检索结果-内蒙古大学图书馆

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Irfan, B. Md. Poornima, V. Mohana Kumar, S. Aswal, Upendra Singh Krishnamoorthy, N. Maranan, Ramya Nalsar University of Law Department of Information Technology Telengana Hyderabad500101 India VISTAS Pallavaram Department of Computer Science Chennai India Ramaiah Institute of Technology Department of Computer Science and Engineering Karnataka Bengaluru560054 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India Vellore Institute of Technology Vellore Campus Department of Software Systems and Engineering Tamilnadu Vellore632014 India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai600124 India

ISBN: (纸本)9798350300888

The security of computer networks is increasingly difficult to maintain due to the rising complexity and frequency of cyber-attacks. Important tools for finding and neutralizing these dangers are intrusion detection systems. This study sets out to do a thorough examination and comparison of the efficacy of several machine learning algorithms for use in intrusion detection. This research study evaluates the efficacy of several machine learning algorithms in correctly categorizing instances of network traffic as normal or invasive via extensive experiments performed on representative datasets. Algorithms like random forests, decision trees, SVMs, DL models and NNs are all being tested and rated. Effectiveness is measured and compared using a variety of performance indicators including accuracy, recall, precision, false positive rate, and F1-score. The results of this study emphasize the potential of deep learning models and Random Forests for use in intrusion detection and add to the body of knowledge around machine learning methods for this task. Professionals in the field of network security might use the results to their advantage when building intrusion detection systems. Future research areas are also mentioned, which will hopefully lead to even greater improvements in the field and safer, more reliable intrusion detection systems. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Can one hear the position of nodes?

arXiv

引用

arXiv 2022年

作者： Puzis, Rami Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva Israel

Wave propagation through nodes and links of a network forms the basis of spectral graph theory. Nevertheless, the sound emitted by nodes within the resonating chamber formed by a network are not well studied. The sound emitted by vibrations of individual nodes reflects the structure of the overall network topology but also the location of the node within the network. In this article a sound recognition neural network is trained to infer centrality measures from the nodes' wave-forms. In addition to advancing network representation learning, sounds emitted by nodes are plausible in most cases. Auralization of the network topology may open new directions in arts, competing with network visualization. © 2022, CC BY.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Scheduling Periodic Real-Time Tasks with Inter-Task Synchronisation

Scheduling Periodic Real-Time Tasks with Inter-Task Synchron...

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Luká š Kohú tka Institute of Informatics Information Systems and Software Engineering Slovak University of Technology in Bratislava Bratislava Slovakia

This paper presents a new FPGA-based task scheduler that has a dedicated support of periodic hard real-time tasks in addition to aperiodic tasks. Whenever a period of a periodic task is elapsed, the task is scheduled automatically. The proposed scheduler is using Earliest Deadline First (EDF) algorithm. For task synchronisation, the scheduler supports temporary suspension of tasks with automatic resumption of tasks. Thanks to FPGA implementation of the scheduler and its priority queues, the scheduler operations take two clock cycles regardless of the number of tasks. The paper contains synthesis results for Intel FPGA Cyclone V.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Multi Objective Approach for Validation of PID Controller for Buck Converter

Development of Multi Objective Approach for Validation of PI...

引用

Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Arun Kumar K Gopi Chand Vegineni C. Suresh Bhagath Chandra Chowdari Marella Sireesha Addanki Palak Chimwal Big Data Architect India Sr.Software Engineer Enrollment and Eligibility Team India Electrical and Electronics Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Samayapuram Trichy Department of Financial Services Insights & Data Capgemini India Principal software developer System soft Technologies llc Information Technology India Department of Electrical Engineering Bipin Tripathi Kumaon Institute of Technology Dwarahat Almora India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Buck converters are a common converter of DCDC used for high energy conversion and power sources. These regulators are utilized in electronic gear to alter the result voltage because of changes in the heap current and information voltage. Therefore, in order to react to enquiries in real time, an efficient control system is required. In this work, an upgraded Sine Cosine Algorithm (ISCA) with proportional-integral-derivative (PID) controller is proposed for Mult objective optimization of a DC-DC buck converter. Through two distinct modifications, the limitations of the traditional SCA were therefore addressed, leading to the innovative use of nonlinear equations in conjunction with instrumental mechanisms to update the average location. By contrasting its response for frequency, response for increment, uncertainties of parametric, statistics of time-space indispensable error execution, objective capability, and resistance from aggravation with the previous methods-based PID for buck converters of DC-DC, the suggested ISCA-PID technique's robustness was *** results obtained later revealed that the suggested approach outperformed its algorithmic predecessors in terms of the DC-DC buck converter's remarkably improved transient responsiveness.

关键词： Buck converters Regulators Machine learning algorithms Uncertainty Heuristic algorithms Velocity control Power system stability Real-time systems Voltage control Optimization

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Detection Using Bag-of-Words, TF-IDF, Parallel CNNs and BiLSTM Neural Networks 23

Cyberbullying Detection Using Bag-of-Words, TF-IDF, Parallel...

引用

23rd International Conference on New Trends in Intelligent software Methodologies, Tools and Techniques, SoMeT 2024

作者： Fattahi, Jaouhar Sghaier, Feriel Mejri, Mohamed Bahroun, Sahbi Ghayoula, Ridha Manai, Elyes Department of Computer Science and Software Engineering Laval University 2325 rue de l'Université QuébecQCG1V 0A6 Canada Ecole Nationale d'Ingénieurs de Carthage Université de Carthage Tunis Tunisia Institut Supérieur d'Informatique Université de Tunis El-Manar Tunis Tunisia Faculty of Engineering Information Systems Department University of Moncton New Brunswick Canada

ISBN: (纸本)9781643685380

Cyberbullying, marked by its persistent and intentional aggression online, yields severe repercussions for its victims, extending beyond immediate distress to long-lasting effects such as heightened anxiety, depression, and social withdrawal. Individuals subjected to Cyberbullying often grapple with diminished self-esteem, compromised academic performance, and strained interpersonal relations. Given the escalating prevalence of this digital menace, there is a pressing need for advanced methodologies to address it effectively. This paper introduces an approach to Cyberbullying detection, integrating techniques such as Bag-of-Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) analyses, along with the parallel processing capabilities of Convolutional Neural Networks (CNNs) and the contextual comprehension provided by Bidirectional Long Short-Term Memory (BiLSTM) networks. Through an experimentation on the latest Ejaz-Choudhury-Razi Cyberbullying dataset, our framework exhibits satisfactory performance in identifying instances of online hostility. These results underscore the potential of our approach to significantly contribute to ongoing efforts aimed at combating Cyberbullying in digital environments. © 2024 IOS Press. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Using Mobile Devices to Realize Blended Learning at the University 2

Using Mobile Devices to Realize Blended Learning at the Univ...

引用

2nd International Conference on Technology Enhanced Learning in Higher Education, TELE 2022

作者： Nass, Oksana Skuliabina, Olga Gushchin, Artem Abuova, Zhanargul Vakhitova, Aizada Diyarova, Lunara Baltic State Technical University Named after D.F. Ustinov Voenmeh Department of Information Systems and Software Engineering St. Petersburg Russia Technologies Zhangir Khan West Kazakhstan Agrarian-Technical University Higher School of Information Uralsk Kazakhstan

ISBN: (纸本)9781665470070

Currently, blended learning is becoming a promising form of organization of higher education. Use of smartphones and other mobile devices for the realization of blended learning makes it possible to provide students with equal access to educational and methodological content, that is, the conditions for reducing the information inequality of students. In this regard, the article reveals the structure of the activities of a teacher and a student in the process of mobile learning in the context of the realization of blended learning. The novelty of the research is determined by the fact that the structure and main content of the advanced refresher course 'Blended learning at the university as a means of improving the quality of education in the context of the spread of coronavirus infection' are formulated. The practical significance of the study is determined by the fact that it shows the experience of organizing teacher training in an online format based on the platform ***. © 2022 IEEE.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

Analysing the Adversarial Landscape of Binary Stochastic Networks 1

引用

iCatse International Conference on information Science and Applications, ICISA 2020

作者： Tan, Yi Xiang Marcus Elovici, Yuval Binder, Alexander ST Engineering-SUTD Cyber Security Laboratory Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva Israel

ISBN: (数字)9789813363854

ISBN: (纸本)9789813363847

We investigate the robustness of stochastic ANNs to adversarial attacks. We perform experiments on three known datasets. Our experiments reveal similar susceptibility of stochastic ANNs compared to conventional ANNs when confronted with simple iterative gradient-based attacks in the white-box settings. We observe, however, that in black-box settings, SANNs are more robust than conventional ANNs against boundary and surrogate attacks. Consequently, we propose improved attacks against stochastic ANNs. In the first step, we show that using stochastic networks as surrogates outperforms deterministic ones, when performing surrogate-based black-box attacks. In order to further boost adversarial success rates, we propose in a second step the novel Variance Mimicking (VM) surrogate training, and validate its improved performance. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Decentralized Breast Cancer Patient Monitoring System for Remote Healthcare Security

Blockchain-Based Decentralized Breast Cancer Patient Monitor...

引用

Advancements in Computing (ICAC), International Conference on

作者： K.N. Dilshan H.A.C.K. Rathnayake L.P.T.L. Pathirana D.H.S.V. Dhanapala Harinda Fernando Pradeep K.W Abeygunawardhana Faculty of Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Faculty of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Faculty of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

Breast cancer is a disease that is prevalent all over the world, and that is essential for the efficient treatment and care of breast cancer patients who are monitored remotely. However, traditional conventional centralized systems for patient monitoring face challenges in providing effective and efficient care for breast cancer patients, including limited access to medical records, ineffective communication, and patient participation. Fragmentation of records and difficulty in obtaining information can hinder patient care in terms of both privacy and data security. The proposed system uses machine learning, blockchain, smart contracts, hybrid access control, and hybrid intrusion prevention and detection to diagnose breast cancer decentralized. The technology analyses medical data using advanced machine learning algorithms to diagnose breast cancer accurately and provide healthcare practitioners with relevant insights. The blockchain stores patient information, diagnostic results, and metadata transparently and securely to protect data integrity and privacy. Smart contracts automate and enforce rules, securing data and improving diagnostic workflow. User roles and attributes are used to manage access to sensitive data and improve collaboration. Patients, doctors, and researchers have different permits and limits. Secures granular data and prevents unauthorized access. Scalability and network congestion are addressed via a hybrid network management system. The system optimizes resource allocation, load balancing, and data transfer by integrating centralized and decentralized methodologies. These features reduce delays and assure seamless operation. Experimental results reveal that the suggested system detects breast cancer more accurately than centralized methods. Blockchain, smart contracts, and access control ensure data integrity, privacy, and over-security. Scalability and reactivity are improved by the hybrid network management system, making breast cancer detec

关键词：

来源：评论

学校读者我要写书评

暂无评论

EXPLOITING META-COGNITIVE FEATURES FOR A MACHINE-LEARNING-BASED ONE-SHOT GROUP-DECISION AGGREGATION

arXiv

引用

arXiv 2022年

作者： Shinitzky, Hilla Shahar, Yuval Avraham, Dan Vaisman, Yizhak Tsizer, Yakir Leedon, Yaniv The Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva Israel

The outcome of a collective decision-making process, such as crowdsourcing, often relies on the procedure through which the perspectives of its individual members are aggregated. Popular aggregation methods, such as the majority rule, often fail to produce the optimal result, especially in high-complexity tasks. Methods that rely on meta-cognitive information, such as confidence-based methods and the Surprisingly Popular Option, had shown an improvement in various tasks. However, there is still a significant number of cases with no optimal solution. Our aim is to exploit metacognitive information and to learn from it, for the purpose of enhancing the ability of the group to produce a correct answer. Specifically, we propose two different feature-representation approaches: (1) Response-Centered feature Representation (RCR), which focuses on the characteristics of the individual response instances, and (2) Answer-Centered feature Representation (ACR), which focuses on the characteristics of each of the potential answers. Using these two feature-representation approaches, we train Machine-Learning (ML) models, for the purpose of predicting the correctness of a response and of an answer. The trained models are used as the basis of an ML-based aggregation methodology that, contrary to other ML-based techniques, has the advantage of being a "one-shot" technique, independent from the crowd-specific composition and personal record, and adaptive to various types of situations. To evaluate our methodology, we collected 2490 responses for different tasks, which we used for feature engineering and for the training of ML models. We tested our feature-representation approaches through the performance of our proposed ML-based aggregation methods. The results show an increase of 20% to 35% in the success rate, compared to the use of standard rule-based aggregation methods. © 2022, CC BY-NC-ND.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Transferable and Automatic Tuning of Deep Reinforcement Learning for Cost Effective Phishing Detection

arXiv

引用

arXiv 2022年

作者： Lavie, Orel Shabtai, Asaf Katz, Gilad Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Be'er Sheva Israel

Many challenging real-world problems require the deployment of ensembles-multiple complementary learning models-to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often unnecessary. Deep Reinforcement Learning (DRL) offers a cost-effective alternative, where detectors are dynamically chosen based on the output of their predecessors, with their usefulness weighted against their computational cost. Despite their potential, DRL-based solutions are not widely used in this capacity, partly due to the difficulties in configuring the reward function for each new task, the unpredictable reactions of the DRL agent to changes in the data, and the inability to use common performance metrics (e.g., TPR/FPR) to guide the algorithm's performance. In this study we propose methods for fine-tuning and calibrating DRL-based policies so that they can meet multiple performance goals. Moreover, we present a method for transferring effective security policies from one dataset to another. Finally, we demonstrate that our approach is highly robust against adversarial attacks. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：