Uav Online Track Planning Based On Dmoea-Aptc Algorithm,
2024
College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China
Uav Online Track Planning Based On Dmoea-Aptc Algorithm, Erchao Li, Shenghui Zhang
Journal of System Simulation
Abstract: In order to solve the dynamic multi-objective optimization problem with time correlation, this paper introduces the concept of time correlation feature and establishes the model of UAV timecorrelation dynamic multi-objective optimization problem moedl on the basis of UAV online track planning problem, and proposes a dynamic multi-objective double-layer optimization algorithm using adaptive predictive response mechanism and time-correlation optimization mechanism (DMOEA-APTC). The intensity of environmental change was judged according to the correlation of environmental change and different response mechanisms were used to quickly adapt to environmental change. In the optimization process, the least square method was used to learn the …
Edge Surveillance Task Offloading And Resource Allocation Algorithm Based On Drl,
2024
School of Computer Science, Hubei University of Technology, Wuhan 430000, China
Edge Surveillance Task Offloading And Resource Allocation Algorithm Based On Drl, Chao Li, Jiabao Li, Caichang Ding, Zhiwei Ye, Fangwei Zuo
Journal of System Simulation
Abstract: For the resource limitation of intensive surveillance tasks in edge computing, a surveillance task offloading and resource allocation algorithm based on DRL is proposed. With the optimization objectives of surveillance task delay and recognition accuracy, the joint decision objective optimization solution of task offloading, wireless channel allocation, and image compression rate was modeled as a Markov decision process. To address the problem of slow and unstable algorithm convergence due to the high volatility of training samples caused by the dynamic nature of wireless channels and the randomness of surveillance tasks, an attention mechanism is used to jointly encode channel …
Modeling And Simulation Of Pipeline Cable Inspection Robot Based On Omnidirectional Wheel,
2024
Department of Automation, North China Electric Power University, Baoding 071003, China
Modeling And Simulation Of Pipeline Cable Inspection Robot Based On Omnidirectional Wheel, Chao Yuan, Yao Zhang, Yadong Zhao, Dawei Xu, Jing Yuan, Yongjie Zhai
Journal of System Simulation
Abstract: Aiming at the problem that the inner space of underground pipeline cable is narrow and closed, which cannot be inspected by humans, and the existing pipeline robot cannot adapt to the special environment of pipeline cable, a miniaturized, compact pipeline cable inspection robot is designed. This robot is capable of operating within the underground pipeline where cables have already been laid to inspect the inner wall of the pipeline and the working condition of the cables. According to the requirements of the working conditions, the whole three-dimensional model of the robot has been established. The mapping relationship between the …
A New Model Predictive Current Controller Forac-Dc Matrix Converter In Unbalanced Grids,
2024
School of Automation and Electronic Information, Xiangtan University, Xiangtan 411105, China
A New Model Predictive Current Controller Forac-Dc Matrix Converter In Unbalanced Grids, Wenlang Deng, Minghai Wu, Haipeng Xie, Yingjie Hu
Journal of System Simulation
Abstract: To reduce the fluctuation of active power on the grid side of AC-DC matrix converters under unbalanced input conditions and to address the issue of variable switching frequency in discrete model predictive control, this paper proposes a novel model predictive control method. This method selects effective vectors based on the phase angle of the grid current, thus avoiding the computational burden of evaluating the value function in traditional model predictive control. Additionally, a second-order extended complex Kalman filter is introduced, which achieves the computation accuracy of the secondorder term of the Taylor series expansion and enables the application of …
Visual Robot Obstacle Avoidance Planning And Simulation Using Mapped Point Clouds,
2024
College of Engineering, South China Agricultural University, Guangzhou 510000, China
Visual Robot Obstacle Avoidance Planning And Simulation Using Mapped Point Clouds, Hanlin Huo, Xiangjun Zou, Yan Chen, Xinzhao Zhou, Mingyou Chen, Chengen Li, Yaoqiang Pan, Yunchao Tang
Journal of System Simulation
Abstract: In response to the large and complex data volume and high redundancy of visual point cloud obstacle recognition in complex unstructured orchard environments, which severely impacts the real-time performance and efficiency of harvesting operations, a point cloud compression algorithm is proposed based on point cloud segmentation to enhance the efficiency of point cloud obstacle recognition and environmental adaptability. An Informed RRT* based approach is used combined with an inverse projection algorithm, mapping-based informed RRT*(M-Informed RRT*) to solve the harvesting path problem. By constructing a highly real-time and robust integrated robot system for sampling, perception, and obstacle avoidance, efficient obstacle …
An Improved Path Planning Algorithm For Mobile Robots,
2024
Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650500, China; Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming 650500, China
An Improved Path Planning Algorithm For Mobile Robots, Haijie Sun, Hongjun San, Le Xiao, Dexin Yao, Jiupeng Chen, Xiaoyuan Yang
Journal of System Simulation
Abstract: To solve the problems of invalid sampling and non-optimal paths of the RRT, the quasi-stream avoidance algorithm is proposed. The RRT algorithm is introduced to specify the sampling interval to limit the sampling points and enhance the goal-oriented nature of sampling. The quasi-stream avoidance algorithm incorporating the A* algorithm (QSA*) is used to quickly bypass the obstacle when it is encountered. A path optimization algorithm is used to smooth the searched path. The simulation results show that compared with the RRT algorithm, the computation time of the RRT-QSA* algorithm is reduced by 96.83%~99.88%, the number of search nodes is …
Research On System-Of-Systems Confrontation Simulation Method Based On Operation Loops,
2024
The 1st Research Department, 28th Research Institute of China Electronics Technology Corporation, Nanjing 210001, China
Research On System-Of-Systems Confrontation Simulation Method Based On Operation Loops, Shan Zhong, Yesheng Zhu, Menglu Zhou
Journal of System Simulation
Abstract: In the field of modeling and analyzing capabilities for operation system-of-systems (SoS), traditional structured capability assessment models lack the analysis of the interaction between both rivals and armies in different roles. The system model based on operation loop theory can be combined with the relationship between sensor, decision-making, influence, and target nodes for system capability calculation, but the existing model is usually only suitable for static analysis and cannot be used for dynamic simulation of SoS confrontation. In order to solve the problems above, a SoS confrontation simulation method based on operation loops is proposed. It abstracts both rivals’ …
Deep Learning Approach In Melanoma Stage Classification,
2024
Copperbelt University
Deep Learning Approach In Melanoma Stage Classification, Frank Lemba Lemba, Clopas Kwenda
African Conference on Information Systems and Technology
Accurate and efficient classification of melanoma stages is crucial for effective treatment planning and improved patient outcomes. Traditional diagnostic methods are often time-consuming and subjective, highlighting the need for advanced computational approaches. This study proposes a self-supervised learning framework combined with a convolutional neural network (CNN) to classify melanoma stages more effectively. Initially, features are extracted from unlabeled skin images using pre-trained VGG16 and ResNet50 models. These features are combined and reduced in dimensionality using Principal Component Analysis (PCA). Subsequently, K-means and DBSCAN clustering is applied to pseudo-label the data, providing a foundation for pre-training a CNN model. This pre-trained …
Trends From 20 Years Of Artificial Intelligence In Financial Services In Africa,
2024
University of Johannesburg
Trends From 20 Years Of Artificial Intelligence In Financial Services In Africa, Nthabiseng Moela, Lerato Matlala, Jackie Ma, Dipuo Maphutha, Hossana Twinomurinzi
African Conference on Information Systems and Technology
The need for financial inclusion in Africa, particularly for marginalised groups like women and small businesses, highlights the importance of leveraging Artificial Intelligence (AI). This study provides a bibliometric analysis of AI's integration into African financial services from 2003 to 2023. The key results show a significant increase in AI use, particularly in fraud detection, credit risk prediction, and stock market volatility forecasting, with 49% of the research coming from South Africa, Nigeria, and Tunisia. However, areas like financial development management, inflation control, and gender disparities in loan access remain underexplored. The emphasis has been on the technical implementation of …
Review Of Data Bias In Healthcare Applications,
2024
Vellore Institute of Technology
Review Of Data Bias In Healthcare Applications, Atharva Prakash Parate, Aditya Ajay Iyer, Kanav Gupta, Harsh Porwal, P. C. Kishoreraja, R. Sivakumar, Rahul Soangra
Physical Therapy Faculty Articles and Research
In the area of medical artificial intelligence (AI), data bias is a major difficulty that affects several phases of data collection, processing, and model building. The many forms of data bias that are common in AI in healthcare are thoroughly examined in this review study, encompassing biases related to socioeconomic status, race, and ethnicity as well as biases in machine learning models and datasets. We examine how data bias affects the provision of healthcare, emphasizing how it might worsen health inequalities and jeopardize the accuracy of AI-driven clinical tools. We address methods for reducing data bias in AI and focus …
Neurosymbolic Cognitive Methods For Enhancing Foundation Model-Based Reasoning,
2024
Penn State University
Neurosymbolic Cognitive Methods For Enhancing Foundation Model-Based Reasoning, Kaushik Roy, Siyu Wu, Alessandro Oltramari
Faculty Publications
Foundation models have emerged as powerful tools, exhibiting extraordinary performance across various tasks, such as language processing, visual recognition, code generation, and human-centered engagement. However, recent studies have highlighted their limitations when grounded, abstract, and generalized reasoning capabilities are required. Complex tasks often involve multiple hierarchical reasoning steps, which are typical features of human thinking processes. In fact, in this chapter we claim that cognitively-inspired computational models, such as the so-called Common Model of Cognition, are key to enable complex reasoning within foundation model-based artificial intelligence (AI) systems. We investigate neurosymbolic approaches for mapping AI system components to those of …
Exploring Artificial Intelligence: A Collaborative Small Group Analysis And Application,
2024
University of North Dakota
Exploring Artificial Intelligence: A Collaborative Small Group Analysis And Application, Ellamarie Powell
AI Assignment Library
In this small group project, students will collaborate to explore the principles and applications of Artificial Intelligence (AI). Each group will research, analyze, and present on a specific AI topic, highlighting its real-world implications and ethical considerations. The project involves team members contributing to various roles, including research, technical analysis, and presentation. The final deliverable will be a video presentation integrating individual contributions, showcasing a comprehensive understanding of AI and its impact on society. This assignment fosters teamwork, critical thinking, and effective communication skills.
A Primer On How Al Algorithms Control You,
2024
Husson University
A Primer On How Al Algorithms Control You, Russell Fulmer
Journal of Technology in Counselor Education and Supervision
Artificial intelligence (AI) algorithms can control you by exerting heavy influence on your worldview. Your worldview is akin to your personal philosophy, which affects how you perceive and label social systems and structures, groups of people, and politics. Algorithms impact your decision-making, beliefs, mood, relationships, and more. My rhetoric is intentionally strong when discussing algorithms, and I invite you to assess its merit by reviewing related literature and thinking critically.
Interoperability In Deep Learning: A User Survey And Failure Analysis Of Onnx Model Converters,
2024
Purdue University
Interoperability In Deep Learning: A User Survey And Failure Analysis Of Onnx Model Converters, Purvish Jajal, Wenxin Jiang, Arav Tewari, Erik Kocinare, Joseph Woo, Anusha Sarraf, Yung-Hsiang Lu, George Thiruvathukal, James C. Davis
Computer Science: Faculty Publications and Other Works
Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environments. Conversion errors compromise model quality and disrupt deployment. However, the failure characteristics of DL model converters are unknown, adding risk when using DL interoperability technologies. This paper analyzes failures in DL model converters. We survey software engineers about DL interoperability tools, use cases, and pain points (N=92). Then, we characterize failures in model converters associated with the main interoperability tool, ONNX (N=200 issues in PyTorch and TensorFlow). Finally, we formulate …
Coarse-Gridded Simulation Of The Nonlinear Schrödinger Equation With Machine Learning,
2024
Air Force Institute of Technology
Coarse-Gridded Simulation Of The Nonlinear Schrödinger Equation With Machine Learning, Benjamin F. Akers, Kristina O. F. Williams
Faculty Publications
A numerical method for evolving the nonlinear Schrödinger equation on a coarse spatial grid is developed. This trains a neural network to generate the optimal stencil weights to discretize the second derivative of solutions to the nonlinear Schrödinger equation. The neural network is embedded in a symmetric matrix to control the scheme’s eigenvalues, ensuring stability. The machine-learned method can outperform both its parent finite difference method and a Fourier spectral method. The trained scheme has the same asymptotic operation cost as its parent finite difference method after training. Unlike traditional methods, the performance depends on how close the initial data …
Adaptive Worlds: Generative Ai In Game Design And Future Of Gaming, And Interactive Media,
2024
Lindenwood University
Adaptive Worlds: Generative Ai In Game Design And Future Of Gaming, And Interactive Media, Jay Ratican, James Hutson
Faculty Scholarship
Generative AI is revolutionizing the field of game design, introducing unprecedented adaptability and personalization in gameplay. The latest advancements in AI-driven engines enable real-time content creation, offering dynamic, player-driven experiences that diverge from traditional pre-programmed narratives. This shift marks a transition toward "choose your own adventure" formats, with an unlimited number of variations in levels, enemies, collectibles, and weaponry, tailored to each player's decisions. Google's GameNGen, for example, showcases AI's capacity to recreate classic games like DOOM, learning and generating gameplay in real time. These innovations are not restricted to gaming alone; they extend to edutainment, television, and film, where …
Multimodal Mixing Convolutional Neural Network And Transformer For Alzheimer’S Disease Recognition,
2024
Chapman University
Multimodal Mixing Convolutional Neural Network And Transformer For Alzheimer’S Disease Recognition, Junde Chen, Yun Wang, Adnan Zeb, M. D. Suzauddola, Yuxin Wen
Engineering Faculty Articles and Research
Early recognition of Alzheimer’s disease (AD) and its precursor state, mild cognitive impairment (MCI), is pivotal in interrupting the progression of the disease and providing suitable treatment. Recent development in deep learning techniques has drawn great research attention for improving the efficacy of AD recognition. However, numerous current methods solely utilize data from a single auxiliary domain, limiting their ability to harness valuable intrinsic insights from multiple domains. To cope with the challenge, this paper is devoted to establishing an innovative multimodal medical data fusion model, termed as MMDF, to perform Alzheimer’s disease recognition. Multimodal data including clinical records and …
Regulating Algorithmic Harms,
2024
University of Michigan Law School
Regulating Algorithmic Harms, Sylvia Lu
Law & Economics Working Papers
In recent years, the rapid expansion of artificial intelligence (AI) innovations has led to a rise in algorithmic harms—harms emerging from AI operations that pose significant threats to civil rights and democratic values in today’s technological landscape. A facial recognition system for improving criminal detection wrongly collected sensitive personal data and flagged racial minorities as shoplifters. A risk-prediction algorithm adopted to identify patients denied medical treatment to Black individuals with poor health conditions. A social media algorithm intended to boost social engagement exacerbated addictive behavior and mental illness in teenagers. These harms are becoming increasingly ubiquitous yet often manifest in …
Rethinking Retrieval Augmented Fine-Tuning In An Evolving Llm Landscape,
2024
Southern Methodist University
Rethinking Retrieval Augmented Fine-Tuning In An Evolving Llm Landscape, Nicholas Sager, Timothy Cabaza, Matthew Cusack, Ryan Bass, Joaquin Dominguez
SMU Data Science Review
This study explores the utilization of Retrieval Augmented Fine-Tuning (RAFT) to enhance the performance of Large Language Models (LLMs) in domain-specific Retrieval Augmented Generation (RAG) tasks. By integrating domain-specific information during the retrieval process, RAG aims to reduce hallucination and improve the accuracy of LLM outputs. We investigate the use of RAFT, an approach that enhances LLMs by incorporating domain-specific knowledge and effectively handling distractor documents. This paper validates previous work, which found that RAFT can considerably improve the performance of Llama2-7B in specific domains. We also expand upon previous work into new state-of-the-art open-source models and other datasets with …
Assessing The Accuracy And Utility Of Chatgpt Responses To Patient Questions Regarding Posterior Lumbar Decompression,
2024
Thomas Jefferson University
Assessing The Accuracy And Utility Of Chatgpt Responses To Patient Questions Regarding Posterior Lumbar Decompression, Alec Giakas, Rajkishen Narayanan, Teeto Ezeonu, Jonathan Dalton, Yunsoo Lee, Tyler Henry, John Mangan, Gregory Schroeder, Alex Vaccaro, Christopher Kepler
Department of Orthopaedic Surgery Faculty Papers
Aim: To examine the clinical accuracy and applicability of ChatGPT answers to commonly asked questions from patients considering posterior lumbar decompression (PLD). Methods: A literature review was conducted to identify 10 questions that encompass some of the most common questions and concerns patients may have regarding lumbar decompression surgery. The selected questions were then posed to ChatGPT. Initial responses were then recorded, and no follow-up or clarifying questions were permitted. Two attending fellowship-trained spine surgeons then graded each response from the chatbot using a modified Global Quality Scale to evaluate ChatGPT’s accuracy and utility. The surgeons then analyzed each question, …
