检索结果-内蒙古大学图书馆

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

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 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

Unified Approach Integrating Machine Learning Algorithms for Detection of e-Mail Phishing Attacks

Unified Approach Integrating Machine Learning Algorithms for...

引用

Computing, sciences and Communications (ICCSC), International Conference on

作者： Abeer Mathur Abhinav Sudhakar Dubey Pranav Singh Mahara Usha Devi Gandhi Department of Software Systems School of Computer Science & Engineering Vellore Institute of Technology Vellore India Department of Information Technology School of Computer Science Engineering & Information Systems Vellore Institute of Technology Vellore India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

With the ever-rising risk of phishing attacks, which capitalize on vulnerable human behavior in the contemporary digital space, requires new cybersecurity methods. This literary work contributes to the solution by novel incorporation of three techniques: Support Vector Machine (SVM), Natural Language Processing (NLP) and Random Forest (RF). Utilizing NLP for deep analysis of text in phishing e-mails, SVM for strong categorization and Random Forest's decision making by group helps in improving detection. This combination of language and pattern analysis along with group learning builds a fortified system. This approach differs from prior work on a variety of factors such as reliability, security, integrity, scalability, interpretability, transparency, and robustness. Thorough evaluation on a reliable dataset aimed to demonstrate the method's effectiveness, which resulted in 98.7 % of accuracy in detection. This majorly aims at showcasing the potential of ensemble techniques to combat against cyber-attacks like phishing for laying a strong foundation for a secure digital environment.

关键词： Support vector machines Radio frequency Phishing Scalability Forestry Natural language processing Vectors Robustness Electronic mail Random forests

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

Crafting Customer Segmentation Strategies for Advanced Recommendation System 3

Crafting Customer Segmentation Strategies for Advanced Recom...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Seethalakshmi, K. Bhagyalakshmi, A. Anitha, G. Sheela, E. Sandeep, Varada Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Tami Nadu Chennai India S.A Engineering College Department of Computer Science and Business Systems Tamil Nadu Chennai India St Peter's Institute of Higher Education and Research Department of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350369083

With the static nature of recommender systems, it is crucial to take into account the intricate details of customer behaviour to better improve operating efficiencies. This paper is about original methods to augment recommendation frameworks by employing spectral clustering methods, to be more specific. Limited segmentation techniques now cannot catch up with the growing complexity and variety of customer conduct. To address this need, we are proposing a new way in which the spectral clustering technique, a supervised learning technique, can be applied. Revealing in-depth relationships inside customer data will enable an upgrade in the segmentation approach beyond the existing norms. Spectral clustering stands out as a really amazing tool for accomplishing extraordinarily precise customer segments, which help understand the tastes of users on a deeper level. Through discovering separate customer groups, we are aiming for a meaningful contribution in the field of recommendation systems. This project combines the effectiveness of spectral clustering with the convenience of a recommendation system that aims to provide a holistic, meaningful, and user-oriented approach to enhancing recommendation systems in the area of personalised recommendation. Our aim is to create recommendation systems that are not only attuned to the heterogeneity of customer preferences but also adopt new trends in user experience design beforehand. The segmentation is done with K-Means along with the proposed algorithm and the clusters are hence compared and Implementation results shows that spectral clustering is much more efficient than the existing K-Means algorithm © 2024 IEEE.

关键词： Sales

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

The Emergence of Artificial Intelligence in Education and its Impact on Individual Literacy in Higher Education 7

The Emergence of Artificial Intelligence in Education and it...

引用

7th IEEE International Conference and Workshop Obuda on Electrical and Power engineering, CANDO-EPE 2024

作者： Farkas, Imre Kovari, Attila Rajcsanyi-Molnar, Monika Institute of Computer Engineering University of Dunaujvaros Department of Computer Systems and Control Technology Dunaujvaros Hungary Eszterházy Károly Catholic University Institute of Digital Technology Faculty of Computer Science Eger Hungary Institute of Electronics and Communication Systems Kandó Kalmán Faculty of Electrical Engineering Obuda University Budapest Hungary John Von Neumann University GAMF Faculty of Engineering and Computer Science Kecskemét Hungary Institute of Social Sciences University of Dunaujvaros Department of Economics and Management Dunaujvaros Hungary

ISBN: (纸本)9798331531119

In the last three years, a new partner has emerged for teachers and educators in the field of education. The mushrooming of applications based on large language models has greatly shaped the educational development fields of the present era. The use of various AI applications has become commonplace among students and teachers alike. Many questions are being raised by researchers in this field. What does the rapid development of AI applications bring to the field of pedagogy? Should the products of such applications be compared with human performance? The form presented in this thesis seeks to answer similar questions. What is the impact of frequent use of these applications on the literacy level of individuals? In which areas do students tend to use these applications? The results indicate that half of the students believe their literacy levels will decrease with the mass emergence of AI applications, while 36% feel it will not change. However, 88 % of students have already dealt with AI-based applications, with 64 % using them several times or more, suggesting a high level of integration into their educational processes. © 2024 IEEE.

关键词： Students

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：