检索结果-内蒙古大学图书馆

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Kim, Geon-Woo Kim, Joo-Chang Department of AI Computer Science and Engineering Kyonggi University Suwon16227 Korea Republic of Contents Convergence Software Research Institute Kyonggi University Suwon16227 Korea Republic of

ISBN: (纸本)9791188428137

This paper proposes a method for expanding the metadata of three-dimensional point cloud data using Large Language Models (LLMs). Currently, point cloud data plays a crucial role in various fields such as autonomous driving and medical image reconstruction, necessitating the expansion of metadata for efficient processing. Traditionally, metadata construction has relied on manual input, which is prone to errors. In this study, we propose a method that utilizes LLMs, particularly the Llama 3.1 model, to extract the center points of each class in the point cloud data and expand the metadata by adding these center points to the annotation files. By using center points, computational costs are reduced, and the performance of segmentation and detection models based on this data is improved. Copyright 2025 Global IT Research institute (GIRI). All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Improving Event Coreference Resolution Using Prompt Learning and U-shaped Module 4

Improving Event Coreference Resolution Using Prompt Learning...

引用

4th International Conference on computer science and Blockchain, CCSB 2024

作者： Zhang, Mengyao Long, Jun Huang, Wenti School of Software Xinjiang University Urumqi China Institute of Big Data Central South University Changsha China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China

ISBN: (纸本)9798350356502

Event Coreference Resolution (ECR) focuses on clustering event mentions that allude to identical actual events. Previous research primarily focuses on encoding event mentions without incorporating human interpretations, making it difficult to integrate human-summarized rules for guiding the ECR task. Furthermore, the semantic relations between event mentions have not been thoroughly explored, which impacts coreference judgment. To address these issues, we first utilize the powerful Longformer to acquire event representations at the document level. In addition, we introduce a prompt learning template to better emphasize event types and parameters, enhancing the interaction between event modeling and coreference judgment. Ultimately, we create matching vectors for event mentions using tensor matching and incorporate a U-shaped module to effectively identify the semantic relationships among these mentions, which enhances coreference discrimination. DPTU surpasses other ECR models on the KBP2017 dataset in cause of some experiments. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Feature Learning for Cross-Project software Defect Prediction

引用

computers, Materials & Continua 2023年第10期77卷 161-180页

作者： Ahmed Abdu Zhengjun Zhai Hakim A.Abdo Redhwan Algabri Sungon Lee School of Software Northwestern Polytechnical UniversityXi’anChina School of Computer Science Northwestern Polytechnical UniversityXi’anChina Department of Computer Science Hodeidah UniversityPO Box 3114Al-HudaydahYemen Research Institute of Engineering and Technology Hanyang UniversityAnsanKorea Department of Robotics Hanyang UniversityAnsanKorea

Cross-project software defect prediction(CPDP)aims to enhance defect prediction in target projects with limited or no historical data by leveraging information from related source *** existing CPDP approaches rely on static metrics or dynamic syntactic features,which have shown limited effectiveness in CPDP due to their inability to capture higher-level system properties,such as complex design patterns,relationships between multiple functions,and dependencies in different software projects,that are important for *** paper introduces a novel approach,a graph-based feature learning model for CPDP(GB-CPDP),that utilizes NetworkX to extract features and learn representations of program entities from control flow graphs(CFGs)and data dependency graphs(DDGs).These graphs capture the structural and data dependencies within the source *** proposed approach employs Node2Vec to transform CFGs and DDGs into numerical vectors and leverages Long Short-Term Memory(LSTM)networks to learn predictive *** process involves graph construction,feature learning through graph embedding and LSTM,and defect *** evaluation using nine open-source Java projects from the PROMISE dataset demonstrates that GB-CPDP outperforms state-of-the-art CPDP methods in terms of F1-measure and Area Under the Curve(AUC).The results showcase the effectiveness of GB-CPDP in improving the performance of cross-project defect prediction.

关键词： Cross-project defect prediction graphs features deep learning graph embedding

来源：评论

学校读者我要写书评

暂无评论

Improving Generalization for Hyperspectral Image Classification:The Impact of Disjoint Sampling on Deep Models

引用

computers, Materials & Continua 2024年第10期81卷 503-532页

作者： Muhammad Ahmad Manuel Mazzara Salvatore Distefano Adil Mehmood Khan Hamad Ahmed Altuwaijri Department of Computer Science National University of Computer and Emerging SciencesChiniot35400Pakistan Institute of Software Development and Engineering Innopolis UniversityInnopolis420500Russia Dipartimento di Matematica e Informatica—MIFT University of MessinaMessina98121Italy School of Computer Science University of HullHullHU67RXUK Department of Geography College of Humanities and Social SciencesKing Saud UniversityRiyadh11451Saudi Arabia

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision *** training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new *** paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or *** demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth *** approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in *** sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral ***,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.

关键词： Hyperspectral image classification disjoint sampling Graph CNN spatial-spectral transformer

来源：评论

学校读者我要写书评

暂无评论

Development of Area-Based Explosive Trace Detection Using Deep Transfer Learning 1

Development of Area-Based Explosive Trace Detection Using De...

引用

1st International Conference on Innovative engineering sciences and Technological Research, ICIESTR 2024

作者： Ohemu, Monday F. Azeta, Ambrose A. Adeyanju, Ibrahim A. Obasi, Chukwuemeka C. Airforce Institute of Technology Department of Electrical/Electronics Engineering Kaduna Nigeria Namibia University of Science and Technology Department of Software Engineering Namibia Federal University Department of Computer Engineering Oye-Ekiti Nigeria Edo State University Department of Computer Engineering Uzairue Nigeria

ISBN: (纸本)9798350348637

Terrorism poses a significant global threat, necessitating comprehensive security measures to protect people and critical infrastructure. With the increasing frequency of explosive-based attacks, there is a pressing need for advanced detection systems to mitigate potential devastation. This paper presents the development of an area-based explosive trace detection system using deep transfer learning. Leveraging deep learning technology trained on a substantial dataset collected from sensor networks, the proposed model, named Deep Transfer Learning for Explosive Trace Detection (DTLETD), demonstrates remarkable capabilities in classifying explosive gases based on concentrations of Carbon (C), Hydrogen (H), Oxygen (O), and Nitrogen (N). The methodology involves converting the dataset into 2D data using a serial data to image generator, followed by the adaptation of a pre-trained model for transfer learning. The DTLETD model outperformed conventional Convolutional Neural Network (CNN) models, achieving a training time reduction of about 92 seconds compared to 1287 seconds for the CNN model. Additionally, the transfer learning model exhibits faster convergence with nearly zero losses during training and validation, yielding an impressive accuracy of 99.7% and an average AUC value of approximately 0.89. This research significantly advances the field of explosive trace detection by integrating machine learning-based approaches with deep transfer learning techniques, thereby enhancing security protocols and mitigating potential threats. © 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

Quantum software Models: Quantum Modules Tomography and Recovery Theorem 35

Quantum Software Models: Quantum Modules Tomography and Reco...

引用

35th International Conference on software engineering and Knowledge engineering, SEKE 2023

作者： Exman, Iaakov Zvulunov, Ariel School of Computer Science Faculty of Sciences HIT – Holon Institute of Technology Holon Israel Software Engineering The Jerusalem College of Engineering Azrieli Jerusalem Israel

Quantum Tomography partially measures and then recovers the remaining density matrix quantum state, in order to verify that a certain device – processor or detector – indeed outputs the intended quantum state. However, single matrix element measurements rapidly increase in number with the density matrix dimension and are error-prone. This work proposes a novel quantum software viewpoint on quantum tomography. Instead of individual matrix elements, measurements and density matrix recovery are performed on higher-abstraction modules, i.e. semantically meaningful groups of matrix elements. Quantum Modules Tomography potentially reduce the necessary number of explicit measurements, while still allowing recovery of the whole density matrix. A Recovery Theorem is formulated and proved: density matrix diagonal measurements suffice to recover the whole system density matrix, in terms of modules. The recovery procedure is illustrated by a few case studies. © 2023 Knowledge Systems institute Graduate School. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

Sankalpa - Interactive Digital Learning Platform to Enrich Students with Special Needs 5

Sankalpa - Interactive Digital Learning Platform to Enrich S...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Basnayaka, A.I. Epitakaduwa, E.K.G.D. Jayawardena, C.P.U. Zoysa, Ashan Dharmakeerthi, Uditha Jayawardena, Sanath Sri Lanka Institute of Information Technology Dept of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept of Computer Science and Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept of Computer Science and Network Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

The term special needs mean the special educational needs that the students who suffer from learning disabilities must have due to several reasons. Learning impairment is a condition of the neurological system that impairs one's capacity to efficiently acquire and process knowledge. Failures in diagnosing the people with learning disabilities have been repeatedly highlighted and remain unpopular among people in the developing countries like Sir Lanka. Dyscalculia (difficulties in math), dysgraphia (difficulties in writing) and dyslexia (difficulties in reading) can be considered as some of the major learning disability issues. The 'mobile application based' solution 'Sankalpa Math Master' has been created to offer a game based all-in-one solution including screening, and intervention to identify one of the above-mentioned learning disabilities called 'Dyscalculia'. Dyscalculia is generally distinguished by challenges in learning math, including organizing problems, multi-step calculations, transposing numbers, distinguishing directions, and understanding mathematical signs, leading to confusion with basic operations and facts. The provided solution has been accurate with the use of machine learning and deep learning techniques. In the process of screening with the use of Support Vector Machine (SVM) machine learning algorithm 99.77% of accuracy level has been obtained. The skill level prediction process has acquired an accuracy level of 97% with the use of Random Forest machine learning algorithm. Sri Lankan traditional education system will be vastly benefited by the high level of accuracy in screening, skill predicting, and other game and voice chat-based activities. The students with special needs will gain more effective and personalized learning experience which will improve their learning abilities and help to close the technology gap in education. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Predicting the Air Pollution Level and Creating an Awareness Platform 5

Predicting the Air Pollution Level and Creating an Awareness...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Nuha, M.N. Wishvajith, G.K.N.P. Caldera, Amitha Weerasinghe, N.T. Weeratunga, G.S. Lokuliyana, Shashika Sri Lanka Institute of Infromation Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Infromation Technology Department of Computer Systems & Network Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This study proposes a comprehensive method to reduce the problems posed by global air pollution. To measure pollution levels and raise public awareness, the research uses a comprehensive strategy that incorporates image processing, time series analysis, chatbot, and facemask recognition. Time series analysis is used to build prediction models by recognizing historical patterns, and image processing techniques are used to examine cloud pictures for precise pollution predictions. Chatbots provide real time communication and may educate the public on environmental facts, health risks, and safety procedures. Additionally, it has a facemask identification system that monitors and promotes the use of masks. Importantly this not only encourages users to take action to reduce pollution but also utilizes predictive models to help mitigate pollution's consequences. These components result in improved public health, environmental conservation, and sustainability. The outcomes reflect significant advantages, with evidence of accuracy and its positive impact on both awareness and proactive measures to combat air pollution. © 2023 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics Based Node Localization Approach for Real-Time Clustered Wireless Networks

引用

computer Systems science & engineering 2023年第1期44卷 1-17页

作者： R.Bhaskaran P.S.Sujith Kumar G.Shanthi L.Raja Gyanendra Prasad Joshi Woong Cho Department of Information Technology PSNA College of Engineering and TechnologyDindigul624622India Department of Computer Science and Engineering MEA Engineering CollegeMallapuram679325KeralaIndia Department of Electronics and Communication Engineering Rajalakshmi Institute of TechnologyKuthambakkamChennai600124India Department of Electronics and Communication Engineering Sri Eshwar College of EngineeringCoimbatore641202India Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Software Convergence Daegu Catholic UniversityGyeongsan38430Korea

In recent times,real time wireless networks have found their applicability in several practical applications such as smart city,healthcare,surveillance,environmental monitoring,*** the same time,proper localization of nodes in real time wireless networks helps to improve the overall functioning of *** study presents an Improved Metaheuristics based Energy Efficient Clustering with Node Localization(IM-EECNL)approach for real-time wireless *** proposed IM-EECNL technique involves two major processes namely node localization and ***,Chaotic Water Strider Algorithm based Node Localization(CWSANL)technique to determine the unknown position of the ***,an Oppositional Archimedes Optimization Algorithm based Clustering(OAOAC)technique is applied to accomplish energy efficiency in the ***,the OAOAC technique derives afitness function comprising residual energy,distance to cluster heads(CHs),distance to base station(BS),and *** performance validation of the IM-EECNL technique is carried out under several aspects such as localization and energy efficiency.A wide ranging comparative outcomes analysis highlighted the improved performance of the IM-EECNL approach on the recent approaches with the maximum packet delivery ratio(PDR)of 0.985.

关键词： Wireless networks real time applications clustering node localization energy efficiency metaheuristics

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：