检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prasanna Kumar, R. Prasanna Kumar, B.G. Sri Ramakrishna Prabhu, A. Upadhyay, Yash Teja, Nunna Vishnu Swamy, Penta Aravinda Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

In deep reinforcement learning, sampling ineffi-ciency is addressed by mimicking human learning which lever-Ages past experiences stored in the hippocampus. Integrating this idea, the proposed approach utilizes a task-conditioned hypernetwork retrieval network with MobileNet for feature extraction from past experiences. Furthermore, BERT was in-Tegrated for advanced natural language understanding, enabling our DRL agents to better interpret and act upon language-based tasks. This approach ensures dynamic adaptability and fosters a more efficient collaboration between retrieval and decision-making processes. Evaluation in MiniGrid demonstrates that the proposed method outperforms strong baselines, showing significant advancements in deep reinforcement learning with natural language processing capabilities. This advancement not only marks progress in sampling efficiency but also opens new avenues for multi-Task learning, paving the way for more intelligent, autonomous AI systems. © 2024 IEEE.

关键词： Bidirectional Encoder Representations from Transformers Deep Reinforcement Learning Episodic Memory Hypernetwork Multi-Task Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Comparative Ranking of LLM Variants in Entity Relationship Prediction 15

Performance Evaluation and Comparative Ranking of LLM Varian...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vardhni, Krisha Devaraja, G. Dharhshita, R. Chowdary, Ritesh Krishna Mahadevan, Anbazhagan Amrita School of Computing Department of Computer Science and Engineering Coimbatore641112 India

ISBN: (纸本)9798350370249

This paper presents a comprehensive evaluation and ranking of five Large Language Models - Mistral, Vicuna, Phi, Llama 2, and Zephyr - across five temperature variants. The focus is on their ability to predict the likelihood of a relationship between pairs of entities within a given context. Each LLM variant is assessed based on stability over multiple epochs, speed, dispersion of results, and the number of incorrect responses. The study aims to provide insights into the performance of these LLMs, thereby facilitating their effective utilization in generating meaningful tabular data. The findings are expected to contribute significantly to the field of artificial intelligence and data analysis. The paper concludes with a comparative ranking of the 25 LLM variants, providing a clear perspective on their relative performances. © 2024 IEEE.

关键词： Artificial Intelligence Data Analysis Entity Relationship Prediction Large Language Models Performance Evaluation Ranking Variants Tabular Data Generation Temperature Variants

来源：评论

学校读者我要写书评

暂无评论

Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1513-1528页

作者： Zhang, Tiehua Liu, Yuze Shen, Zhishu Ma, Xingjun Qi, Peng Ding, Zhijun Jin, Jiong Tongji University School of Computer Science and Technology Shanghai201804 China Ant Group Shanghai200122 China Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Fudan University School of Computer Science Shanghai200438 China Tongji University Department of Control Science and Engineering Shanghai201804 China Swinburne University of Technology School of Science Computing and Engineering Technologies Melbourne3122 Australia

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this article, we propose a hypergraph learning framework named learning from heterogeneity (LFH) that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterward, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with twelve state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experimental results demonstrate a significant performance gain (an average of 12.9% in node classification and 12.8% in link prediction) compared with recent state-of-the-art methods. © 2020 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptive Algorithms for Local Urban Traffic Control: Deep Reinforcement Learning with DQN 2

Deep Adaptive Algorithms for Local Urban Traffic Control: De...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Subba Rao, P.V.R. Polisetty, Venkata Ramana Murthy Jayanth, K Krishna Sai Manoj, N.V. Mohith, Vankadari Kumar, R. Prasanna Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

The paper uses Deep Reinforcement Learning (DRL) to traffic signal regulation, solving urban traffic congestion. Our research paper demonstrates the simulation of intricate traffic conditions with microscopic accuracy, utilizing the Simulation of Urban Mobility (SUMO) platform. As the foundation for DRL, a state representation and action space are established. The learning process is guided by the Deep Q-Network (DQN) architecture, precisely set hyperparameters, and epsilon-greedy exploration. To improve stability, training data is gathered and stored in an experience replay buffer. The DQN-based technology is built into the SUMO simulation and allows for dynamic traffic signal modifications. Updates to the target network on a regular basis increase stability. Metrics for evaluation include average waiting time, traffic flow efficiency, and congestion levels, which compare favorably to baseline approaches. In conclusion, this study shows the usefulness of DRL in optimizing traffic signal control, providing viable strategies to minimize urban traffic congestion and increase transportation efficiency. © 2024 IEEE.

关键词： Congestion Reduction Deep Reinforcement Learning DQN Architecture Epsilon-Greedy Exploration SUMO Traffic Signal Control

来源：评论

学校读者我要写书评

暂无评论

Augmenting Clinical Decisions with Deep Learning Lung Cancer Image Abnormality Segmentation 14

Augmenting Clinical Decisions with Deep Learning Lung Cancer...

引用

14th International Conference on Cloud computing, Data science and engineering, Confluence 2024

作者： Venkatraman, K. Reddy, Sirigiri Naga Pavan Sathvik Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India

ISBN: (纸本)9798350344837

Lung cancer is a major global cause of death, highlighting the critical need for quick and accurate detection methods. The exploration of computational alternatives arose from the standard way of manually processing CT images, which is time-consuming and error-prone. In this work, we combine the advantages of Support Vector Machine (SVM) and VGG16 classifiers to provide a novel method for enhancing lung cancer diagnosis. By analyzing the 'IQ-OTH/NCCD' dataset, our hybrid model-which combines the VGG 16 and SVM algorithms-performs admirably in differentiating between aggressive, benign, and normal lung cancer cases. This combination of traditional machine learning with deep learning tackles accuracy and efficiency issues, which is a promising development over current diagnostic methods. We conduct a comprehensive comparative analysis with prominent architectures to select the optimal model based on accuracy, efficiency, and resource requirements. In addition to introducing the VGG 16+SVM model, our research provides valuable insights into deep learning architectures, with the ultimate goal of advancing precise and efficient diagnosis of lung cancer, which is crucial in combating this global health challenge in the future. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

ConfigMaster: An Interactive Solution for System Management 8

ConfigMaster: An Interactive Solution for System Management

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Ganapathi, Ananya Sivakumar, Parikshith Divya, K.V. Elango, Aditya Gupta, Hardik Amrita School of Computing Dept. of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331505462

The 'ConfigMaster: An interactive solution for system management' is a simple utility written using Bash scripting. It is designed for Unix-like systems. The tool lets users easily configure system settings and do administrative tasks without having to remember complex commands. The tool minimizes user's work by automating tasks. The tool can be used even by users with very little technical knowledge, as it has a simple menu-based interface to manage things like network settings, software packages, and wireless connections directly from the terminal. By automating common tasks, the tool makes system management more efficient and accessible. By automating common tasks, the tool makes system management more efficient and accessible. It's very useful to simplify system configuration on Unix-like systems using scripting languages like Bash. 'ConfigMaster' aims to offer a smooth user experience with the incorporation of core management principles from an operating system, such as disk scheduling, process synchronization, and memory management etc. Being flexible itself, this tool will bring further improvements to make effective responses to emerging user needs. The framework being flexible, it can be expanded to add new features to configure under different scenarios. By integrating essentials operating system operations, 'ConfigMaster' enables users to efficiently perform system configurations along with promoting ease of use. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of computer science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

A review on the energy efficient resource allocation schemes with improved quality of services in green cloud computing

A review on the energy efficient resource allocation schemes...

引用

International Conference on Artificial Intelligence, Blockchain, computing and Security, ICABCS 2023

作者： Fiaz, A.S. Syed Sonai, Veeramani Computer Science and Engineering Amrita Viswa Vidhyapeetham School of Computing Chennai India Department of Computer Science and Engineering School of Engineering Shiv Nadar University Chennai India

ISBN: (纸本)9781032669663

The vast changes in the computing utilization have created a need with the improvised resource availability and reliability. The virtualization of servers and data centers to increase their efficiency has transformed how enormous data is stored and handled. Cloud computing has created a supreme and impressive approach to virtualize servers and data centers and to make them energy efficient in order to leverage on diverse IT resources. Massive power and energy consumption by IT resources leads to an energy crisis and a change in the planet’s climate. But because these IT resources use so much energy and power, they end up being a significant source of CO2 emissions. Due to this, green cloud computing is now required in order to make IT resources cost-and energy-effective. It is necessary to do a thorough analysis of the cloud’s power efficiency in order to arrive at the best options for green cloud computing. Green Cloud computing is well known to be a broad domain and a popular field for research because of the increasing rise of enormous data storage and computational demand. It can generate solutions that not only make IT resources energy efficient but also reduce operational expenses. This review’s objective is to highlight some of the best practices for achieving green cloud computing, including workload clustering, Auction-Based Resource Optimization techniques, Hardware and Software controlled solutions, Minimize cooling requirements scheduling, clustering, virtualization and other energy-saving techniques. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

A Game Theoretic Link Scheduler for Wireless Networks with Heterogeneous Energy Sources

引用

China Communications 2024年第12期21卷 108-125页

作者： He Tengjiao Kwanwu Chin Wang Yishun Sieteng Soh College of Information Science and Technology Jinan UniversityGuangzhouChina School of Electrical Computer and Telecommunications EngineeringUniversity of WollongongNSWAustralia School of Electrical Engineering Computing and Mathematical SciencesCurtin UniversityWAAustralia

This paper considers link scheduling in a wireless network comprising of two types of nodes:(i)hybrid access points(HAPs)that harvest solar en-ergy,and(ii)devices that harvest radio frequency(RF)energy whenever HAPs *** aim is to de-rive the shortest possible link schedule that determines the transmission time of inter-HAPs links,and uplinks from devices to *** first outline a mixed in-teger linear program(MILP),which can be run by a central node to determine the optimal schedule and transmit power of HAPs and *** then out-line a game theory based protocol called Distributed Schedule Minimization Protocol(DSMP)that is run by HAPs and ***,it does not require causal energy arrivals and channel gains *** results show that DSMP produces schedule lengths that are at most 1.99x longer than the schedule computed by MILP.

关键词： channel access finite battery mathemati-cal program renewable energy wireless power trans-fer

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Based Approach to Partition Testing

引用

计算机科学技术学报（英文版） 2025年第1期40卷 99-118页

作者：孙昌爱肖明俊代贺鹏刘淮 1School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083 China 2Department of Computing Technologies Swinburne University of Technology Hawthorn VIC 3122 Australia

Partition testing is one of the most fundamental and popularly used software testing *** first di-vides the input domain of the program under test into a set of disjoint partitions,and then creates test cases based on these *** by the theory of software cybernetics,some strategies have been proposed to dynamically se-lect partitions based on the feedback information gained during *** basic intuition of these strategies is to assign higher probabilities to those partitions with higher fault-detection potentials,which are judged and updated mainly ac-cording to the previous test *** a feedback-driven mechanism can be considered as a learning process—it makes decisions based on the observations acquired in the test ***,advanced learning techniques could be leveraged to empower the smart partition selection,with the purpose of further improving the effectiveness and efficiency of partition *** this paper,we particularly leverage reinforcement learning to enhance the state-of-the-art adaptive partition testing *** algorithms,namely RLAPT_Q and RLAPT_S,have been developed to implement the proposed *** studies have been conducted to evaluate the performance of the proposed approach based on seven object programs with 26 *** experimental results show that our approach outperforms the existing partition testing techniques in terms of the fault-detection capability as well as the overall testing *** study demonstrates the applicability and effectiveness of reinforcement learning in advancing the performance of software testing.

关键词： partition testing reinforcement learning temporal-difference learning intelligent software engineering

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：