检索结果-内蒙古大学图书馆

2024 IEEE International Performance, computing, and Communications Conference, IPCCC 2024

作者： Dhar, Nobel Deng, Bobin Islam, Md Romyull Ahmad Nasif, Kazi Fahim Zhao, Liang Suo, Kun Kennesaw State University College of Computing and Software Engineering United States

ISBN: (纸本)9798350367942

Deploying local AI models, such as Large Language Models (LLMs), to edge devices can substantially enhance devices' independent capabilities, alleviate the server's burden, and lower the response time. Owing to these tremendous potentials, many big tech companies have been actively promoting edge LLM evolution and released several lightweight Small Language Models (SLMs) to bridge this gap. However, SLMs currently only work well on limited real-world applications. We still have huge motivations to deploy more powerful (larger-scale) AI models on edge devices and enhance their smartness level. Unlike the conventional approaches for AI model compression, we investigate from activation sparsity. The activation sparsity method is orthogonal and combinable with existing techniques to maximize compression rate while maintaining great accuracy. According to statistics of open-source LLMs, their Feed-Forward Network (FFN) components typically comprise a large proportion of parameters (around 2/3). This internal feature ensures that our FFN optimizations would have a better chance of achieving effective compression. Moreover, our findings are beneficial to general LLMs and are not restricted to ReLU-based *** work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art LLMs. Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation. This extra 50% sparsity does not naturally exist in the current LLMs, which require tuning LLMs' activation outputs by injecting zero-enforcing thresholds. To obtain the benefits of activation sparsity, we provide a guideline for the system architect for LLM prediction and prefetching. Moreover, we further verified the predictability of activation patterns in recent LLMs. The success prediction allows the system to prefetch the necessary weights while omitting

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of an ERC-20 Smart Contract on the Ethereum Blockchain

Design and Implementation of an ERC-20 Smart Contract on the...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Priest, Joshua Cooper, Cameron Lovell, Savvy Shi, Yong Lo, Dan Kennesaw State University College of Computing and Software Engineering Marietta United States

ISBN: (纸本)9798350324457

As technology continues to develop, there is a growing need to find sustainable solutions in all industries, including cryptocurrency. Due to the high energy consumption that cryptocurrencies are known for, there have been efforts to reduce waste consumption and in turn minimize the carbon footprint. We support the trends for creating an environment-friendly crypto token using the ERC-20 standard on the Ethereum blockchain. We outline the various aspects that make a token more sustainable and highlight the potential benefits of such tokens. Our proposal involves the design of a smart contract that incorporates eco-friendly features such as lower energy consumption, carbon offsetting, and more efficient methods or algorithms. We also discuss the importance of transparency and accountability in the design and implementation of such tokens. This paper discusses not only the practical tools and steps necessary in creating a crypto token but also highlights the challenges associated with creating a more sustainable token. © 2023 IEEE.

关键词： ERC-20 [Ethereum Request for Comment] Ethereum Gas Fee MetaMask Remix IDE Smart Contract Solidity

来源：评论

学校读者我要写书评

暂无评论

Cyber Security in Blockchain 6

Cyber Security in Blockchain

引用

6th IEEE Conference on Dependable and Secure computing, DSC 2023

作者： Cooper, Eric Weese, Eric Fortson, Alex Lo, Dan Shi, Yong Kennesaw State University College of Computing and Software Engineering Marietta United States

ISBN: (纸本)9798350382112

Blockchain is a growing technology that utilizes a decentralized public record of transactions. It is not only used for cryptocurrency, but also IoT, financial systems, healthcare, supply chain, etc. Although blockchain is quite robust, it is not invulnerable. This project will explain and demonstrate several weaknesses of blockchain and how to prevent them. We will demonstrate the following attacks and how to prevent them using Solidity: Transaction Order Dependence, Denial of Service, Replay Attack, Writing of Arbitrary Storage Address Attack, Weak Randomness, and Honeypot *** Concepts:Security and Privacy $\to$ software and Application Security $\to$ software Security engineering © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Analysis of Climate Change Impacts on Public Health: A Systematic Review and Future Directions

Data-Driven Analysis of Climate Change Impacts on Public Hea...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Yarmohammadtoosky, Sahar Xie, Ying Kennesaw State University School of Data Science and Analytics MariettaGA United States Kennesaw State University College of Computing and Software Engineering MariettaGA United States

ISBN: (纸本)9798350362480

Climate change profoundly impacts human health, ecosystems, and food and water security. This review provides a comprehensive analysis of climate change's effects on human health using data science methods, including statistical and machine learning models, to assess current knowledge. It identifies critical gaps in data collection and methodological limitations across different regions and climates. Key recommendations include improving data resolution and duration to enhance model accuracy, as well as fostering collaboration between data scientists, public health experts, and climate specialists. The review underscores the need for innovative, data-driven models to better predict and address the health impacts of climate change. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

An ensemble deep learning model for cyber threat hunting in industrial internet of things

引用

Digital Communications and Networks 2023年第1期9卷 101-110页

作者： Abbas Yazdinejad Mostafa Kazemi Reza M.Parizi Ali Dehghantanha Hadis Karimipour Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical Engineering Faculty of EngineeringShahed UniversityTehranIran College of Computing and Software Engineering Kennesaw State UniversityGAUSA School of Engineering University of GuelphOntarioCanada

By the emergence of the fourth industrial revolution,interconnected devices and sensors generate large-scale,dynamic,and inharmonious data in Industrial Internet of Things(IIoT)*** vast heterogeneous data increase the challenges of security risks and data analysis *** IIoT grows,cyber-attacks become more diverse and complex,making existing anomaly detection models less effective to *** this paper,an ensemble deep learning model that uses the benefits of the Long Short-Term Memory(LSTM)and the AutoEncoder(AE)architecture to identify out-of-norm activities for cyber threat hunting in IIoT is *** this model,the LSTM is applied to create a model on normal time series of data(past and present data)to learn normal data patterns and the important features of data are identified by AE to reduce data *** addition,the imbalanced nature of IIoT datasets has not been considered in most of the previous literature,affecting low accuracy and *** solve this problem,the proposed model extracts new balanced data from the imbalanced datasets,and these new balanced data are fed into the deep LSTM AE anomaly detection *** this paper,the proposed model is evaluated on two real IIoT datasets-Gas Pipeline(GP)and Secure Water Treatment(SWaT)that are imbalanced and consist of long-term and short-term dependency on *** results are compared with conventional machine learning classifiers,Random Forest(RF),Multi-Layer Perceptron(MLP),Decision Tree(DT),and Super Vector Machines(SVM),in which higher performance in terms of accuracy is obtained,99.3%and 99.7%based on GP and SWaT datasets,***,the proposed ensemble model is compared with advanced related models,including Stacked Auto-Encoders(SAE),Naive Bayes(NB),Projective Adaptive Resonance Theory(PART),Convolutional Auto-Encoder(C-AE),and Package Signatures(PS)based LSTM(PS-LSTM)model.

关键词： Internet of things IIoT Anomaly detection Ensemble deep learning Neural networks LSTM

来源：评论

学校读者我要写书评

暂无评论

On Bounding the Behavior of a Neuron 36th

On Bounding the Behavior of a Neuron

引用

36th International Florida Artificial Intelligence Research Society Conference, FLAIRS-36 2023

作者： Borowski, Richard Choi, Arthur Computer Science Department College of Computing and Software Engineering Kennesaw State University United States

A neuron with binary inputs and a binary output represents a Boolean function. Our goal is to extract this Boolean function into a tractable representation that will facilitate the explanation and formal verification of a neuron's behavior. Unfortunately, extracting a neuron's Boolean function is in general an NP-hard problem. However, it was recently shown that prime im-plicants of this Boolean function can be enumerated efficiently, with only polynomial time delay. Building on this result, we propose a best-first search algorithm that is able to incrementally tighten inner and outer bounds of a neuron's Boolean function. These bounds correspond to truncated prime-implicant covers of the Boolean function. We provide two case studies that highlight our ability to bound the behavior of a neuron. © 2023 by the authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

EduMAS: A Novel LLM-Powered Multi-Agent Framework for Educational Support

EduMAS: A Novel LLM-Powered Multi-Agent Framework for Educat...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Li, Qiaomu Xie, Ying Chakravarty, Sumit Lee, Dabae Kennesaw State University College of Computing and Software Engineering MariettaGA30060 United States Kennesaw State University Department of Instructional Technology MariettaGA30060 United States

ISBN: (纸本)9798350362480

In general, educational support with Large Language Models (LLMs) faces challenges in knowledge organization, expertise integration, and contextual adaptation. So, we present EduMAS, a novel multi-agent framework that coordinates specialized agents with graph-based knowledge navigation. Our framework introduces three key innovations: (1) Specialized Agents that provide expertise in different learning aspects to solve decomposed subtasks professionally;(2) Graph Navigator for graph-based knowledge extraction and selection to improve the quality of responses;(3) The Emotional Awareness mechanism for better contextual adaptation. Through comprehensive experiments on college-level physics education and evaluated by six state-of-the-art LLMs, EduMAS demonstrates significant improvements over the baseline model in complex concept integration, cross-disciplinary understanding, and theory-to-application translation. Ablation studies further validate the contribution of each framework component, Specialized Agents and Graph Navigator play important roles in performance improvement. Our work provides strong support for LLM-powered multi-agent system in AI-assisted education. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Reducing peak to average power ratio in optical NOMA based 5G system using advanced SLM method

引用

Optical and Quantum Electronics 2024年第10期56卷 1-13页

作者： Kumar, Arun Chakravarty, Sumit Nanthaamornphong, Aziz Department of Electronics and Communication Engineering New Horizon College of Engineering Bengaluru India Department of Electrical Engineering and Computer Engineering Kennesaw State University KennesawGA United States College of Computing Prince of Songkla University Phuket Thailand

One of the most critical challenges in optical fiber communication systems using non-orthogonal multiple access (NOMA) techniques is reducing the peak-to-average power ratio (PAPR). Optical NOMA often leads to high PAPR, causing non-linear distortion and limiting the system’s gain. The advanced Selected Mapping (SLM) algorithm is introduced in this work to reduce the PAPR of the O-NOMA. In conventional SLM, multiple phase sequences are applied to the input data, which requires numerous Inverse Fast Fourier Transform, increasing computational complexity. The proposed approach simplifies this by selecting a central reference phase sequence, reducing the number of candidate sequences and the number of IFFT operations required. This reduction in complexity does not significantly compromise the PAPR reduction capability, making the method more efficient. The SLM algorithm addresses this issue by applying the phase rotation factor to the transmitted signals, redistributing the power, and reducing the peak levels. This article highlights the benefits and challenges of implementing SLM in optical NOMA systems, including its compatibility with existing NOMA schemes. Matlab 2016 analyzes parameters such as bit error rate (BER), PAPR, and out-of-band radiation. A 66% PAPR reduction can be obtained using the suggested SLM with various phase variables. Furthermore, there is a −2650 reduction in spectrum leakage. The simulation outcomes of the work reveal the potential of SLM to reduce PAPR and enhance the BER and PSD performance of optical NOMA compared with the existing algorithms. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

The Robustness of Spiking Neural Networks in Communication and its Application towards Network Efficiency in Federated Learning

The Robustness of Spiking Neural Networks in Communication a...

引用

2024 IEEE International Performance, computing, and Communications Conference, IPCCC 2024

作者： Nguyen, Manh V. Zhao, Liang Deng, Bobin Severa, William Xu, Honghui Wu, Shaoen Kennesaw State University College of Computing and Software Engineering GA United States Sandia National Laboratories Department of Cognitive & Emerging Computing NM United States

ISBN: (纸本)9798350367942

Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). However, to extend SNNs to a Federated Learning (FL) setting involving collaborative model training, the communication between the local devices and the remote server remains the bottleneck, which is often restricted and costly. In this paper, we first explore the inherent robustness of SNNs under noisy communication in FL. Building upon this foundation, we propose a novel Federated Learning with Top-κ Sparsification (FLTS) algorithm to reduce the bandwidth usage for FL training. We discover that the proposed scheme with SNNs allows more bandwidth savings compared to ANNs without impacting the model's accuracy. Additionally, the number of parameters to be communicated can be reduced to as low as 6% of the size of the original model. We further improve the communication efficiency by enabling dynamic parameter compression during model training. Extensive experiment results demonstrate that our proposed algorithms significantly outperform the baselines in terms of communication cost and model accuracy and are promising for practical network-efficient FL with SNNs. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Multistage Framework for Detection of Very Small Objects 23

A Multistage Framework for Detection of Very Small Objects

引用

6th International Conference on Machine Vision and Applications, ICMVA 2023

作者： Don, Duleep Rathgamage Aygun, Ramazan Karakaya, Mahmut School of Data Science and Analytics College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States Department of Computer Science College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States

ISBN: (纸本)9781450399531

Small object detection is one of the most challenging problems in computer vision. Algorithms based on state-of-the-art object detection methods such as R-CNN, SSD, FPN, and YOLO fail to detect objects of very small sizes. In this study, we propose a novel method to detect very small objects, smaller than 8×8 pixels, that appear in a complex background. The proposed method is a multistage framework consisting of an unsupervised algorithm and three separately trained supervised algorithms. The unsupervised algorithm extracts ROIs from a high-resolution image. Then the ROIs are upsampled using SRGAN, and the enhanced ROIs are detected by our two-stage cascade classifier based on two ResNet50 models. The maximum size of the images used for training the proposed framework is 32×32 pixels. The experiments are conducted using rescaled German Traffic Sign Recognition Benchmark dataset (GTSRB) and downsampled German Traffic Sign Detection Benchmark dataset (GTSDB). Unlike MS COCO and DOTA datasets, the resulting GTSDB turns out to be very challenging for any small object detection algorithm due to not only the size of objects of interest but the complex textures of the background as well. Our experimental results show that the proposed method detects small traffic signs with an average precision of 0.332 at the intersection over union of 0.3. © 2023 ACM.

关键词： Object detection

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：