Complex & Intelligent Systems最新文献

{"title":"Generative language models potential for requirement engineering applications: insights into current strengths and limitations","authors":"Summra Saleem, Muhammad Nabeel Asim, Ludger Van Elst, Andreas Dengel","doi":"10.1007/s40747-024-01707-6","DOIUrl":"https://doi.org/10.1007/s40747-024-01707-6","url":null,"abstract":"<p>Traditional language models have been extensively evaluated for software engineering domain, however the potential of ChatGPT and Gemini have not been fully explored. To fulfill this gap, the paper in hand presents a comprehensive case study to investigate the potential of both language models for development of diverse types of requirement engineering applications. It deeply explores impact of varying levels of expert knowledge prompts on the prediction accuracies of both language models. Across 4 different public benchmark datasets of requirement engineering tasks, it compares performance of both language models with existing task specific machine/deep learning predictors and traditional language models. Specifically, the paper utilizes 4 benchmark datasets; Pure (7445 samples, requirements extraction), PROMISE (622 samples, requirements classification), REQuestA (300 question answer (QA) pairs) and Aerospace datasets (6347 words, requirements NER tagging). Our experiments reveal that, in comparison to ChatGPT, Gemini requires more careful prompt engineering to provide accurate predictions. Moreover, across requirement extraction benchmark dataset the state-of-the-art F1-score is 0.86 while ChatGPT and Gemini achieved 0.76 and 0.77, respectively. The State-of-the-art F1-score on requirements classification dataset is 0.96 and both language models 0.78. In name entity recognition (NER) task the state-of-the-art F1-score is 0.92 and ChatGPT managed to produce 0.36, and Gemini 0.25. Similarly, across question answering dataset the state-of-the-art F1-score is 0.90 and ChatGPT and Gemini managed to produce 0.91 and 0.88 respectively. Our experiments show that Gemini requires more precise prompt engineering than ChatGPT. Except for question-answering, both models under-perform compared to current state-of-the-art predictors across other tasks.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"104 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Advanced fault diagnosis in industrial robots through hierarchical hyper-laplacian priors and singular spectrum analysis","authors":"Riyadh Nazar Ali Algburi, Hakim S. Sultan Aljibori, Zaid Al-Huda, Yeong Hyeon Gu, Mugahed A. Al-antari","doi":"10.1007/s40747-025-01915-8","DOIUrl":"https://doi.org/10.1007/s40747-025-01915-8","url":null,"abstract":"<p>In industrial cases, robustness of the robots is mandatory and thus the development of fault diagnosis systems is essential. This study introduces a novel fault diagnosis method that merges two elements: Two methods shared here are the hierarchical hyper-Laplacian prior (HHLP) and singular spectrum analysis (SSA). The SSA technique decomposes the encoder signals into three components; residual, periodic oscillation and trend. In addition, the HHLP algorithm can identify harmonic interference, periodical impulses, and noise, with maximal posterior probabilities compared to the other algorithms. Compared to traditional Laplacian prior models, this approach provides higher accuracy, which verify the HHLP algorithm can effectively extract fault feature. Real-world applications and some computational studies provide additional light on the practicability of SSA-HHLP method. The research also compares the results with kurtosis-based weighted sparse prototypes, spectral kurtosis, and minimax concave regularization, and indicates that the proposed SSA-HHLP method outperforms other methods in both low outlier and high outlier contamination.\u0000</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"119 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"MLK-TR: a Multi-branch Large Kernel TRansformer for UAV-based images","authors":"Xun Li, Yuzhen Zhao, Yang Zhao, Zhun Guo, Jianjing Gao, Baoxi Yuan","doi":"10.1007/s40747-025-01901-0","DOIUrl":"https://doi.org/10.1007/s40747-025-01901-0","url":null,"abstract":"<p>Object detection from the perspective of unmanned aerial vehicles (UAV) is a technology that utilizes visual sensors mounted on UAV to automatically identify and locate ground targets. However, due to the small size of targets captured by UAV, along with challenges such as scale variation and blurred edges, existing methods struggle to maintain high detection accuracy while ensuring efficient inference speed. To address this, this paper proposes a Multi-branch Large-Kernel TRansformer network (MLK-TR) for small target detection in UAV scenarios. Compared with existing detectors, MLK-TR improves detection performance through the following innovations. First, the Sparse Large-Kernel Attention Mechanism (SLK-Atten) proposed selects key information in the image by sparsifying feature representations. Next, the C3PA2 module enhances the feature extraction capability of the detector, thus improving the detector’s focus on foreground targets. In addition, the Frequent Interaction Feature Fusion Network (FIFFN) facilitates feature interaction between different levels, enhancing the detector’s adaptability to different scales. Finally, super high-resolution prediction feature maps are introduced to enhance edge details, thereby improving the detector’s sensitivity to small targets. Notably, the proposed modules can be easily integrated into the YOLO series framework. Compared to the original YOLO11n, MLK-TR achieves a 9% improvement in mAP50 on the publicly available VisDrone dataset, a 1.9% improvement in mAP50 on the UAVDT dataset, and a 3.6% improvement in mAP50 on the PVD dataset. These results confirm the effectiveness of MLK-TR in addressing the complexities of UAV object detection.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"3 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Evaluation of public bus transport service quality based on circular Pythagorean fuzzy soft Einstein aggregation operators","authors":"Zeeshan Ali, Muhammad Waqas, Sarbast Moslem, Tapan Senapati, Domokos Esztergár-Kiss","doi":"10.1007/s40747-025-01864-2","DOIUrl":"https://doi.org/10.1007/s40747-025-01864-2","url":null,"abstract":"<p>In this article, we introduce the technique of circular Pythagorean fuzzy soft (CPFS) sets and their reliable properties, such as algebraic optional laws and Einstein operational laws. We further develop the CPFS Einstein weighted averaging (CPFSEWA) operator and the CPFS Einstein weighted geometric (CPFSEWG) operator, highlighting their fundamental properties. Additionally, we integrate the evaluation based on the distance from average solution (EDAS) method with the CPFSEWA and CPFSEWG operators, illustrated through relevant examples. The multi-attribute decision-making (MADM) method is applied using the proposed techniques, enhancing the evaluation process of public bus transport service quality. Specifically, the Dublin Bus 16 route is analyzed, focusing on criteria such as reliability, speed, approachability, directness, and time availability. Our methodology evaluates various alternatives, including the purchase of new buses, relocation of bus stops, changes in timetables, introduction of new bus lines, and improvement in driver training. Finally, we compare the proposed ranking values with those from existing techniques, demonstrating the flexibility and proficiency of the CPFS-based approach. This comprehensive evaluation aims to provide policymakers and operators with robust tools for improving public transport services.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"7 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Attention-aware upsampling-downsampling network for autonomous vehicle vision-based multitask perception","authors":"Chongjun Liu, Haobo Zuo, Jianjun Yao, Yuchen Li, Frank Jiang","doi":"10.1007/s40747-025-01870-4","DOIUrl":"https://doi.org/10.1007/s40747-025-01870-4","url":null,"abstract":"<p>Vision-based environmental perception has demonstrated significant promise for autonomous driving applications. However, the traditional unidirectional feature flow in many perception networks often leads to inadequate information propagation, which hinders the system’s ability to comprehensively perceive complex driving environments. Issues such as similar objects, illumination variations, and scale differences aggravate this limitation, introducing noise and reducing the reliability of the perception system. To address these challenges, we propose a novel Attention-Aware Upsampling-Downsampling Network (AUDNet). AUDNet utilizes a bidirectional feature fusion structure, incorporating a multi-scale attention upsampling module (MAU) to enhance the fine details in high-level features by guiding the selection of feature information. Additionally, the multi-scale attention downsampling module (MAD) is designed to reinforce the semantic understanding of low-level features by emphasizing relevant spatial dfigureetails. Extensive experiments on a large-scale, real-world driving dataset demonstrate the superior performance of AUDNet, particularly in multi-task environment perception in complex and dynamic driving scenarios.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"3 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Complexity analysis and practical resolution of the data classification problem with private characteristics","authors":"David Pantoja, Ismael Rodríguez, Fernando Rubio, Clara Segura","doi":"10.1007/s40747-025-01911-y","DOIUrl":"https://doi.org/10.1007/s40747-025-01911-y","url":null,"abstract":"<p>In this work we analyze the problem of, given the probability distribution of a population, questioning an unknown individual that is representative of the distribution so that our uncertainty about certain characteristics is significantly reduced—but the uncertainty about others, deemed private or sensitive, is not. Thus, the goal of the problem is extracting information being relevant to a legitimate purpose while preserving the privacy of individuals, which is crucial to enable non-intrusive selection processes in several areas. For instance, it is essential in the design of non-discriminatory personnel selection, promotion, and layoff processes in companies and institutions; in the retrieval of customer information being relevant to the service provided by a company (and no more); in certifications not revealing sensitive industrial information being irrelevant for the certification itself; etc. Interactive questioning processes are constructed for this purpose, which requires generalizing the notion of <i>decision trees</i> to account the amount of desired and undesired information retrieved for each branch of the plan. Our findings about this problem are both theoretical and practical: on the one hand, we prove its NP-completeness by a reduction from the Set Cover problem; and on the other hand, given this intractability, we provide heuristic solutions to find reasonable solutions in affordable time. In particular, a greedy algorithm and two genetic algorithms are presented. Our experiments indicate that the best results are obtained using a genetic algorithm reinforced with a greedy strategy.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"35 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Hybrid mechanism and data driven approach for high-precision modeling of gas flow regulation systems of VFDR","authors":"Zongyu Zhang, Huan Wang, Meng Tang, Jie Zhang, Xinhan Hu","doi":"10.1007/s40747-025-01899-5","DOIUrl":"https://doi.org/10.1007/s40747-025-01899-5","url":null,"abstract":"<p>The variable flow ducted rocket (VFDR) poses significant challenges for high-precision modeling due to its complex nonlinear dynamics, harsh operational conditions, and integration of multiple physical fields. To address this challenge, this paper introduces a hybrid mechanism and data-driven modeling approach. Initially, the parameter perturbation method was employed to elucidate the interdependencies between system parameters and the VFDR's dynamic and steady-state responses. Entropy weight method (EWM) and technique for order preference by similarity to ideal solution (TOPSIS) were utilized for ranking the compensation parameters of the dynamic-state and steady-state models of the VFDR. Additionally, the throat area of the regulation valve was chosen as a compensatory parameter for the steady-state model. A data-driven residual compensation model was developed using the nonlinear autoregressive neural networks with external inputs (NARX) algorithm to enhance the steady-state mechanistic VFDR model, addressing its time-varying and high uncertainty characteristics. To mitigate dynamic response errors in the mechanistic model, a compensation strategy integrating error and similarity evolution with extreme learning machine (ELM) was implemented to generate compensation value. Simulation and ground experiment results validate the efficacy of the proposed algorithm, the experimental results indicate that, after compensation using the proposed strategy, the maximum error in a single test is reduced by 24.19%, and the average error is decreased by 17.81%.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"205 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Parameter-efficient weakly supervised referring video object segmentation via chain-of-thought reasoning","authors":"Xing Wang, Zhe Xu, Yuanshi Zheng, Handing Wang","doi":"10.1007/s40747-025-01900-1","DOIUrl":"https://doi.org/10.1007/s40747-025-01900-1","url":null,"abstract":"<p>Referring video object segmentation (RVOS) aims to segment the object corresponding to a language expression in a video. Most existing RVOS methods are trained using accurate per-pixel annotations, which are expensive and time-consuming to obtain. Moreover, they need to update the entire parameter of a segmentation model, making it inefficient to train as the model scale increases. In this paper, we propose a novel parameter-efficient framework under weak supervision, dubbed ReferringAdapter, to ameliorate both of issues. Specifically, we propose to adapt an off-the-shelf image segmentation model for RVOS by plugging a small set of trained parameters, i.e., an adapter, into the intermediate layer. This efficiently endows a uni-modal image segmentation model with the cross-modal ability to segment the video object referred by a language expression. To update the adapter parameters under weak supervision, instead of directly fuse the video and sentence-level language features, we propose chain-of-thought reasoning to consider the intermediate steps along the thought process. Extensive experiments demonstrate that training the adapter with 1.1% of total parameters can outperform previous weakly supervised methods by 11.6<span>(-)</span>15.3 mAP and achieve comparable performance with fully supervised ones.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"11 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Towards precision diagnosis: a novel hybrid DC-CAD model for lung disease detection leveraging multi-scale capsule networks and temporal dynamics","authors":"Esther Stacy E. B. Aggrey, Qin Zhen, Seth Larweh Kodjiku, Linda Delali Fiasam, Collins Sey, Chiagoziem C. Ukwuoma, Evans Aidoo, Emmanuel Osei-Mensah","doi":"10.1007/s40747-025-01917-6","DOIUrl":"https://doi.org/10.1007/s40747-025-01917-6","url":null,"abstract":"<p>The early detection of lung diseases, including cancer, is essential for improving patient outcomes. However, traditional diagnostic approaches and standard deep learning models often face challenges in effectively analyzing the complex spatial and temporal variations in medical imaging data, particularly in CT scans. To address these challenges, we propose DC-CAD, a novel hybrid framework that integrates Dilated Capsule Networks, Channel-wise Attention Mechanisms, and Distanced Long Short-Term Memory for precise and early diagnosis of lung diseases. DC-CAD is innovative in its ability to combine multi-scale feature extraction and temporal dynamic analysis, enabling the model to capture intricate spatial relationships and sequential changes in lung tissue. The model consists of three main contributions: (1) Dilated Capsule Networks for improved multi-scale context aggregation, which captures subtle textural variations, (2) a Channel-wise Attention Mechanism to focus on the most relevant regions of interest, minimizing the impact of irrelevant features, and (3) Distanced LSTM layers to model temporal dependencies across sequential CT scans, providing insights into disease progression. Through comprehensive experiments on the LC25000 dataset, DC-CAD achieves 99.52% accuracy, significantly outperforming baseline models such as standard Capsule Networks and Convolutional Neural Networks. The model also reduces the error rate to 0.48%, demonstrating substantial improvements in diagnostic performance, including increased accuracy, sensitivity, and specificity. These results establish DC-CAD as a powerful and reliable tool for automated lung disease diagnosis, with significant potential to enhance clinical workflow by reducing radiologists’ workload through its interpretability and efficiency. Moving forward, we plan to extend the model to handle multi-modal data and investigate advanced attention mechanisms to further improve diagnostic accuracy and generalizability.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"53 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Deep reinforcement learning for path planning of autonomous mobile robots in complicated environments","authors":"Zhijie Zhang, Hao Fu, Juan Yang, Yunhan Lin","doi":"10.1007/s40747-025-01906-9","DOIUrl":"https://doi.org/10.1007/s40747-025-01906-9","url":null,"abstract":"<p>In complicated environments, which include dynamic and narrow areas, the path planning of Autonomous Mobile Robots (AMRs) encounters challenges, like slow model convergence and limited representational capabilities, often resulting in the robot taking longer, less efficient paths or even colliding with obstacles. To tackle these challenges, the Gated Attention Prioritized Experience Replay Soft Actor-Critic (GAP_ SAC) algorithm is proposed. Key improvements include expanding the state space for better perception, designing a dynamic heuristic reward function to more effectively guide the AMR in achieving its path planning objectives and integrating Prioritized Experience Replay (PER) to improve sample efficiency and accelerate convergence. Additionally, a gated attention mechanism is also introduced to focus on critical environmental features, enhancing the models’ perception capability. Comparative experiments validate that the proposed GAP_SAC algorithm outperforms TD3, SAC and SAC’s variant, demonstrating superior robustness and generalization in complicated environments.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"19 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143920594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}