检索结果-内蒙古大学图书馆

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Shah, Muhammad Huzaifa Abu Bakar, Muhammad Ali, Raja Hashim Ul Abideen, Zain Arshad, Usama Ijaz, Ali Zeeshan Ali, Nisar Imad, Muhammad Nabi, Said Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350315974

This study investigates the application of the Mutual Information (MI) feature selection technique to improve the accuracy of Machine Learning (ML) models on NSL-KDD datasets, building upon prior research. Six ML models, namely Decision Tree (DT), Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM) with different kernels (1st, 2nd, and 3rd), are implemented for classification purposes. The proposed DT model in this study shows higher accuracy than the DT model proposed in the original paper by Ingre et al. for Intrusion Detection System (IDS). Additionally, a multi-class classification model for NSL-KDD datasets is developed, considering both normalized and non-normalized features. Interestingly, it is observed that the models trained without normalized features achieve higher accuracies compared to those trained with normalized features. Moreover, the study enhances the classification performance of the DT-based IDS using the Correlation based Feature Selection (CFS) technique for feature selection. The proposed IDS is evaluated both before and after feature selection for multi-class classification (normal and various attack types) and binary classification (normal and abnormal data). © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Activity Diagram Synthesis Using Labelled Graphs and the Genetic Algorithm

引用

Journal of computer science & Technology 2021年第6期36卷 1388-1406页

作者： Chun-Hui Wang Zhi Jin Wei Zhang Didar Zowghi Hai-Yan Zhao Wen-Pin Jiao Key Laboratory of High Confidence Software Technology(Ministry of Education) Peking University Beijing 100871China Institute of Software School of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China School of Computer Science Inner Mongolia Normal UniversityHohhot 010022China Faculty of Engineering and Information Technology University of TechnologySydney 2007Australia

Many applications need to meet diverse requirements of a large-scale distributed user *** challenges the current requirements engineering ***-based requirements engineering was proposed as an umbrella term for dealing with the requirements development in the context of the large-scale user ***,there are still many *** others,a key issue is how to merge these requirements to produce the synthesized requirements description when a set of requirements descriptions from different participants are *** techniques are needed for supporting the requirements *** are widely used in industry to represent *** paper chooses the activity diagrams and proposes a novel approach for the activity diagram synthesis which adopts the genetic algorithm to repeatedly modify a population of individual solutions toward an optimal *** a result,it can automatically generate a resulting diagram which combines the commonalities as many as possible while leveraging the variabilities of a set of input *** approach is featured by:1)the labelled graph proposed as the representation of the candidate solutions during the iterative evolution;2)the generalized entropy proposed and defined as the measurement of the solutions;3)the genetic algorithm designed for sorting out the high-quality *** cases of different scales are used to evaluate the effectiveness of the *** experimental results show that not only the approach gets high precision and recall but also the resulting diagram satisfies the properties of minimization and information preservation and can support the requirements traceability.

关键词： crowd-based requirements engineering requirements synthesis activity diagram genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Method for Analyzing the Situation Based on Cumulative Fully Vaccinated and Confirmed Cases of Covid-19 in Malaysia 4

A Hybrid Method for Analyzing the Situation Based on Cumulat...

引用

4th International Conference on Sustainable Technologies for Industry 4.0, STI 2022

作者： Ahmed, Marzia Sulaiman, Mohd Herwan Mohamad, Ahmad Johari Rahman, Mostafijur Faculty of Electrical & Electronics Engineering Technology Pahang Malaysia Daffodil International University Department of Software Engineering Dhaka Bangladesh Green University of Bangladesh Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9781665490450

SARS-CoV-2 is an infection that affects several organs and has a wide range of symptoms in addition to producing severe acute respiratory syndrome. Millions of individuals were infected when it first started because of how quickly it travelled from its starting location to nearby countries. Anticipating positive Covid-19 incidences is required in order to better understand future risk and take the proper preventative and precautionary measures. As a result, it is critical to create mathematical models that are durable and have as few prediction errors as possible. This study suggests a unique hybrid strategy for examining the status of Covid-19 confirmed patients in conjunction with complete vaccination. First, the selective opposition technique is initially included into the Grey Wolf Optimizer (GWO) in this study to improve the exploration and exploitation capacity for the given challenge. Second, to execute the prediction task with the optimized hyper-parameter values, the Least Squares Support Vector Machines (LSSVM) method is integrated with Selective Opposition based GWO as an objective function. The data source includes daily occurrences of confirmed cases in Malaysia from February 24, 2021 to July 27, 2022. Based on the experimental results, this paper shows that SOGWO-LSSVM outperforms a few other hybrid techniques with ideally adjusted parameters. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Neural Networks and Deep Learning: Innovations and Applications in Soft Computing 7

Neural Networks and Deep Learning: Innovations and Applicati...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Abdulkadar, Jahagirdar Imran Mohan, Chinnem Rama Bharati, P. Vijaya Palit, Shamik Rao, Gunda Srinivasa Mudholkar, Pankaj Savitribai Phule Pune University India Narayana Engineering College Department of Computer Science and Engineering Andhra Pradesh Nellore524004 India Vignans Institute of Engineering for Women Department of Cse Andhra Pradesh Visakhapatnam530049 India University of Stirling Department of Computing Science and Software Engineering RAK Campus United Arab Emirates Mallareddy University School of Management and Commerce Kompally500100 India Marwadi University Faculty of Computer Applications Gujarat Rajkot360003 India

ISBN: (纸本)9798350350067

The Paper explores different aspects of deep learning techniques and neural networks in the fields of healthcare, time-series forecasting, agriculture, and other relevant sectors through soft computing. The objective of the report is to examine the significant potential and applications of neural networks. While machine learning techniques called neural networks (NN) are utilized for audio, picture, and the processing of natural languages, it has huge implications in robotics where several machine learning algorithms are significantly required. Improvements in deep machine learning are also investigated in the article specifically in the fields of drug construction, genetics, recognizing faces, farming, biological medicine, biological informatics, medical treatment, natural language, multimedia analysis of data, and mobility prediction. However black box challenges and privacy concerns with data are often ignored in this research. The paper also outlines deep learning-driven data mining techniques for precisely predicting, displaying, evaluating, and classifying data. The report has also emphasized on addressing the potential privacy concerns and challenges associated to information representation. By reviewing recent literature sources about neural network techniques, the study proposes innovation strategies and potential improvement areas for the development of advanced technologies like deep learning and neural networks while addressing the key privacy concerns in data processing. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Estimating Chlorophyll Content from Hyperspectral Data Using Gradient Features 23rd

Estimating Chlorophyll Content from Hyperspectral Data Usin...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Ruszczak, Bogdan Wijata, Agata M. Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Opole Poland Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Gliwice Poland KP Labs Gliwice Poland

ISBN: (纸本)9783031360206

Non-invasive estimation of chlorophyll content in plants plays an important role in precision agriculture. This task may be tackled using hyperspectral imaging that acquires numerous narrow bands of the electromagnetic spectrum, which may reflect subtle features of the plant, and inherently offers spatial scalability. Such imagery is, however, high-dimensional, therefore it is challenging to transfer from the imaging device, store and investigate. We propose a machine learning pipeline for estimating chlorophyll content from hyperspectral data. It benefits from the Savitzky-Golay filtering to smooth the (potentially noisy) spectral curves, and from gradient-based features extracted from such a smoothed signal. The experiments revealed that our approach significantly outperforms the state of the art according to the widely-established estimation quality metrics obtained for four chlorophyll-related parameters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cloud-Assisted Secure and Cost-Effective Authenticated Solution for Remote Wearable Health Monitoring System

引用

IEEE Transactions on Network science and engineering 2023年第5期10卷 2710-2718页

作者： Mahmood, Khalid Obaidat, Mohammad S. Ghaffar, Zahid Alzahrani, Bander A. Shamshad, Salman Saleem, Muhammad Asad Hussain, Shafiq Lahore Campus Lahore55150 Pakistan University of Padua Department of Mathematics Padua35131 Italy University of Jordan KASIT Amman11942 Jordan University of Science and Technology Beijing100083 China Barani Institute of Sciences Department of Computer Science Sahiwal57000 Pakistan King Abdulaziz University Faculty of Computing and Information Technology Jeddah Saudi Arabia The University of Lahore Department of Software Engineering Lahore54590 Pakistan COMSATS University Islamabad Department of Computer Science Sahiwal Campus Sahiwal57000 Pakistan University of Sahiwal Department of Computer Science Sahiwal57000 Pakistan

Security and privacy are the leading solicitude in cloud computing since users have restricted privilege on the data maintained by distinct service providers at remote locations. The situation becomes more strenuous when a huge amount of data is sensed and produced by wearable devices as it is usually considered more sensitive and heterogeneous. The majority of existing authenticated solutions for such a challenging environment either suffer due to high computation and communication costs or due to the fact that they are susceptible to known cyber threats making them impractical for utilization. Therefore we introduced a cost-effective and secure authenticated scheme for the cloud-assisted remote wearable health monitoring system. Informal security proof is discussed to showcase the security strength of the proposed scheme against known security threats. After that a detailed performance analysis of the proposed scheme with related protocols reveals the fact that it can reduce the computation and communication costs by more than 37% and 40%, respectively. Moreover, our scheme offers some added security features like physical and desynchronization attacks prevention. © 2013 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification of Depression Levels Based on Blood Biomarkers 8

Multi-Classification of Depression Levels Based on Blood Bio...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Kavak, Rahmi Ozel, Selma Ayse Polat, Sema Ozler, Sinan Adana Alparslan Türkeş Science and Technology University Department of Software Engineering Adana Turkey Çukurova University Department of Computer Engineering Adana Turkey Çukurova University Faculty of Medicine Department of Anatomy Adana Turkey The Seyhan State Hospital Department of Mental and Nervous Diseases Adana Turkey

ISBN: (纸本)9798331531492

Depression is a psychiatric condition characterized by a persistent feeling of sadness and diminished interest in significant activities. Diagnosing this health problem is challenging because it relies on several social and physiological factors. The timely identification of depression aids in the prevention of severe outcomes, such as suicide. Early detection of depression levels is crucial to prevent adverse effects and enhance the quality of everyday life. The purpose of this work is to use data preprocessing techniques to create a clean dataset from noisy and incomplete medical data that includes blood biomarker values of patients and then apply data mining techniques to this dataset to predict the degree of depression. Adana Dr. Ekrem Tok Mental Health Hospital supplied the raw data for the study, with consent from the ethics committee. Missing data are completed by filling with the constant value and the most frequent value methods (i.e., 0 and mode values) in the relevant column. The classification of the dataset is performed using AdaBoost, Decision Tree (DT), and Logistic Regression (LR) classifiers, which have been previously used in medical datasets and demonstrated to be effective. The Logistic Regression classifier achieved the highest success rate (Accuracy: 0.541 and weighted F-score: 0.481). © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Robust and Reliable Liveness Detection Models for Facial Recognition Systems 20

Robust and Reliable Liveness Detection Models for Facial Rec...

引用

20th International Conference on Frontiers of Information Technology, FIT 2023

作者： Anjum, Haris Arshad, Usama Ali, Raja Hashim Ul Abideen, Zain Shah, Muhammad Huzaifa Khan, Talha Ali Ijaz, Ali Zeeshan Siddique, Abu Bakar Imad, Muhammad Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain

ISBN: (纸本)9798350395785

Facial Liveness Detection is instrumental in combating fraudulent practices and identity theft by differentiating genuine faces from forgeries. Given that facial recognition is now an integral part of many sectors like banking and law enforcement, liveness detection has become a vital aspect for maintaining the trustworthiness of these applications. Unfortunately, the utility of prevalent facial liveness detection models is constrained by their lack of generalizability to novel, unseen data, which presents a substantial impediment to practical applications. To mitigate this issue, our research endeavored to construct a reliable and precise facial liveness detection model that can effectively navigate this challenge and ensure consistent performance across diverse datasets. The devised model exhibited excellent accuracy, which attests to its robustness. This research underscores the advantages of employing deep learning methods such as Convolutional Neural Networks (CNNs) as they significantly enhance the model's accuracy. We intend for our findings to drive further research and progress in this critical field, by laying the groundwork for future work that integrates multiple liveness detection methods and collects more varied training data to develop an even more resilient and efficient system. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

AdaptVR: An Adaptive Learning VR System for Dental Students Training

AdaptVR: An Adaptive Learning VR System for Dental Students ...

引用

International Conference on computer and Applications (ICCA)

作者： Meriam Sherif Nahla Barakat Abeer Hamdy Department of Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt Department of Artificial Intelligence Faculty of Informatics and Computer Science The British University in Egypt Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

The paper proposes “AdaptVR” a virtual reality (VR) system designed to enhance dental training through realistic real tile simulations and adaptive learning environment, to overcome traditional training challenges in dental education. The system aims to provide personalized learning experiences, facilitating skill development and comprehensive assessments for students. The proposed system was tested by 17 dentistry students and 5 experts. AdaptVR framework is done for operative dentistry which is removing decay especially Class I and Class II of classification of caries. Results from the experiment revealed that 77.3% of participants exceed their expectations, 59.1% saw a positive effect on their dental skills, 90.9% reported higher levels of engagement, and 65% indicated that vibration and force feedback provided students with a genuine sensation. AdpatVR's experimental findings show an average accuracy of 50.85% for Class I, 51.7% for Class II, and 82.09% for the Class II box technique. The error percentage averages 49% for Class I, 48% for Class II, and 18% for Class II box technique.

关键词： Training Vibrations Drilling Solid modeling Adaptive learning Adaptation models Force feedback Virtual reality Teeth Dentistry

来源：评论

学校读者我要写书评

暂无评论

A Metamodel for a DSL to Design Decision Support Systems in Smart Tourism

A Metamodel for a DSL to Design Decision Support Systems in ...

引用

Decision Aid sciences and Application (DASA), International Conference on

作者： Charaf Ouaddi Lamya Benaddi Adnane Souha Lahbib Naimi El mahi Bouziane Abdeslam Jakimi Department of Computer Sciences Software Engineering and Information Systems Engineering Team Faculty of Science and Technology Errachidia Moulay Ismail University Morocco

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

The development of Decision Support Systems (DSS) for several companies operating in sectors such as tourism, healthcare, or others, presents significant challenges due to the nature of their multi-component architecture. A typical DSS consists of a data component, a model component incorporating machine learning and deep learning techniques, and a user interface component, each one requires diverse technologies. This complexity increases development time and effort, hindering the efficient design of DSS tailored to specific domains like tourism, where real-time decision-making is essential. One promising approach to overcome these challenges is the use of Domain-Specific Languages (DSLs). DSLs allow developers to model and generate code more efficiently by providing high-level abstractions suited to the domain. By leveraging DSLs, it is possible to simplify the design process and automate the generation of code or parts of the DSS, thereby reducing the overall complexity and time required for development. This paper proposes a metamodel for designing DSS, specifically for the Smart Tourism sector. The metamodel serves as a foundation for the creation of DSL. The goal is to provide a solution to facilitate the development of DSS for the demands of tourism. The paper outlines the key concepts, approach, and results, presenting the first element of the proposed DSL which is the metamodel capturing the essential components and relationships for DSS in Smart Tourism.

关键词： Decision support systems Codes Source coding Medical services User interfaces Syntactics Real-time systems Complexity theory DSL software engineering

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：