检索结果-内蒙古大学图书馆

7th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2025

作者： Jang, Jae-Geun Jung, Jin-Uk Kim, Seonhyeong Choi, Ayoung Kwon, Young-Woo Graduate School of Data Science Kyungpook National University Daegu Korea Republic of School of Computer Science and Engineering Kyungpook National University Daegu Korea Republic of

ISBN: (纸本)9798331507022

The majority of road accidents occur as a result of driver irresponsibility. Utilizing deep learning models to analyze traffic CCTV can effectively mitigate traffic accidents. This paper aims to identify and monitor vehicles and assess traffic conditions by comparing and categorizing the similarities between vehicle trajectories. Three similarity measurement methods are employed: cosine similarity, Jensen-Shannon divergence, and Euclidean distance similarity. The results show that lanes and traffic patterns can be effectively identified using the presented approach. Through our approach, one can further develop traffic monitoring and analysis advancements, thereby enhancing road safety and traffic management © 2025 IEEE.

关键词： Highway traffic control

来源：评论

学校读者我要写书评

暂无评论

GENTEEL-NEGOTIATOR: LLM-Enhanced Mixture-of-Expert-Based Reinforcement Learning Approach for Polite Negotiation Dialogue 39

GENTEEL-NEGOTIATOR: LLM-Enhanced Mixture-of-Expert-Based Rei...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Priya, Priyanshu Chigrupaatii, Rishikant Firdaus, Mauajama Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna India Dhanbad India School of Artificial Intelligence and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)157735897X

Developing intelligent negotiation dialogue systems that resolve conflicts and promote equitable, inclusive, and sustainable outcomes is at the forefront of advancing automated negotiation technology for social good. Negotiation involves balancing cooperation and competition to maximize value without causing offense. Using polite language fosters mutual understanding and creates a respectful and collaborative environment essential for successful negotiations in various domains. Considering this, in this paper, we propose a polite negotiation dialogue system, GENTEEL-NEGOTIATOR for social good applications to boost the overall quality of negotiation outcomes. We focus on developing a negotiation dialogue system for two key application areas, namely tourism and e-commerce. We begin by curating a unique negotiation dialogue dataset, NEGOCHAT for tourism. We further enrich the NEGOCHAT and Integrative Negotiation dataset (IND) for e-commerce with various negotiation strategies. These datasets are then used to develop the GENTEEL-NEGOTIATOR, leveraging the Large Language Model (LLM) and mixture-of-expert (MoE)-based reinforcement learning approach. The proposed MoE-based method employs heuristic experts dedicated to negotiation, politeness, and dialogue coherence to facilitate the learning of diverse semantics by analyzing the dialogue context. A novel reward function with negotiation strategy congruence, politeness, dialogue coherence, and engagingness rewards is designed to guide the policy's learning for generating responses. Automatic and human evaluations on NEGOCHAT and IND datasets validate the effectiveness of GENTEEL-NEGOTIATOR in generating polite responses during negotiation while maintaining conversation goals, including coherence and engagingness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attribute-based Message Recovery Designated Verifier Proxy Signature Scheme in Telemedicine System

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 101-113页

作者： Hu, Yu Zhang, Yi-Fan Huang, Hui Zhou, Yu-Ping School of Computer Science Minnan Normal University Zhangzhou363000 China School of Computer Science Minnan Normal University Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou363000 China

With the promotion of cloud medical diagnostic applications, the telemedicine system has become increasingly mature, which brings about much convenience to the people’s lives. Meanwhile, the diagnostic time was greatly reduced. Due to telemedicine system usually involves the sensitive information of users, the privacy issue is urgently to be solved. In order to solve the above problem, an attribute-based designated verifier proxy signature scheme, combined with message recovery, is proposed for the telemedicine system. A proxy delegation is designed to allow the proxy signer to obtain the same signing capacity as the original signer, the attribute-based fine-grained access control is also present to enable the valid verification of the signature and recovery of data. In addition, the scheme achieves unforgeability of signature and can resist the chosen message attack in Random Oracle Model. The comparisons of performance analysis demonstrates that the scheme is efficient in signing and verification phases. Therefore, it could be well appropriate for telemedicine system. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Aggregating Structural Features for Computational Analysis of Mutations in BRCT Domains of BRCA1 Protein

Aggregating Structural Features for Computational Analysis o...

引用

2023 International Conference on Informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Hidayat, Alam Ahmad Nirwantono, Rudi Isnan, Mahmud Trinugroho, Joko Pebrianto Pardamean, Bens Bina Nusantara University School of Computer Science Bioinformatics and Data Science Research Center Mathematics Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Engineering Bioinformatics and Data Science Research Center Biotechnology Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia Binus Graduate Program Bioinformatics and Data Science Research Center Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350307306

Understanding the mechanistic interpretability of mutation effects in a protein can help predict the clinical implications of the genetic variants. Hence, computational variant effect predictions that involve protein structural features of the protein mutations might be suitable in this case. In this work, we focus on BRCT domains of BRCA1 gene that is widely studied in breast cancer studies. We retrieved 88 selected missense variants found in BRCT domains annotated in both ClinVar and gnomAD databases. To computationally characterize the pathogenic property of the mutations we used two types of features extracted from protein structures: a change in free Gibbs energy and a set of features derived from molecular dynamics simulations of each mutant. Using a dimensional reduction and Gaussian mixture model (GMM)-based clustering we demonstrate that the variants are segregated into two regions that may correspond to their pathogenic status. This method can be a potential computational pipeline for providing the preliminary mechanistic interpretation of mutation effects in terms of their thermodynamic and structural features. © 2023 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Brain State Transition Disruptions in Alzheimer's Disease: Insights from EEG State Dynamics 22

Brain State Transition Disruptions in Alzheimer's Disease: I...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Razavi, Seyed Majid Tran, Triet M. Wilson, Steven E. Khanmohammadi, Sina Data Science And Analytics Institute University of Oklahoma NormanOK73109 United States School of Computer Science University of Oklahoma NormanOK73109 United States

ISBN: (纸本)9798331520526

Alzheimer's Disease (AD) has been associated with reduced neuroplasticity, but the extent to which such reduction impacts large-scale neural dynamics is not yet fully understood. Here, we use a network dynamics analysis framework based on Laplacian Eigenmaps to study the disruptions of brain state transitions associated with AD. Specifically, we utilize the Normalized Variability Index (NVI) to quantify the consistency of nonlinear brain state transitions in resting state electroencephalogram (EEG). Our results show that AD patients tend to have significantly lower NVI values compared to control subjects, reflecting more consistent brain state transitions. The difference was most significant in the Beta band, which has been associated with memory encoding and retrieval. Overall, our results suggest a reduced flexibility in brain state transitions among Alzheimer's patients. These results could provide new insights into large-scale neural dynamics in Alzheimer's disease and pave the path for developing new biomarkers for early detection and diagnosis. © 2025 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Action Recognition Using Graph Convolutional Network with Pose Correction and Channel Topology Refinement

引用

computers, Materials & Continua 2025年第4期83卷 701-718页

作者： Yuxin Gao Xiaodong Duan Qiguo Dai School of Engineering Guangzhou College of Technology and BusinessFoshan528138China School of Computer Science and Engineering Dalian Minzu UniversityDalian116000China SEAC key Laboratory of Big Data Applied Technology Dalian Minzu UniversityDalian116000China

Graph convolutional network(GCN)as an essential tool in human action recognition tasks have achieved excellent performance in previous ***,most current skeleton-based action recognition using GCN methods use a shared topology,which cannot flexibly adapt to the diverse correlations between joints under different motion *** video-shooting angle or the occlusion of the body parts may bring about errors when extracting the human pose coordinates with estimation *** this work,we propose a novel graph convolutional learning framework,called PCCTR-GCN,which integrates pose correction and channel topology refinement for skeleton-based human action ***,a pose correction module(PCM)is introduced,which corrects the pose coordinates of the input network to reduce the error in pose feature ***,channel topology refinement graph convolution(CTR-GC)is employed,which can dynamically learn the topology features and aggregate joint features in different channel dimensions so as to enhance the performance of graph convolution networks in feature ***,considering that the joint stream and bone stream of skeleton data and their dynamic information are also important for distinguishing different actions,we employ a multi-stream data fusion approach to improve the network’s recognition *** evaluate the model using top-1 and top-5 classification *** the benchmark datasets iMiGUE and Kinetics,the top-1 classification accuracy reaches 55.08%and 36.5%,respectively,while the top-5 classification accuracy reaches 89.98%and 59.2%,*** the NTU dataset,for the two benchmark RGB+Dsettings(X-Sub and X-View),the classification accuracy achieves 89.7%and 95.4%,respectively.

关键词： Pose correction multi-stream fusion GCN action recognition

来源：评论

学校读者我要写书评

暂无评论

Transform Sequential data to Image for Detecting Covert Timing Channel

引用

International Journal of Network Security 2024年第2期26卷 224-234页

作者： Huang, Xuwen Chen, Yonghong Zhuang, Xiaolong Lin, Yuwei School of Computer Science and Technology Huaqiao University China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Xiamen Fujian 361000 China

The network covert timing channel utilizes inter-packet delay to encode binary data to achieve information leakage and other purposes. In recent years, Covert Timing Channels (CTCs) have been demonstrated to be applicable across various protocols and networks, posing a significant threat to network security. Simultaneously, new CTCs have challenged the efficacy of CTC detection schemes. The recent ϵ-κlibur and ϵ-κlibur-O channels exhibit structural and characteristic similarities to legitimate channels, rendering ML-based detection methods like GAS and Snap ineffective. In this paper, we investigate an approach based on Gramian Angular Field (GAF), Markov Transition Field (MTF), and Recurrence Plot (RP) image processing. We further employ the knowledge-distilled and compressed image classification model MobileVit for detection. Our approach achieves a detection rate 98.24% for seven different channels within a sampling window of 64 IPDs. Experimental results demonstrate our proposed scheme’s generality, sensitivity, and effectiveness. © 2024, Femto Technique Co.. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Kathakali Mudras: An AI-Enhanced Predictive Approach 11

Kathakali Mudras: An AI-Enhanced Predictive Approach

引用

11th International Conference on Soft Computing and Machine Intelligence, ISCMI 2024

作者： Mulerikkal, Jaison Paul Janani, K. Sreelakshmi, P.S. James, Divya Lakshmi, K.S. Sajanraj, T.D. Binu, A. Department of Information Technology India Rajagiri School of Engineering & Technology Kochi India Department of Computer Science and Engineering India Department of Computer Science and Business Systems India Department of Artificial Intelligence and Data Science India Department of Computer Science Loughborough University Leicester United Kingdom

ISBN: (纸本)9798331518127

The goal of this research is to integrate an artificial intelligence framework for predicting Kathakali mudras, a crucial component of the traditional Indian dance style that is renowned for its complex hand and facial motions. Our goal is to protect and improve the accessibility of this traditional art form by utilising deep learning technology. To be more precise, we used the object identification model YOLOv8 together with convolutional neural networks (CNNs) like VGG 19, Inception V3, and ResNet 152 to predict and analyse Kathakali mudras. Furthermore, Few-shot learning (FSL) and support vector machines (SVMs) were used to offer a comparative viewpoint on the efficacy of machine learning method in this situation. The study entailed a thorough analysis of how well-performing different deep learning techniques performed. The predictive accuracy of VGG 19, Inception V3, and ResNet 152 for intricate mudras of Kathakali was subjected to a thorough evaluation process. In addition, an evaluation of YOLOv8's real-time object identification capabilities was conducted in order to investigate its potential in live performance circumstances. The results of the experiment showed that VGG 19 performed better than the other models and had the highest accuracy in mudra prediction. As a result, VGG 19 was chosen as the best algorithm for this particular application. The results of this study demonstrate how artificial intelligence (AI) technologies may support and preserve traditional artistic forms. This AI-integrated framework is a useful tool for scholars, educators, and dancers, promoting a deeper knowledge and enjoyment of this cultural legacy through its accurate analysis and prediction of Kathakali mudras. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

3D Based CNN for Improved Segmentation from the Hyperspectral Images 1

3D Based CNN for Improved Segmentation from the Hyperspectra...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Narmadha, T. Arockia Raj, A. Saravanan, P. Kumar, A. Suresh Sekaran, Ramesh Gowri Shankar, J. School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering - Data Science Madanapalle India School of Computing Science and Engineering Galgotias University Delhi NCR India

ISBN: (纸本)9798350341737

In this paper, we develop a 3D based CNN for Improved Segmentation of Paddy Fields from the HSI. Within the scope of this research, we will investigate a unique deep learning model, specifically 3D-CNN. In order to evaluate the validity of the model, it is applied to three separate datasets, each of which is then subjected to one of four distinct dimensionality reduction strategies. The purpose of this is to determine which of these four models is the most effective at reducing the number of dimensions. According to the findings, the 3D-CNN model is superior to both the AlexNet and CNN models in terms of the accuracy of its segmentations. In addition to this, the findings demonstrate that the 3D-CNN models perform better than the other approaches in terms of segmentation accuracy with a smaller number of datasets. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Design of an Automatic Price Tag System for Web-Based Retail Business 9

Design of an Automatic Price Tag System for Web-Based Retail...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Liawatimena, Suryadiputra Gunawan, Devina Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Deparment BINUS Graduate Program Master of Computer Science Jakarta11480 Indonesia Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Modern retail businesses face a significant challenge with the inefficiency of manually changing price labels on shelves. This manual process not only consumes valuable time and resources but also increases the likelihood of errors, leading to potential inaccuracies in pricing and a less streamlined shopping experience for customers. The proposed solution is the implementation of an Electronic Shelf Label (ESL) system that automatically displays the prices of goods on retail business shelves. This system connects a website (front end and back end) to e-paper via a Wi-Fi network and microcontroller, allowing retail business owners to update prices more easily. Additionally, buyers can search for desired items through the website. The results are the time to send data from the website to the e-paper, namely, to know the performance of the e-paper used. The average time required from 10 attempts to send data from the website to the e-paper is 20.935 seconds. Since the data is connected to the server and will be updated automatically, using this system will be more efficient than manually changing the price label, although it takes time to transfer data from the website to the e-paper. © 2024 IEEE.

关键词： Sales

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：