检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Zhang, Zheng Xu, Liangliang Bao, Yida Baskiyar, Sanjeev Auburn University Dept. of Computer Science & Software Engineering Dept. of Mathematics & Statistics AuburnAL United States

ISBN: (纸本)9798350345346

Heart disease is one of the leading causes of death worldwide. Understanding the presence of heart disease is crucial for timely intervention and effective management. However, it is still a challenging task to accurately diagnose and treat heart disease. In this paper, we propose an ensemble machine learning model that combines the predictive power of three state-of-the-art machine learning algorithms: BERT (Bidirectional Encoder Representations from Transformers), FT-transformer, and XG-Boost. Through extensive training and evaluation, we assess the performance of our model using established metrics such as accuracy, precision, recall, F1-score, and receiver operating char-acteristic (ROC) curve analysis. The results obtained demonstrate the effectiveness and validity of our machine learning system in predicting heart disease accurately. This paper presents a promising approach that can assist healthcare professionals in making informed decisions and improving patient outcomes, enhances our understanding of heart disease patterns, and contributes to the development of effective diagnostic and treatment approaches. © 2023 IEEE.

关键词： Autoencoder BERT Heart Disease Machine Learning Transformer XG-Boost

来源：评论

学校读者我要写书评

暂无评论

software Code De-Compilation Techniques and Approaches: A Comparative Study 25

Software Code De-Compilation Techniques and Approaches: A Co...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Fawareh, Hamed Al-Smadi, Yazan Hassan, Mohammad Fawareh, Faid AlNoor Elrashidi, Ali Zarqa University Dept. of Software Engineering Jordan Zarqa University Dept. of Computer Science Jordan Zarqa University Dept. Of Mathmitical Science Jordan University of Business and Technology Dept. of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

De-compilation is the process of executable files as input where the de-compilation process tries to get away the source code, or the majority of it, if the file's source code is lost or damaged for whatever cause. De-compilation has many uses such as code recovery, security testing, and errors corrections, however, de-compilation is cautious since it depends on certain approaches and techniques. Nowadays de-compilation done by many automated and semi-automated tools, but the accuracy and the efficiency of it depend on the proposed approaches and techniques to stand in front of reengineering challenges. This paper aims to highlight up-to-date prior contributions in the field where 8 published research papers from May 2020 until May 2023 were collected to investigate the state-of-art. As a result, some of the researchers tend to develop their own tools and others tend to use popular automated with different approaches and techniques where the majority of the researchers focused on C, C++, and JAVA programming languages where 50% were de-compilation on C language. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Risk Prediction of Opioid Dependency Using Machine Learning Based on Electronic Health Record

Risk Prediction of Opioid Dependency Using Machine Learning ...

引用

2023 IEEE Asia-Pacific Conference on computer Science and Data engineering, CSDE 2023

作者： Madanian, Samaneh Dai, Sherry Natarajan, Priyadarshini Rasoulipanah, Hamidreza Auckland University of Technology Dept. of Computer Science and Software Engineering Auckland New Zealand

ISBN: (纸本)9798350341072

Opioid abuse and dependence have emerged as a pressing global concern, posing significant challenges to public health and society. Early identification and prediction of opioid dependency represent crucial steps in mitigating its abuse impact on individuals and communities. The application of machine learning techniques to analyze medical data has opened new avenues for achieving this goal. While this field and the prediction is still in its infancy, our research explores the potential of several machine learning algorithms including LightGBM for this risk prediction. To tackle the inherent class imbalance in the MIMICIII dataset, we implemented the Synthetic Minority Oversampling Technique (SMOTE). We developed predictive models using four distinct algorithms: decision trees, random forests, support vector machines, and LightGBM. These models were meticulously evaluated to assess their performance. Ultimately, our findings revealed that the LightGBM model outperformed the other algorithms, demonstrating superior accuracy and achieving a higher Area Under the Curve value. This outcome underscores the potential of LightGBM as a valuable algorithm in the early prediction of the risk of opioid dependence, thereby offering substantial benefits to both patients and society at large. © 2023 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Two-Factor Authentication Protocol with Zero-Knowledge over an Extended Field of Elliptic Curves 6

Two-Factor Authentication Protocol with Zero-Knowledge over ...

引用

6th IEEE International Conference on Information and Telecommunication Technologies and Radio Electronics, UkrMiCo 2023

作者： Strelkovska, Iryna Onatskiy, Oleksiy Yona, Larysa International Humanitarian University Dept. Cybersecurity Software Engineering and Computer Science Odesa Ukraine

ISBN: (纸本)9798350348484

The paper proposes a cryptographic protocol two-factor authentication with the zero-knowledge over the extended field GF(2m) on elliptic curves using biometric data and private key of the user. The implementation of a cryptographic protocol with zero-knowledge proof based on elliptic curves allows significantly reducing the size of protocol parameters and increasing the cryptographic strength (computational complexity of the breaking). The cryptographic protocol was modeled in the High-Level Protocol Specification Language, the model validation and protocol verification was performed using the Security Protocol Animator tool for Automated Validation of Internet Security Protocols and Applications. The software verification of the cryptographic protocol was performed using the software modules On the Fly Model Checker and Constraint Logic based Attack Searcher. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Quantitative Trends Analysis on Russian Literature Research in Korean Academia: Insights from KCI Data 10

Quantitative Trends Analysis on Russian Literature Research ...

引用

10th International Conference on Platform Technology and Service, PlatCon 2024

作者： Iosifovich, Ten Alexander Yeo, Sang-Soo Jung, Young-Ae Dept. of Computer Science Sun Moon University Asan Korea Republic of Dept. of Computer Engineering Mokwon University Daejeon Korea Republic of Dept. of AI Software Technology Sun Moon University Asan Korea Republic of

ISBN: (纸本)9798350367874

This paper presents a quantitative analysis of trends in Russian literature and Korean-Russian translated literature within Korean academia from 1996 to 2024. By analyzing frequency themes and contexts, the study explores evolving research trends, revealing how sociocultural, political, and artistic exchanges between Korea and Russia have influenced each other. Future research using text mining promises to uncover more specific patterns, offering deeper insights into literary and cultural exchanges. This study contributes to understanding the role of literature in expressing and understanding sociopolitical and cultural values in both countries. © 2024 IEEE.

关键词： Korean Citation Index Korean-Russian literature Quantitative analysis Research trend analysis Text mining

来源：评论

学校读者我要写书评

暂无评论

Suitable and Style-Consistent Multi-Texture Recommendation for Cartoon Illustrations

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2024年第7期20卷 1-26页

作者： Wu, Huisi Wang, Zhaoze Li, Yifan Liu, Xueting Lee, Tong-Yee College of Computer Science and Software Engineering Shenzhen University No. 3688 Nanhai Road Nanshan District Guangdong Shenzhen518060 China Dept. of Computer Science and Information Engineering National Cheng-Kung University No. 1 University Road Tainan70101 Taiwan

Texture plays an important role in cartoon illustrations to display object materials and enrich visual experiences. Unfortunately, manually designing and drawing an appropriate texture is not easy even for proficient artists, let alone novice or amateur people. While there exist tons of textures on the Internet, it is not easy to pick an appropriate one using traditional text-based search engines. Although several texture pickers have been proposed, they still require the users to browse the textures by themselves, which is still labor-intensive and time-consuming. In this article, an automatic texture recommendation system is proposed for recommending multiple textures to replace a set of user-specified regions in a cartoon illustration with visually pleasant look. Two measurements, the suitability measurement and the style-consistency measurement, are proposed to make sure that the recommended textures are suitable for cartoon illustration and at the same time mutually consistent in style. The suitability is measured based on the synthesizability, cartoonity, and region fitness of textures. The style-consistency is predicted using a learning-based solution since it is subjective to judge whether two textures are consistent in style. An optimization problem is formulated and solved via the genetic algorithm. Our method is validated on various cartoon illustrations, and convincing results are obtained. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Energy Efficiency Maximization in Massive MIMO-NOMA Networks with Multiple RISs 6

Deep Learning-Based Energy Efficiency Maximization in Massiv...

引用

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Perdana, Ridho Hendra Yoga Nguyen, Toan-Van Pramitarini, Yushintia An, Beongku Hongik University Dept. of Software and Communications Engineering in Graduate School Korea Republic of San Diego State University Department of Electrical and Computer Engineering San DiegoCA United States Hongik University Dept. of Software and Communications Engineering Korea Republic of

ISBN: (纸本)9798350344349

In this paper, we study a deep learning (DL)-based energy efficiency maximization (EEM) problem in massive multiple-input multiple-output (MIMO)-non-orthogonal multiple access (NOMA) networks with multiple reconfigurable intelligent surfaces (RISs). These RISs are deployed randomly at the edge of the near radius to assist the base station (BS) in communicating with near and far users. We formulate the problem of jointly optimizing the precoding matrix and phase shift of the RISs to maximize the overall energy efficiency subject to the quality-of-service of each user, phase shift of RISs, and power budget of the BS constraints. To address this challenging non-convex problem with mixed-integer constraints, the original problem is decoupled into phase shift and beamforming sub-problems, then addressed them separately. We introduce the bisection search algorithm to address the challenge of the phase shifts optimization problem. For the beamforming optimization, it is transformed into an equivalent non-convex problem but with a more tractable form. Then, we propose an iterative algorithm based on the inner approximation method for its solution. To support real-Time optimization, we design a deep learning framework to predict optimal solutions of phase shifts at RISs and precoding matrix under different parameter settings. Simulation results show that the proposed DL-based approach can predict the optimal solution with high accuracy in a short time compared to the conventional approach. Additionally, the effect of the maximum power budget at the base station, the number of RISs, and BS's antennas are evaluated thoroughly. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

IoT Security: A Deep Learning-Based Approach for Intrusion Detection and Prevention

IoT Security: A Deep Learning-Based Approach for Intrusion D...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Kauhsik, Bhanu Nandanwar, Himanshu Katarya, Rahul Delhi Technological University Dept. of Software Engineering Delhi India Delhi Technological University Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350313413

The size and market worth of the Internet of Things (IoT) have expanded, but unfortunately, the likelihood of user data being compromised has also risen. This presents a notable danger that has the potential to create disorder. Consequently, the main aim of this paper is to recognize any weaknesses within existing security solutions and suggest an innovative approach to address them. In order to accomplish this, the paper puts forth four research inquiries concerning IoT security that leverage Machine Learning and Deep Learning techniques. Additionally, it conducts an extensive review of the latest publications and concludes that a combination of specific techniques can provide a potential solution to the security problems in IoT. Overall, the findings of this study suggest that this systematic literature review could help in significantly enhancing the security of IoT devices and applications, safeguarding user data from unauthorized access and potential misuse. © 2023 IEEE.

关键词： Cyberattack Deep Learning Internet of Things (IOT) Intrusion Detection System (IDS) Network Security

来源：评论

学校读者我要写书评

暂无评论

Medicinal Plants Recognition Using Deep Learning

Medicinal Plants Recognition Using Deep Learning

引用

2023 International Conference on Multimedia Computing, Networking and Applications, MCNA 2023

作者： Sharrab, Yousef Al-Fraihat, Dimah Tarawneh, Monther Sharieh, Ahmad Isra University Dept. of Computer Science Amman Jordan Isra University Dept. of Software Engineering Amman Jordan The University of Jordan Dept. of Computer Science Amman Jordan

ISBN: (纸本)9798350339277

The use of medicinal plants has been a longstanding practice in traditional medicine worldwide. Accurately identifying medicinal plants is crucial for determining their medicinal properties and potential applications. However, it can be a challenging task due to the complexity of their appearance. Variations in growth stage, lighting, and imaging conditions can make classification challenging, which limits the application of traditional methods for plant identification. This paper proposes a deep learning-based approach that uses a convolutional neural network (CNN) based on the VGG-16 model. With a dataset of 25,686 images, the CNN is capable of learning and representing complex features in images, enabling it to recognize and classify medicinal plants with high accuracy. The proposed approach can efficiently classify plants with different growth stages, lighting conditions, and imaging settings, providing a reliable tool for plant identification. We achieved an impressive recognition rate of 98%, demonstrating the feasibility of using deep learning techniques for accurate plant classification. The proposed approach has enormous potential for providing healthcare professionals and herbal medicine researchers with a reliable tool for identifying herbal plants. the study represents an essential advancement in the use of deep learning techniques for medicinal plant recognition, overcoming the challenges posed by their complex appearance. The proposed approach has farreaching implications and can significantly impact the field of herbal medicine research, enabling researchers and healthcare professionals to identify and classify medicinal plants more accurately © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review on Pattern-based GUI Testing of Android and Web Apps: State-of-the-Art, Taxonomy, Challenges and Future Directions 25

A Systematic Review on Pattern-based GUI Testing of Android ...

引用

25th International Multi Topic Conference, INMIC 2023

作者： Kousar, Ambreen Khan, Saif Ur Rehman Hussain, Shahid Abdul Basit Ur Rahim, M. Wang, Wen-Li Ibrahim, Naseem Comsats University Islamabad Dept of Computer Science Islamabad Pakistan Shifa Tameer-e-Millat University Dept. of Software Engineering Islamabad Pakistan Penn State University Behrend School of Computer Science and Software Engineering Pennsylvania16563 United States California State University Dept. of Computer Engineering and Computer Science Long Beach United States Penn State Erie Dept. of Computer Science and Software Engineering United States

ISBN: (纸本)9798350317701

Graphical User Interface (GUI) designing and testing of different applications is significant from a user point of view. GUI testing ensures that the user interface of apps is visually appealing, user-friendly, and enhances user satisfaction. Pattern-Based GUI Testing (PBGT) is a new model-based testing approach that aims to enhance reusability while reducing the workload associated with modeling user interfaces and testing applications. The objective of conducting a Systematic Literature Review (SLR) on pattern-based GUI testing is to consolidate existing knowledge and provide insights for improving the effectiveness of PBGT methods. The objectives of conducting an SLR are the identification of current state-of-the-art approaches and tools in the targeted research context. To accomplish the mentioned objectives, A hybrid methodology combining Kitchenham's SLR and PRISMA guidelines was used to conduct this SLR. We performed a keyword-based search on well-known databases IEEE, ACM, Science Direct, Wiley, and Springer Link to determine the potential studies published in the last 10 years. Following a comprehensive systematic analysis, we identified a total of twenty-four studies employing varied approaches for pattern-based GUI testing. Additionally, we identified 11 tools that have been used and proposed in PBGT for Android and web apps and made a taxonomy of tools. We also identified challenges and research directions. The implications of this study are significant. The current study is helpful for researchers intending to work in pattern-based GUI testing. The comprehensive knowledge about the current state-of-the-art Tools, techniques, and approaches will help practitioners to effectively apply them in industry and enable researchers to extend their work in this context in future research. © 2023 IEEE.

关键词： Graphical user interfaces

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：