检索结果-内蒙古大学图书馆

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kalaiselvi, K. Thilak, K.Deepa Devi, K.Lalitha Kumaresan, K. Malathi, M. Faculty of Engineering and technology Department of Networking and communications SRM Institute of science and technology Kattankulathur Tamilnadu Chennai India Department of Computer science and Engineering Sathyabama Institute of Science and Technology India Department of CSE KSR College of Engineering Tiruchengode Tamilnadu Namakkal India Tamilnadu Namakkal India

ISBN: (纸本)9798331300579

A Wireless Sensor Network is made up of a large number of small, low-power sensor nodes that are randomly or manually distributed across an uncontrolled target ***, the WSNs' main constraint is the sensor nodes' restricted power *** a result, energy saving at sensor nodes is the most difficult barrier for WSNs' long-term *** and low-energy routing are two well-known optimization tasks that have received a lot of attention in the quest to extend the life of wireless sensor networks (WSNs).In a periodic data gathering application, the Particle Swarm Optimization (PSO) technique is employed to overcome this *** monitor the environment on a regular basis and send data to the base station (BS), which analyses the data and draws conclusions about the field activities.A cluster is used to send the data to the base station.A cluster head receives data from sensor nodes and transmits it to the cluster head, which combines the information and sends it to the base *** packet delivery ratios and throughput have both been *** a result, total energy consumption is reduced. © Grenze Scientific Society, 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration 31

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Chen, Yuzong Abouelhamayed, Ahmed F. Dai, Xilai Wang, Yang Andronic, Marta Constantinides, George A. Abdelfattah, Mohamed S. Cornell University Computer Systems Lab United States Systems and Networking Research Group Microsoft Research United States Imperial College London Department of Electrical and Electronic Engineering United Kingdom

ISBN: (纸本)9798331506476

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD1, an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bitserial processing element to easily support multiple numerical precisions and data types;our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4 -bit with © 2025 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Disaster Assistance Intelligent Agent 14

Disaster Assistance Intelligent Agent

引用

14th International Conference on Computing Communication and networking Technologies, ICCCNT 2023

作者： Priyadarshi, Siddhant Rastogi, Mudit Gayathri, V.M. SRM Institute of Science and Technology Computer Science Engineering Chennai India SRM Institute of Science and Technology Department of Networking with Comunication Chennai India

ISBN: (纸本)9798350335095

Virtual characters are controlled by artificial intelligence in video games and movies. Controlling these characters when they are surrounded by people is known as crowd simulation. In this work, we propose to employ intelligent agents and decision trees to simulate a realistic scenario in which our agent will lead the human behavioural AI and identify the best route to the goal or the best circumstances to the objective avoiding all the obstacles in the path. This crowd simulation will be used to make intelligent agents which can find the best path during the situation of any disaster and show humans the safest path which the humans can follow to get to the nearest safe points. Multiagent simulation, commonly referred to as a Crowd and Agent Simulation, is an approach used to simulate many people, animals or other characters interacting with each other in one place. These actors are expected to pursue their objectives, engage in the environment and coordinate with each other. It is expected that the simulated actors will pursue their goals, interact with the environment, and communicate among themselves. Crowd simulations find utility in various areas, including the enhancement of training environments and virtual worlds, the optimization of architectural planning, and the refinement of AI-driven characters' driving behaviors in video games and movies. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Rainfall Prediction using ARIMA and Linear Regression 1

Rainfall Prediction using ARIMA and Linear Regression

引用

1st International Conference on computer, Power and Communications, ICCPC 2022

作者： Vijayalakshmi, C. Sangeeth, K. Josphineleela, R. Shalini, R. Sangeetha, K. Jenifer, D. Srm Institute of Science & Technology Department of Networking and Communications India Panimalar Engineering College Department of Computer Science and Engineering India

ISBN: (纸本)9798350397840

Rainfall is the greatest of nature's gifts for our daily life, as well as the most important climate factor affecting human lives with farmers and agricultural complex systems. Rainfall forecasting is very difficult because excessive and sudden rainfall can have numerous problems, such as agriculture and property destruction, so for a better forecasting model is required for early warning that can save risk to agriculture and life property. Time series data have been used extensively in classical statistics. The proposed methodology predicts annual rainfall by time series ARIMA model and Linear Regression a machine learning algorithm. Time series data have been used extensively in classical statistics. The ARIMA has been trained to produce excellent outcomes. The ARIMA model demonstrated greater accuracy in all seasonal and yearly rains. To offer a solid prediction, this method, like time series ARIMA, requires a strict assumption of stationarity. We use real data from the Indian government website and Kaggle to compare model quality in ARIMA using different evaluation metrics. As a result, the ARIMA model accurately predicts rainfall and it is used for agriculture purpose in future. © 2022 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Joint Optimizations for Double-IRS' Cooperative Positioning and Beamforming Over Massive-MIMOAP Based 6G Secure Mobile Wireless Networks

Joint Optimizations for Double-IRS' Cooperative Positioning ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Wang, Jiaojie Wang, Fei Zhang, Xi Yang, Yuanyuan Southwest University College of Electronic and Information Engineering Chongqing400715 China Texas A&m University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States

ISBN: (纸本)9798350351255

Intelligent reflecting surface (IRS) has been widely recognized as one of the key techniques to improve secure communications performances. However, most existing works mainly focus on the passive beamforming, i.e., phase-shifts, design of a single IRS, without taking into account the cooperations among multiple IRSs and the optimizations of their relative positions. To overcome these deficiencies, in this paper we propose the joint optimizations between the transmit beamforming of massive multiple-input multiple-output (massive-MIMO) access point (AP) and double-IRS' positions and passive beamforming over 6G secure mobile networks. In our proposed networking architectures, AP transmits data to multiple mobile users (MUs) through reflections of two cooperative IRSs under the existence of one eavesdropper (Eve). First, we formulate a secrecy rate optimization problem to maximize the expectations of all MUs' aggregate secrecy rates when Eve's exact position is unknown. Second, leveraging the deep reinforcement learning (DRL), we develop two joint deploying and beamforming schemes to tackle the uncertainty of Eve's exact position. Finally, we validate and evaluate our developed schemes by conducting the extensive simulations, showing the significant performances improvements of our developed schemes through jointly optimizing IRSs' positions/orientations and transmit-beamforming of massive-MIMOAP as the function of the predicted Eve's deploying areas. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Trade-off Between Latency and Energy for Offloading Tasks in Maritime Internet of Things 4

Trade-off Between Latency and Energy for Offloading Tasks in...

引用

4th International Conference on Sustainable Technologies for Industry 4.0, STI 2022

作者： Ghoshal, Sudip Chandra Maruf Hossain, Md Das, Bishozit Chandra Roy, Palash Razzaque, Md. Abdur Green University of Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh University of Dhaka Green Networking Research Group Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9781665490450

With the advancement of maritime activities, the number of Maritime Internet-of-Things (M-IoT) devices is growing exponentially. However, due to the limited computational capacity of the M-IoT devices and the complex maritime network environment, the edge and central cloud computing scenarios can be adopted. Existing works have neither considered interference between the communication of ships nor the trade-off scenario between latency and energy consumption. In this paper, we have provided an optimization framework, namely VESBELT, which enable a trade-off between the minimization of service latency and energy consumption for offloading tasks on the edge or central cloud servers. Our experimental results depict that the developed system VESBELT is superior to contemporary works in terms of service latency and energy usage. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Autonomous Robot Navigation in Unknown Terrains using Generative Adversarial Networks 4

Autonomous Robot Navigation in Unknown Terrains using Genera...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Chitra, P. Sridar, K. Govindan, Sudha Britto Raj, S. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. St Joseph's Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Veerammal Engineering College Department of Computer Science and Engineering Dindigul India Sona College of Technology Department of Computer Science and Engineering Salem India RRASE College of Engineering Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computational Intelligence Chennai India SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798331515720

Autonomous Robot Navigation in unknown and dynamic environments is considered one of the grand challenges in robotics. These motions that guide it span from rescue operations to planetary exploration. Classical methods for path planning, including A*, Dijkstra, and RRT, were unable to balance the efficiency and adaptability of motion planning over complex terrain. This may have a powerful solution using Generative Adversarial Networks (GANs) with advanced machine learning techniques to improve the ability of robotic navigation. This study proposes a GAN-based approach for designing an effective self-adaptive path planning and obstacle avoidance system for autonomous robots. Despite performing well in structured environments, traditional techniques normally fail in analysing the unstructured terrains with real-time adjustments and dynamic changes due to the high computational costs and lack of flexibility involved. In this regard, the proposed GAN-based system resolves these issues by rating navigation paths concerning safety and efficiency. Quantitative analysis demonstrates that within a forest, desert, urban, or off-road environment, the computational times by using the developed strategy turn out to be 0.12 seconds, 0.10 seconds, 0.14 seconds, and 0.13 seconds, respectively, behaving much lower than what can be achieved with other algorithms. This approach proves much superior in terms of computational efficiency path smoothness and adaptability under different environmental conditions in applications related to autonomous robot navigation systems. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent personalised learning system based on emotions in e-learning

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2211-2223页

作者： Karthika, R. Jesi, V. Elizabeth Christo, Mary Subaja Deborah, L. Jegatha Sivaraman, Audithan Kumar, Sanjeev Department of Computer Science and Engineering University College of Engineering Tindivanam Tamil Nadu Melpakkam604001 India Department of Networking and Communications School of Computing College of Engineering SRM Institute of Science and Technology Chennai Kattankulathur603203 India Department of Information Technology Netaji Subhas University of Technology New Delhi110078 India Department of Electronics and Communication Engineering Netaji Subhas University of Technology New Delhi110078 India

One of the greatest challenges in the success of a personalised e-learning system lies in the behaviour identification of the learners during the learning and evaluation phase. The content delivery in an e-learning system must be modified and updated periodically according to the preference and behaviour of the learners. Usually, the behaviour of the learners drastically changes according to their affective states during the learning phase. The accurate identification of the learner’s negative emotions and addressing such emotions carefully in a positive sense can greatly provide success to the learners. In this paper, the learner’s emotions especially frustration emotion are automatically and accurately estimated using the information received from learning management systems (LMS) using the Takagi sugeno fuzzy inference engine. Based on this estimation, several motivational messages are distributed according to the identified emotions which had greatly helped them to succeed during e-learning. The motivational messages that are used for sending to the learners are based on regulatory fit theory. Several kinds of statistical tests are used in this paper for deep analysis. Two sets of learners, namely, control and experimental sets, are identified from undergraduate students. Experimental results are shown for these two sets to reveal the increase in their emotional strength after receiving the motivational messages. Statistical analysis t-test is also applied to the two sets, and the experimental results have shown that there is a significant difference between the two groups which shows the dominance of the proposed system. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Detecting the symptoms of COVID-19 during pandemic environment using smart spectacle thermal images and deep capsule networks

引用

Multimedia Tools and Applications 2025年第8期84卷 4475-4501页

作者： Dwarakanath, B. Pandimurugan, V. Mohandas, R. Sambath, M. Baiju, B.V. Chinnasamy, A. SRM Institute of Science and Technology Ramapuram Chennai India Networking and Communications School of Computing SRMIST kattankulathur Chennai India Computational Intelligence School of Computing SRMIST kattankulathur Chennai India Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Data Science and Business Systems School of Computing SRMIST kattankulathur Chennai India

The pandemic creates a more complicated providence of medical assistance and diagnosis procedures. In the world, Covid-19, Severe Acute Respiratory Syndrome Coronavirus-2 (SARS Cov-2), and plague are widely known pandemic disease desperations. Due to the recent COVID-19 pandemic tragedies, various medical diagnosis models and intelligent computing solutions are proposed for medical applications. In this era of computer-based medical environment, conventional clinical solutions are surpassed by many Machine Learning and Deep Learning-based COVID-19 diagnosis models. Anyhow, many existing models are developing lab-based diagnosis environments. Notably, the Gated Recurrent Unit-based Respiratory Data Analysis (GRU-RE), Intelligent Unmanned Aerial Vehicle-based Covid Data Analysis (Thermal Images) (I-UVAC), and Convolutional Neural Network-based computer Tomography Image Analysis (CNN-CT) are enriched with lightweight image data analysis techniques for obtaining mass pandemic data at real-time conditions. However, the existing models directly deal with bulk images (thermal data and respiratory data) to diagnose the symptoms of COVID-19. Against these works, the proposed spectacle thermal image data analysis model creates an easy and effective way of disease diagnosis deployment strategies. Particularly, the mass detection of disease symptoms needs a more lightweight equipment setup. In this proposed model, each patient's thermal data is collected via the spectacles of medical staff, and the data are analyzed with the help of a complex set of capsule network functions. Comparatively, the conventional capsule network functions are enriched in this proposed model using adequate sampling and data reduction solutions. In this way, the proposed model works effectively for mass thermal data diagnosis applications. In the experimental platform, the proposed and existing models are analyzed in various dimensions (metrics). The comparative results obtained in the experiments just

关键词： COVID-19

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：