Digital Commons Network^™

Research On Control Strategy For Shortest Time Occupancy Of Auv Based On Improved Td3, Wenzhe Ren, Min Li, Xiangguang Zeng, Tao Zhang, Dijie Xie, Bei Peng

Journal of System Simulation

Existing occupancy models fail to fully consider the interference of underwater time-varying ocean currents and task time constraints, and AUVs lacks real-time motion control. To address these issues, a shortest time occupancy method based on quantile regression and distributed TD3 was proposed. The Bayesian inference method was used to identify hydrodynamic parameters, and the kinematic and dynamic models of AUVs were established; the shortest time occupancy equation was constructed, and the occupancy target point and occupancy time were solved; a first-order Gauss-Markov process was introduced to simulate the time-varying ocean current environment, and the training of control strategy for AUV …

Impact Angle-Constrained Dive Maneuver Guidance Method For Hypersonic Vehicles, He Wang, Gang Lei, Shaopeng Li

Journal of System Simulation

To address the impact angle control and maneuvering flight problem of hypersonic vehicles in the dive phase, this paper proposed a tracking guidance method integrating optimal Bézier curves and super-twisting sliding mode control. A three-dimensional Bézier curve trajectory satisfying the impact angle constraint was designed, and the maneuvering flight in dive phase was achieved by adding dynamic control points; to optimize impact velocity, a rapid calculation method for the impact velocity of the vehicle flying along the curve was derived, and the optimal reference trajectory was obtained by optimizing the control point parameters through sequential quadratic programming; to ensure …

Two-Stage Calibration And Optimization Method For Microscopic Traffic Simulation Model Parameters Based On Neural Network Surrogate Models, Yijia Liu, Chenjing Zhou, Dong Pan, Jian Rong, Yang Xiao

Journal of System Simulation

A two-stage calibration and optimization method is proposed to address the problem that parameter calibration methods for microscopic traffic simulation models are time-consuming. In the first stage, a surrogate model based on neural networks is trained to establish the mapping relationship between model parameters and evaluation indicators, and a genetic algorithm (GA) is combined to screen candidate parameters. In the second stage, after obtaining the approximate optimal parameters, by employing this set of parameters as initial values, a genetic algorithm is re-executed by combining the real simulation model for optimization to further improve calibration accuracy. Experimental results show that the …

Application Of Improved Multi-Objective Differential Algorithm In Robotic Arm Multi-Objective Trajectory Planning, Manqiang Liu, Ziqiang Shang

Journal of System Simulation

It is difficult for single-objective trajectory planning methods to meet the requirements of precision, diversity and complexity of robotic arms. A trajectory planning model based on an improved multi-objective differential evolution algorithm (guided multi-objective differential evolution, GMODE) algorithm is proposed. Cubic polynomial interpolation and B-spline curves are employed to construct multi-objective functions, while GMODE is adopted to overcome the limitations of traditional algorithms, such as insufficient population diversity, the tendency to fall into local optima, and slow convergence. A grouping strategy, parameter generation mechanism, and elite mutation based on fuzzy Cmeans clustering are introduced to optimize B-spline control nodes. …

Current Status And Prospects Of Complex Scene Reconstruction Based On Gaussian Splatting, Hong'an Li, Jiale Yang, Qingfang Liu, Yu Shi

Journal of System Simulation

Three-dimensional Gaussian splatting (3DGS) provides an alternative approach for novel view synthesis from the perspective of explicit representation. By reconstructing scenes using 3D Gaussian primitives and replacing traditional ray integration with a point-based rasterization process, it not only improves training and rendering efficiency but also offers new insights for complex scene reconstruction. This paper divided 3DGS-based complex scene reconstruction methods into three major categories and elaborated on them around large-scale scenes, sparse views, and dynamic scenes. It reviewed the current development status of this field and pointed out possible future research directions.

Experimental And Simulation Study On Energy Release Of Extended Sources Influenced By Atmospheric Pressure Variation, Kai Guo, Feiyu Zhao, Hao Zhang, Liang Wang, Kai Zhang

Journal of System Simulation

To investigate the energy release characteristics of extended sources in low-pressure environments, a combined experiment and simulation approach was adopted. Four typical altitudecorresponding pressures were selected as experimental conditions. An infrared thermal imager was employed to monitor parameters such as combustion temperature, radiance, and combustion area during the combustion process of the extended source. When the pressure decreases from 101 kPa to 30 kPa, the ignition time of the extended source doubles; the total energy release attenuates by 44.78%, and the combustion area reduces by 45.95%, but the fluctuations of peak temperature and average temperature are less than 3%, …

Research On Output Feedback Control Based On Reinforcement Learning For Overhead Crane, Minghui Li, Daoxiang Gao

Journal of System Simulation

An output feedback control algorithm is designed based on reinforcement learning for the optimal control problem of overhead crane system. A high gain observer (HGO) is designed using output data to estimate the unmeasurable states of the overhead crane system. Based on the estimated states from the high-gain observer, a policy iteration (PI) method is designed with integral reinforcement learning, which uses Critic and Actor neural networks to approximate the optimal value function and control strategy, and adjusts the neural network weights in real time through online adaptive algorithms. According to the Lyapunov stability theory, the uniform ultimate boundedness of …

Object Detection Networks And Their Interpretability In Rain, Fog, And Snow Scenarios, Yanji Jiang, Jiayu Cui, Hao Dong, Daqian Liu, Bowen Fei, Miao Yu, Jinshan Huang

Journal of System Simulation

To address the severe degradation of object detection performance under extreme weather conditions, a detection framework based on the Kolmogorov-Arnold theorem, termed KADet, is proposed. A dynamic Kolmogorov-Arnold Transformer is designed, which leverages learnable nonlinear activation functions to enhance the modeling capability for complex distortions introduced by weather degradation. A Kolmogorov-Arnold spatial-channel network is developed by integrating KAT convolution with spatial-channel convolution to strengthen feature learning of relationships between targets and backgrounds in degraded scenes. An improved loss function is introduced to guide the optimization of the activation functions, and interpretability is analyzed through visualization of their curves. …

Pattern Identification And Mechanism Analysis Of Nonlinear Oscillations In Grid-Connected Direct-Drive Wind Turbines, Libin Wen, Shaopu Tang, Xianfa Hu, Jinji Xi, Tongtong Zhang, Hong Hu, Weijie Zhang

Journal of System Simulation

Taking a grid-connected direct-drive wind turbine system as an example, a comprehensive model is developed that incorporates nonlinear elements such as prime mover control, machine-side and grid-side converter control, multiple limiters, and control switching. A nonlinear oscillation pattern identification method based on density clustering and manual identification is proposed. The results show that the proposed method can efficiently identify various typical patterns, including quasi-constant amplitude oscillations, period-doubling oscillations, and chaotic oscillations. Oscillations dominated by nonlinear factors such as control switching, limiter collision, and limiter saturation are essentially caused by the transition of the associated components from passive responses to …

Iterative Evolution And Innovation Of Simulation-Based Experimental Teaching In Software Engineering, Jun Guo, Yixian Liu, Lianbo Ma, Jian Liu, Chunyan Xu

Journal of System Simulation

In view of the structural disconnection between talent training and industry needs caused by the limitations of traditional computer experiment teaching in scenario authenticity, technological frontier, interdisciplinary integration, and student subjectivity, this paper proposed and practiced a new simulation-based experimental teaching system deeply integrating Chinese educational wisdom. Taking "incremental progress and learning by guided inquiry" as the core philosophy, through a four-in-one paradigm transformation of "task modularization, scenario virtualization, technological frontier, and integration deepening", this paper promoted the teaching to shift from closed skill verification to open engineering innovation and constructed a complete implementation path including "closed-loop iterative teaching process" …

Robot Friction Force Compensation Algorithm Integrating Temperature And Speed Factors, Jinwang Lü, Ankai Ying, Ming Li, Tao Song, Jie Zhang, Fanghui Qiu, Changcheng Shi, Guokun Zuo, Jialin Xu

Journal of System Simulation

Insufficient friction force compensation accuracy degrades motion smoothness, stability, and assistive compliance of elbow joint rehabilitation robots. To address this issue, an improved Stribeck friction force model integrating temperature and speed factors was proposed. The model employed an exponentially decaying friction factor to describe the characteristic that the increase rate of friction force slowed down with the rise of the robot's operating speed and designed a viscous function considering temperature effects to suppress friction force fluctuations caused by temperature changes. Experimental results indicate that the model achieves stable friction force compensation under different operating states of the robot and has …

Building Trustworthy Information Systems: A Unified Framework For Comparative Risk Detection, Parisa Momeni

USF Tampa Graduate Theses and Dissertations

Risk detection in large scale information systems increasingly depends on heterogeneous data generatedby both centralized and distributed ecosystems. While centralized systems provide curated and validated reports, distributed environments produce large-scale and real-time observational evidence. Existing computational approaches analyze these ecosystems in isolation, limiting systematic comparison of risk repre-sentations across heterogeneous sources.

This dissertation presents a unified computational framework for comparative risk detection across centralized and distributed information systems. The framework provides a domain independent methodology for transforming heterogeneous risk reporting data into comparable multidimensional representations. To enable interpretable comparison of heterogeneous risk distributions, this work introduces the Geometric Overlap Score …

To What Extent Could Quantum Computing Pose A Threat To Global Modern Data Security?, Aniket Maheshwari

Journal of Cybersecurity Education, Research and Practice

Quantum computing has emerged as a transformative technology with the potential to fundamentally disrupt modern cryptographic systems that underpin global data security. This paper examines the extent to which quantum computing could pose a threat to modern global data security by synthesising existing technical, institutional, and policy-oriented literature. Drawing on a narrative review of scholarly research, industry reports, and government frameworks, the analysis focuses on the implications of quantum algorithms such as Shor’s and Grover’s, which challenge the mathematical foundations of widely used cryptographic schemes. The findings suggest that while quantum computing presents a credible long-term threat to asymmetric encryption …

Label-Flip Attack Detection Via Trust-Weighted Aggregation In Federated Learning For Underground Mine Security, Md Sazedur Rahman, Sanjay Madria, Samuel Frimpong

Computer Science Faculty Research & Creative Works

Underground mining operations are increasingly dependent on autonomous vehicles, robotic drilling systems, and intelligent inspection platforms operating in confined, GPS-denied tunnel environments. These systems rely on distributed perception models to interpret navigation cues, hazard warnings, and environmental signals in real time. While centralized deep learning can enhance model performance, transferring raw operational data across mining sites introduces serious confidentiality and security risks. Federated Learning (FL) offers a privacy-preserving alternative by enabling collaborative model training without sharing local datasets. However, deploying FL in underground mining introduces several critical challenges: (i) Training labels may be modified either maliciously by compromised clients or …

Where Evidence-Based Medicine Meets Ai: Promise, Pitfalls, And Practice, Sangil Lee, Joshua Davis, Ken Milne, Christina Shenvi, Lars K. Beattie, Martin Wegman, Laura Melville, Richard D. Shih, Bryan Kane

Department of Emergency Medicine Faculty Papers

No abstract provided.

Artificial Intelligence Empowers Particle Physics And Nuclear Physics: From Fundamental Research To Major Applications, Yifang Wang, Yuan He, Yao Huang, Wanbing He, Yi Jiao, Congqiao Li, Ke Li, Beijiang Liu, Yingqi Ma, Yugang Ma, Longgang Pang, Fazhi Qi, Sichao Tan, Chunpeng Wang, Meng Wang, Xiaoheng Xu, Xing Xu, Zhentang Zhao, Yingxun Zhang, Zhengde Zhang, Hongwei Zhao, Lina Zhao

Bulletin of Chinese Academy of Sciences (Chinese Version)

Particle physics and nuclear physics are core foundational disciplines for exploring the fundamental structure of matter and the origin of the universe. The deep integration of artificial intelligence (AI) technology is providing entirely new pathways to address systemic challenges such as the processing of massive amounts of multimodal data, the realization of extreme experimental conditions, bottlenecks in theoretical calculations, and the intelligent control of large-scale scientific facilities. The article systematically elaborates on how AI deeply empowers particle physics and nuclear physics, particularly in major application scenarios such as research on the fundamental structure and origin of mass of matter, the …

Consolidating Chemical Substance Creation Capability Through Ai For Science-Enabled Innovation Equity, Mengchu Jin, Wandong Wang, Jun Zhang, Yi Luo, Zaiku Xie, Jinlong Yang, Jun Jiang

Bulletin of Chinese Academy of Sciences (Chinese Version)

AI for Science (hereinafter referred to as AI4S) is driving profound changes in the paradigm of scientific research. Chemistry, as a central discipline for creating new substances and supporting major national strategic needs such as energy, health, dual carbon goals, advanced manufacturing, and ecological governance, is an important application scenario of AI4S. At present, innovation in the discipline of chemistry by young researchers still faces knowledge silos, capability silos, and resource silos: the accumulation of professional knowledge requires years of effort, frontier knowledge is highly differentiated, experimental capabilities are difficult to reuse, and high-end resources are difficult to coordinate, which …

Artificial Intelligence-Enabled Materials Innovation: Implementation Levels And Strategic Layout, Ziwei Zhao, Fengxiang Zhou, Yanglili Zhou, Can Wang, Pei Zhang, Weihua Wang

Bulletin of Chinese Academy of Sciences (Chinese Version)

Materials innovation has long been constrained by vast design spaces, complex processing routes, lengthy validation cycles, and difficulties in engineering translation. Traditional research and development models, which mainly rely on accumulated experience, theoretical deduction, and experimental trial and error, have become increasingly insufficient to meet the demand for rapid breakthroughs in critical materials. In recent years, artificial intelligence has been increasingly integrated into materials design, synthesis, and processing, characterization, evaluation, optimization, and application feedback, promoting the transformation of materials innovation from experience-driven exploration to data-driven development and from discrete trial and error to closed-loop optimization. Based on an analysis of …

Artificial Intelligence Empowering Space Science—Case Study Of Space Weather, Chi Wang, Hui Li, Bingxian Luo, Fang Shen, Jingjing Wang, Lingqian Zhang, Yi Yang, Dong Zhao

Bulletin of Chinese Academy of Sciences (Chinese Version)

Space science is currently confronted with a triple challenge: the explosive growth of observational data, the strongly coupled cross-scale nature of physical processes, and the increasingly urgent national strategic demands. The limitations of traditional research paradigms in analytical efficiency, forecast accuracy, and autonomous capability hinder their effectiveness in meeting critical requirements such as safeguarding on-orbit satellites and ensuring the successful execution of major space missions. This study proposes a three-layer “perception–cognition–decision-making” architecture for intelligent space science. Taking space weather—a domain with strong operational relevance—as a representative case, the four-dimensional paradigm transformation driven by artificial intelligence is systematically examined across key …

Artificial Intelligence Empowering Remote Sensing: Challenges, Paradigms And Strategic Layout, Jiayuan Shen, Peirui Cheng, Zhirui Wang, Wei Liang, Xian Sun, Yirong Wu

Bulletin of Chinese Academy of Sciences (Chinese Version)

Remote sensing science and technology, as a key discipline for Earth observation and global change research, faces systemic challenges in processing massive multi-source data, accurately extracting complex information, and delivering high-timeliness application services. The rapid advances in artificial intelligence (AI) provide a new opportunity to address the deep-seated dilemma in remote sensing of being “data-rich but insufficient in effective information mining”. Guided by a problem-oriented approach, this study first systematically analyzes the core challenges facing the development of remote sensing across four dimensions: data understanding, technical methods, scientific mechanisms, and application ecosystems. It then reviews the technical evolution of AI-empowered …

Artificial Intelligence For Deep Earth Science: Key Challenges, Major Application Scenarios And Development Pathways, Qingyun Di, Liang Zhao, Yikang Zheng, Zhi Geng, Zhichao Yu, Xiaocai Shan, Chao Li, Zhiyao Xu, Pengfei Lv

Bulletin of Chinese Academy of Sciences (Chinese Version)

Deep Earth science is central to understanding Earth’s internal architecture and the coupled evolution of its major spheres, while also underpinning energy security, the supply of critical mineral resources, and resilience to major geohazards. Nevertheless, the advancement of deep Earth science is currently hindered by insufficient in situ observations under extreme conditions, the difficulty of integrating multi-source heterogeneous data, and the limited capability to model complex multiphysics coupling processes. Recent advances in artificial intelligence offer a potential route beyond these limitations. By integrating data-driven learning with physical and geological understanding, AI is reshaping deep Earth science from empirical interpretation to …

Artificial Intelligence Empowered Biological Research: Paradigm Shifts, Application Scenarios, And Strategic Layout, Xinguang Zhu, Yiming Bao, Zhenong Jin, Xin Li, Sijia Wang, Yueming Wang, Yungui Yang, Cao Xu, Yan Xiong, Bin Han

Bulletin of Chinese Academy of Sciences (Chinese Version)

Life related processes are characterized by high dimensionality and multi-scale properties. Understanding mechanisms underpinning life processes helps promote national healthcare, agricultural development, sustainable ecological civilization, and national security. Current life science research is confronted with an enormous challenge of dimensionality stemming from data explosion and data fragmentation, for which the recent rapid advancement of artificial intelligence (AI) provides novel solutions. AI will catalyze a paradigm shift in life science research from the current experiment based empirical induction to a new closed-loop knowledge acquisition including large scale data collection, model building, model prediction, experimental validation, and iterative of these procedures. Life …

Artificial Intelligence–Driven Paradigm Transformation In Biopharmaceutical R&D: Applications And Emerging Scenarios, Lili Liu, Mingyue Zheng, Ye Yuan, Xutong Li, Rong Fan, Wei Wei, Jinxin Zhao, Guobin Qi, Hua Yue, Likun Gong, Songping Zhang, Jiachen Li, Yuchen Sun, Xiaoyan Chen, Yao Chen, Xin Liu, Xiao Zhang, Yuehong Gao, Jianfeng Li, Kaixian Chen, Guanghui Ma, Jianmin Yue

Bulletin of Chinese Academy of Sciences (Chinese Version)

The biopharmaceutical industry is a critical domain underpinning national scientific and technological innovation development and public health. With the rapid advancement of artificial intelligence (AI) and its deep integration with the life sciences, biomedicine research is undergoing a paradigm shift from traditional experience-driven trial-and-error approaches to data-driven and predictive validation-based models. This study systematically examines the pathways for reshaping research in biomedicine paradigms under the convergence of data-driven, mechanism-driven, and intelligence-driven approaches. It focuses on recent advances in the application of AI across key stages, including drug discovery and design, druggability evaluation, delivery system design and optimization, nonclinical and clinical …

Optimization Of Sea Transportation Services In The Kepulauan Seribu Using The Vehicle Routing Problem (Vrp) Model, Darmadi Darmadi, Sutanto Soehodho, Nahry Nahry

Smart City

The Kepulauan Seribu regency relies heavily on sea transportation for passenger mobility and goods distribution. However, current systems face efficiency challenges, high operational costs, and potential imbalances between demand and service capacity. This study proposes a framework to optimize sea transportation services in the Kepulauan Seribu using the Vehicle Routing Problem (VRP) method, especially the Capacitated Vehicle Routing Problem – Many Single Depot (CVRP–MSD) model with heterogeneous fleets and mixed cargo (passenger and goods). The main objective is to minimize total operating costs, which include fixed costs of using the vessel and variable travel costs, and unmet demand, both passenger …

An Empirical Study Of Rlvr Fine-Tuning For Mathematical Problem Solving In Llms, Rashmi Konnur

Master’s Dissertations

Large language models have shown immense improvement in coding and math performances thanks to reinforcement learning boosted algorithms. However, its true impact on broadening the reasoning and analytical capacities of an LLM is still contended. In this dissertation, we outline the foundations of Large Language Models, and delve into Reinforcement Learning with Verifiable Rewards (RLVR). We discuss various strategies to efficiently manipulate memory during a fine tuning update. We finally perform RLVR fine-tuning techniques on different models with varied use cases and compare their performances, which corroborate the efficiency of RLVR.

Development Of An Adaptive Pelican Crossing Model Using Fuzzy Logic In Mixed Traffic Conditions, Manazil Adam, Andyka Kusuma, R. Jachrizal Sumabrata

Smart City

Traffic management at at-grade pedestrian crossing facilities (pelican crossings) in highly populated areas, such as the Universitas Indonesia Station, faces significant inefficiency challenges. During peak hours, the fixed-time system is frequently disabled and replaced with subjective manual control by security personnel, thereby triggering irregular stop-and-go cycles and a high accumulation of vehicle delays. This study aims to develop a hybrid adaptive control model integrating Computer Vision, Genetic Algorithm (GA), and Fuzzy Logic to optimize intersection performance under mixed traffic conditions. The research methodology begins with the extraction of traffic and pedestrian characteristic data, calculated manually through recorded field observations. This …

Spatial Tax Intelligence: Implementing Integrated Spatial Decision Support Systems For Smart Urban Governance, Wildan R. Irfana, Haldis A. Bahar, Muhammad H. Candra

Smart City

The transition toward smart governance requires local governments to adopt data-driven policy approaches, particularly in managing urban tax capacity. However, tax administration in many developing regions remains predominantly tabular and administrative, limiting the ability to capture the spatial dynamics of economic activities. This reveals a critical knowledge gap, as integrated frameworks combining spatial and tax data to identify geographic disparities in tax performance remain limited. Consequently, areas with high economic activity but low tax compliance, referred to as tax blind spots, often remain undetected. This study aims to analyze the effectiveness of integrating spatial and tax data in identifying spatial-tax …

Learning In Infants Using Intrinsically Motivated Goal Conditioned Reinforcement Learning, T I Darsan

Master’s Dissertations

Traditional artificial intelligence models learn by passively digesting large datasets. In contrast, human infants discover skills by actively interacting with their bodies and environments without explicit external rewards. This thesis introduces the Composer Architecture, a machine learning framework designed to mimic this autonomous, open-ended development. The Composer architecture operates in a multi-stage loop, the latent model using Contrastive Learning Through Time (CLTT) to compress high-dimensional raw data from visual, proprioceptive, and touch sensors into a low-dimensional space. To preserve data relationships and prevent topological collapse, a Softmax activation forces these latent representations to lie smoothly on a probability simplex. A …

Tinyvgg-Based Real-Time Degradation Classification For Adverse Driving Scenes Using A Newly Collected Iraqi Driving Dataset, Yousif N. Abbas, Matheel E. Abdulmunim, Nada H. Ali, Ismail A. Mageed

Journal of Soft Computing and Computer Applications

Environmental conditions such as low-light at night, fog scattering, glare artifacts, rain streaks, and rain smear distortions are significant issues of camera-based perception in Autonomous Vehicles (AVs). These degradations alter the statistics of the scene, mask structure, introduce non-uniform noise, and adversely affect downstream vision processes, including detection and tracking. To overcome this shortcoming, this paper presents a lightweight TinyVGG-based degradation classification system that runs in real time. The network extracts discriminative spatial features with hierarchical convolutional encoding and projects them to a lower-dimensional semantic representation with fully connected layers and a multi-class predictor based on SoftMax. In addition, a …

Improving Approach Of Evolutionary Strategies For Clustering Technique Enhancement, Duaa Mahde Saleh, Hasanen S. Abdullah, Ahmad Zamsuri

Journal of Soft Computing and Computer Applications

The existence of the information has been the essential aspect of the whole society. Information is concentrated in all forms to be effectively utilized. Clustering — an unsupervised learning technique. It is based on data similarity that gives rise to issues in collection, challenges and instability in data structure. It proposes an advanced evolutionary method by combining two approaches. Firstly, it adopts the evolutionary approach and integrates the advantages between two methods to design one. Among them are Differential Evolution (DE) and Genetic Algorithm (GA), Evolutionary Strategy (ES) and Genetic Programming (GP), and Evolutionary Programming (EP) and Particle Swarm Optimization …