检索结果-内蒙古大学图书馆

Predicting software vulnerability based on software metrics: a deep learning approach

Iran Journal of computer science 2024年第4期7卷 801-812页

作者： Agbenyegah, Francis Kwadzo Asante, Micheal Chen, Jinfu Akpaku, Ernest Department of Computer Science Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Department of Information Technology Faculty of Computing and Information Systems Ghana Communication Technology University Accra Ghana

The security of IT systems is the topmost priority of software developers. Software vulnerabilities undermine the security of computer systems. Lately, there have been a lot of reported issues of software vulnerabilities recorded in individuals and corporate systems. Software metrics-based techniques have been used and found to be effective due to low false positives and false negatives. However, there are software metrics that have not been investigated and could have an impact on the performance of the predictive model. In this study, we developed an ensemble deep learning algorithm made of LSTM, CNN, and MLP models with the non-investigated metrics as a feature to learn the latent representation of code metrics to predict anomalies in source code effectively. We trained the proposed model on the SySeVR datasets and compared the model's performance against five deep learning algorithms and four state-of-the-art SVPs. The proposed model performs better than the other deep learning with a classification accuracy of 96.17%, and a precision of 97.72%. The model's classification accuracy is 4.98% higher than that of the five deep learning models and 1.71% lower in precision than the state-of-the-art SVP. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Deep learning Machine learning Software metrics Software security Software vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Multi-Product Parallel Disassembly Line Balancing Problem Considering Multi-Skilled Workers Using a Discrete Chemical Reaction Optimization Algorithm

引用

computers, Materials & Continua 2024年第9期80卷 4475-4496页

作者： Xiwang Guo Liangbo Zhou Zhiwei Zhang Liang Qi Jiacun Wang Shujin Qin Jinrui Cao College of Information and Control Engineering Liaoning Petrochemical UniversityFushun113000China Department of Computer Science and Technology Shandong University of Science and TechnologyQingdao266590China Department of Computer Science and Software Engineering Monmouth UniversityWest Long BranchNJ 07764USA Research Center of the Economic and Social Development of Henan East Provincial Joint Shangqiu Normal UniversityShangqiu476000China Department of Computer Science New Jersey City UniversityJersey CityNJ 07305USA

This work investigates a multi-product parallel disassembly line balancing problem considering multi-skilled workers.A mathematical model for the parallel disassembly line is established to achieve maximized disassembly profit and minimized workstation cycle *** on a product’s AND/OR graph,matrices for task-skill,worker-skill,precedence relationships,and disassembly correlations are developed.A multi-objective discrete chemical reaction optimization algorithm is *** enhance solution diversity,improvements are made to four reactions:decomposition,synthesis,intermolecular ineffective collision,and wall invalid collision reaction,completing the evolution of molecular *** established model and improved algorithm are applied to ball pen,flashlight,washing machine,and radio combinations,*** a Collaborative Resource Allocation(CRA)strategy based on a Decomposition-Based Multi-Objective Evolutionary Algorithm,the experimental results are compared with four classical algorithms:MOEA/D,MOEAD-CRA,Non-dominated Sorting Genetic Algorithm Ⅱ(NSGA-Ⅱ),and Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ).This validates the feasibility and superiority of the proposed algorithm in parallel disassembly production lines.

关键词： Parallel disassembly line balancing problem multi-product multiskilled workers discrete chemical reaction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Crop Productivity Enhancement Through Data Analytics and IOT 10

Crop Productivity Enhancement Through Data Analytics and IOT

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Siva, K.P. Shri Suriya, P. Praveen, R. Nimesh Rajan, D. Santhosh Kumar, G. Sri Eshwar College of Engineering Department of Computer Science and Business Systems Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

The goal of this project is to create a web-based application for smart farming that makes use of IoT technology to enable real-time monitoring, data analysis, and remote control for improving crop productivity. The solution connects numerous IoT sensors, offers data visualization, applies machine learning for predictive analytics, and assures data security. A sustainable and fruitful future for agriculture is made possible by the application, which equips farmers with useful knowledge. The MQTT protocol collects the data from a variety of IoT sensors, including temperature, humidity, soil moisture, and weather sensors. Using the HTTPS and TLS protocols, data transfer and communication are done using a security-focused approach. An efficient alert and notification system is built up utilizing Twilio for SMS and email services to inform farmers of important occurrences. The project's accomplishments demonstrate the value of incorporating contemporary technology into agriculture and pave the way for more research and development in the area of smart farming. Future improvements may involve extending the selection of IoT sensors that are supported, including drone technology for aerial monitoring, and working with agricultural specialists to adapt the program for various crop kinds and geographical locations. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Fractional-order binary bat algorithm for feature selection on high-dimensional microarray data

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7453-7467页

作者： Esfandiari, Ahmad Farivar, Faezeh Khaloozadeh, Hamid Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Systems and Control Faculty of Electrical Engineering K. N. Toosi University of Technology Seyed-Khandan Shariati Ave. Tehran16317-14191 Iran

High-dimensional microarray data suffer from the confounding effects of irrelevant, redundant and noisy genes on the scalability and efficiency of classification algorithms. In order for an effective dimensionality reduction and the selection of informative genes, this paper introduces a novel approach using fractional calculus concepts. This study proposes a modified version of binary the bat algorithm named fractional-order binary bat algorithm (FBBA) able to control the convergence process using more historical memory of bat behaviors. The gene selection technique contains a two-stage hybrid filter/wrapper method which employs a new correlation-based feature clustering (CFC) algorithm in the filter stage and the FBBA in the wrapper stage. The CFC-FBBA is evaluated on ten microarray gene expression datasets by employing the support vector machine classifier with a k-fold Monte Carlo cross validation data partitioning model. Furthermore, the results show that the CFC-FBBA, while minimizing the size of the gene subset, achieves the highest classification accuracy in most cases compared to several state-of-art hybrid techniques. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhancing URL Security and Access control Using Hash-Based Shortening Algorithm 2

Enhancing URL Security and Access Control Using Hash-Based S...

引用

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

作者： Haripriya, K. Preethi, C. Hameed, S. Shahul Pavalarajan, S. Shushmmitha, T. Haripriya, V. PSNA College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798331534950

Shortening URLs has become an integral part of modern digital communication, as it simplifies long and complex internet addresses, making them more user-friendly. However, conventional URL shortening methods often lack adequate security provisions, leaving shortened links vulnerable to various risks. This project aims to develop a secure URL-shortening service by incorporating a hash-based access control mechanism. By using a hash-based approach, we can significantly enhance the security of shortened URLs. In this method, a unique hash value is generated for each URL, which serves as a link to the shortened URL. The generated hash is highly resistant to decryption, making it difficult for unauthorized users to retrieve the original URL, thereby ensuring that only the intended recipient can access the link. The goal of this project is to develop a protected and secure URL-shortening service that utilizes a hash-based access control mechanism. By generating a unique hash for each shortened URL, the system will enhance both security and user privacy. Furthermore, the implementation of granular access control will be a key factor in maintaining the system's overall security. SHA-256 can be utilized to generate unique, unpredictable shortened URLs by creating secure hash values. Integrating OAuth2 and JWT provides robust access control, enabling seamless user authentication and authorization across multiple systems. Additionally, AES encryption ensures the protection of sensitive data by offering strong encryption, safeguarding both the original URL and user information. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Review of IoT-Driven Innovations in Supply Chain Management 3

A Review of IoT-Driven Innovations in Supply Chain Managemen...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Chandankhede, Arpit Gourshettiwar, Palash Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Sawangi Meghe Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Computer Science and Engineering Sawangi Meghe Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Supply Chain Management (SCM) worldwide makes major advancements through the Internet of Things (IoT) by enabling real-time monitoring and prediction analytics and automatic decision capabilities in worldwide deliver chains. Through IoT technology integration with Artificial Intelligence (AI) and blockchain and cloud computing the supply chain solves major operational problems including monitoring difficulties and waste reduction and regulatory compliance requirements and operation leadership deficits. The implementation of IoT for supply chain management encounters major adoption barriers from high installation costs combined with security risks and operability complications as well as limited scalability capacity that affects especially small to medium enterprises (SMEs) and developing markets. The evaluation paper examines the shifting impact of IoT in supply chain management which enhances performance metrics and brings greater clarity and strengthens supply chain resilience. A scientist studied existing papers and case studies to reveal several essential advantages which include better inventory management, predictive analysis systems and more effective supply-chain collaborations. The analysis emphasizes effective solutions for security privacy and moral and environmental issues to guarantee sustainable expanded IoT adoption. This paper delivers practical knowledge alongside best practices to help organizations adopt IoT systems which create adaptable efficient deliver chains with sustainability at their core thus achieving long-term market benefits in today's complex global marketplace. © 2025 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Integrating Decision Trees with Cloud Computing for Predicting Cognitive Decline in Alzheimer's Patients 2

Integrating Decision Trees with Cloud Computing for Predicti...

引用

2nd IEEE International Conference on Integrated Circuits and Communication systems, ICICACS 2024

作者： Meenakshi, K. Ravinder, Bathini Pasha, Mohammed Rehaman Thinakaran, K. Jayanayudu, Dabbara Maniraj, S.P. SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Vadapalani India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur India Malla Reddy Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Saveetha School of Engineering Tamil Nadu Chennai India Siddartha Institute of Science and Technology Department of Electronics and Communication Engineering Andhra Pradesh Puttur India SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350317558

The proposed research work suggests a combined technique based on decision trees and cloud computing for predicting cognitive decline in Alzheimer's patients. Medical records and data from wearable devices are among the many sources that perform preprocessing and feature engineering. Decision tree models can make the most efficient use of computing resources. Decision tree topologies are tested for performance criteria, including accuracy and F1 score. The system's predictive powers are rather encouraging since it frequently achieves accuracy rates over 90%. However, limitations in data quality and the intricacy of decision tree interpretation provide challenges. The prediction of cognitive deterioration in Alzheimer's patients may be made more scalable and interpretable by integrating decision trees with cloud computing. This method has promise for early identification and intervention despite its limitations. To further improve prediction accuracy and clinical value, future research should increase data quality and make it easier to understand. © 2024 IEEE.

关键词： Alzheimer's disease Cloud computing Decision trees Early detection Healthcare

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Detecting Diabetic Retinopathy

A Deep Learning Approach for Detecting Diabetic Retinopathy

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Nabil, Mohamed Hossam Hassan Hammam, Laila Bastawrous, Hany Ayad Ebrahim, Gamal A. The British University in Egypt Electrical Engineering Department Cairo Egypt Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft Netherlands Ain Shams University Faculty of Engineering Computer and Systems Engineerig Department Cairo Egypt

ISBN: (纸本)9798350367560

The World Health Organization (WHO) reports that diabetic retinopathy affects one-third of diabetics, regardless of their stage of the disease. Several research efforts are focused on its automated detection and diagnosis. Identifying diabetic retinopathy is crucial due to the damage that occurs to the blood vessels of the eye retina, leading to vision blur or even complete blindness. Thus, an annual checkup is needed for people with diabetes. Moreover, uncontrolled sugar levels for diabetes patients could worsen the current stage of diabetic retinopathy. Consequently, automated detection can greatly contribute to the treatment of disease. This can be carried out through several algorithms, including deep learning models and support vector machines, in addition to transfer learning. This contribution proposes a new approach for diabetic retinopathy automated detection based on convolutional neural network (CNN) models. The proposed model provides both binary and multi-class detection. Both scenarios have shown promising results, where the training accuracies of both the binary classification and the multi-class are 92% and 94%, respectively. © 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

Polarization Insensitive Broadband Zero Indexed Nano-Meta Absorber for Optical Region Applications

引用

computers, Materials & Continua 2022年第4期71卷 993-1009页

作者： Ismail Hossain Md Samsuzzaman Ahasanul Hoque Mohd Hafiz Baharuddin Norsuzlin Binti Mohd Sahar Mohammad Tariqul Islam Space Science Center(ANGKASA) Universiti Kebangsaan Malaysia43600UKM BangiSelangorMalaysia Department of Computer and Communication Engineering Faculty of Computer Science and EngineeringPatuakhali Science and Technology UniversityDumki8602PatuakhaliBangladesh Department of Electrical Electronic and Systems EngineeringFaculty of Engineering and Built EnvironmentUniversiti Kebangsaan Malaysia43600UKM BangiSelangorMalaysia

Broadband response metamaterial absorber(MMA)remains a challenge among researchers.A nanostructured new zero-indexed metamaterial(ZIM)absorber is presented in this study,constructed with a hexagonal shape resonator for optical region *** design consists of a resonator and dielectric layers made with tungsten and quartz(Fused).The proposed absorbent exhibits average absorption of more than 0.8972(89.72%)within the visible wavelength of 450–600 nm and nearly perfect absorption of 0.99(99%)at 461.61 *** on computational analysis,the proposed absorber can be characterized as *** developments of ZIM absorbers have demonstrated plasmonic resonance characteristics and a perfect impedance *** incidence obliquity in typically the range of 0◦–90◦both in TE and TM mode with maximum absorbance is more than 0.8972(∼89.72%),and up to 45◦angular stability is suitable for solar cell applications,like exploiting solar *** proposed structure prototype is designed and simulated by studying microwave technology numerical computer simulation(CST)*** finite integration technique(FIT)based simulator CST and finite element method(FEM)based simulator HFSS also helps validate the numerical data of the proposed ZIM *** proposed MMA design is appropriate for substantial absorption,wide-angle stability,absolute invisible layers,magnetic resonance imaging(MRI),color images,and thermal imaging applications.

关键词： Hexagonal resonator loaded star shaped polarization insensitive compact broadband metamaterial absorber optical region applications

来源：评论

学校读者我要写书评

暂无评论

Collective Multi-Trends Sentiment Classifiers for Trending Tweets in Social Media 5

Collective Multi-Trends Sentiment Classifiers for Trending T...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Kalaimani, I. Mohammed Upayathulla, M. Sanjuriya, V. Swetha, S. K S Rangasamy College of Technology Faculty of Computer Science and Engineering Department of Computer Science and Engineering Tiruchengode India

ISBN: (纸本)9798350321425

To train sentiment classifiers, a collective multi-Trends sentiment classification approach is proposed for numerous tweets simultaneously. This technique uses sentiment facts from exceptional tweets to train accurate and potent classifiers. The sentiment classifiers are divided into universal and trend-specific components. The approach automatically recognizes key elements in online customer reviews, diagnoses critical product components based on observations, and administers exams and assessments using language-neutral skills. The global version captures the entire sentiment expertise across multiple tweets. Each Trend's emotional emotions are captured by the Greedy & Dynamic Blocking Algorithms model Naive Bayes and Drimux SVM. For sentiment knowledge, it uses labeled and unlabeled samples, and tweet similarity is taken into account as a regularizer. This study considers two different versions, one based on language and the other on facial expressions. For clarity, green algorithms are shown. The performance of the multi-Trends sentiment class has enhanced. © 2023 IEEE.

关键词： Support vector machines

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：