Complex & Intelligent Systems最新文献_第10页

Preference learning based deep reinforcement learning for flexible job shop scheduling problem 基于偏好学习的柔性作业车间调度问题深度强化学习

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-15 DOI: 10.1007/s40747-024-01772-x

Xinning Liu, Li Han, Ling Kang, Jiannan Liu, Huadong Miao

{"title":"Preference learning based deep reinforcement learning for flexible job shop scheduling problem","authors":"Xinning Liu, Li Han, Ling Kang, Jiannan Liu, Huadong Miao","doi":"10.1007/s40747-024-01772-x","DOIUrl":"https://doi.org/10.1007/s40747-024-01772-x","url":null,"abstract":"The flexible job shop scheduling problem (FJSP) holds significant importance in both theoretical research and practical applications. Given the complexity and diversity of FJSP, improving the generalization and quality of scheduling methods has become a hot topic of interest in both industry and academia. To address this, this paper proposes a Preference-Based Mask-PPO (PBMP) algorithm, which leverages the strengths of preference learning and invalid action masking to optimize FJSP solutions. First, a reward predictor based on preference learning is designed to model reward prediction by comparing random fragments, eliminating the need for complex reward function design. Second, a novel intelligent switching mechanism is introduced, where proximal policy optimization (PPO) is employed to enhance exploration during sampling, and masked proximal policy optimization (Mask-PPO) refines the action space during training, significantly improving efficiency and solution quality. Furthermore, the Pearson correlation coefficient (PCC) is used to evaluate the performance of the preference model. Finally, comparative experiments on FJSP benchmark instances of varying sizes demonstrate that PBMP outperforms traditional scheduling strategies such as dispatching rules, OR-Tools, and other deep reinforcement learning (DRL) algorithms, achieving superior scheduling policies and faster convergence. Even with increasing instance sizes, preference learning proves to be an effective reward mechanism in reinforcement learning for FJSP. The ablation study further highlights the advantages of each key component in the PBMP algorithm across performance metrics.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"74 2 Pt 2 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142981765","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}

引用次数: 0

Enhancing zero-shot stance detection via multi-task fine-tuning with debate data and knowledge augmentation 通过多任务微调与辩论数据和知识增强增强零射击姿态检测

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-15 DOI: 10.1007/s40747-024-01767-8

Qinlong Fan, Jicang Lu, Yepeng Sun, Qiankun Pi, Shouxin Shang

{"title":"Enhancing zero-shot stance detection via multi-task fine-tuning with debate data and knowledge augmentation","authors":"Qinlong Fan, Jicang Lu, Yepeng Sun, Qiankun Pi, Shouxin Shang","doi":"10.1007/s40747-024-01767-8","DOIUrl":"https://doi.org/10.1007/s40747-024-01767-8","url":null,"abstract":"In the real world, stance detection tasks often involve assessing the stance or attitude of a given text toward new, unseen targets, a task known as zero-shot stance detection. However, zero-shot stance detection often suffers from issues such as sparse data annotation and inherent task complexity, which can lead to lower performance. To address these challenges, we propose combining fine-tuning of Large Language Models (LLMs) with knowledge augmentation for zero-shot stance detection. Specifically, we leverage stance detection and related tasks from debate corpora to perform multi-task fine-tuning of LLMs. This approach aims to learn and transfer the capability of zero-shot stance detection and reasoning analysis from relevant data. Additionally, we enhance the model’s semantic understanding of the given text and targets by retrieving relevant knowledge from external knowledge bases as context, alleviating the lack of relevant contextual knowledge. Compared to ChatGPT, our model achieves a significant improvement in the average F1 score, with an increase of 15.74% on the SemEval 2016 Task 6 A and 3.55% on the P-Stance dataset. Our model outperforms current state-of-the-art models on these two datasets, demonstrating the superiority of multi-task fine-tuning with debate data and knowledge augmentation.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142981772","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}

引用次数: 0

MKER: multi-modal knowledge extraction and reasoning for future event prediction MKER：用于未来事件预测的多模态知识提取和推理

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-09 DOI: 10.1007/s40747-024-01741-4

Chenghang Lai, Shoumeng Qiu

{"title":"MKER: multi-modal knowledge extraction and reasoning for future event prediction","authors":"Chenghang Lai, Shoumeng Qiu","doi":"10.1007/s40747-024-01741-4","DOIUrl":"https://doi.org/10.1007/s40747-024-01741-4","url":null,"abstract":"Humans can predict what will happen shortly, which is essential for survival, but machines cannot. To equip machines with the ability, we introduce the innovative multi-modal knowledge extraction and reasoning (MKER) framework. This framework combines external commonsense knowledge, internal visual relation knowledge, and basic information to make inference. This framework is built on an encoder-decoder structure with three essential components: a visual language reasoning module, an adaptive cross-modality feature fusion module, and a future event description generation module. The visual language reasoning module extracts the object relationships among the most informative objects and the dynamic evolution of the relationship, which comes from the sequence scene graphs and commonsense graphs. The long short-term memory model is employed to explore changes in the object relationships at different times to form a dynamic object relationship. Furthermore, the adaptive cross-modality feature fusion module aligns video and language information by using object relationship knowledge as guidance to learn vision-language representation. Finally, the future event description generation module decodes the fused information and generates the language description of the next event. Experimental results demonstrate that MKER outperforms existing methods. Ablation studies further illustrate the effectiveness of the designed module. This work advances the field by providing a way to predict future events, enhance machine understanding, and interact with dynamic environments.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"28 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142937248","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}

引用次数: 0

RL4CEP: reinforcement learning for updating CEP rules RL4CEP：用于更新CEP规则的强化学习

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-09 DOI: 10.1007/s40747-024-01742-3

Afef Mdhaffar, Ghassen Baklouti, Yassine Rebai, Mohamed Jmaiel, Bernd Freisleben

引用次数: 0

A joint learning method for low-light facial expression recognition 微光面部表情识别的联合学习方法

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-09 DOI: 10.1007/s40747-024-01762-z

Yuanlun Xie, Jie Ou, Bihan Wen, Zitong Yu, Wenhong Tian

引用次数: 0

Sentimentally enhanced conversation recommender system 情感增强对话推荐系统

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-08 DOI: 10.1007/s40747-024-01766-9

Fengjin Liu, Qiong Cao, Xianying Huang, Huaiyu Liu

{"title":"Sentimentally enhanced conversation recommender system","authors":"Fengjin Liu, Qiong Cao, Xianying Huang, Huaiyu Liu","doi":"10.1007/s40747-024-01766-9","DOIUrl":"https://doi.org/10.1007/s40747-024-01766-9","url":null,"abstract":"Conversation recommender system (CRS) aims to provide high-quality recommendations to users in fewer conversation turns. Existing studies often rely on knowledge graphs to enhance the representation of entity information. However, these methods tend to overlook the inherent incompleteness of knowledge graphs, making it challenging for models to fully capture users’ true preferences. Additionally, they fail to thoroughly explore users’ emotional tendencies toward entities or effectively differentiate the varying impacts of different entities on user preferences. Furthermore, the responses generated by the dialogue module are often monotonous, lacking diversity and expressiveness, and thus fall short of meeting the demands of complex scenarios. To address these shortcomings, we propose an innovative Sentimentally Enhanced Conversation Recommender System (SECR). First, we construct a comprehensive and highly optimized knowledge graph, termed MAKG, which provides a rich and complete set of entities to help the model capture user preferences more holistically. This significantly improves the inference depth and decision accuracy of the recommender system. Second, by deeply analyzing the emotional semantics in dialogues, the system accurately identifies users’ emotional tendencies toward entities and recommends those that best align with their preferences. To refine the recommendation strategy, we design an emotional weighting mechanism to quantify and distinguish the importance of different entities in shaping user preferences. Lastly, we develop an efficient text filter to extract movie introductions from external data sources and integrate them into the dialogue, greatly enhancing the diversity and semantic richness of the generated responses. Extensive experimental results on two public CRS datasets demonstrate the effectiveness of our approach. Our code is released on https://github.com/Janns0916/EECR.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"203 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142936269","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}

引用次数: 0

Practice of an improved many-objective route optimization algorithm in a multimodal transportation case under uncertain demand 需求不确定多式联运情况下改进的多目标路线优化算法的实践

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-08 DOI: 10.1007/s40747-024-01725-4

Tianxu Cui, Ying Shi, Jingkun Wang, Rijia Ding, Jinze Li, Kai Li

{"title":"Practice of an improved many-objective route optimization algorithm in a multimodal transportation case under uncertain demand","authors":"Tianxu Cui, Ying Shi, Jingkun Wang, Rijia Ding, Jinze Li, Kai Li","doi":"10.1007/s40747-024-01725-4","DOIUrl":"https://doi.org/10.1007/s40747-024-01725-4","url":null,"abstract":"In recent decades, multimodal transportation has played a crucial role in modern logistics and transportation systems because of its high capacity and low cost. However, multimodal transportation driven mainly by fossil fuels may result in significant carbon emissions. In addition, transportation costs, transportation efficiency, and customer demand are also key factors that constrain the development of multimodal transportation. In this paper, we develop, for the first time, a many-objective multimodal transportation route optimization (MTRO) model that simultaneously considers economic cost, carbon emission cost, time cost, and customer satisfaction, and we solve it via the nondominated sorting genetic algorithm version III (NSGA-III). Second, to further improve the convergence performance, we introduce a fuzzy decision variable framework to improve the NSGA-III algorithm. This framework can reduce the search range of the optimization algorithm in the decision space and make it converge better. Finally, we conduct numerous simulation experiments on test problems to verify the applicability and superiority of the improved algorithm and apply it to MTRO problems under uncertain demand. This work fills the research gap for MTRO problems and provides guidance for relevant departments in developing transportation and decarbonization plans.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"24 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142936270","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}

引用次数: 0

A semi-supervised learning technique assisted multi-objective evolutionary algorithm for computationally expensive problems 半监督学习技术辅助多目标进化算法求解计算量大的问题

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-07 DOI: 10.1007/s40747-024-01715-6

Zijian Jiang, Chaoli Sun, Xiaotong Liu, Hui Shi, Sisi Wang

{"title":"A semi-supervised learning technique assisted multi-objective evolutionary algorithm for computationally expensive problems","authors":"Zijian Jiang, Chaoli Sun, Xiaotong Liu, Hui Shi, Sisi Wang","doi":"10.1007/s40747-024-01715-6","DOIUrl":"https://doi.org/10.1007/s40747-024-01715-6","url":null,"abstract":"Existing multi-objective evolutionary algorithms (MOEAs) have demonstrated excellent efficiency when tackling multi-objective tasks. However, its use in computationally expensive multi-objective issues is hindered by the large number of reliable evaluations needed to find Pareto-optimal solutions. This paper employs the semi-supervised learning technique in model training to aid in evolutionary algorithms for addressing expensive multi-objective issues, resulting in the semi-supervised learning technique assisted multi-objective evolutionary algorithm (SLTA-MOEA). In SLTA-MOEA, the value of every objective function is determined as a weighted mean of values approximated by all surrogate models for that objective function, with the weights optimized through a convex combination problem. Furthermore, the number of unlabelled solutions participating in model training is adaptively determined based on the objective evaluations conducted. A group of tests on DTLZ test problems with 3, 5, and 10 objective functions, combined with a practical application, are conducted to assess the effectiveness of our proposed method. Comparative experimental results versus six state-of-the-art evolutionary algorithms for expensive problems show high efficiency of SLTA-MOEA, particularly for problems with irregular Pareto fronts.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"7 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142934944","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}

引用次数: 0

RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans RenalSegNet：在增强CT扫描中自动分割肾肿瘤、静脉和动脉

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-07 DOI: 10.1007/s40747-024-01751-2

Rashid Khan, Chao Chen, Asim Zaman, Jiayi Wu, Haixing Mai, Liyilei Su, Yan Kang, Bingding Huang

{"title":"RenalSegNet: automated segmentation of renal tumor, veins, and arteries in contrast-enhanced CT scans","authors":"Rashid Khan, Chao Chen, Asim Zaman, Jiayi Wu, Haixing Mai, Liyilei Su, Yan Kang, Bingding Huang","doi":"10.1007/s40747-024-01751-2","DOIUrl":"https://doi.org/10.1007/s40747-024-01751-2","url":null,"abstract":"Renal carcinoma is a frequently seen cancer globally, with laparoscopic partial nephrectomy (LPN) being the primary form of treatment. Accurately identifying renal structures such as kidneys, tumors, veins, and arteries on CT scans is crucial for optimal surgical preparation and treatment. However, the automatic segmentation of these structures remains challenging due to the kidney's complex anatomy and the variability of imaging data. This study presents RenalSegNet, a novel deep-learning framework for automatically segmenting renal structure in contrast-enhanced CT images. RenalSegNet has an innovative encoder-decoder architecture, including the FlexEncoder Block for efficient multivariate feature extraction and the MedSegPath mechanism for advanced feature distribution and fusion. Evaluated on the KiPA dataset, RenalSegNet achieved remarkable performance, with an average dice score of 86.25%, IOU of 76.75%, Recall of 86.69%, Precision of 86.48%, HD of 15.78 mm, and AVD of 0.79 mm. Ablation studies confirm the critical roles of the MedSegPath and MedFuse components in achieving these results. RenalSegNet's robust performance highlights its potential for clinical applications and offers significant advances in renal cancer treatment by contributing to accurate preoperative planning and postoperative evaluation. Future improvements to model accuracy and applicability will involve integrating advanced techniques, such as unsupervised transformer-based approaches.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"15 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142934949","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}

引用次数: 0

Balanced coarse-to-fine federated learning for noisy heterogeneous clients 针对有噪声的异构客户机的平衡的从粗到精的联邦学习

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2025-01-07 DOI: 10.1007/s40747-024-01694-8

Longfei Han, Ying Zhai, Yanan Jia, Qiang Cai, Haisheng Li, Xiankai Huang

{"title":"Balanced coarse-to-fine federated learning for noisy heterogeneous clients","authors":"Longfei Han, Ying Zhai, Yanan Jia, Qiang Cai, Haisheng Li, Xiankai Huang","doi":"10.1007/s40747-024-01694-8","DOIUrl":"https://doi.org/10.1007/s40747-024-01694-8","url":null,"abstract":"For heterogeneous federated learning, each client cannot ensure the reliability due to the uncertainty in data collection, where different types of noise are always introduced into heterogeneous clients. Current existing methods rely on the specific assumptions for the distribution of noise data to select the clean samples or eliminate noisy samples. However, heterogeneous clients have different deep neural network structures, and these models have different sensitivity to various noise types, the fixed noise-detection based methods may not be effective for each client. To overcome these challenges, we propose a balanced coarse-to-fine federated learning method to solve noisy heterogeneous clients. By introducing the coarse-to-fine two-stage strategy, the client can adaptively eliminate the noisy data. Meanwhile, we proposed a balanced progressive learning framework, It leverages the self-paced learning to sort the training samples from simple to difficult, which can evenly construct the client model from simple to difficult paradigm. The experimental results show that the proposed method has higher accuracy and robustness in processing noisy data from heterogeneous clients, and it is suitable for both heterogeneous and homogeneous federated learning scenarios. The code is avaliable at https://github.com/drafly/bcffl.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"28 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142934946","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}

引用次数: 0