检索结果-内蒙古大学图书馆

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： MD Abdul Barek Md Mostafizur Rahman Shapna Akter A.B.M Kamrul Islam Riad Md Abdur Rahman Hossain Shahriar Akond Rahman Fan Wu Department of Intelligent Systems and Robotics University of West Florida USA Dept. of Cybersecurity and Information Technology University of West Florida USA Center for Cybersecurity University of West Florida USA Computer Science and Software Engineering Auburn University USA Dept. of Computer Science Tuskegee University USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Large Language Models (LLMs) have extensive ability to produce promising output. Nowadays, people are increasingly relying on them due to easy accessibility, rapid and outstanding outcomes. However, the use of these results without appropriate scrutiny poses serious security risks, particularly when they are integrated with other software, APIs, or plugins. This is because the LLM outputs are highly dependent on the prompts they receive. Therefore, it is essential to carefully clean these outputs before using them in additional software environments. This paper is designed to teach students about the potential dangers of contaminated LLM output within the context of web development through prelab, hands-on, and postlab experiences. Hands-on lab provides practical guidance on how to handle LLM vulnerabilities to make applications safe with some real-world examples in Python. This approach aims to provide students with a deeper understanding of the precautions necessary to ensure software against the vulnerabilities introduced by LLM output.

关键词： Training Navigation Large language models Computational modeling software Security software development management

来源：评论

学校读者我要写书评

暂无评论

N-Gram-Based Machine Learning Approach for Bot or Human Detection from Text Messages 22

N-Gram-Based Machine Learning Approach for Bot or Human Dete...

引用

6th International Conference on Intelligent systems, Metaheuristics and Swarm Intelligence, ISMSI 2022

作者： Kavadi, Durga Prasad Sanaboina, Chandra Sekhar Patan, Rizwan Gandomi, Amir Department Of Information Technology B V Raju Institute Of Technology Narsapur Telangana India Department Of Computer Science And Engineering University College Of Engineering Kakinada Jawaharlal Nehru Technological University Kakinada India Decentralized Science Lab College Of Computing And Software Engineering Kennesaw State University MariettaGA30060 United States Faculty Of Engineering And Information Systems University Of Technology Sydney UltimoNSW Australia

ISBN: (纸本)9781450396288

Social bots are computer programs created for automating general human activities like the generation of messages. The rise of bots in social network platforms has led to malicious activities such as content pollution like spammers or malware dissemination of misinformation. Most of the researchers focused on detecting bot accounts in social media platforms to avoid the damages done to the opinions of users. In this work, n-gram based approach is proposed for a bot or human detection. The content-based features of character n-grams and word n-grams are used. The character and word n-grams are successfully proved in various authorship analysis tasks to improve accuracy. A huge number of n-grams is identified after applying different pre-processing techniques. The high dimensionality of features is reduced by using a feature selection technique of the Relevant Discrimination Criterion. The text is represented as vectors by using a reduced set of features. Different term weight measures are used in the experiment to compute the weight of n-grams features in the document vector representation. Two classification algorithms, Support Vector Machine, and Random Forest are used to train the model using document vectors. The proposed approach was applied to the dataset provided in PAN 2019 competition bot detection task. The Random Forest classifier obtained the best accuracy of 0.9456 for bot/human detection. © 2022 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Digitalization of Railway Transportation as a Factor for Improving the Quality of the Service

Digitalization of Railway Transportation as a Factor for Imp...

引用

International Conference on Applied Mathematics & computer Science (ICAMCS)

作者： Lily Petriashvili Zurab Modebadze Tamar Lominadze Mzia Kiknadze Nona Otkhozoria Taliko Zhvania Software Engineering Georgian Technical University Tbilisi Georgia Information Systems Georgian Technical University Tbilisi Georgia Information Technology Georgian Technical University Tbilisi Georgia Computer Engineering Georgian Technical University Tbilisi Georgia Microprocessors and Measurement Systems Georgian Technical University Tbilisi Georgia

Current global events, such as the COVID-19 pandemic and the Russian-Ukrainian war, have had a notable impact on the rise in the volume of freight transportation on the Georgian railway. Consequently, the efficient utilization of railway systems, along with monitoring the state of operational processes and technical equipment, plays a crucial role in ensuring smooth and uninterrupted transportation. Key factors to consider include speed, reliability, and the quality of shipments. Railway transportation is progressing worldwide, and effective management is undeniably a priority for our *** essential element for identifying and managing freight wagons is the Arabic numerals printed on them, which indicate their main characteristics and ownership. According to internationally recognized agreements, foreign wagons, as well as those owned or temporarily used by railway administrations, must be promptly returned to their country of dispatch. Within the first 24 hours of crossing the border, "inventory" freight wagons are subject to an average daily charge of 20 Swiss francs, while owned wagons incur an average daily rental fee of US$30. This circumstance, along with rolling stock management, presents one of the critical ***, hundreds of railway employees are involved in identifying the rolling stock in our country. These workers walk along the stations where the parked rolling stock is located. Once they visually recognize the freight car numbers, they relay the information to the relevant station operators via transmitters. Initially, these operators manually record the numbers in special journals and then enter the data into a unified electronic registry system. As a result, railway freight shipments require significant human and time resources, with a high probability of error. This situation considerably slows down the speed of railway service and increases its costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Directional Antenna Based Spatial and Energy Efficient Semi-Distributed Spectrum Sensing in Cognitive Internet-of-Things Networks

SSRN

引用

SSRN 2023年

作者： Lee, Chunghyun Oh, Junsuk Na, Woongsoo Yoon, Jongha Noh, Wonjong Cho, Sungrae School of Software ChungAng University Seoul Korea Republic of Air and Missile Defense Team in Hanwha Systems Seongnam Korea Republic of Division of Computer Science and Engineering Kongju National University Cheonan Korea Republic of School of Software Hallym University Chuncheon Korea Republic of

Recently, cognitive networks and mmWave-based massive antenna transmission are becoming promising approaches for high performance in dense, complicated 6G networks. However, accurate and efficient spectrum sensing that can provide primary user and secondary user (SU) with satisfactory performance is still difficult. In this paper, we propose a new semi-distributed and cooperative passive spectrum sensing method for directional antenna based cognitive radio networks, which can be considered as a key technology of industrial-internet-of-things systems. It finds optimal directional sensing-beams and spectrum detection energy threshold to maximizes a system utilization that consists of accurate spectrum sensing probability and spatial efficiency. To find the optimal controls in a semi-distributed manner, we employ a modified elimination method and a low-complex coordination algorithm among localized user groups with proof of concavity. The simulation results reveal that the proposed control provides enhanced spectrum sensing in terms of sensing accuracy, spatial efficiency, and energy consumption compared to legacy omnidirectional antenna-based sensing approach and directional antenna-based fully distributed sensing approach. In fact, the performance gain becomes larger as the number of SUs increases. We also confirm that the proposed scheme achieves a near-optimal performance within around 5% of a directional antenna-based centralized sensing approach. © 2023, The Authors. All rights reserved.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Machine Learning Technique for Stroke Prognosis

引用

computer systems Science & engineering 2023年第10期47卷 413-429页

作者： Mesfer Al Duhayyim Sidra Abbas Abdullah Al Hejaili Natalia Kryvinska Ahmad Almadhor Uzma Ghulam Mohammad Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz University Al-Kharj16273Saudi Arabia Department of Computer Science COMSATS UniversityIslamabad53000Pakistan Computer Science Department Faculty of Computers&Information TechnologyUniversity of TabukTabuk71491Saudi Arabia Information Systems Department Faculty of ManagementComenius University in BratislavaOdbojárovBratislava440Slovakia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Department of Computer Science and Software Engineering International Islamic UniversityIslamabad44000Pakistan

Stroke is a life-threatening disease usually due to blockage of blood or insufficient blood flow to the *** has a tremendous impact on every aspect of life since it is the leading global factor of disability and *** can range from minor to severe(extensive).Thus,early stroke assessment and treatment can enhance survival *** prediction is extremely time and resource *** prediction methods such as Modern Information and Communication Technologies(ICTs),particularly those inMachine Learning(ML)area,are crucial for the early diagnosis and prognosis of ***,this research proposed an ensemble voting model based on three Machine Learning(ML)algorithms:Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Light Gradient Boosting Machine(LGBM).We apply data preprocessing to manage the outliers and useless instances in the ***,to address the problem of imbalanced data,we enhance the minority class’s representation using the Synthetic Minority Over-Sampling Technique(SMOTE),allowing it to engage in the learning process *** reveal that the suggested model outperforms existing studies and other classifiers with 0.96%accuracy,0.97%precision,0.97%recall,and 0.96%*** experiment demonstrates that the proposed ensemble voting model outperforms state-of-the-art and other traditional approaches.

关键词： Stroke prediction machine learning ensemble model data analysis Synthetic Minority Over-Sampling

来源：评论

学校读者我要写书评

暂无评论

SUPPLYDECK - A Blockchain-Based Pharmaceutical Supply Chain Management 4

SUPPLYDECK - A Blockchain-Based Pharmaceutical Supply Chain ...

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Amarasinghe, A.A.B.G. Gamagedara, G.M.H.S. Pitigala, K.K. Subawickrama, H.D.A.E. Abeywardena, Kavinga Yapa Yapa, Kanishka Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398090

With the rising competition among pharmaceutical companies, the current drug supply chain market has become more competitive with high-quality product segments. The rapid growth of internet pharmacies has made it more difficult to standardize drug safety throughout in complex distributed supply chain networks. There is a high chance of introducing counterfeit drugs which are almost the same as the original pharmaceuticals. Due to the lack of transparency the possibility of tampering with drugs in the current manual and web-based pharmaceutical systems is extremely high. Throughout the past recent years, these counterfeit drugs were recognized as the one of major worldwide problems. This situation is worse in developing countries. The unavailability of verifying the legitimacy of drug suppliers and poor mechanisms to trace the drugs were identified as critical points that need to be resolved. SUPPLYDECK comes as a solution for the critical scenario mentioned. This solution addresses the above problems using blockchain technology, as a distributed digital ledger that ensures transparency, traceability, and security. This can show promise for solving some global supply chain management problems using smart contracts and user authentication along with IoT technology and machine learning concepts that are critically examined with this potential application. © 2022 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Enhanced Student Stress Prediction in Higher Education Using a TriBranch CNN Framework

Enhanced Student Stress Prediction in Higher Education Using...

引用

Integrated Circuits and Communication systems (ICICACS), IEEE International Conference on

作者： Fateh Bahadur Kunwar Satyajee Srivastava R Dhivya Monika Gulati K. Amudha D Antony Arul Raj Department of Computer Science and Engineering Geetanjali Institute of Technical Studies Udaipur India Department of Computer Science and Engineering School of Engineering and Technology Manav Rachna International Institute of Research and Studies Faridabad India Department of Information Technology M.Kumarasamy College of Engineering Karur India MMIM Maharishi Markandeshwar (Deemed to be University) Mullana Ambala India Department of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Trichy India Department of Software Systems PSG College of Arts & Science Coimbatore India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Students' stress levels have a significant impact on their academic performance in higher education, thus it's important to identify signs of stress early on and intervene to improve academic performance. Machine learning has evolved into a powerful tool for stress prediction, allowing for proactive support of at-risk youngsters. In order to better anticipate college students' stress levels, this study presents an enhanced TriBranch CNN framework. In order to provide the best possible performance, the technique includes data preparation, feature extraction, and model training. The dimensionality and redundancy are reduced using Principal Component Analysis (PCA). After being trained and tested against other models, the Fully Conditional Temporal Bayesian Network (Fully CTBN) outperformed them all with an accuracy of 93.29%, beating both traditional CNN and FCN approaches. These findings demonstrate that the Fully CTBN approach is useful for identifying students who may be struggling academically and providing schools with the information they need to implement data-driven interventions that boost student well-being and performance.

关键词： Training Accuracy Redundancy Human factors Machine learning Mental health Convolutional neural networks Integrated circuit modeling Stress Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Implementation of Multi-Agent Energy Management for Secondary Control of a Microgrid

Implementation of Multi-Agent Energy Management for Secondar...

引用

International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD

作者： Yeliz Yoldas Ahmet Onen Khaled Alawasa Abdelsalam El Haffar Razzaqul Ahshan Md. Rabiul Islam S.M. Muyeen Nadya Noorfatima Jaesung Jung Department of Software Engineering Kayseri University Kayseri Turkey Department of Electrical and Computer Engineering Sultan Qaboos University Muscat Oman School of Electrical Computer and Telecommunications Engineering University of Wollongong New South Wales Australia Electrical Engineering Department Qatar University Doha Qatar Department of Energy Systems Research Ajou University Suwon South Korea

The multi-agent energy management system (EMS) is needed to coordinate multiple agents of a microgrid to provide efficient operation of the system. In this study, multi-agent EMS is seen as the middle controller between primary and tertiary control levels. It is responsible for determining the relevant set points based on data gathered from the tertiary control level and sending them to the appropriate primary control level agents. The main objective of this paper is to propose a new optimization model for multi-agent EMS to minimize errors between the forecasted and real-time data at every predetermined time interval. Rather than using a traditional centralized microgrid controller to determine the dispatch of resources, a new framework-based multi-agent coordination is proposed to achieve the following objectives: minimizing load shedding, maximizing load dispatch and reliability, providing frequency, and maintaining voltage stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Concealing Sensitive Samples against Gradient Leakage in Federated Learning

arXiv

引用

arXiv 2022年

作者： Wu, Jing Hayat, Munawar Zhou, Mingyi Harandi, Mehrtash Department of Electrical and Computer Systems Engineering Monash University Australia Department of Data Science and AI Monash University Australia Department of Software Systems and Cybersecurity Monash University Australia

Federated Learning (FL) is a distributed learning paradigm that enhances users’ privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users’ private data via eavesdropping on the shared gradient information. We hypothesize that a key factor in the success of such attacks is the low entanglement among gradients per data within the batch during stochastic optimization. This creates a vulnerability that an adversary can exploit to reconstruct the sensitive data. Building upon this insight, we present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples. To achieve this, we propose synthesizing concealed samples to mimic the sensitive data at the gradient level while ensuring their visual dissimilarity from the actual sensitive data. Compared to the previous art, our empirical evaluations suggest that the proposed technique provides the strongest protection while simultaneously maintaining the FL performance. Code is located at https://***/JingWu321/DCS-2. Copyright © 2022, The Authors. All rights reserved.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Cryptocurrency Trading Platforms Using the Analytic Hierarchy Process 3

Comparative Analysis of Cryptocurrency Trading Platforms Usi...

引用

3rd International Workshop on Information Technologies: Theoretical and Applied Problems, ITTAP 2023

作者： Kuznetsov, Oleksandr Kryvinska, Natalia Ilchenko, Oleksii Smirnova, Tetiana Ulianovska, Yuliia Department of Political Sciences Communication and International Relations University of Macerata Via Crescimbeni 30/32 Macerata62100 Italy Department of Information and Communication Systems Security School of Computer Sciences V. N. Karazin Kharkiv National University 4 Svobody Sq. Kharkiv61022 Ukraine Department Department of Information Systems University of Comenius Bratislava Slovakia Oracle Slovensko spol. s r.o. Bratislava Slovakia Department of cyber security and software Central Ukrainian National Technical University 8 University Ave Kropyvnytskyi25006 Ukraine Department of Computer Science and Software Engineering University of Customs and Finance av. Volodymira Vernadskogo 2/4 Dnipro49000 Ukraine

In the rapidly evolving world of cryptocurrency trading, selecting an optimal trading platform is paramount for both novice and seasoned investors. This study aims to provide a comprehensive evaluation of leading cryptocurrency trading platforms using the Analytic Hierarchy Process (AHP). The AHP, a structured technique for organizing and analyzing complex decisions, was employed to rank platforms based on multiple criteria, including UI/UX, security protocols, asset diversity, and more. Initial findings, considering equal importance for all criteria, highlighted Binance as the most favorable platform. However, when varying the importance of criteria based on empirical data, the distinctions between platforms became less pronounced, yet Binance retained its top position. This research not only offers valuable insights for potential investors but also emphasizes the significance of considering multiple criteria in decision-making processes. Furthermore, the study underscores the versatility of the AHP in evaluating multifaceted scenarios, making it a valuable tool for future research in diverse domains. © 2023 CEUR-WS. All rights reserved.

关键词： Analytic hierarchy process

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：