Applied Soft Computing最新文献_第9页

Bug priority prediction using deep ensemble approach 使用深度集合方法预测错误优先级

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-29 DOI: 10.1016/j.asoc.2025.113098

P.G.S.M. Dharmakeerthi , R.A.H.M. Rupasingha , B.T.G.S. Kumara

{"title":"Bug priority prediction using deep ensemble approach","authors":"P.G.S.M. Dharmakeerthi , R.A.H.M. Rupasingha , B.T.G.S. Kumara","doi":"10.1016/j.asoc.2025.113098","DOIUrl":"10.1016/j.asoc.2025.113098","url":null,"abstract":"<div><div>A software bug is a fault in the programming of software or an application. Bugs cause problems ranging from stability to operability and are typically the result of human error during the programming process. They could be the result of a mistake or error, as well as a fault or defect. Software bugs should be discovered during the testing stage of the software development life cycle, but some may go undetected until after deployment. When addressing a bug, it is critical to consider its priority, which is determined manually. However, it was a difficult task, and making the wrong decision could lead to major software failures. Therefore, the primary goal of this study is to propose an ensemble approach for predicting bug priority levels in bug reports. We make use of Bugzilla's dataset, which includes over 25,000 bug reports. After preprocessing the data, this study applies a variety of feature extraction techniques, including Glove, Word2Vec TF-IDF, and Doc2Vec. Then, a model that primarily employs seven architectures of Convolutional Neural Network (CNN) Algorithms, including AlexNet, LeNet, VGGNet, 1DCNN, ResNet, ZF Net, and DenseNet as the basic models. The five architectures with the highest accuracy were then used in the ensemble method, which included ResNet, DenseNet, LeNet, AlexNet, and 1DCNN, with the final results determined by the majority values. The ensemble approach performed with 79.18 % of the final accuracy result. Other architectures include AlexNet 77.1 %, ZF Net 44.50 %, VGG Net 39.30 %, 1DCNN 75.44 %, ResNet 77.34 %, DenseNet 77.32 %, and LeNet 48.58 %. It was discovered that the proposed ensemble model outperformed each algorithm. Finally, when a new bug is discovered, it can be added to the proposed model, which will then determine its priority level.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113098"},"PeriodicalIF":7.2,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735024","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

Robust and fast subspace representation learning for multi-view subspace clustering 基于多视图子空间聚类的鲁棒快速子空间表示学习

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113050

Tailong Yu, Yesong Xu, Nan Yan, Mengyang Li

{"title":"Robust and fast subspace representation learning for multi-view subspace clustering","authors":"Tailong Yu, Yesong Xu, Nan Yan, Mengyang Li","doi":"10.1016/j.asoc.2025.113050","DOIUrl":"10.1016/j.asoc.2025.113050","url":null,"abstract":"<div><div>Multi-view subspace clustering (MVSC) plays an indispensable role in the domains of data mining and machine learning. Compared to single-view analysis, this integration of information leads to more accurate and comprehensive clustering results, providing a solution for large-scale data clustering. Notably, various techniques have been proposed in the field. In the present context, most multi-view clustering methods mainly focus on enhancing the consistency of clustering and handling noise. Adapting multi-view subspace clustering effectively for the clustering of big data poses a significant challenge. To overcome this challenge, we propose a new method called “robust and fast subspace representation learning for multi-view subspace clustering (RFSR)”, which utilizes a unified encoder to process information from each view and integrates the information between different views. In this process, we reduce the impact of noise, employing either correntropy or <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mi>2,1</mi></mrow></msub></math></span>-norm for handling it. Specifically, we start by randomly sampling from each view and then process the sampled data for noise. Subsequently, we train a unified encoder for each view to leverage complementary information from multiple views, thereby enhancing the robustness of clustering. We not only consider the multi-view data features but also account for its large scale and noise structure. Furthermore, we demonstrate through experiments the efficiency and robustness of our approach in multi-view subspace clustering.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113050"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143746375","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

Finite-time stabilization of fractional-order neural networks with time-varying delays: A generalized inequality approach and controller design 时变时滞分数阶神经网络的有限时间镇定：一种广义不等式方法及控制器设计

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113074

M. Shafiya , N. Padmaja

{"title":"Finite-time stabilization of fractional-order neural networks with time-varying delays: A generalized inequality approach and controller design","authors":"M. Shafiya , N. Padmaja","doi":"10.1016/j.asoc.2025.113074","DOIUrl":"10.1016/j.asoc.2025.113074","url":null,"abstract":"<div><div>This paper explores finite-time stabilization methods for a specific class of neural networks with fractional-order dynamics and time-varying delays. The first contribution involves introducing a generalized inequality, an extension of the existing one, to analyze the finite-time stabilization behavior of the addressed model. This extension has successfully addressed numerous limitations and challenges present in existing works. Additionally, an explicit formula for calculating the finite-time stabilization duration is provided. Subsequently, two types of controllers—delay-independent and delay-dependent feedback controllers—are developed to achieve finite-time stabilization for the neural networks under consideration. The conditions for stability, dependent on both the delay and the order, are formulated as linear matrix inequalities using inequality techniques, Lyapunov stability theory, and the newly proposed finite-time stability inequality. These conditions ensure that the fractional-order neural network model is stabilized in finite-time. The efficacy of the suggested design approach is demonstrated through two numerical case studies.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113074"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735023","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

Forecasting realized volatility using deep learning quantile function 利用深度学习分位数函数预测实现波动率

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113016

Jungyoon Song , Hyunju Lee , Jongu Lee , Woojin Chang

{"title":"Forecasting realized volatility using deep learning quantile function","authors":"Jungyoon Song , Hyunju Lee , Jongu Lee , Woojin Chang","doi":"10.1016/j.asoc.2025.113016","DOIUrl":"10.1016/j.asoc.2025.113016","url":null,"abstract":"<div><div>The accurate prediction of realized volatility is an essential component of effective investment strategies. Existing studies have often focused on modeling selective features of intraday return series, overlooking the comprehensive information embedded within them due to challenges such as microstructure noise and the complexity of handling numerous data points. To address these limitations, this paper proposes a novel deep learning quantile function (DLQF) framework that directly leverages intraday return series to forecast realized volatility. The proposed model integrates a Bi-LSTM network to capture the long memory of realized volatility and a quantile function implemented as a deep neural network to extract rich information from intraday returns. A loss function based on <span><math><msub><mrow><mi>L</mi></mrow><mrow><mi>p</mi></mrow></msub></math></span> distance measures is defined to estimate the probabilistic distribution of intraday returns, enabling both intraday return prediction and realized volatility estimation. Empirical results demonstrate that DLQF outperforms traditional benchmarks across major ETFs, including SPY, DIA, and QQQ, which represent the S&P 500, Dow Jones Industrial Average, and Nasdaq 100, respectively. This model offers significant potential for applications in portfolio optimization, option pricing, and risk management.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113016"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759721","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

Optimizing learning paths: Course recommendations based on graph convolutional networks and learning styles 优化学习路径：基于图卷积网络和学习风格的课程推荐

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113083

Guodao Zhang , Xiaoyun Gao , Haiyang Ye , Junyi Zhu , Wenqian Lin , Zizhao Wu , Haijun Zhou , Zi Ye , Yisu Ge , Alireza Baghban

{"title":"Optimizing learning paths: Course recommendations based on graph convolutional networks and learning styles","authors":"Guodao Zhang , Xiaoyun Gao , Haiyang Ye , Junyi Zhu , Wenqian Lin , Zizhao Wu , Haijun Zhou , Zi Ye , Yisu Ge , Alireza Baghban","doi":"10.1016/j.asoc.2025.113083","DOIUrl":"10.1016/j.asoc.2025.113083","url":null,"abstract":"<div><div>With the rise of Massive Open Online Course (MOOC) platforms and the growing popularity of self-directed learning, an increasing number of learners are utilizing online platforms to access educational resources. While these extensive course resources offer learners diverse and accessible learning experiences, they also present challenges in personalized course selection. Traditional recommendation models often lack sufficient interpretability and fail to effectively leverage the interactive data generated during curriculum learning or account for the impact of individual learning styles on recommendations. To address these limitations, this study proposes a novel model, Course Recommendations based on Graph Convolutional Networks and Learning Styles to Optimize Learning Paths. Firstly, learner-course interaction data is recursively propagated through graph convolutional networks to generate predictive scores for courses. Secondly, a matching scale between courses and learning styles is established to compute similarity scores. Finally, the predictive scores and learning style similarity scores are integrated to achieve personalized course recommendations. The experimental results on the MOOCCube dataset demonstrate that CGCNLS significantly outperforms the baseline methods across multiple evaluation metrics, and the average performance of Precision, Recall and NDCG is improved by 6.94 %, 6.63 % and 7.98 %, respectively, under different Top-K Settings (K = 5, 10, 20, and 30), which can more effectively recommend courses for learners. The findings of this research provide robust support for further advancements in recommender systems and are expected to enhance the user experience and learning outcomes on online learning platforms.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113083"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776296","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

Multi-stage feature fusion network for polyp segmentation 基于多阶段特征融合网络的息肉分割

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113034

Guangzu Lv , Bin Wang , Cunlu Xu , Weiping Ding , Jun Liu

引用次数: 0

Strategic integration of adaptive sampling and ensemble techniques in federated learning for aircraft engine remaining useful life prediction 自适应采样和集成技术在联邦学习中的策略集成，用于飞机发动机剩余使用寿命预测

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113067

Ancha Xu , Renbing Wang , Xinming Weng , Qi Wu , Liangliang Zhuang

{"title":"Strategic integration of adaptive sampling and ensemble techniques in federated learning for aircraft engine remaining useful life prediction","authors":"Ancha Xu , Renbing Wang , Xinming Weng , Qi Wu , Liangliang Zhuang","doi":"10.1016/j.asoc.2025.113067","DOIUrl":"10.1016/j.asoc.2025.113067","url":null,"abstract":"<div><div>In industrial manufacturing, predicting the remaining useful life of machines is crucial for improving operational efficiency and reducing maintenance costs. However, data privacy concerns and commercial competition make traditional centralized data collection methods insufficient to meet these needs. Federated learning offers a decentralized training approach that protects data privacy, but existing research faces challenges such as inadequate performance of single models, data quality disparities, and improper client selection strategies. To address these issues, this study proposes an adaptive sampling-based ensemble federated learning framework. By integrating the predictions of multiple models, the framework reduces model errors and enhances prediction accuracy and generalization capability. Additionally, we design an adaptive sampling method that dynamically adjusts the client selection strategy based on data quality, focusing on clients with low-quality data to ensure that their contributions are effectively utilized. Experimental results show that the proposed framework significantly outperforms existing benchmark methods on the turbofan engine dataset, with a 12% reduction in RMSE and a 35% decrease in Score. Ablation experiments and sensitivity analysis confirm that the framework maintains reliable predictive performance and efficiency in dealing with issues such as data imbalance, missing data, and scale changes. Supplementary materials for this article are available online.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113067"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738481","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

Covariance matrix adaptation driven dynamic multi-population colony predation optimizer: Insights, qualitative analysis, and constrained engineering optimization 协方差矩阵自适应驱动的动态多种群群体捕食优化器：见解，定性分析和约束工程优化

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113041

Xinsen Zhou , Jie Xing , Wenyong Gui , Ali Asghar Heidari , Zhennao Cai , Huiling Chen , Guoxi Liang

{"title":"Covariance matrix adaptation driven dynamic multi-population colony predation optimizer: Insights, qualitative analysis, and constrained engineering optimization","authors":"Xinsen Zhou , Jie Xing , Wenyong Gui , Ali Asghar Heidari , Zhennao Cai , Huiling Chen , Guoxi Liang","doi":"10.1016/j.asoc.2025.113041","DOIUrl":"10.1016/j.asoc.2025.113041","url":null,"abstract":"<div><div>The Colony Predation Algorithm (CPA) is a straightforward population-based algorithm with few control parameters. Nevertheless, its initial design has limitations, including a tendency for local optimization and limited search ability, leading to subpar solutions. In response to these concerns, a novel approach named the Covariance Matrix Adaptive-Driven Dynamic Multi-Population Colony Predation Algorithm (ICPA) is introduced. Qualitative analysis experiments are carried out to determine ICPA's feasibility, including historical search trajectory analyses and balanced diversity assessments. Additionally, a comparative study involving 11 well-known algorithms, 11 state-of-the-art algorithms, and four champion algorithms (EBOwithCMAR, SPS_L_SHADE_EIG, LSHADE_cnEpSi, and LSHADE) using the IEEE CEC 2014 test suite confirmed its superior optimization capabilities. Statistical tests consistently rank ICPA first on the Friedman test (with scores of 2.17, 3.37, and 2.27) and demonstrate its outperformance of state-of-the-art algorithms in at least 40 % of tested functions in the Wilcoxon sign-rank test. The Bonferroni Dunn post-hoc statistical test reveals that ICPA significantly outperforms 61.53 % of the compared algorithms. Additionally, the efficacy of ICPA was evaluated on seven constrained real-world engineering problems, encompassing gear train design, speed reducer design, multi-disc clutch and brake design, cantilever beam design, three-bar truss design, I-beam design, and combined economic emission dispatch. The experimental outcomes underscore the potential of ICPA in addressing practical engineering challenges, thereby validating its optimization effectiveness. Utilizing extensive experimentation and comparative analyses, the feasibility, superiority, and effectiveness of ICPA have been substantiated, encompassing both qualitative and quantitative perspectives.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113041"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759720","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

Federated Bayesian optimization on random Fourier additive margin features and random kernel mapping 随机傅里叶加性边缘特征和随机核映射的联邦贝叶斯优化

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.112925

Fazhen Jiang , Xiaoyuan Yang

引用次数: 0

Attention-aware ensemble learning for face-periocular cross-modality matching 人脸-眼周交叉模态匹配的注意感知集成学习

IF 7.2 1区计算机科学

Applied Soft Computing Pub Date : 2025-03-28 DOI: 10.1016/j.asoc.2025.113044

Tiong-Sik Ng, Andrew Beng Jin Teoh

{"title":"Attention-aware ensemble learning for face-periocular cross-modality matching","authors":"Tiong-Sik Ng, Andrew Beng Jin Teoh","doi":"10.1016/j.asoc.2025.113044","DOIUrl":"10.1016/j.asoc.2025.113044","url":null,"abstract":"<div><div>Face and periocular regions serve as complementary biometric modalities in identity recognition. The face-periocular cross-modality matching (FPCM) provides a versatile solution, especially when traditional face recognition systems encounter challenges due to occlusions or the presence of sunglasses, which can obscure the periocular region, rendering it less effective in periocular recognition systems. This paper introduces a novel approach based on attention-aware ensemble learning (AEL) to address these challenges. This notion is embodied in AELNet, which features an attention-aware shared-parameter encoder and multiple classifier heads. AELNet is designed to harness the complementary features of the face and periocular regions, enhancing the quality of joint embeddings. A key aspect of AELNet is its ability to foster diversity among the classifier heads through unique embedding techniques and batch sampling strategies, ultimately boosting FPCM performance. We demonstrate the effectiveness of the AELNet by conducting extensive experiments on five unconstrained periocular-face datasets as a benchmark. Codes are publicly available at <span><span>https://github.com/tiongsikng/ael_net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113044"},"PeriodicalIF":7.2,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738477","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