检索结果-内蒙古大学图书馆

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Mirza Nadim Saad Esrat Jahan Shifat Ahmed Khandaker Mohammad Mohi Uddin Dept. of Computer Science and Engineering Southeast University Dhaka Bangladesh

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

Heart disease remains the leading cause of mortality globally, emphasizing the critical need for better diagnostics. This study used a variety of machine learning methods to forecast cardiac disease, using SVM, Random Forest, Decision Tree, KNN, and LGBM. The evaluation measures include accuracy, ROC, precision, recall, and F1 score. data pretreatment procedures such as cleansing, transformation, integration, and reduction were used to guarantee reliable analysis. The model's performance was further enhanced by hyperparameter tuning. SVM had the lowest performance of the models examined, with 57.23% accuracy, 86% precision, 89% recall, and an F1 score of 87%. The study used three different datasets, combining their strengths to improve model discrimination, decrease overfitting, and increase overall accuracy. We developed multiple models from the combination of RF, DT and LGBM. We found accuracy of up to 99.54% by merging LGBM and Random Forest. These findings illustrate the efficacy of the ensemble approaches and data integration in improving heart disease prediction skills using machine learning.

关键词： Heart Support vector machines Accuracy Mortality Nearest neighbor methods Reliability Random forests Tuning Diseases Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

An Automated and Generalizable Technique for Left Ventricle Segmentation in 2D Echocardiography Utilizing Generative Adversarial Network

An Automated and Generalizable Technique for Left Ventricle ...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Sajjad Afrakhteh Noreen Fatima Libertario Demi Dept. of Information Engineering and Computer Science University of Trento Italy

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Accurately segmenting the left ventricle (LV) is crucial for understanding normal heart anatomy and identifying abnormal or diseased structures based on the estimated ejection fraction (EF). A significant challenge in LV segmentation is ensuring generalizability across diverse datasets with various acquisition settings. Addressing this challenge is a key focus, and we aim to provide a solution to ensure a generalizable segmentation. This study utilizes Pix2Pix Generative Adversarial Networks (GANs) for robust and adaptable left ventricle (LV) segmentation in 2D echocardiography images. Specifically, through the integration of adversarial loss, our model learns to generate anatomically accurate segmentations, which helps to enhance accuracy and adaptability across diverse echocardiography datasets. Our evaluation involved two datasets: the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset and the EchoNet dataset, both captured from a 4-chamber (4CH) view. To assess generalizability, we train the model using the EchoNet training set and test it on the CAMUS data test set, and vice versa. When trained on the EchoNet dataset and tested on CAMUS, the method achieved a mean absolute error of 4.6%, and a correlation coefficient of 0.98 for EF estimation, which outperforms the state of the arts. Conversely, training on CAMUS and testing on EchoNet resulted in a mean absolute error of 9% and a correlation coefficient of 0.75.

关键词： Training Correlation coefficient Heart Image segmentation Adaptation models Accuracy Ultrasonic imaging Echocardiography Generative adversarial networks Testing

来源：评论

学校读者我要写书评

暂无评论

TexAVi: Generating Stereoscopic VR Video Clips from Text Descriptions

TexAVi: Generating Stereoscopic VR Video Clips from Text Des...

引用

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Shruti Jayaraman R Bhavya Vriksha Srihari V Mary Anita Rajam Dept. of Computer Science and Engineering College of Engineering Guindy Chennai India

ISBN: (数字)9798350376876

ISBN: (纸本)9798350376883

While generative models such as text-to-image, large language models and text-to-video have seen significant progress, the extension to text-to-virtual-reality remains largely unexplored, due to a deficit in training data and the complexity of achieving realistic dept. and motion in virtual environments. This paper proposes an approach to coalesce existing generative systems to form a stereoscopic virtual reality video from text. Carried out in three main stages, we start with a base text-to-image model that captures context from an input text. We then employ Stable Diffusion on the rudimentary image produced, to generate frames with enhanced realism and overall quality. These frames are processed with dept. estimation algorithms to create left-eye and right-eye views, which are stitched side-by-side to create an immersive viewing experience. Such systems would be highly beneficial in virtual reality production, since filming and scene building often require extensive hours of work and post-production effort. We utilize image evaluation techniques, specifically Fréchet Inception Distance and CLIP Score, to assess the visual quality of frames produced for the video. These quantitative measures establish the proficiency of the proposed method. Our work highlights the exciting possibilities of using natural language-driven graphics in fields like virtual reality simulations.

关键词： Headphones Solid modeling Visualization Stereo image processing Text to image Virtual environments Training data Production Media Text to video

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning Algorithms in Edge Intelligence for Ultra-Reliable and Low-Latency Communications in the Industrial Metaverse 29

Using Machine Learning Algorithms in Edge Intelligence for U...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Mohammadvand, Reza Mozayani, Naser Dept. Computer Engineering Iran University of Science and Technology Tehran Iran

ISBN: (纸本)9798331523114

Given the rapid advancements in technologies such as the metaverse and digital twins, the need for effective integration of communication, computation, and storage in complex systems and edge computing environments is becoming increasingly apparent. This paper proposes an architecture to support an industrial metaverse based on digital twins that optimizes resources by leveraging mobile edge computing and ultra-reliable low-latency communication. This architecture reduces latency by employing task offloading and storage methods on nearby edge servers, meeting the precise requirements of future metaverses in terms of reliability and latency minimization. The proposed model, utilizing reinforcement learning algorithms such as Deep Q-Network (DQN), Double Deep Q-Network (DDQN), and Dueling Double Deep Q-Network (Dueling DDQN), is capable of achieving adaptability in dynamic conditions and making intelligent decisions. The simulation results demonstrate that the proposed method reduces by more than 10% on average compared to the best method available in the literature and improves resource utilization efficiency. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Navigating Green Transportation in Urban Agglomerations: A Refined Approach for Carbon Emissions Assessment 24

Navigating Green Transportation in Urban Agglomerations: A R...

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Chen, Boyou Wang, Yuanqing Abolarin, Emmanuel Zhang, Shuangyan Liu, Xihao Guo, Hanlin Ren, Baolong Dept. of Built Environment Bartlett School of Planning Univ. College London London United Kingdom Dept. of Transportation Engineering College of Transportation Engineering Chang’an Univ. Xi’an China Dept. of Industrial and Manufacturing Systems Engineering College of Engineering and Computer Science Univ. of Michigan–Dearborn Dearborn United States School of Civil and Transportation Engineering Beijing Univ. of Civil Engineering and Architecture Beijing China Sino-French Engineer School Beihang Univ. Beijing China Dept. of Instrument Science and Technology College of Mechanical Engineering Nanjing Univ. of Science and Technology Nanjing China Sino-Danish College Univ. of Chinese Academy of Sciences Beijing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

Rapid urbanization has expanded urban agglomerations, escalating carbon emissions from increased transportation needs. These agglomerations have distinct multi-modal transportation systems. Analyzing their carbon footprints and eco-friendly transportation evolution is essential for sustainability. However, research in this domain is limited. This research refines emissions estimation methods, introducing models tailored for urban agglomerations. An evaluation framework for green transportation detailing a computational method for future policies is proposed. The research highlights primary transportation structures and energy consumption. Using a "bottom-up" approach, carbon estimation models for inter- and intra-city transportation are drafted. Assessment indicators are redefined by merging the DPSIR model with urban metrics, forming five main modules with 19 indicators. Using the Regression Random Forest method and focusing on the Yangtze River Delta in China, the link between annual emissions and these indicators is examined, providing a theoretical analysis approach for general cases. © ASCE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Visualizing Causes of Poverty in India: A data-Driven Approach Using HPCC Systems

Analyzing and Visualizing Causes of Poverty in India: A Data...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Skanda P R Shobha G Jyoti Shetty Dept. of Computer Science and Engineering RV College of Engineering Bengaluru India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

Poverty in India is a complex issue with multiple causes. This paper mainly focuses on three of the main causes for poverty: Education, Unemployment and Consumer Price Index. This study makes use of data received from the National Informatics Center (NIC) of India to predict poverty across the various states of India. Through applying preprocessing techniques and employing the HPCC Systems Visualization bundle, the research shows that Bihar is facing a higher level of poverty, whereas Mizoram exhibits converse trend. Subsequently, the HPCC ML_Core bundle is applied to conduct linear regression analysis for predicting poverty scores. This predictive model demonstrated an accuracy of 97%. Lastly, the difference between a single-node and 8-node cluster is presented for runtime performance which clearly shows that the 8-node cluster has an advantage for similar computational tasks and thus makes it suitable.

关键词： Accuracy Runtime Linear regression data visualization Predictive models Market research Unemployment Information technology Informatics Non-governmental organizations

来源：评论

学校读者我要写书评

暂无评论

Automail AI: Intelligent Voice-Controlled Email Generator

Automail AI: Intelligent Voice-Controlled Email Generator

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Kavitha Jayaram Samarth Mandagere Sampriti Gopisetti Sahit S Dept. of Computer Science and Engineering BNM Institute of Technology Bengaluru India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The complexity of contemporary communication further emphasizes the need to automate monotonous work to increase efficiency and effectiveness. This paper introduces a new advance, voice-controlled Automail AI, in the form of an email generation tool that automatically sends an email according to end-user-specified keywords. Automail AI utilizes NLP, ML, and Speech Recognition to differentiate formal emails from informal ones and draft appropriate responses as the situation demands. It has been tuned with Naive Bayes Classifier that yields a better level of accuracy as compared to models such as Decision Tree, SVM, and Logistic Regression. Setting the benchmark for Automated Communication tools, Automail AI combines diverse technologies like SMTP to guarantee secure Email delivery, Google Text-to-Speech or GTTS for auditory feedback, and a module providing an interface for speech recognition that offers the possibility to use the tool with no hands.

关键词： Support vector machines Logistic regression Accuracy Speech recognition Machine learning Natural language processing Real-time systems Electronic mail Internet Decision trees

来源：评论

学校读者我要写书评

暂无评论

Reducing Redundant Computation in Multi-Agent Coordination through Locally Centralized Execution

arXiv

引用

arXiv 2024年

作者： Bai, Yidong Sugawara, Toshiharu Dept. Computer Science and Engineering Waseda University Tokyo Japan

In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to overlapping observations. To address this issue, this study introduces a novel method referred to as locally centralized team transformer (LCTT). LCTT establishes a locally centralized execution framework where selected agents serve as leaders, issuing instructions, while the rest agents, designated as workers, act as these instructions without activating their policy networks. For LCTT, we proposed the team-transformer (T-Trans) architecture that allows leaders to provide specific instructions to each worker, and the leadership shift mechanism that allows agents autonomously decide their roles as leaders or workers. Our experimental results demonstrate that the proposed method effectively reduces redundant computation, does not decrease reward levels, and leads to faster learning convergence. © 2024, CC BY-NC-ND.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Drone Swarm Coordination Using Reinforcement Learning for Efficient Wildfires Fighting

引用

SN computer science 2024年第3期5卷 314页

作者： Blais, Marc-Andrė Akhloufi, Moulay A. Dept. of Computer Science Université de Moncton Moncton NB Canada Perception Robotics and Intelligent Machines (PRIME) Université de Moncton Moncton NB Canada

Natural events, such as wildfires, pose a serious threat to the human population and cause significant environmental and economic damage. As climate change increases the frequency and intensity of extreme natural events, more efficient solutions are required to mitigate their impacts. One proposed solution is the usage of a swarm of drones and unmanned ground vehicles to extinguish wildfires. Controlling a swarm of drones is a challenging task that requires a complex control system capable of providing a good coordination between multiple vehicles. Artificial intelligence, particularly reinforcement learning, has been proposed as a solution for the autonomous control of a swarm. In this paper, we propose a conceptual system based on reinforcement learning and swarm robotics to efficiently combat wildfires. Our system consists of an overwatch drone and multiple payload drones which are responsible for carrying fire suppressants. The goal of our research is to guide a swarm of payload drones to a wildfire while preserving a tight swarm grouping. Each drone is individually controlled and aware of the position of the goal and the positions of other agents. To compare different algorithms, we tested a DQN, Rainbow DQN and FQF using a simulation and four AirSim scenarios. With our approach, we achieve impressive results in controlling a swarm of drones towards a common goal. Our research demonstrates the possibility of utilizing reinforcement learning to control a swarm of drones for wildfire fighting. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Drones Intelligent system Reinforcement learning Swarm Wildfires

来源：评论

学校读者我要写书评

暂无评论

G-TRETA A Novel Multi-Objective Task Scheduling Algorithm in Cloud Computing

G-TRETA A Novel Multi-Objective Task Scheduling Algorithm in...

引用

IEEE International Conference on Utility and Cloud Computing (UCC)

作者： K. M. S. U. Bandaranayake Sunimal Rathnayake Dept. of Computer Science and Engineering University of Moratuwa Sri Lanka

ISBN: (数字)9798350367201

ISBN: (纸本)9798350367218

Cloud computing has revolutionized the IT industry by granting users to access computing resources and services over the Internet. Cloud offers an array of benefits like on-demand, scalable, cost-effective, and reliable resources and services to end users. This revolutionized technology enables various computing capabilities and data requirements to cloud users making it one of the most used computing models in the IT industry today. Task scheduling is considered an NP-complete problem. Genetic algorithms are widely used to find an optimal schedule for a task-scheduling problem with multiple objectives. None of the previous studies has considered the total resource execution time of the virtual machine as a scheduling parameter for finding a better schedule using metaheuristics like genetic algorithms. In this study, we propose a novel fitness function considering total resource execution time and cost in finding an optimum schedule. Hence we propose a novel multi-objective genetic algorithm G-TRETA with the above fitness function. The proposed algorithm was compared with FCFS, MaxMin, MinMin and MCT algorithms for the degree of imbalance, makespan, cost, and system throughput. CloudSim 5.0 simulator and DEAP framework with synthetic data traces and Nasa Ames/iPSC 860 real world traces were used to evaluate the algorithm. From the evaluation results the proposed algorithm gives better results. We can observe 36.37% and 50.46% for makespan, 57.16%, 101.88% for system throughput, 1.47 and 0.94 differences of index improvement for the degree of imbalance for synthetic and real world traces respectively while having efficient cost values.

关键词： Industries Cloud computing Schedules Job shop scheduling Costs Optimal scheduling Throughput Virtual machines Genetic algorithms Synthetic data

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：