International Journal of Intelligent Systems最新文献

This work introduces a multiagent deep reinforcement learning (MADRL) framework for energy harvesting (EH) in unmanned aerial vehicle (UAV) networks aided by reconfigurable intelligent surfaces (RIS). The core goal is to maximize quantities of harvested energy subject to quality of service (QoS) constraints in dynamic wireless setups. The considered model involves centralized training alongside decentralized execution, together with replay-based learning to yield stable convergence. Extensive experiments are included in a comparison between MADRL and evolution strategies (ES), deep deterministic policy gradient (DDPG), stochastic DDPG (SD3), and state of the art twin delayed DDPG (TD3)–based approaches. The outcomes verify that MADRL ensures an average throughput of over 300 Mbps when deployed with four UAVs, exceeding DDPG and closing in on TD3 and adaptive TD3, and consumes minimal processing time and memory resources. In time-domain tests, MADRL maintains an EH fraction in the range of approximately 0.27–0.31 ((mean≈0.29)), and in dual-domain evaluation, it sustains an EH fraction of approximately 0.73–0.75 (mean≈0.74), indicating robust energy performance under both scenarios. Parameter sensitivity analysis also confirms the selection of hyperparameter α, β, η, and γ as optimal trade-offs at α = 0.6, β = 0.8, η = 3 × 10⁻⁴, γ = 0.98. The computational tests verify potential practicability in real-time applications, where MADRL only takes 0.42 s and 1.8 GBs, respectively, for each episode, and in terms of memory. These confirmations reflect the potential applicability of MADRL in scalable UAV RIS networks and thus provide potential applications in energy-efficient wireless setups.

Traffic condition estimation and distinguishing from real-time video cameras are essential research in traffic information systems (ITSs), providing accurate and live traffic information to commuters and traffic management, as video-based traffic data are available ubiquitously. However, many challenges need to be resolved, including the complexity of video data with multiple vehicle types in chaos traffic environments, such as those in developing countries like Vietnam, the lack of specific training datasets, and the appropriate selection or modification of pretrained deep learning (DL) models for video data processing. This paper proposes a novel traffic congestion prediction method based on real-time traffic video analysis utilizing appropriate DL models. The proposed approach using YOLOv10, YOLOv8, and Faster R-CNN to detect and classify vehicles and region of interest (ROI) to calculate the occupied their area, which resulted in a prototype system for real-world applications consisting of three main stages: (i) traffic video data in a chaos traffic environment, specifically in Hanoi, Vietnam, are collected, preprocessed, and annotated for traffic conditions; (ii) various pretrained DL models for video data analysis specified to traffic condition estimations are studied to apply to the above traffic video data; and (iii) thorough evaluations using the implemented prototype with real-time video traffic data to confirm the effectiveness and the efficiency of the proposed method have been analyzed. The results indicate that the proposed method achieves up to 94% accuracy in vehicle detection and processes at a speed of 27 frames per second. The implemented prototype also provides a visual presentation of traffic density and makes reliable congestion predictions to commuters and management. The proposed approach not only supports traffic operation and management in regulating traffic flows but also paves the way for applying technology to address complex urban traffic challenges, especially in developing countries.

P. Liu and P. Wang, “Some q-Rung Orthopair Fuzzy Aggregation Operators and their Applications to Multiple-Attribute Decision Making,” International Journal of Intelligent Systems 33, no. 2 (2018): 259–280, https://doi.org/10.1002/int.21927.

In the article, there is an error in the definition of indeterminacy degree presented in Definition 1. The correct Definition 1 is shown below:

We apologize for this error.

The International Collegiate Programming Contest (ICPC) is widely regarded as one of the most prestigious algorithmic programming competitions for university students. Given the challenges faced by students from developing countries in preparing for the contest, it is important to examine how generative AI tools can support their learning and preparation. The effectiveness of two leading generative AI models, ChatGPT and DeepSeek, is evaluated in addressing complex programming problems based on the Association for Computing Machinery (ACM)’s International Collegiate Programming Contest (ICPC) (ACM ICPC). The evaluation of both models in terms of readability, error handling, computation speed, code accuracy, and educational value is presented in this study. In a two-trial experimental setup, both models are evaluated on 145 different ICPC problems from data structures, algorithms, mathematics, geometry, advanced optimization, and so on. Prompts were standardized, and evaluation was conducted over two iterations to simulate iterative learning. The results indicate that both DeepSeek and ChatGPT improved their performance over time. DeepSeek consistently outperformed ChatGPT in code accuracy (88.28% vs. 84.14%), both generated more efficient algorithms for linear time complexity (41 vs. 19), and had lower logical error rates (7.58% vs. 15.86%). DeepSeek and ChatGPT performed almost the same in code quality scores (37.79 vs. 37.85). Approximately 46.90% of the solutions generated by DeepSeek were fully insightful, surpassing ChatGPT’s 42.07%. However, ChatGPT demonstrated significant improvement across trials, particularly drastically reducing syntax errors from 4.83% to 0.69%. DeepSeek outperforms ChatGPT in high-stakes programming scenarios, making it the more suitable choice. These results offer actionable guidance for incorporating generative AI tools into advanced programming education.

Risk disclosures play a crucial role in the investment decision-making processes for investors. However, extracting relevant variables from unstructured financial text poses a nontrivial challenge. In this paper, we propose RiskBERT, a large language model (LLM) trained on financial texts and risk knowledge graphs, specifically designed for risk factors extraction. By incorporating both finance and risk knowledge, RiskBERT significantly improves the extraction of risk factors in financial texts. We evaluate RiskBERT’s performance on a labeled risk factors dataset comprising 119,153 sentences from 2400 Chinese A-listed companies and compare it against other LLMs and automated text analysis algorithms for risk types’ classification. Our findings demonstrate that RiskBERT outperforms alternative models, particularly when the training sample size is limited. Moreover, we uncover that RiskBERT provides risk informativeness estimates in annual reports that are at least 4.5% higher than those derived from other models. These results highlight the value of RiskBERT as a powerful tool for extracting risk factors and enhancing risk analysis in finance and accounting domains.

The growing requests for extremely fast indoor wireless connectivity have introduced significant challenges in designing next-generation communication systems to build Internet of things (IoT)–enabled fully connected smart environments, particularly at higher frequency bands such as millimeter wave (mmWave/MMW). Accurate channel modeling is critical for optimizing these systems, especially in indoor environments where reflections, diffractions, and penetration losses considerably impact signal propagation. This study presents a detailed channel modeling approach using ray tracing techniques to characterize mmWave signal behavior in complex indoor scenarios. To accurately capture essential parameters including path loss, delay spread, and angular spread, the approach simulates signal interactions with environmental elements (e.g., walls, floors, and furniture) by leveraging three-dimensional (3D) building models. The study provides a deeper understanding of line-of-sight (LOS) and non-line-of-sight (NLOS) propagation. Furthermore, it comprehensively compares the propagation characteristics of various frequency bands, ranging from sub-6 GHz (e.g., 2.4 and 6 GHz) to mmWave (e.g., 28, 60, and 100 GHz), thereby highlighting their distinct behaviors under identical indoor conditions and user trajectories. Using ray tracing, channel impulse responses and path loss metrics are extracted, and coverage map of received power is proposed for each position. Results demonstrate that mmWave bands experience higher path losses than sub-6 GHz frequencies and are significantly affected by shadowing and blockage. This study not only validates the accuracy of the ray tracing model against empirical data but also demonstrates its utility in designing robust mmWave communication systems, optimizing network deployments, and enhancing beamforming strategies for future 5G and 6G networks.

In recent years, the plagiarism of comic images has become increasingly prevalent, drawing growing attention to copyright protection within the comic industry. To address the limitations of existing object detection models in capturing the distinctive visual characteristics of comic images, this paper proposes an optimized detection framework, MANGA-YOLOv8s (MA-YOLOv8s). Specifically, a large separable kernel attention-based spatial pyramid pooling (SPPF-LSKA) module is designed to expand the effective receptive field and enhance multiscale feature aggregation for small-object detection. The C2f-DBB module is introduced into the detection head to refine deep feature representation while maintaining lightweight computation. Furthermore, a separated and enhancement attention module (SEAM) is incorporated into the detection heads to improve robustness against scale variation and suppress false detections. Unlike simple combinations of existing modules, these designs form a theoretically motivated and task-specific integration that adapts the YOLOv8 framework to the structural and stylistic characteristics of comic images. Experiments on the Manga109 dataset demonstrate that MA-YOLOv8s achieves a 3.7% improvement in mAP and a 3.4% increase in precision compared with YOLOv8s. The proposed method offers both theoretical and practical contributions to the development of efficient detection techniques for comic copyright protection.

Deepfake technology, driven by advancements in deep learning and large language models, has found widespread applications across various fields. In the context of physical health management and application, deepfake presents new possibilities for media production, athlete representation, training enhancement, and historical event recreation. This review explores the multifaceted applications of deepfake in the health industry with the help of various generative technologies like large language models, analyzing its potential to transform broadcasting, virtual athlete branding, and tactical simulation. While the technology offers numerous benefits, it also poses significant risks, such as the spread of misinformation, privacy violations, unfair competition, and ethical dilemmas. This paper addresses these challenges and discusses the regulatory measures needed to ensure the ethical deployment of deepfake technology in physical health. Additionally, it highlights emerging detection techniques and suggests proactive strategies for health organizations to mitigate deepfake-related threats. The review concludes with an outlook on future innovations, emphasizing the importance of balancing technological advancement with legal and ethical considerations to safeguard the integrity of the health industry.

In response to the multifactory collaborative distributed characteristics of building material equipment during the manufacturing process, this paper studies the two-stage (production–assembly) distributed assembly flexible job shop scheduling problem (DAFJSP) and constructs a corresponding mathematical model. To address this complex NP-hard problem, a hybrid genetic algorithm with variable neighborhood search (HGA-VNS) is proposed. The algorithm integrates multiple crossover and mutation strategies, thereby significantly enhancing global search capabilities. Concurrently, the implementation of four neighborhood operations has been demonstrated to enhance local search efficiency. To validate the effectiveness and superiority of the proposed algorithm, comparative experiments with other scheduling algorithms were conducted. The findings indicate that the proposed algorithm demonstrates notable advantages in addressing the DAFJSP.

The location of a robot is a key aspect in the field of mobile robotics. This problem is particularly complex when the initial pose of the robot is unknown. In order to find a solution, it is necessary to perform a global localization. In this paper, we propose a method that addresses this problem using a coarse-to-fine solution. The coarse localization relies on a probabilistic approach of the Monte Carlo localization (MCL) method, with the contribution of a robust deep learning model, the MinkUNeXt neural network, to produce a robust description of point clouds of a 3D LiDAR within the observation model. The MCL method has been approached from a topological perspective, considering that the particles are initialized on the map positions where LiDAR scans have been previously captured. For fine localization, global point cloud registration has been implemented. MinkUNeXt aids this by exploiting the outputs of its intermediate layers to produce deep local features for each point in a scan. These features facilitate precise alignment between the current sensor observation (query) and one of the point clouds on the map. The proposed MCL method incorporating deep local features for fine localization is termed MCL-DLF. Alternatively, a classical ICP method has been implemented for this precise localization aiming at comparison purposes. This method is termed as MCL-ICP. In order to validate the performance of the MCL-DLF method, it has been tested on publicly available datasets such as the NCLT dataset, which provides seasonal large-scale environments. In addition, tests have been also performed with our own data (UMH) that also include seasonal variations on large indoor/outdoor scenarios. The results, which were compared with established state-of-the-art methodologies, demonstrate that the MCL-DLF method obtains an accurate estimate of the robot localization in dynamic environments despite changes in environmental conditions. For reproducibility purposes, the code is publicly available.