Complex & Intelligent Systems最新文献

{"title":"VLA-Grasp: a vision-language-action modeling with cross-modality fusion for task-oriented grasping","authors":"Jianwei Zhu, Xueying Sun, Qiang Zhang, Mingmin Liu","doi":"10.1007/s40747-025-01893-x","DOIUrl":"https://doi.org/10.1007/s40747-025-01893-x","url":null,"abstract":"<p>Task-oriented grasping (TOG) aims to predict the appropriate pose for grasping based on a specific task. While recent approaches have incorporated semantic knowledge into TOG models to enable robots to understand linguistic commands, they lack the ability to leverage relevant information from vision, language, and action. To address this problem, we propose a novel multimodal fusion grasping framework called VLA-Grasp. VLA-Grasp utilizes prompted large language model for task inference, and multi-channel multimodal encoders and cross-attention modules are proposed to capture the intrinsic links between vision-language-action, thus improving the generalization ability of the model. In addition, we introduce a multiple grasping decision method that can provide multiple feasible grasping actions. We experimentally evaluate our approach on a publicly available dataset and compare it to state-of-the-art methods. In addition, we experimentally validate our model in a real-world scenario to evaluate its performance. The results show that our method provides a reliable and efficient solution for the TOG task. The code is available at https://github.com/Jianwei915/VLA-Grasp.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"9 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143910502","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":"Hide and seek in transaction networks: a multi-agent framework for simulating and detecting money laundering activities","authors":"Qianyu Wang, Wei-Tek Tsai, Tianyu Shi, Wang Tang, Bowen Du","doi":"10.1007/s40747-025-01913-w","DOIUrl":"https://doi.org/10.1007/s40747-025-01913-w","url":null,"abstract":"<p>Detecting money laundering within financial networks presents a complex challenge due to the elusive behavior patterns of laundering agents, often resulting in data gaps. In this research, we propose a ‘Multiverse Simulation’ framework using a multi-agent system to generate synthetic datasets for anti-money laundering (AML) training and detection. This framework creates diverse virtual worlds, each with unique parameters to represent varying levels of illicit activity, thus mimicking the dynamics of money laundering and legitimate transactions. Our framework comprises two main types of agents: (1) the Detector, trained to identify laundering signs, and (2) Transaction agents, divided into those involved in laundering and those in legal transactions. These agents interact in a synthetic environment governed by rules that simulate real-world financial behaviors, enabling the generation of complex, realistic data. In the <i>hide-and-seek</i> multiverse simulation, the Detector learns to distinguish between licit and illicit transactions, a process refined by the evolving strategies of transaction agents to avoid detection. This adversarial setup fosters the co-evolution of laundering techniques and detection methods, enhancing system robustness. We demonstrate the efficacy of this approach by pre-training on synthetic cross-bank data, then evaluating with real-world data from the Elliptic dataset. Our results show that transfer learning significantly improves AML system performance, effectively bridging the gap between synthetic and authentic transaction patterns. The ‘Multiverse Simulation’ offers a scalable, dynamic approach to better understand and mitigate the gap between simulation and reality, contributing to more resilient and intelligent AML solutions.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"18 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143909824","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":"Four-dimensional green transportation problem considering multiple objectives and product blending in Fermatean fuzzy environment","authors":"Monika Bisht, Ali Ebrahimnejad","doi":"10.1007/s40747-025-01829-5","DOIUrl":"https://doi.org/10.1007/s40747-025-01829-5","url":null,"abstract":"<p>This paper presents a study on the multi-objective green four-dimensional transportation problem (MOG4DTP) with product blending. Due to uncontrollable circumstances and globalization, it is not always practical to exactly determine the parameters of the MO4DGTP. In such situations, decision experts sometimes have to deal with data that can be described by a membership degree (MD) and a non-membership degree (NMD), such that their total does not fall within the range <span>(left[ 0,1right] )</span>. Such a situation cannot be addressed by fuzzy set theory or intuitionistic fuzzy set (IFS) theory. However, there are cases where the sum of the cubes of the MD and the NMD of the data lies within the range <span>(left[ 0,1right] )</span>, even though their sum is greater than 1. Fermatean fuzzy sets (FFSs) can deal with such ambiguous data. Thus, we consider parameters such as transportation cost, time, availability, demand, conveyance capacity and carbon emission as triangular Fermatean fuzzy numbers (TrFFNs). Also, since greenhouse gas emission is the most controversial issue in present times, we have considered carbon emission as one of the objectives of our problem. Both these considerations make our problem more realistic. Additionally, we propose a ranking index for TrFFNs and, by utilizing its linearity, transform the Fermatean fuzzy model into its corresponding deterministic form. Further, we obtain the Pareto-optimal solution of this model by four methods, namely, fuzzy TOPSIS, <span>(epsilon )</span>-constraint method, augmented Tchebycheff method (ATM) and weighted Tchebycheff metrics programming (WTMP) method. We describe a real-world industrial transportation problem (TP) and compare the solutions obtained using different techniques in order to show the value and applicability of the suggested model. The proposed algorithm’s performance is validated through comparisons with state-of-the-art multi-objective algorithms, ensuring credibility and demonstrating its effectiveness in solving complex optimization problems. Further, a comprehensive sensitivity analysis is conducted to assess the robustness of the proposed algorithm, ensuring its reliability across varying parameter settings and problem instances. Lastly, we present key conclusions along with the limitations of the proposed approach, and suggest directions for future research building upon this work.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"8 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884570","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":"Flexible and objective diagnosis of type II diabetes by using a fuzzy deep learning ensemble approach","authors":"Min-Chi Chiu, Tin-Chih Toly Chen, Yu-Cheng Wang","doi":"10.1007/s40747-025-01894-w","DOIUrl":"https://doi.org/10.1007/s40747-025-01894-w","url":null,"abstract":"<p>Deep learning (DL) applications have potential for improving the accuracy of type II diabetes diagnoses. However, existing DL applications for the diagnosis of type II diabetes have several drawbacks. For example, they maximize overall diagnostic performance rather than the diagnostic performance for each patient, they do not use objective rules to identify whether a patient has type II diabetes, and they sometimes provide the same diagnostic results for patients with different real diagnoses. To address these drawbacks, the present study developed a fuzzy DL ensemble (FDLE) approach. In this approach, several autoencoder (AE)–fuzzy deep neural networks (FDNNs) with different configurations are constructed and used to predict the probability of a patient having type II diabetes. The probability predictions are fuzzy values based on the patient’s attributes. The fuzzy probabilities predicted by the constructed AE-FDNNs are then aggregated using the fuzzy weighted intersection–radial basis function method. Subsequently, on the basis of the aggregated result, several objective and subjective diagnostic rules are created. The developed FDLE approach was applied to a real case to examine its effectiveness. According to the experimental results, this approach outperformed 10 existing methods by up to 21% in terms of accuracy in diagnosing type II diabetes. The different diagnostic rules created in the FDLE approach complement each other and facilitate an accurate diagnosis.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"8 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873074","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":"Directly Attention loss adjusted prioritized experience replay","authors":"Zhuoying Chen, Huiping Li, Zhaoxu Wang","doi":"10.1007/s40747-025-01852-6","DOIUrl":"https://doi.org/10.1007/s40747-025-01852-6","url":null,"abstract":"<p>Prioritized Experience Replay enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that is originally used to estimate Q-value functions, which brings about the estimation deviation. In this article, a novel off-policy reinforcement learning training framework called Directly Attention Loss Adjusted Prioritized Experience Replay (DALAP) is proposed, which can directly quantify the changed extent of the shifted distribution through Parallel Self-Attention network, enabling precise error compensation. Furthermore, a Priority-Encouragement mechanism is designed to optimize the sample screening criteria, and enhance training efficiency. To verify the effectiveness of DALAP, a realistic environment of multi-USV, based on Unreal Engine, is constructed. Comparative experiments across multiple groups demonstrate that DALAP offers significant advantages, including faster convergence and smaller training variance.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"6 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873073","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":"MSTNet: a multi-stage progressive network with local–global transformer fusion for image restoration","authors":"Ruyu Liu, Lin Wang, Jie He, Jiajia Wang, Jianhua Zhang, Xiufeng Liu, Chaochao Wang, Haoyu Zhang, Sheng Dai","doi":"10.1007/s40747-025-01892-y","DOIUrl":"https://doi.org/10.1007/s40747-025-01892-y","url":null,"abstract":"<p>Image restoration is a challenging and complex problem involving recovering the original clear image from a degraded or noisy image. In the medical field, image restoration techniques can significantly improve the quality of endoscopic images, helping doctors make more accurate diagnoses and providing higher-quality data support for computer vision-assisted detection. Existing methods for image restoration mainly use convolutional neural networks (CNNs) or Transformer models, which have different advantages and limitations in capturing spatial and channel information of the image. This paper proposes a novel Multi-Stage progressive image restoration Network based on a blend of local–global Transformers, named MSTNet. Our network consists of three stages, each using a different type of Transformer module to obtain local and global information. The first two stages use window-based Transformer modules, which can effectively extract local spatial information within each window. The third stage uses channel-level Transformer modules to capture global channel information across the whole image. We also introduce a fusion module to combine the features from different Transformer branches and obtain a comprehensive and accurate feature representation. We conduct extensive experiments on various image restoration tasks, such as deblurring and denoising, evaluating our approach on both general image restoration datasets and our proposed colon dataset. The results demonstrate the effectiveness and superiority of our network over state-of-the-art methods.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"43 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873075","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":"VTformer: a novel multiscale linear transformer forecaster with variate-temporal dependency for multivariate time series","authors":"Rui Dai, Zheng Wang, Jing Jie, Wanliang Wang, Qianlin Ye","doi":"10.1007/s40747-025-01866-0","DOIUrl":"https://doi.org/10.1007/s40747-025-01866-0","url":null,"abstract":"<p>Recently, the prosperity of linear models has raised questions about capturing the sequential capabilities of Transformer forecasters. Although the latest Transformer-based studies have alleviated some of these concerns, the limited information utilization still constrains the model’s comprehensive exploration of complex dependencies, as these forecasters often prioritize global dependence on time stamps and overlook correlations between different variates. To this end, we reflect on the competence of Transformer components and present an efficient lightweight Transformer forecaster named VTformer. Concretely, a Transformer with multiscale linear attention is constructed to mine the global variate correlation and long-term temporal dependence of time series data in parallel, providing multifaceted dynamics for the downstream self-attention mechanism. Moreover, a novel adaptive fusion method is designed to propagate complementary information from the perspective of variate and temporal to promote prediction. Extensive experiments on eight real-world datasets demonstrate that VTformer outperforms state-of-the-art models in long-term Multivariate Time Series Forecasting (MTSF) tasks, thereby advancing the accuracy and efficiency of Transformers.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"47 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143866190","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":"An edge enhancement graph neural network model with node discrimination for knowledge graph representation learning","authors":"Tao Wang, Bo Shen","doi":"10.1007/s40747-025-01860-6","DOIUrl":"https://doi.org/10.1007/s40747-025-01860-6","url":null,"abstract":"<p>The vectorized representation of a knowledge graph is essential for effectively utilizing its implicit knowledge. Graph neural networks (GNNs) are particularly adept at learning graph representations due to their ability to handle graph topologies. However, GNN-based approaches face two main challenges: first, they fail to differentiate between the types of adjacent nodes during the information aggregation process; second, the edge representations lack relational semantic information and fail to capture the characteristics of adjacent nodes. Conventional methods typically treat source and destination nodes as identical, ignoring the distinct information that arises from different node types. This results in a failure to accurately capture the various semantic features, leading to feature redundancy. Additionally, many existing methods derive edge representations through random initialization or linear transformations, which do not adequately reflect relational semantics and adjacent node information, resulting in ineffective edge representations.To address these limitations, we propose the Edge Enhancement GNN model with Node Discrimination (NDEE-GNN). This model establishes node discrimination information aggregation mechanisms for source and destination nodes, allowing for a deeper investigation into the impact of various adjacent node types. It also employs a specially designed information aggregation mechanism for each edge, incorporating relation and adjacent node features. Experimental results across multiple real-world datasets demonstrate that by discriminating node types and enhancing edge representations, NDEE-GNN can accurately capture and represent complex associations between entities and relations, significantly improving link prediction performance and outpacing other baseline models.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"73 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143866192","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":"Analysis of quantum fully homomorphic encryption schemes (QFHE) and hierarchial memory management for QFHE","authors":"Shreya Savadatti, Aswani Kumar Cherukuri, Annapurna Jonnalagadda, Athanasios V. Vasilakos","doi":"10.1007/s40747-025-01851-7","DOIUrl":"https://doi.org/10.1007/s40747-025-01851-7","url":null,"abstract":"<p>Homomorphic encryption is a recent and fundamental breakthrough in modern cryptography, which allows the performance of operations on encrypted data without unveiling the data. Leveraging quantum mechanics principles, quantum computers can potentially solve certain computational problems exponentially faster than classical computers. This immense computational power offers new possibilities for various fields, including cryptography. The rapid evolution of both these fields has led to the development of quantum fully homomorphic encryption (QFHE), which makes the capabilities of classical HE extend into the quantum domain. However, many existing QFHE schemes require significant memory due to complex calculations and fault-tolerance needs. This paper contributes in two ways. First, we provide a comprehensive survey of two specific QFHE schemes, discussing their underlying principles, mathematical frameworks, security aspects, and practical applications. We also explore the challenges posed by quantum computing and how QFHE addresses these to achieve both security and computational efficiency. Second, we propose a new hierarchical memory management system for QFHE, which includes a “quantum cache” (a specialized memory storage for quantum data) and a “reinforcement learning agent” (an intelligent system that learns from experience to optimize decisions). This system dynamically manages data movement between the cache and classical memory, improving memory efficiency and potentially boosting computational performance.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"35 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862910","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":"An extended TOPSIS technique based on correlation coefficient for interval-valued q-rung orthopair fuzzy hypersoft set in multi-attribute group decision-making","authors":"Rana Muhammad Zulqarnain, Imran Siddique, Sameh Askar, Ahmad M. Alshamrani, Dragan Pamucar, Vladimir Simic","doi":"10.1007/s40747-025-01838-4","DOIUrl":"https://doi.org/10.1007/s40747-025-01838-4","url":null,"abstract":"<p>The accurate determination of results in decision analysis is usually predicated on the association between two factors. Although generating data for analytical purposes presents an apparent hurdle, the data obtained may present hurdles in its interpretation. Correlation coefficients can be used to analyze the interaction between two factors and their variations. These coefficients deliver an objective description of the association between parameters, assisting in predicting and assessing alterations between particular parameters. The purpose of this research is to explore the applicability of correlation coefficients (CC) and weighted correlation coefficients (WCC) in interval-valued q-rung orthopair fuzzy hypersoft sets (IVq-ROFHSS) structures with their essential characteristics. These measures are developed to address the inevitable confusion, inconsistency, and volatility in real-life decision-making challenges. The implementation of these components attempts to boost the productivity of the technique for order preference by similarity to the ideal solution (TOPSIS) method. The computational models with correlation constraints are presented to determine the reliability and regularity of the proposed method. This research proves that the proposed technique is effective for multi-attribute group decision-making (MAGDM), particularly for analyzing and prioritizing convoluted data sets. Moreover, a numerical illustration is presented to clarify how the advocated decision-making methodology can be implemented in reality in evaluating bio-medical disposal techniques for hospitals. This study determines incineration as the most beneficial method for BMW disposal, demonstrating its more efficient use of alternative disposal techniques. A comparative analysis further substantiates the feasibility and effectiveness of the proposed approach over other decision-making techniques.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"33 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143862906","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}