Numerical Analysis and Scientific Computing Commons^™

Implementation And Numerical Simulation On Object-Oriented Elastic-Plastic Finite Element Method Based On Python, Henghui Li, Yingxiong Xiao

Journal of System Simulation

Abstract: With the continuous expansion of the application fields of finite element methods, higher requirements are put forward for the scalability of finite element methods. In order to overcome the defects of the traditional finite element methods, a simple and easily extensible object-oriented elasticplastic finite element program framework is proposed based on Python. Combined with the characteristics of Python, we design some finite element classes such as the pre-processing class, the post-processing class, the linear solution class, the stress integration class and the analysis class. By applying the resulting framework to several typical elastic-plastic mechanical problems and comparing the results …

Optimization Of Highway Emergency Lane Control Based On Kriging Genetic Algorithm, Jinjun Tang, Lipeng Hu, Mingyang Li, Xuan Zhang

Journal of System Simulation

Abstract: To address the issue of how to effectively improve the highway operational efficiency and reduce the safety risks under different traffic flow conditions, this study proposed a genetic algorithm based on Kriging agent model is proposed to optimize the emergency lane control strategy. A mathematical optimization model is designed by combining the spatial and temporal characteristics of the emergency lane opening strategy. By introducing Kriging agent model, combining the genetic algorithm to build the optimization framework, and using simulation software to obtain data to train the agent model, the problem of minimizing the total travel time and the total …

Research On Forest Fire Spread Simulation System Based On Osg, Lei Shao, Xiaotian Yan, Jian Liu, Yuming Liu

Journal of System Simulation

Abstract: A novel expended lattice structure of DEM-Cell model incorporating DEM elevation information is proposed, in response to the requirements of extrapolation of trends and hazards of forest fire spread, as well as the need of route selection and real-time path optimization for rescuers. Combining vegetation attributes of meta cells with geographic elevation information, we develop a simulation and fire fighting exercise system that computing the resultant data in real time and converting it into renderable resource, which is directly used by the OSG engines. With the help of the same data structure and the corresponding key algorithms and technologies, …

Hierarchical Guided Enhanced Multi-Objective Firefly Algorithm, Jia Zhao, Zhizhen Lai, Runxiu Wu, Zhihua Cui, Hui Wang

Journal of System Simulation

Abstract: The multi-objective firefly algorithm is easy to produce oscillation and aggregation phenomenon in the solution process, which leads to weak development ability and poor solution accuracy. This paper proposes a hierarchical guided enhanced multi-objective firefly algorithm (HGEMOFA). HGEMOFA builds a hierarchical guidance model, uses non-dominated sorting to obtain different levels of individuals. The individuals in the dominant layer are used to guide the evolution of the individuals in the inferior layer, the guidance direction is clear, the oscillation in the evolution process is solved, the aggregation phenomenon is reduced, and the convergence of the algorithm is enhanced. The Lévy …

Research On Path Planning Of Warehouse Robot With Improved Harris Hawks Algorithm, Xu Lei, Jingyi Chen, Xiaoyang Chen

Journal of System Simulation

Abstract: To improve the path planning efficiency of warehouse mobile robots in static environments, and to solve the problems of slow convergence and local optimum of traditional Harris Hawk (HHO) algorithm in path planning, a Harris Hawk optimization algorithm based on Tent chaotic mapping fused with Cauchy's back-learning variant (TCLHHO) is proposed. The population diversity is increased by Tent Chaotic mapping to speed up convergence. An exponential prey escape energy updating strategy is proposed to balance the global search and local exploitation capabilities of the algorithm. The optimal individual is disturbed by Cauchy mutation operator and inverse learning strategy to …

Image Self-Enhancement De-Hazing Algorithm Combined With Generative Adversarial Network, Wanjun Liu, Yuqian Cheng, Haicheng Qu

Journal of System Simulation

Abstract: To solve the problem that existing dehazing models are prone to over fitting after training with synthetic hazy image data sets, an image self-enhancement dehazing algorithm is proposed in combination with generative adversarial network. The depth information of an image is estimated while combining two Generative Adversarial Networks. The first GAN uses a clear image to learn the process of image hazing, and then adopts the hazed image generated by it as the input of the second GAN to guide the second GAN to correct dehazing. In order to reduce the difference before and after image processing, the consistency …

Cooperative And Optimal Control Of Multiple Mimo Objects Under Information Sharing, Jiong Shao, Xinchun Jie, Meng Wu

Journal of System Simulation

Abstract: Aiming at the problems of low cooperative efficiency and slow convergence of control algorithm for multiple MIMO objects in cyber-physical system (CPS), a cooperative optimization control strategy for multiple MIMO objects under the condition of information sharing is proposed. A new network control system structure with only physical layer and information layer is used to realize real-time sharing of state variables, control and detection information of multiple MIMO objects. Under the condition of information sharing, based on the performance indexes assigned by CPS and the physical constraints between each object, the cooperative controller designed by minimum principle realizes the …

Research On Collaborative Optimization Method Of Multi-Uav Task Allocation And Path Planning, Peng Xiao, Feng Xie, Haihong Ni, Min Zhang, Zhili Tang, Ni Li

Journal of System Simulation

Abstract: Aiming at the task requirements of multi-UAV to perform multi-target collaborative reconnaissance, a collaborative optimization method of multi-machine and multi-objective task allocation and path planning is proposed. Based on the partheno genetic algorithms (PGA), a cost function combined with the actual path cost is constructed through the Dubins curve. To further reduce the calculation cost, a clustering algorithm based on UAV detection distance is proposed, and the generated clustering point is used as a new waypoint of UAV. The simulation results show that considering the dangerous area and the large number of reconnaissance points, the algorithm can effectively complete …

Tri-Training Algorithm Based On Density Peaks Clustering, Yuhang Luo, Runxiu Wu, Zhihua Cui, Yiying Zhang, Yeshen He, Jia Zhao

Journal of System Simulation

Abstract: Tri-training can effectively improve the generalization ability of classifiers by using unlabeled data for classification, but it is prone to mislabeling unlabeled data, thus forming training noise. Tritraining (Tri-training with density peaks clustering, DPC-TT) algorithm based on density peaks clustering is proposed. The DPC-TT algorithm uses the density peaks clustering algorithm to obtain the class cluster centers and local densities of the training data, and the samples within the truncation distance of the class cluster centers are identified as the samples with better spatial structure, and these samples are labeled as the core data, and the classifier is updated …

Deep Learning Based Local Path Planning Method For Moving Robots, Zesen Liu, Sheng Bi, Chuanhong Guo, Yankui Wang, Min Dong

Journal of System Simulation

Abstract: In order to integrate visual information into the robot navigation process, improve the robot's recognition rate of various types of obstacles, and reduce the occurrence of dangerous events, a local path planning network based on two-dimensional CNN and LSTM is designed, and a local path planning approach based on deep learning is proposed. The network uses the image from camera and the global path to generate the current steering angle required for obstacle avoidance and navigation. A simulated indoor scene is built for training and validating the network. A path evaluation method that uses the total length and the …

Path Planning Of Unmanned Delivery Vehicle Based On Improved Q-Learning Algorithm, Xiaokang Wang, Jie Ji, Yang Liu, Qing He

Journal of System Simulation

Abstract: To solve the traditional Q-learning algorithm for unmanned vehicle path planning suffers from the problems of low planning efficiency and slow convergence speed, for this reason, a path planning algorithm for unmanned delivery vehicles based on the improved Q-learning algorithm is proposed. Learning from the energy iteration principle of the simulated annealing algorithm, adjusts the greedy factor ε to make it change dynamically during the training process, so as to balance the relationship between exploration and utilization, and thus improve the planning efficiency. The reward value in the reward mechanism is changed from a discrete value to a continuous …

Research On Simulation Methods For Forest Fire Extinguishing Using Water Mist, Bing Xiang, Xiaohong Dong, Yang Li

Journal of System Simulation

Abstract: As a highly hazardous natural disaster, the occurrence and spread of forest fires are usually affected by a variety of complex factors such as climate, terrain, vegetation, combustible materials, etc., which makes it difficult to accurately simulate the spread and extinguishing process of forest fires. The spread of forest fires and the process of water mist fire extinguishing are physically modele. The spread model adopts a tree module structure to simulate the pyrolysis reaction of tree burning, and considers the effects of temperature, wind field,mass loss rate and other factors on the spread of tree burning.In the fire extinguishing …

Time Slot Allocation Method Of Data Link Based On Improved Difference Algorithm, Yuting Zhu, Huankun Su, Xiaodong Feng, Shijie Lei, Yanfang Fu

Journal of System Simulation

Abstract: Aiming at the problems of single algorithm, being prone to local optima, and weak generalization ability of the current strategies, based on an improved differential evolutionary algorithm, a chaos algorithm, an adaptive variational crossover algorithm, and a problem solution processing mechanism, a time slot allocation strategy is proposed. The chaos algorithm is used to initialize the population to increase the diversity and avoid the premature convergence. The selection probability parameter is then used to make the crossover and variation process more flexible, expanding the search range in early to increase the possibility of global optima in late. The experiment …

Research On Verification Method Of Missile Elastic Suppression Based On Frequency Compensation, Rixin Su, Ou Zhang

Journal of System Simulation

Abstract: For the elastic model of missile body in six degree of freedom mathematical simulation, the research on the verification method of elastic vibration suppression is carried out.. The notch filter used for elastic vibration suppression is introduced, the verification idea for filter design in boost-phase and passive-phase stages of missile flight is analyzed, and the problem currently existing in mathematical simulation verification is pointed out. Based on the frequency modulation phenomenon, an online verification method of frequency compensation for the notch filter is put forward, and it can be found that the function can be applied to any order …

Gradient-Based Deep Reinforcement Learning Interpretation Methods, Yuan Wang, Lin Xu, Xiaoze Gong, Yongliang Zhang, Yongli Wang

Journal of System Simulation

Abstract: The learning process and working mechanism of deep reinforcement learning methods such as DQN are not transparent, and their decision basis and reliability cannot be perceived, which makes the decisions made by the model highly questionable and greatly limits the application scenarios of deep reinforcement learning. To explain the decision-making mechanism of intelligent agents, this paper proposes a gradient based saliency map generation algorithm SMGG. It uses the gradient information of feature maps generated by high-level convolutional layers to calculate the importance of different feature maps. With the known structure and internal parameters of the model, starting from the …

Prediction Of Converter Gas Generation Based On Intermission Production Improved Elman, Jiajie Fei, Dinghui Wu, Junyan Fan, Jing Wang

Journal of System Simulation

Abstract: Aiming at large fluctuations of intermission and low prediction accuracy in iron and steel industry, based on the classification of intermission characteristics, a converter gas generation predicting model(CPSO-Elman) based on Elman neural network(ENN) optimized by chaotic PSO(CPSO) algorithm is proposed. The intermittent characteristics of converter gas generation time series are extracted and raw data is classified according to intermittent duration. The PSO algorithm improved by chaotic disturbance is introduced to optimize the initial weight and threshold of ENN and inertia weight of nonlinear updating is designed to balance global search ability and local search ability. Construct the combined prediction …

Analysis And Computation Of Constrained Sparse Coding On Emerging Non-Von Neumann Devices, Kyle Henke

Mathematics & Statistics ETDs

This dissertation seeks to understand how different formulations of the neurally inspired Locally Competitive Algorithm (LCA) represent and solve optimization problems. By studying these networks mathematically through the lens of dynamical and gradient systems, the goal is to discern how neural computations converge and link this knowledge to theoretical neuroscience and artificial intelligence (AI). Both classical computers and advanced emerging hardware are employed in this study. The contributions of this work include:

1. Theoretical Work: A comprehensive convergence analysis for networks using both generic Rectified Linear Unit (ReLU) and Rectified Sigmoid activation functions. Exploration of techniques to address the binary …

Enhancing Visual Grounding In Vision-Language Pre-Training With Position-Guided Text Prompts, Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt ( PTP ) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects …

Choreographing The Rhythms Of Observation: Dynamics For Ranged Observer Bipartite-Unipartite Spatiotemporal (Robust) Networks, Edward A. Holmberg Iv

LSU New Orleans Theses and Dissertations

Existing network analysis methods struggle to optimize observer placements in dynamic environments with limited visibility. This dissertation introduces the novel ROBUST (Ranged Observer Bipartite-Unipartite SpatioTemporal) framework, offering a significant advancement in modeling, analyzing, and optimizing observer networks within complex spatiotemporal domains. ROBUST leverages a unique bipartite-unipartite approach, distinguishing between observer and observable entities while incorporating spatial constraints and temporal dynamics.

This research extends spatiotemporal network theory by introducing novel graph-based measures, including myopic degree, spatial closeness centrality, and edge length proportion. These measures, coupled with advanced clustering techniques like Proximal Recurrence, provide insights into network structure, resilience, and the effectiveness …

Cornac-Ab : An Open-Source Recommendation Framework With Native A/B Testing Integration, Rong Sheng Ong, Quoc Tuan Truong, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Recommender systems significantly impact user experience across diverse domains, yet existing frameworks often prioritize offline evaluation metrics, neglecting the crucial integration of A/B testing for forward-looking assessments. In response, this paper introduces a new framework seamlessly incorporating A/B testing into the Cornac recommendation library. Leveraging a diverse collection of model implementations in Cornac, our framework enables effortless A/B testing experiment setup from offline trained models. We introduce a carefully designed dashboard and a robust backend for efficient logging and analysis of user feedback. This not only streamlines the A/B testing process but also enhances the evaluation of recommendation models in …

Reinforcement Learning With Maskable Stock Representation For Portfolio Management In Customizable Stock Pools, Wentao Zhang, Yilei Zhao, Shuo Sun, Jie Ying, Yonggang Xie, Zitao Song, Xinrun Wang, Bo An

Research Collection School Of Computing and Information Systems

Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors’ practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing …

Term Importance For Transformer-Based Qa Retrieval : A Case Study Of Stackexchange, Bryan Zhi Yang Tan, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Question-answering (QA) retrieval is the task of retrieving the most relevant answer to a given question from a collection of answers. Various approaches to QA retrieval have been developed recently. One successful and popular model is Contextualized Late Interaction over BERT (ColBERT), a transformer-based approach that adopts a query-document scoring mechanism that retains the granularity of transformer matching, whilst improving on efficiency. However, one key limitation is that it requires further fine-tuning for new query or collection types. In this work, we explore and propose several non-parametric retrieval augmentation methods based on explicit signals of term importance that improve over …

Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges, Ce Zhang, Menglin Yang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Text documents are usually connected in a graph structure, resulting in an important class of data named text-attributed graph, e.g., paper citation graph and Web page hyperlink graph. On the one hand, Graph Neural Networks (GNNs) consider text in each document as general vertex attribute and do not specifically deal with text data. On the other hand, Pre-trained Language Models (PLMs) and Topic Models (TMs) learn effective document embeddings. However, most models focus on text content in each single document only, ignoring link adjacency across documents. The above two challenges motivate the development of text-attributed graph representation learning, combining GNNs …

Learning Adversarial Semantic Embeddings For Zero-Shot Recognition In Open Worlds, Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Research Collection School Of Computing and Information Systems

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of “Zero-Shot Open-Set Recognition” (ZS-OSR), where a model is trained under the ZSL …

Grasper: A Generalist Pursuer For Pursuit-Evasion Problems, Pengdeng Li, Shuxin Li, Xinrun Wang, Jakub Cerny, Youzhi Zhang, Stephen Mcaleer, Hau Chan, Bo An

Research Collection School Of Computing and Information Systems

Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in Policy-Space Response Oracles (PSRO) to improve scalability in solving large-scale PEGs. However, these methods primarily focus on specific PEGs with fixed initial conditions that may vary substantially in real-world scenarios, which significantly hinders the applicability of the traditional methods. To address this issue, we introduce Grasper, a GeneRAlist purSuer for Pursuit-Evasion pRoblems, capable of efficiently generating pursuer policies tailored to specific PEGs. Our contributions are threefold: …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

Evaluation Of Orca 2 Against Other Llms For Retrieval Augmented Generation, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

This study presents a comprehensive evaluation of Microsoft Research’s Orca 2, a small yet potent language model, in the context of Retrieval Augmented Generation (RAG). The research involved comparing Orca 2 with other significant models such as Llama-2, GPT-3.5-Turbo, and GPT-4, particularly focusing on its application in RAG. Key metrics, included faithfulness, answer relevance, overall score, and inference speed, were assessed. Experiments conducted on high-specification PCs revealed Orca 2’s exceptional performance in generating high quality responses and its efficiency on consumer-grade GPUs, underscoring its potential for scalable RAG applications. This study highlights the pivotal role of smaller, efficient models like …

Towards Explainable Harmful Meme Detection Through Multimodal Debate Between Large Language Models, Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao Yang

Research Collection School Of Computing and Information Systems

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models …

Code For Care: Hypertension Prediction In Women Aged 18-39 Years, Kruti Sheth

Electronic Theses, Projects, and Dissertations

The longstanding prevalence of hypertension, often undiagnosed, poses significant risks of severe chronic and cardiovascular complications if left untreated. This study investigated the causes and underlying risks of hypertension in females aged between 18-39 years. The research questions were: (Q1.) What factors affect the occurrence of hypertension in females aged 18-39 years? (Q2.) What machine learning algorithms are suited for effectively predicting hypertension? (Q3.) How can SHAP values be leveraged to analyze the factors from model outputs? The findings are: (Q1.) Performing Feature selection using binary classification Logistic regression algorithm reveals an array of 30 most influential factors at an …

Intelligent Optimization Method Of Cloud Manufacturing Swarm Based On Incomplete Information Game, Kunpeng Zhang, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: In the process of cloud manufacturing, the incomplete information status and the mutual competition and restriction relationship between cloud platform operator and demander lead to the difficult choice of manufacturing services. A cloud manufacturing swarm intelligent optimization method based on incomplete information game model is proposed. A static game model based on incomplete information is established for the interest competition between demand-side and cloud platform, with the goal of rationally pursuing the maximization of their own revenue function. The competition rules between demand-side and cloud platform are proposed, which are introduced into nature through Harsanyi transformation and converted into …