首页期刊导航|International journal of modeling, simulation and scientific computing
期刊信息/Journal information
International journal of modeling, simulation and scientific computing
World Scientific Publishing
International journal of modeling, simulation and scientific computing

World Scientific Publishing

季刊

1793-9623

International journal of modeling, simulation and scientific computing/Journal International journal of modeling, simulation and scientific computing
正式出版
收录年代

    YOLO-TFD: An efficient object detecting model for automatic monitoring of the degree of fermentation of tea

    Yintana BaLinxuan Zhang
    1.1-1.18页
    查看更多>>摘要：Tea is a popular beverage with significant economic value, but its production process has a low level of intelligence and is mainly monitored manually, which affects the economic benefits. In order to solve this problem, this paper proposes a system to classify different fermentation levels of tea based on computer vision. The system consists of two stages. In the first phase, the YOLO v7 detection model is improved by adding densely connected transformer encoders at the tail of the backbone, which improves the extraction of key features in the target area. Meanwhile, the MobileOne module is used instead of the E-ELAN module of the YOLO v7 backbone to reduce the inference speed of the model. BiFPN is selected instead of PA-FPN to improve the feature fusion performance further and reduce the computational complexity. For the feature of mutual occlusion in tea leaf greening images, in order to capture a broader range of background information, the structure of SPPCSPC in YOLO v7 is changed, the maximum pooling layer running in parallel is changed to serial operation, and the global average pooling layer and the global maximum pooling layer are introduced, in order to reduce the loss of crucial semantic information that may be caused by relying on the edge information only and ignoring the background information. In the second stage, the detected tea leaves are graded on the basis of their color characteristics by the RGB model for the degree of fermentation of the tea leaves. The experimental results show that The mAP, precision, and recall of YOLO-TFD are higher by 6.2%, 8.6%, and 6% than YOLO v7. In addition, the model was deployed in PyQt5 for real-time detection and grading of tea during fermentation. This method provides a new solution for enhancing the intelligence of the tea production process and has potential industrial applications.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Erasing backdoor of deep neural networks using neural perturbation-based attention distillation

    Jiaxing ChenHan YanBo LiuShaofeng Zhao...
    1.1-1.27页
    查看更多>>摘要：In the realm of safety-critical domains, the security of Deep Neural Networks (DNNs) is constantly challenged by the insidious threat of backdoor attacks. These attacks, which manipulate model outputs through malicious triggers, impede the development of DNNs in mission-critical applications. Despite the progress made by existing defense mechanisms, it remains unclear how to remove backdoor-related neurons from DNNs effectively. To address this challenge, we propose a novel eraser-based framework called Neural Perturbation-based Attention Distillation (NPAD). NPAD utilizes the ideas of neural perturbation and neural attention distillation. Initially, the teacher network perturbs the backdoor neurons to reveal their presence, followed by the targeted pruning operations. Subsequently, attention distillation is performed on the student network under the guidance of the adapted teacher network, thus maintaining its resilience against backdoor attacks and enhancing defense performance. During the knowledge transfer process, we introduce a weighted attention alignment mechanism to accelerate convergence during training, thereby achieving the resultant student network with heightened robustness. The experimental results clearly demonstrate that NPAD consistently outperforms a variety of existing state-of-the-art methods in mitigating the effects of backdoor attacks, where NPAD outperforms Neural Attention Distillation (NAD) (the best of the four defense methods) by 9.75% in the average reduction on the attack success rate of 10 backdoor attacks. Furthermore, the results also show that NPAD effectively eliminates backdoor triggers by utilizing a mere 1% of clean training data while simultaneously preventing any significant decline in performance on clean data.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Numerical computation of dropper stress and fatigue life in a catenary system under fluctuating wind load

    Fan HeJiangchuan HaoXinxin ShenLiming Chen...
    1.1-1.25页
    查看更多>>摘要：In this paper, numerical computation of dropper stress and fatigue life in a catenary system under fluctuating wind load is performed. We take contact wire as a beam element and obtain the response equation under the action of moving load and fluctuating wind load. Thus, we determine the initial boundary value conditions of the vibration equation of the dropper and calculate dropper stress and fatigue life under different conditions. The results show that when contact wire is subjected to fluctuating wind load with a constant wind attack angle, the higher the wind speed, the more serious the fatigue damage caused by fluctuating wind to the dropper. When the wind speed is constant, the smaller the wind attack angle is, the smaller the adverse effects of fluctuating wind on the dropper are. Under the fluctuating wind, fixed wind attack angle and wind speed, the higher the amplitude of the sinusoidal force is, the more likely the dropper is to break, and dropper IV is more sensitive to the amplitude increase. Under the conditions of different wind speeds, attack angles, and amplitudes, dropper IV is most likely to break. This work is helpful to analyze the train safety problems caused by droppers, so as to reduce the safety risks.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Novel results on impulsive Caputo–Hadamard fractional Volterra–Fredholm integro-differential equations with a new modeling integral boundary value problem

    Abdulrahman A. SharifMaha M. HamoodAhmed A. HamoudKirtiwant P. Ghadle...
    1.1-1.21页
    查看更多>>摘要：The purpose of this paper is to investigate, the existence and uniqueness of solutions for nonlinear fractional impulsive fractional Volterra–Fredholm integro-differential equations of the Caputo–Hadamard type, with a new modeling integral boundary value problem. The Krasnoselskii fixed-point theorem, Schaefer’s fixed point theorem, and the Banach contraction principle serve as the basis of this unique strategy and are used to achieve the desired results. An example illustrates the theoretical findings.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    An enhanced asymmetric quantization Boolean encryption for secure routing in wireless sensor networks

    M. SudhaM. SaravanakumarPradeep JangirElangovan Muniyandy...
    1.1-1.26页
    查看更多>>摘要：For Wireless Sensor Networks (WSNs) to be both secure and effective, a secure routing method is essential. Enhancing data aggregation, data security, and routing security has been the focus of recent research; nonetheless, these strategies frequently face major obstacles, such as time complexity, vulnerability to malicious assaults, and worries about data insecurity. In order to tackle these problems, a secure routing protocol for WSNs named Asymmetric Quantization Boolean Encryption Growth Network with Leopard Seal Routing Protocol (AQBEGNet-LSRP) has been suggested. In order to cluster sensor nodes, this model uses the Growth Optimizer (GO) technique, choosing the Cluster Head (CH) according to node similarity. A Deep Progressive Asymmetric Quantization Neural Network (DPAQNNet) is used for data aggregation, and Boolean Network Encryption with Asynchronous Updating Algorithm (BNEAUA) protects data during transmission and thwarts attacks. For encrypted data transit, the best routes are then chosen by the upgraded Leopard Seal Routing Protocol (LSRP). With its remarkable performance characteristics, which include a 110 Kbps throughput, an 80% network lifetime, and a low latency of 0.02ms, in addition to its 99% Packet Delivery Ratio (PDR) and 99% network security, the suggested model is a dependable and effective method for transmitting secure data.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Can short-term memory processes be accurately detected? A reexamination of existing definitions

    Hossein HassaniManuela Royer-CarenziMohammad Reza YeganegiLeila Marvian Mashhad...
    1.1-1.16页
    查看更多>>摘要：One major inadequacy in using the sample autocorrelation function (ACF) is the results from sample properties. Hassani’s −12 theorem demonstrates that the sum of the sample ACF is always −12 for any time series with any length. This result has led to doubts about methodologies that sum sample ACFs for diagnostics and analyses. Thus, the current tools and approaches fall short in detecting short-memory processes with due accuracy. Perhaps the larger question that looms here is about whether, with such definitions and methods, short-memory processes can really be picked up? Resolving this issue stands as a basic precursor to strong predictions and to precluding model mis-specification.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Effective numerical simulation of fault transient system

    Sixu WuFeng JiLu GaoRuili Zhang...
    1.1-1.24页
    查看更多>>摘要：Power systems, including synchronous generator systems, are typical systems that strive for stable operation. In this paper, we numerically study the fault transient process of a synchronous generator system based on the first benchmark model. That is, we make it clear whether an originally stable generator system can restore its stability after a short time of unstable transient process. To achieve this, we construct a structure-preserving method and compare it with the existing and frequently-used predictor–corrector method. We newly establish a reductive form of the circuit system and accelerate the reduction process. Also a switching method between two stages in the fault transient process is given. Numerical results show the effectiveness and reliability of our method.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Research on optimization A* algorithm based on energy consumption of mobile navigation robot

    Bin HongZhan CaoFugeng LiYahui Nie...
    1.1-1.20页
    查看更多>>摘要：A novel energy-efficient optimization A* algorithm is proposed to address the performance requirements of energy consumption reduction and global optimality in the context of mobile navigation robots for the visually impaired. The energy cost function of mobile navigation robots is incorporated into a heuristic algorithm based on the A* algorithm to plan energy-optimal paths quickly. The optimized A* algorithm was compared with the original A* algorithm and the Q-learning algorithm through simulation experiments on a grid map using the MATLAB platform. The experimental results show that compared with the standard A* algorithm, the optimized A* algorithm reduces the path-planning time by 37.2% and the energy consumption by 29.5%. In addition, compared with the Q-learning algorithm, this algorithm’s overall search efficiency is improved by 76.8%. Simulation results show that the optimized A* algorithm is more efficient in searching and has a shorter seek time, fully saving energy.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Collaborative decision modeling of multi-agent based on BC-QMIX for air mission wargaming

    Ze WangNi LiGuanghong Gong
    1.1-1.27页
    查看更多>>摘要：The existing methods for air mission wargaming autonomous decision-making, such as optimization theory-based and expert systems, often suffer from insufficient real-time performance and high modeling workload. The application of multi-agent reinforcement learning (RL) in autonomous decision-making for air mission wargaming has received extensive attention. However, most existing RL approaches require online interaction, leading to low efficiency of sample collection and network training. This paper proposes BC-QMIX, the network structure of BC-QMIX employs supervised learning method to train a behavior cloning network for each sub-agent on the basis of the QMIX network, which provides a basis for action selection. Therefore, BC-QMIX alleviates the extrapolation error in the offline training of QMIX. Furthermore, when offline pre-training is conducted by utilizing domain knowledge-based samples, it accelerates the online training and convergence of network. Through experiments conducted in the Multi Drones Monitoring environment and two collaborative air mission wargaming scenarios, BC-QMIX demonstrates a significant reduction in extrapolation error and outperforms QMIX, MADDPG, and MATD3 in offline training. Specifically, it achieves a 10.1% improvement in average winning rate over QMIX, with this enhancement rising to 47.9% when domain knowledge is incorporated into the training process. This validation demonstrates the feasibility and advantage of constructing a collaborative autonomous decision-making model using BC-QMIX for air mission wargaming scenarios.
      原文链接:
    • NETL
    • NSTL
    • World Scientific

    Numerical analysis and stability of a fractional glucose–insulin regulatory system using the laplace residual power series method incorporating the Atangana–Baleanu derivative

    Sayed SaberSafa M. Mirgani
    1.1-1.22页
    查看更多>>摘要：This paper investigates the dynamics of a fractional-order glucose–insulin regulatory system using an enhanced Laplace residual power series method incorporating the Atangana–Baleanu derivative. The Atangana–Baleanu derivative, characterized by its nonlocal and nonsingular kernel, offers a more accurate representation of memory and hereditary effects in biological systems compared to traditional derivatives. By employing the enhanced Laplace residual power series method, the study achieves precise numerical solutions and captures the complex behaviors of the system, including stability, bifurcations, and chaotic oscillations. Stability analysis through Lyapunov exponents and bifurcation diagrams reveals the intricate transitions between stable, oscillatory, and chaotic regimes, influenced by fractional-order dynamics and parameter variations. The proposed method demonstrates significant improvements in computational efficiency and solution accuracy, particularly for fractional-order systems with complex interactions. This work highlights the potential of fractional calculus, especially the Atangana–Baleanu framework, in advancing our understanding of glucose–insulin regulation and designing effective strategies for diabetes management.
      原文链接:
    • NETL
    • NSTL
    • World Scientific