检索结果-内蒙古大学图书馆

14th IEEE International Conference on Software engineering and Service science, ICSESS 2023

作者： Xu, Jianyong Zhang, Lichen Guangdong University of Technology Faculty of Computer Science and Technology Guangdong Province Guangzhou China Guangzhou Vocational and Technical University of Science and Technology Faculty of Computer Science and Technology Guangdong University of Technology School of Information Engineering Guangdong Province Guangzhou China

ISBN: (纸本)9798350336269

In recent years, knowledge graphs have been widely applied in the research of recommendation algorithms. However, most recommendation models focus on modeling item features in the relational space of the knowledge graph while neglecting the differences between the user side and the item side during feature extraction. Furthermore, they fail to comprehensively capture and fully utilize the high-order interaction relationships between users and items. To address these issues, we propose a method that combines knowledge graph and graph convolutional network, named the Hybrid-Aware Attention Network Incorporating Knowledge Graph for Recommendation (HAN). HAN jointly extracts the interaction information between users and items and the associative information of the knowledge graph to enable accurate recommendations. To validate the feasibility and effectiveness of the proposed model, experiments were conducted on three real datasets, demonstrating that the proposed algorithm achieves favorable recommendation performance compared to other benchmark models. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Ac...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Chen, Zhaoyu Li, Xing Huang, Qian Geng, Qiang Yang, Tianjin Han, Shihao College of Information Science and Technology & Artificial Intelligence Nanjing Forestry University China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350368741

Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method. © 2025 IEEE.

关键词： 3D action recognition D-Hyperpoint KAN-HyperpointNet point cloud sequence

来源：评论

学校读者我要写书评

暂无评论

An Efficient Long Short-Term Memory and Gated Recurrent Unit Based Smart Vessel Trajectory Prediction Using Automatic Identification System Data

引用

computers, Materials & Continua 2024年第10期81卷 1789-1808页

作者： Umar Zaman Junaid Khan Eunkyu Lee Sajjad Hussain Awatef Salim Balobaid Rua Yahya Aburasain Kyungsup Kim Department of Computer Engineering Chungnam National UniversityDaejeon34134Republic of Korea Department of Environmental IT Engineering Chungnam National UniversityDaejeon34134Republic of Korea Autonomous Ship Research Center Samsung Heavy IndustriesDaejeon34051Republic of Korea ICAROS Center(PRISMA Lab) University of Naples Federico IINaples80131Italy Department of Computer Science College of Computer Science and Information TechnologyJazan UniversityJazan45142Saudi Arabia

Maritime transportation,a cornerstone of global trade,faces increasing safety challenges due to growing sea traffic *** study proposes a novel approach to vessel trajectory prediction utilizing Automatic Identification System(AIS)data and advanced deep learning models,including Long Short-Term Memory(LSTM),Gated Recurrent Unit(GRU),Bidirectional LSTM(DBLSTM),Simple Recurrent Neural Network(SimpleRNN),and Kalman *** research implemented rigorous AIS data preprocessing,encompassing record deduplication,noise elimination,stationary simplification,and removal of insignificant *** were trained using key navigational parameters:latitude,longitude,speed,and *** aware processing through trajectory segmentation and topological data analysis(TDA)was employed to capture dynamic *** using a three-month AIS dataset demonstrated significant improvements in prediction *** GRU model exhibited superior performance,achieving training losses of 0.0020(Mean Squared Error,MSE)and 0.0334(Mean Absolute Error,MAE),with validation losses of 0.0708(MSE)and 0.1720(MAE).The LSTM model showed comparable efficacy,with training losses of 0.0011(MSE)and 0.0258(MAE),and validation losses of 0.2290(MSE)and 0.2652(MAE).Both models demonstrated reductions in training and validation losses,measured by MAE,MSE,Average Displacement Error(ADE),and Final Displacement Error(FDE).This research underscores the potential of advanced deep learning models in enhancing maritime safety through more accurate trajectory predictions,contributing significantly to the development of robust,intelligent navigation systems for the maritime industry.

关键词： Trajectory prediction AIS data smart vessel deep learning LSTM GRU

来源：评论

学校读者我要写书评

暂无评论

Implementation of Deep Learning Using Convolutional Neural Network for Skin Disease Classification with DenseNet-201 Architecture 8

Implementation of Deep Learning Using Convolutional Neural N...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Pramesti, Evita Mutiara, Achmad Benny Refianti, Rina Gunadarma University Informatics Engineering Depok Indonesia Gunadarma University Computer Science and Information Technology Depok Indonesia

ISBN: (纸本)9798350342604

The skin is the outermost organ of the human body, playing a crucial role in maintaining internal balance and protecting vital organs from factors that could disrupt health. As the outermost part of the body, the skin is also vulnerable to various environmental exposures, such as sunlight radiation, air pollution, viruses, bacteria, and parasitic agents that cause skin diseases. Skin diseases can vary from mild conditions like rashes to more serious skin issues such as skin cancer. This diversity often poses challenges for medical professionals in accurately identifying and classifying skin diseases. However, the process of diagnosing skin diseases is still predominantly carried out manually, resulting in suboptimal accuracy and effectiveness. Thus, alternative methods are needed to address these limitations. Notably, Convolutional Neural Network (CNN) techniques have led to remarkable advancements in computers' ability to recognize patterns in images, including medical images like skin images. This research aims to build a CNN model and compare the performance of DenseNet-201 with other CNN architectures. The dataset consists of 1,789 dermoscopy images of skin diseases. The training process involves a series of preprocessing techniques and the use of optimization algorithms. Evaluation results utilizing a confusion matrix demonstrate that the DenseNet-201 architecture achieves an accuracy of 99%. The model with the best accuracy is implemented into a web application using the Flask framework. This application allows users to upload images of skin diseases and promptly receive accurate prediction results. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Deep-Based Hybrid Model For Enhancing Land Region Prediction Outcomes 2

Deep-Based Hybrid Model For Enhancing Land Region Prediction...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Selvapandian, D. Raja, Laxmi Tharageswari, K. Vm, Senthilkumar Jc, Nikitha Hemalatha, M. Karpagam Academy of Higher Education Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Karpagam Academy of Higher Education Faculty of Engineering Department of Cyber Security Coimbatore India Mahendra Institute of Technology Department of Information Technology Namakkal India Nandha Arts and Science College Department of Information Technology Erode India

ISBN: (纸本)9798331534950

Although satellite data is not a novel approach to mapping wetlands, its accuracy depends on data quality and categorization algorithms, making it a continuous challenge. The increasing accessibility of satellite data and the development of data modelling technologies, such as big data modelling using machine learning (ML) algorithms, have improved the accuracy of this type of mapping. Our work demonstrated a simple, scalable, and reliable wetland classification using linear Support Vector Machine (l-SVM) and unsupervised k-Nearest Neighbor (k-NN) machine learning approaches. Normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), the two primary inputs were modelled using Landsat optical data. Subsequently, l-SVM was used to supervise k-NN data using training data collected from outside observations. The accuracy test results indicate that there is a considerable reduction in error for both optical indices, and all prediction models have an accuracy of about 99%. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Analysis of Government Flagship Programs using Public Feedbacks 2

Analysis of Government Flagship Programs using Public Feedba...

引用

2nd International Conference for Innovation in technology, INOCON 2023

作者： Chauhan, Ganpat Puri, Shalini Nahta, Ravi Manipal University Jaipur Department of Information Technology India Nirma University Department of Computer Science & Engineering India

ISBN: (纸本)9798350320923

In the last decades, a variety of government policies are introduced in the areas of teaching, healthcare, games, and social safety. The assessment and measuring of the impact of these programs on society is a difficult and tedious job. The real success of any of the government policies depends on how it makes a difference in public life. Citizen feedback on government policies plays an important role in deciding the success and failure of the scheme. In current times, the major concern is the unavailability of any digital medium to evaluate citizen feedback on various government programs. In this article, a government online platform is proposed in which citizens can provide their opinions about the functioning of various government programs. Along with this, the ministry of concern department is included to evaluate the public reviews to estimate the success or failure of the scheme. Feature-level sentiment analysis is performed on large public-produced reviews to find citizen overviews. Feature-level sentiment extraction was performed using a deep learning-based method to retrieve sentiments and feedback regarding various aspects mentioned in the reviews. The investigational findings were reviewed in the planned study to assess the effect of the public reviews' feature-based analysis. The findings of this work can help individuals, companies, religious institutions, academics, or researchers as they think and rethink their decisions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An effective method for fault localization based on combination of convolution and LSTM 19th

An effective method for fault localization based on combinat...

引用

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Li, Jinfeng Yu, Haihao College of Computer and Information Technology Mudanjiang Normal University Mudanjiang157012 China College of Computer Science and Technology Heilongjiang Institute of Engineering Harbin150050 China

ISBN: (纸本)9789819968817

Software testing takes up a sizeable portion of the overall process of developing software. The process of software testing must always include software fault localization as one of its core components. CNN-LSTM-FL is the name of the effective method for fault localization that we propose in this paper. Deep learning’s convolutional and recurrent neural network serve as the foundation for this model’s deep learning architecture. This method is applied to Siemens programs that are stored in the Software Infrastructure Repository (SIR), and it is contrasted with fault localization techniques using convolutional neural networks (CNN-FL) and fault localization techniques using recurrent neural networks (LSTM-FL). The method that is proposed in this paper is found to be superior to the other two methods in terms of both effectiveness and stability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Proficient job scheduling in cloud computation using an optimized machine learning strategy

引用

International Journal of information technology (Singapore) 2023年第5期15卷 2409-2421页

作者： Neelakantan, P. Yadav, N. Sudhakar Computer Science and Engineering Department VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad 500090 India Department of Information Technology VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad 500090 India

In contemporary technology, cloud computing is applicable in many fields like biomedical systems, transactions, data mining, etc. In that, cloud computing job scheduling is a problematic task. Consequently, different operating systems and virtual machines have validated the user’s requirements and necessitated effective scheduling techniques in the cloud environment. Moreover, resource allocation and job scheduling are significant features in cloud computing. Nevertheless, the main drawback of the cloud computing model is the higher computation time that causes the deadline of all work. Previously, several approaches were proposed to diminish the computation time, but those techniques only apply to a few tasks. Therefore the novel Whale-based Convolution Neural Framework (WbCNF) strategy can effectively improve the task allocation system and reduce the job execution time. Moreover, the developed approach is implemented in the Python framework, and results show that the computation time has reduced the quantity of the tasks taken for the experimentation. Consequently, to verify the proposed technique’s efficiency, the proposed method is compared with conventional techniques in terms of performance metrices;the outcomes prove the enhancement of the cloud computing system. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Cloud computing Data mining Deadline Makespan time Resource allocation Scheduling time Whale based convolution neural framework

来源：评论

学校读者我要写书评

暂无评论

Modality aware contrastive learning for multimodal human activity recognition

Modality aware contrastive learning for multimodal human act...

引用

作者： Dixon, Sam Yao, Lina Davidson, Robert School of Computer Science and Engineering University of New South Wales SydneyNSW Australia Defence Science and Technology Group Information Sciences Division EdinburghSA Australia

Human activity recognition is a well-established research problem in ubiquitous computing. The increased dependency on various smart devices in our daily lives allows us to investigate the sensor data world produced by multimodal sensors embedded in smart devices. However, the raw sensor data are often unlabeled and annotating this vast amount of data are a costly exercise that can often lead to privacy breaches. Self-supervised learning-based approaches are at the forefront of learning semantic representation from unlabeled sensor data, including when applied to human activity recognition tasks. As inferring human activity depends on multimodal sensors, addressing the modality difference and inter-modality dependencies in a model is an important process. This paper proposes a novel self-supervised learning approach, modality aware contrastive learning (MACL), for representation learning using multimodal sensor data. The approach uses different sensing modalities to create different views of an input signal. Thus, the model is able to learn the representations by maximizing the similarity among different sensing modalities of the same input signal. Extensive experiments were performed on four publicly available human activity recognition data sets to verify the effectiveness of our proposed MACL method. The experimental evaluation results show that the MACL method attains a comparable performance for human activity recognition to the compared baseline models, directly exceeding the performance of models using standard augmentation transformation strategies. © 2024 The Authors. Concurrency and Computation: Practice and Experience published by John Wiley & Sons Ltd.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effects of Blackhole Attacks on MANET Reliability and Security

Assessing the Effects of Blackhole Attacks on MANET Reliabil...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Fadhil, Saif Aamer Najim, Ali Hamza Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisha Hassan Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Baghdad10011 Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

Mobile Ad Hoc Networks (MANETs) are characterized by some important attributes, including infrastructure, mobile, and dynamic nature, which makes them have vast applications in different areas of computer networks. The black hole attack falls among the strongly criticized security threats within the framework of the MANETs. This deceptive behavior captures data packets from a source destined for the malicious node and then declines them when they are received. This paper comprehensively reviews prior studies done to analyze and mitigate black hole attacks in MANETs. Besides this, we will conduct a comparative analysis of the research above projects. The present paper extends prior work by actually performing the black hole assault simulations in a MANETs environment. This is done with the aid of the NS2 simulator and the Ad Hoc On-Demands Distance Vector (AODV) routing protocol. In this study, the black hole attack is analyzed and the consequences of the attack are assessed in terms of the system performance and security. We analyze crucial parameters like end-to-end latency, PDR, packet drop, and throughput to evaluate the consequences of this assault. From our results derived from the analysis of our simulations, we aim to present substantial points to do with the impacts of blackhole attacks on MANETs. In this way, our goal is to participate in the perpetually evolving efforts aimed at enhancing the security and reliability of such dynamic networks. © 2024 IEEE.

关键词： Mobile ad hoc networks

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：