检索结果-内蒙古大学图书馆

IEEE International Conference on Performance, computing and Communications (IPCCC)

作者： Manh V. Nguyen Liang Zhao Bobin Deng William Severa Honghui Xu Shaoen Wu College of Computing and Software Engineering Kennesaw State University Georgia USA Department of Cognitive & Emerging Computing Sandia National Laboratories New Mexico USA

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

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.

关键词： Training Accuracy Costs Federated learning Noise Spiking neural networks Bandwidth Robustness System-on-chip Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Beyond Adult and COMPAS: Fair Multi-Class Prediction via Information Projection 36

Beyond Adult and COMPAS: Fair Multi-Class Prediction via Inf...

引用

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Alghamdi, Wael Hsu, Hsiang Jeong, Haewon Wang, Hao Winston Michalak, P. Asoodeh, Shahab Calmon, Flavio P. John A. Paulson School of Engineering and Applied Sciences Harvard University United States Department of Computing and Software McMaster University Canada

ISBN: (纸本)9781713871088

We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of "projecting" a pre-trained (and potentially unfair) classifier onto the set of models that satisfy target group-fairness requirements. The new, projected model is given by post-processing the outputs of the pre-trained classifier by a multiplicative factor. We provide a parallelizable, iterative algorithm for computing the projected classifier and derive both sample complexity and convergence guarantees. Comprehensive numerical comparisons with state-of-the-art benchmarks demonstrate that our approach maintains competitive performance in terms of accuracy-fairness trade-off curves, while achieving favorable runtime on large datasets. We also evaluate our method at scale on an open dataset with multiple classes, multiple intersectional groups, and over 1M samples. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Multimodal Aspect-Level Sentiment Analysis based on Deep Neural Networks 8

Multimodal Aspect-Level Sentiment Analysis based on Deep Neu...

引用

8th International Symposium on System Security, Safety, and Reliability, ISSSR 2022

作者： Ban, Minchao Zong, Liansong Zhou, Jie Xiao, Zhiming School of Computer and Software Engineering Xihua University Chengdu China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

ISBN: (数字)9781665453974

ISBN: (纸本)9781665453974

Aspect-level sentiment analysis is a fine-grained task of sentiment analysis that aims to identify the sentiment polarity of specific aspect words in a sentence. However, most existing approaches rely mainly on text content and ignore other potentially useful data (e.g., images) that can complement the text content and thus more accurately represent the user's sentiment. Therefore, we focus on Aspect-level Multi-model Sentiment Analysis(AMSA). Analyzing the current research status of AMSA, explore the independence and correlation between multiple modal data, capture their deep interaction information, and improve the data feature analysis and fusion capability from feature extraction methods and feature fusion strategies, respectively. Finally, the corresponding modeling scheme is proposed for aspect-level multimodal aspect-level sentiment analysis. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Network with Two Types of Weight Mechanisms for Aspect-Based Sentiment Analysis 8

Graph Convolutional Network with Two Types of Weight Mechani...

引用

8th International Symposium on System Security, Safety, and Reliability, ISSSR 2022

作者： Xiao, Zhiming Zong, Liansong Ban, Minchao Zhao, Fanjie School of Computer and Software Engineering Xihua University Chengdu China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

ISBN: (数字)9781665453974

ISBN: (纸本)9781665453974

In this paper, we propose an approach to leverage inter aspects relation and Rely Graph Convolutional Networks (RelyGCN) for aspect sentiment analysis. More specifically, an ordinary dependency graph is first constructed for each sentence over the dependency tree. Then we extract aspects by L-Layer GCNs and construct their relation. Finally, we will predict the sentiment polarity (negative, neutral and positive) of the sentence S towards the aspect A by the feature fusing layer and the output layer. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic text classification system based on AI technology

Automatic text classification system based on AI technology

引用

2022 International Symposium on Artificial Intelligence Control and Application Technology, AICAT 2022

作者： Xu, Rui Department of Computing and Software Faculty of Engineering McMaster University HamiltonL8S 1L9 Canada

ISBN: (纸本)9781510656710

At present, the commonly used text classification methods are based on the classification function provided by the supervised learning algorithm. Faced with massive data, it has the problems of slow classification speed, low accuracy and single classification function. In response to this urgent problem, this paper designs a text classification system based on AI technology. The Visual C++ programming language is used in the design of the classification system, and the modular design is used for the system function modules, which makes the system stable and efficient under this development environment. In order to compare the applicability of manual classification methods and AI automatic classification methods, this paper conducts classification efficiency experiments and classification accuracy experiments. In the classification efficiency experiments, it is found that the larger the amount of text, the faster the AI automatic classification method is compared to the manual classification method. The faster it is, in the classification accuracy experiment, comparing the classification accuracy of the two methods for five types of texts, it is concluded that the average classification accuracy of the AI automatic classification method is 85.38%, which is 6.32% higher than that of the manual classification method. In general, the introduction of AI automatic classification methods into the classification system can achieve efficient and accurate classification. © 2022 SPIE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Graph Convolution Model for Intelligent Datum Features Selection

引用

Procedia CIRP 2024年 129卷 1-6页

作者： Wenbo Lv Chaolong Zhang Yuanping Xu Chao Kong Jin Jin Tukun Li Xiangqian Jiang Dan Tang Jian Huang Zongzheng Zhang School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield Huddersfield HD1 3DH UK

The datum is a crucial component in tolerance specification, which is the foundation for the selections of geometric tolerances and tolerance principles. Currently, intelligent datum reasoning is largely based on logical rules that are mainly extracted from human experience, resulting in the high uncertainty and low efficiency. To tickle these issues, this study proposes a data selection model based on the GCN (Graph Convolutional Networks), In the devised model, the different geometric features of a workpiece are represented in a graph structure. The geometric, spatial, and assembly relationships, as well as positioning features are computed to obtain vectorized representations of the different geometric features, which serve as inputs to the constructed GCN model. Then, based on the GCN, a datum discriminant classifier has been developed on the training samples. To enhance the classifier accuracy, multiple GCN layers are employed for training, with the output of each GCN module added to a list. Ultimately, the outputs of all GCN modules are concatenated and subjected to classification prediction through fully connected layers. Datum specifications are established based on the classification of geometric features. The effectiveness and feasibility of this method are validated through case studies, e.g. rear floor crossbeams, with comparative results indicating a similarity rate of 85.19% with manually designed outcomes.

关键词： Datum GCN Diagram structure representation Geometric elements Eigenvectors

来源：评论

学校读者我要写书评

暂无评论

An IT/OT Converged Cyber Range Framework Supporting Ensemble of Large Multimodal Models-Human Teaming and RAG Capability for Bigdata Information Retrieval - 6G Perspective

An IT/OT Converged Cyber Range Framework Supporting Ensemble...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Rahman, M. Abdur Islam, M. Saiful Islam, M. Repon Hossain, M. Shamim Al-Hazzaa, Selwa University of Prince Mugrin Cyber Security and Forensic Computing Department Medina Saudi Arabia UoL Worldwide University of London London United Kingdom Khulna University of Engineering & Technology Department of Computer Science and Engineering Khulna Bangladesh King Saud University Department of Software Engineering Riyadh Saudi Arabia Riyadh Saudi Arabia

ISBN: (纸本)9798350351255

In IT/OT converged enterprise networks, the management of multimodal big data has surpassed human capabilities, presenting critical challenges in business decision-making. This paper introduces an innovative IT/OT Converged Cyber Range Framework, leveraging the power of 6G technology alongside an ensemble of large multimodal models (LMMs) equipped with Retrieval Augmented Generation (RAG) capabilities. Our proposed framework excels at parsing and retrieving information from diverse and massive multimodal datasets in near real-time, driven by the integration of LMMs and human interactions in natural language. The framework's advanced configuration with RAG achieved top performance with an average score of 80.5 across key metrics, including an 86 in answer relevancy and an 88 in faithfulness, while effectively reducing hallucinations to a score of 26. By combining 6G's connectivity with advanced LMM capabilities, we significantly improve the efficiency of automated big data processing and information retrieval, thereby transforming decision-making processes in IT/OT environments. The implementation of our framework, validated through real-life big data sources, and the encouraging test results showcase its effectiveness and transformative potential in managing and utilizing big data far beyond traditional human capabilities. © 2024 IEEE.

关键词： 6G Technology Human-LMM Teaming IT/OT Converged Network Large Multimodal Models (LMMs) Multimedia Bigdata Retrieval Augmented Generation (RAG)

来源：评论

学校读者我要写书评

暂无评论

Novel Mvgg Classifier for Identifying Floor and Building and Myolo Regressor to Find Position in Indoor Application by Converting Wifi Signals to Image

SSRN

引用

SSRN 2024年

作者： Arbabmir, Mohammadvali Das, Debashish Elezaj, Ogerta Alsewari, AbdulRahman Islam, Md Baharul Faculty of Computing Engineering and the Built Environment Birmingham City University United Kingdom Faculty of Computing and Software Engineering Florida Gulf Coast University Fort MyersFL United States

This article implies a novel MVGG classifier to finding floor and building as well as a novel MYOLO regressor to find position in indoor environment based on converting the WiFi signals to image. Comparing these novel models to state of the art shows the accuracy of these models to use for indoor positioning. The proposed novel models are compared with CNN, U-Net, LSTM, ResNet, GoogLeNet, Xception, and MobileNet by evaluating on two distinct datasets, UJIIndoorLoc and IMUWiFine. The MVGG classifier exhibits remarkable accuracy, achieving 99.80% for building and 98.74% for floor identification based on the UJIIndoorLoc dataset. Meanwhile, the MYOLO regressor stands out in position identification on the IMUWiFine dataset, boasting a notably low mean squared error (MSE) of 0.65 and a high R2 score of 0.9936. Furthermore, MYOLO Regressor excels in mean absolute error (MAE) values for distance, latitude, longitude, and altitude, showcasing precision in predicting geographic coordinates. Despite its relatively low speed (ms/step) of 21, MYOLO regressor emerges as a computationally efficient choice. These findings emphasize MYOLO's robust suitability for accurate and efficient position identification and MVGG classifier for accurate floor and building identification in indoor localization scenarios. © 2024, The Authors. All rights reserved.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

A Linguistic Approach Towards Automatic Acquisition and Classification of Common Chinese Affective Events

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 2025年第5期24卷

作者： Wang, Ya Cao, Cungen Huang, Xin Hui, Ming Zheng, Wei School of Artificial Intelligence and Software Engineering Nanyang Normal University Nanyang China Institute of Computing Technology Chinese Academy of Sciences Beijing China

Affective events are events that are typically associated with a positive or negative emotional state. For example, get food is a desirable event, while suffer from asthma is an undesirable event. Identifying affective events and their polarities is essential for many artificial intelligence (AI) tasks. Since sentiments toward an affective event is often implicit, affective event acquisition and classification have always been two great challenges. Encounter events are a special type of affective events. The goal of this article is to automatically acquire and classify stereotypically positive and negative encounter events in Chinese. First of all, we collect a comprehensive list of Chinese encounter event indicators based on the literature related to Chinese encounter events. Then, we automatically extract candidate encounter events from a text corpus using these indicators as. In order to acquire high-quality encounter events, we design an event filtering scheme and generate a novel stopword list. Finally, we classify these obtained encounter events exploiting the indicators. Experimental results show that the proposed approaches to acquire and classify Chinese encounter events perform promisingly well. One advantage of the method is that no labelling and training of data is required. The automatically constructed common affective event knowledge base contains more than 38,000 encounter events annotated with affective polarity labels (negative or positive), which is currently the only resource of common affective events in Chinese language. Related resources including encounter event indicators and encounter events will be released after the publication of this article. © 2025 Copyright held by the owner/author(s).

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Opinion Mining and Topic Classification of Course Reviews

arXiv

引用

arXiv 2023年

作者： Koufakou, Anna Department of Computing & Software Engineering Florida Gulf Coast University United States

Student opinions for a course are important to educators and administrators, regardless of the type of the course or the institution. Reading and manually analyzing open-ended feedback becomes infeasible for massive volumes of comments at institution level or online forums. In this paper, we collected and pre-processed a large number of course reviews publicly available online. We applied machine learning techniques with the goal to gain insight into student sentiments and topics. Specifically, we utilized current Natural Language Processing (NLP) techniques, such as word embeddings and deep neural networks, and state-of-the-art BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach) and XLNet (Generalized Auto-regression Pre-training). We performed extensive experimentation to compare these techniques versus traditional approaches. This comparative study demonstrates how to apply modern machine learning approaches for sentiment polarity extraction and topic-based classification utilizing course feedback. For sentiment polarity, the top model was RoBERTa with 95.5% accuracy and 84.7% F1-macro, while for topic classification, an SVM (Support Vector Machine) was the top classifier with 79.8% accuracy and 80.6% F1-macro. We also provided an in-depth exploration of the effect of certain hyperparameters on the model performance and discussed our observations. These findings can be used by institutions and course providers as a guide for analyzing their own course feedback using NLP models towards self-evaluation and improvement. © 2023, CC0.

关键词： Sentiment analysis

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：