi-reference images and improve the quality of super-resolution reconstruction of remote sensing images, a multi-reference super-resolution reconstruction of remote sensing images based on hierarchical similarity mapping is proposed. It is very important in both military and civilian fields. Firstly, one low resolution image and three reference images are used as the input of VGG network to extract their feature maps at 4 × , 2 × , and 1 × scales. These feature maps at each scale are respectively blocked and used as a set of inputs in subsequent operations. Specifically, the low resolution features are divided into <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>i</mi></mrow></msub></math></span>blocks, and each block is further divided into <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>c</mi></mrow></msub></math></span>sub-feature-blocks. And the <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>m</mi></mrow></msub></math></span>reference image features are divided into <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>r</mi></mrow></msub></math></span> sub-feature-blocks. Then the <span><math><msub><mrow><mi>N</mi></mrow><mrow><mi>c</mi></mrow></msub></math></span>low-resolution sub-feature blocks are mapped for similarity with the reference features within the range of all reference sub-feature blocks, individual reference features, and all reference image features. The outputs of each layer are then iteratively mapped with the low-resolution features as inputs for next layers. Thus the final features include information from all the reference images and low-resolution image. Subsequently, an adaptive transfer module with multi-reference features and channel attention is used to match and transfer the information of each reference image, while achieving edge smoothing and noise filtering between different reference features. Finally, the quadruple super-resolution reconstruct result is got from the multi-scale feature fusion module and decoder. Experimental results show that our improvements can reconstruct better super-resolution results with more details for utilizing information of multi-reference images, which is superior to single image super-resolution methods and single reference super-resolution methods.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113027"},"PeriodicalIF":7.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724733","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}
Dongxu Cheng , Zifang Zhou , Hao Li , Jingwen Zhang , Yan Yang
{"title":"A morphological difference and statistically sparse transformer-based deep neural network for medical image segmentation","authors":"Dongxu Cheng , Zifang Zhou , Hao Li , Jingwen Zhang , Yan Yang","doi":"10.1016/j.asoc.2025.113052","DOIUrl":"10.1016/j.asoc.2025.113052","url":null,"abstract":"<div><div>Medical image segmentation plays a pivotal role in enhancing disease diagnosis and treatment planning. However, existing methods often struggle with the complexity of lesion boundaries and the computational demands of Transformer-based approaches. To address these challenges, we propose a morphological difference and statistically sparse Transformer-based deep neural network for medical image segmentation, termed MD-SSFormer. It comprises two critical modules: the dual branch encoder (DBEncoder) module, and the morphological difference catcher (MDC). To extract abundant information at different aspects, a novel DBEncoder module integrates the capability of the convolutional neural network-based method in capturing local texture and the ability of the Transformer-based method in modeling global information. Compared to the conventional feature extraction methods, DBEncoder achieves comprehensive improvement. Furthermore, the statistics-based sparse Transformer (SSFormer) module develops an innovative statistical analysis and an adaptive patch-dividing strategy to perform attention-computing, which addresses the computational challenges associated with conventional Transformer-based models. Finally, considering the impacts of the blurry and complex boundaries, the MDC module employs the morphological operation and differential information extractor to refine the details, which achieves high-precision boundary understanding. Experimental results on five public datasets demonstrate MD-SSFormer's superior performance, achieving state-of-the-art Dice scores of 83.60 % on ISIC 2017, 79.52 % on Kvasir-SEG, 61.89 % on BUSI, 78.62 % on BraTS21, and 85.85 % on 3DIRCADb, outperforming other methods in accuracy, precision, and computational efficiency respectively.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"174 ","pages":"Article 113052"},"PeriodicalIF":7.2,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698029","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}