检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ameerbakhsh, Omair Ghabban, Fahad M Alfadli, Ibrahim AbuAli, Amer Nizar Al-Dhaqm, Arafat Al-Khasawneh, Mahmoud Ahmad College of Computer Science and Engineering Information system department Taibah University Madina Saudi Arabia School of Computing Faculty of Engineering University Technology Malaysia Johor Malaysia Faculty of Computer & Information Technology Al-Madinah International University Shah Alam Malaysia

Metamodeling is used as a general technique for integrating and defining models from different domains. This technique can be used in diverse application domains, especially for purposes of standardization. Also, this process mainly has a focus on the identification of general concepts that exist in various problem domain and their relations and to solve complexity, interoperability, and heterogeneity aspects of different domains. Several diverse metamodeling development approaches have been proposed in the literature to develop metamodels. Each metamodeling development process has some advantages and disadvantages too. Therefore, the objective of this paper is to provide a comprehensive review of existing metamodeling development approaches and conduct a comparative study among them-eventually selecting the best approach for metamodel development in the perspective of digital forensics. © 2021, CC BY.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Visualizing the Battery Degradation through Non-destructive Methods on Predicting the State of Health (SoH) of Second Life Batteries (SLB)

Visualizing the Battery Degradation through Non-destructive ...

引用

Advances in Electrical, Electronics and Computational Intelligence (ICAEECI), International Conference on

作者： Vignesh S Jeyraj A-L Selvaraj Hang Seng Che Kok Soon Tey HiCoE UMPEDAC Level 4 WISMA R&D Faculty of Institute for Advanced Studies Universiti Malaya Kuala Lumpur Malaysia HiCoE UMPEDAC Level 4 WISMA R&D Universiti Malaya Kuala Lumpur Malaysia Department of Computer System & Technology Universiti Malaya Kuala Lumpur Malaysia

Ever since the vehicle electrification era had started, lithium-ion batteries become the sole fore runner in powering the Electric Vehicles (EV). Vehicle electrification contributed vastly in public transportation which further promoted the surge in usage of EV in recent days. The EVs are deployed in different climatic environment, and user defined handling which lead the battery to undergo non-uniform degradation as it undergoes a series of charge and discharge cycles. State of Health (SoH) is an indicator to quantify the battery health. When the SoH of lithium-ion batteries deployed in EV application reaches 80% of its nominal capacity, then the battery is said to be reached its End of Life (EoL) in EV application. Such batteries, when translated in to second life applications, its SoH estimation at second life is vital information on defining the operating points of the Second Life Battery (SLB). The SoH estimation of SLB is expected to be non-destructive in nature. This article deals with the SoH estimation of pouch cells that underwent lab level testing for 100 charge and discharge cycles. The battery degradation from cycle 1 to 100 is visualized through Incremental Capacity Differential Voltage (ICDV) method. Based on the degradation modes observed in the battery, the Health Indicators (HI) were summarized and the insights on dominant degradation phase can be visualized through bifurcating the operating voltage of the cell in to a particular zones of interest. This voltage band in particular, caters preliminary insights regarding the battery degradation and the same information can be translated to second life thereby reducing the cycle life testing time and efforts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Mou, Luntian Zheng, Changwen Gao, Wen The University of Chinese Academy of Sciences Beijing100049 China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing100086 China Beijing Institute of Artiicial Intelligence Faculty of Information Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing100124 China The School of Electronics Engineering and Computer Science Peking University Beijing100871 China

Freeform handwriting authentication verifies a person’s identity from their writing style and habits in messy handwriting data. This technique has gained widespread attention in recent years as a valuable tool for various fields, e.g., fraud prevention and cultural heritage protection. However, it still remains a challenging task in reality due to three reasons: (i) severe damage, (ii) complex high-dimensional features, and (iii) lack of supervision. To address these issues, we propose SherlockNet, an energy-oriented two-branch contrastive self-supervised learning framework for robust and fast freeform handwriting authentication. It consists of four stages: (i) pre-processing: converting manuscripts into energy distributions using a novel plug-and-play energy-oriented operator to eliminate the influence of noise;(ii) generalized pre-training: learning general representation through two-branch momentum-based adaptive contrastive learning with the energy distributions, which handles the high-dimensional features and spatial dependencies of handwriting;(iii) personalized fine-tuning: calibrating the learned knowledge using a small amount of labeled data from downstream tasks;and (iv) practical application: identifying individual handwriting from scrambled, missing, or forged data efficiently and conveniently. Considering the practicality, we construct EN-HA, a novel dataset that simulates data forgery and severe damage in real applications. Finally, we conduct extensive experiments on six benchmark datasets including our EN-HA, and the results prove the robustness and efficiency of SherlockNet. We will release our code and dataset at https://***/WangJingyao07/SherlockNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CIPM: Common identification process model for database forensics field

arXiv

引用

arXiv 2021年

作者： Alfadli, Ibrahim Ghabban, Fahad M Ameerbakhsh, Omair AbuAli, Amer Nizar Al-Dhaqm, Arafat Al-Khasawneh, Mahmoud Ahmad College of Computer Science and Engineering Information system department Taibah University Madina Saudi Arabia Faculty of Engineering School of Computing University Technology Malaysia Johor Malaysia Faculty of Computer & Information Technology Al-Madinah International University Shah Alam Malaysia

Database Forensics (DBF) domain is a branch of digital forensics, concerned with the identification, collection, reconstruction, analysis, and documentation of database crimes. Different researchers have introduced several identification models to handle database crimes. Majority of proposed models are not specific and are redundant, which makes these models a problem because of the multidimensional nature and high diversity of database systems. Accordingly, using the metamodeling approach, the current study is aimed at proposing a unified identification model applicable to the database forensic field. The model integrates and harmonizes all exiting identification processes into a single abstract model, called Common Identification Process Model (CIPM). The model comprises six phases: 1) notifying an incident, 2) responding to the incident, 3) identification of the incident source, 4) verification of the incident, 5) isolation of the database server and 6) provision of an investigation environment. CIMP was found capable of helping the practitioners and newcomers to the forensics domain to control database crimes. © 2021, CC BY.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Soft Set Based Clustering and Its Comparison on Categorical Data

Soft Set Based Clustering and Its Comparison on Categorical ...

引用

Information technology International Seminar (ITIS)

作者： Iwan Tri Riyadi Yanto Cheah WaiShiang Rahmat Hidayat Rofiul Wahyudi Suprihatin Ani Apriani Information System Department Universitas Ahmad Dahlan Yogyakarta Indonesia Faculty of Computer Science & IT Universiti Malaysia Sarawak Samarahan Sarawak Malaysia Information Technology Department Politeknik Negeri Padang Padang Indonesia Islamic Banking Department Universitas Ahmad Dahlan Yogyakarta Indonesia Institute Teknologi Nasional Yogyakarta Yogyakarta Indonesia

Categorical data clustering is problematic since it is difficult or complex to determine how comparable the data is. Several methods, most recently centroid-based strategies, have been developed to reduce the complexity of the similarity of categorical data. These methods nevertheless result in lengthy processing durations. Another method, soft set-based clustering (SSC), based on the probability function of multivariate multinomial distributions, is suggested in this article. Soft sets are used to represent the data, and each soft set has a probability for each object. The joint cluster distribution function determines the probability for each object after the multivariate multinomial distribution function. The connected cluster would receive the highest likelihood. Benchmark data sets from UCI machine learning are used to compare the performance of the approach to the baseline techniques. The outcomes demonstrate that the suggested strategy performed better in purity, rank index, and calculation time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shilling Attacks Detection in Collaborative Recommender system: Challenges and Promise

Shilling Attacks Detection in Collaborative Recommender Syst...

引用

Workshops of the 34th International Conference on Advanced Information Networking and Applications, WAINA 2020

作者： Zayed, Reda A. Ibrahim, Lamiaa F. Hefny, Hesham A. Salman, Hesham A. Faculty of Graduate Studies for Statistical Research Cairo University Giza Egypt Management Information System Department Higher Institute of Computer and Information Technology Al Shorouk Egypt

ISBN: (纸本)9783030440374

The reliability of the recommender system is highly essential for the continuity of any system. Fake and malicious users may be spoiling system predictions reliability by inserting and injecting fake profiles called "shilling attacks" into the target recommender system. Thus, the detection of these attacks is necessary for any recommender system. Therefore, several shilling attacks detection approaches have proposed. In this work, we propose a survey for the recent detection methods, which pick up famous shilling attack models against the collaborative filtering recommender systems. © 2020, Springer Nature Switzerland AG.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Student Assessment Factors in Study Success Using the Decision Tree Algorithm

Student Assessment Factors in Study Success Using the Decisi...

引用

Interdisciplinary Approaches in technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Dina Fitria Murad Bambang Dwi Wijanarko Hendra Mayatopani Rosilah Hassan Arba’Iah Inn Sunardi Information Systems Department Binus Online Learning Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia Department of Information System Pradita University Tangerang Indonesia Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Pusat Pengajian Diploma SPACE Universiti Teknologi Malaysia Kuala Lumpur Malaysia

The evaluation of students is essential to comprehending and enhancing successful learning in an educational setting. In the era of information technology, the use of decision tree algorithms has become increasingly pertinent in this sphere. This study seeks to identify the student assessment factors that have the greatest impact on learning success when using the Decision Tree algorithm. The collection and analysis of student assessment data, including test scores, class participation, and other variables Modeling the relationship between these factors and student learning outcomes using decision trees. The results of the analysis permit the identification of the most influential factors in predicting the success of student learning. The findings of this study can aid educators, schools, and educational institutions in designing learning strategies that are more effective and tailored to the specific needs of each student, as well as in identifying students who are at high risk and require special attention. The implementation of the Decision Tree algorithm in student evaluation is a crucial step toward a more individualized and effective educational approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data collection in sensor cloud: Recent advances, taxonomy, use cases and open challenges

TechRxiv

引用

TechRxiv 2020年

作者： Ali, Ihsan Department of Computer System & Technology Faculty of Computer Science & Information Technology University of Malaya Malaysia

In recent years, Wireless Sensor Networks (WSNs) technologies are used in many important areas, including weather forecasting, security, environmental monitoring, health care, and industry. Nonetheless, due to the constraints of WSNs in terms of energy, processing, connectivity, computation and data integrity. An important issue in this research field is the efficient management of the large number of WSN’s data. Therefore, there is a need for strong and scalable high-performance computing and large storage infrastructure for real-time processing and storage of WSN’s data. This article attempts to discuss data collection methods in WSNs, sensor cloud, and IoT. Also, in this context, a general overview of WSNs and sensor cloud platforms, including their definitions, architectures, and applications are given. We investigate, highlight and report recent advances in data collection technology by categorizing and classifying data collection methods in WSNs, sensor cloud, IoT and developing a taxonomy based on these classifications. Furthermore, the analysis and synthesis of existing works in this research domain is highlighted. The identification of key research challenges for future work and use case in this research domain were also highlighted and discussed. © 2020, CC BY-NC-SA.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Classification of Student Academic Performance using Fuzzy Soft Set

Classification of Student Academic Performance using Fuzzy S...

引用

2020 International Conference on Smart technology and Applications, ICoSTA 2020

作者： Riyadi Yanto, Iwan Tri Sutoyo, Edi Rahman, Arif Hidayat, Rahmat Ramli, Azizul Azhar Fudzee, Mohd Farhan Md. Universitas Ahmad Dahlan Departement of Information System Yogyakarta Indonesia Telkom University Departement of Information System Bandung Indonesia Politeknik Negeri Padang Department of Information Technology Padang Indonesia Universiti Tun Hussein Faculty of Computer and Information Technology Onn Malaysia Malaysia

ISBN: (纸本)9781728130835

Students are one of the substances that need to be considered in relation to the world of education, because students are translators of the dynamics of science, and carry out the task of exploring that knowledge. As a subject with potential and, at the same time, objects in their activities and creativity, students are expected to be able to develop their qualities. The quality can be seen from the academic achievements achieved, which are evidence of the effort earned by students. Student academic achievement is evaluated at the end of each semester to determine the learning outcomes that have been achieved. If a student cannot meet certain academic criteria to be declared eligible to continue their studies, the student is declared to be not graduating on time or even dropout (DO). The high number of students not graduating on time or dropouts at higher institutions can be minimized by the policies of higher institutions by directing and detecting at-risk students in the early stages of education. Therefore, in this paper, we present the use of Fuzzy Soft Set Classification (FSSC), which is based on the Fuzzy Soft set theory to predict student graduation. The 2068 dataset was taken from the Directorate of Information systems, Ahmad Dahlan University. The results showed that the FSSC reached up to 0.893292 in terms of accuracy. So, it is expected to be able to detect students at risk in the early stages of education so that higher education can minimize students not graduating on time or dropout by providing appropriate treatment and designing strategic programs. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Detection of S100 Calcium Binding Protein A6 by Silicon Nitride Photonic Sensor

Detection of S100 Calcium Binding Protein A6 by Silicon Nitr...

引用

2022 International Electrical Engineering Congress, iEECON 2022

作者： Udomsom, Suruk Rattakorn, Punramon Mankong, Ukrit Umezawa, Toshimasa Matsumoto, Atsushi Kanno, Atsushi Yamamoto, Naokatsu Mendez-Astudillo, Manuel Atthi, Nithi Yamwong, Wittawat Intuyod, Kitti Pinlaor, Somchai Kawanishi, Tetsuya Imai, Kazuo Chiang Mai University Biomedical Engineering Institute Chiang Mai Thailand Chiang Mai University Faculty of Engineering Department of Electrical Engineering Chiang Mai Thailand National Institute of Information and Communications Network System Research Institute Tokyo Japan Ansys Inc. Tokyo Japan Thai Microelectronics Center National Electronics and Computer Technology Center Chachoengsao Thailand Khon Kaen University Faculty of Medicine Department of Pathology Khon Kaen Thailand Khon Kaen University Faculty of Medicine Department of Parasitology Khon Kaen Thailand Waseda University Department of Electronic and Physical Systems Tokyo Japan Imai Engineering Tokyo Japan

ISBN: (纸本)9781665402064

The detection of S100 Calcium Binding Protein A6, a useful cholangiocarcinoma marker, has been demonstrated for the first time using silicon nitride photonic resonator sensor. The sensor was designed and fabricated by low-cost 500 nm technology. Label-free sensing results based on the reactions between anti-S100A6 antibody and S100A6 antigen, showed good sensitivity and specificity. This sensing technique has potential in low-cost and low-level detection of the biomarker, deserving further study. © 2022 IEEE.

关键词： Silicon nitride

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：