检索结果-内蒙古大学图书馆

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Omkaresh S. Kulkarni Jatin Khurana Mamatha G N Preeti Naval Harshita Kaushik G. Renuka Department of Computer Science and Engineering (AI & ML) Vishwakarma Institute of Information Technology Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Department of Electronics and Communication Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

The security of Wi-Fi networks is a crucial situation for community directors. DNS-based total authentication is frequently mentioned as an opportunity for traditional username and password authentication since it gives appropriate scalability, stepped-forward security, and reduced risk. This paper strives to analyze the practicality of using the area name structures (DNS) for authentication of Wi-Fi networks, which integrates the users' authentication, roaming, and different operations along with encryption key distribution into the structure's core. The point of interest of the paper is to assess the ease of implementation, scalability, security, and overall performance of the DNS-based authentication technique. This study examines the practicality of using domain name system (DNS)-based authentication as a security measure for wireless networks. DNS-based authentication is a promising approach that leverages the inherent security of DNS and its widespread use. Through a literature review and analysis of existing protocols, this study explores the strengths and limitations of DNS-based authentication, and evaluates its effectiveness in mitigating common security threats in wireless networks. The findings suggest that while DNS-based authentication offers certain advantages, it also faces challenges such as scalability and single point of failure. Further research and development are needed to fully harness its potential and integrate it into existing wireless network security practices. In the end, the paper offers pointers for future studies. Universal, the paper suggests that DNS-primarily based authentication can be visible as a powerful method for securing wireless networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-cost IoT-Based sensors dashboard for monitoring the state of health of mobile harbor cranes: Hardware and software description

引用

Heliyon 2024年第22期10卷 e40239页

作者： Awad, A.H. Alsabaan, Maazen Ibrahem, Mohamed I. Saraya, M.S. Elksasy, M.S.M. Ali-Eldin, Amr M.T. Abdelsalam, Mohamed M. Computers Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura 35516 Egypt Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia School of Computer and Cyber Sciences Augusta University Augusta 30912 GA United States Faculty of Engineering Delta University for Science and Technology Gamasa 7731168 Egypt

A cost-effective IoT-based real-time data acquisition and analysis hardware system was developed to enhance the performance of the mobile harbor cranes using a combination of a cost-effective quality control monitoring sensor dashboard (proximity sensors, angle position sensor, weight sensor, vibration sensor, and wind sensor), embedded microcontroller (Arduino), and embedded computer (Raspberry Pi). Hardware was operated using a specially developed novel Quality Control and Data Acquisition Multiprocessing software (QC-DAS). The QC-DAS can automatically collect and save real-time data of the sensors in a large-capacity SD card, monitor the state of health of the hardware, and transmit the real-time data of the sensors and the working state of the crane to an IoT server. The novelty of the QC-DAS design is that each function is encapsulated in a predefined module that is “immersed” in a message transmission medium. Modules interact by sending and receiving various signals through this medium. Modularity makes system design simpler, faster, and flexible. Thanks to modularity, users may incorporate their data processing modules when new sensors are added to match the system's needs. Thanks to modularity the DC-DAS can operate quality control hardware for any mobile cranes. There are several constraints in the quality control data acquisition system used by the Damietta Port Authority in Damietta, Egypt, SESCO TRANS company which cause the loading and unloading process to be slowed down. As a result, the SESCO TRANS company upgraded its quality control data acquisition system using the QC-DAS. The hardware was deployed for six months, during which the collected data was used to verify the crane's performance. The vibration produced by the slewing of the crane was monitored and compared with the bearing fault frequency limits, during the operation the wind speed was monitored and compared with the critical wind speed to stop the crane operation automatically, and the pa

关键词： IoT Low-cost Mobile harbor Crane Raspberry pi

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Diseases Risk Analysis using Distance-Based Similarity Measure of Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2021年 47卷 26-37页

作者： Mustapha, Norzieha Alias, Suriana Yasin, Roliza Md Abdullah, Ilyani Broumi, Said Faculty of Computer and Mathematical Sciences Universiti Teknologi MARA Kelantan Kelantan Bukit Ilmu Machang18500 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus21030 Malaysia Laboratory of Information Processing Faculty of Science Ben M’Sik University Hassan II Casablanca Morocco

One of the highest causes of death in many countries in this modern era is cardiovascular diseases. There are a few symptoms that linked significantly to the cardiovascular diseases. The symptoms and diseases relationship can be represented by neutrosophic set values. In general, neutrosophic set gives remarkable contribution in denoising, clustering, segmentation, and classification in handling data of many real applications including in medical field. This study aims to analyse the cardiovascular disease risks by a new distance-based similarity measure motivated from intuitionistic fuzzy set theory. The proof for all the properties is presented clearly. Then, a case study is conducted by using the data on the severity level of the six symptoms found in two different patients. The neutrosophic data are analysed to determine the patients’ possibility of having any one or combination of the three types of cardiovascular diseases. A comparative study involving three common distance measures is conducted. The results show that the similarity indexes for all measures of both patients are less than 0.5. This situation can further conclude as both patients are possibly not suffering from cardiovascular diseases. © 2021, Neutrosophic Sets and Systems. All Rights Reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey

arXiv

引用

arXiv 2023年

作者： Chen, Shengchao Long, Guodong Jiang, Jing Liu, Dikai Zhang, Chengqi Australian Artificial Intelligence Institute School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia Robotics Institute University of Technology Sydney SydneyNSW2007 Australia

As artificial intelligence (AI) continues to rapidly evolve, the realm of Earth and atmospheric sciences is increasingly adopting data-driven models, powered by progressive developments in deep learning (DL). Specifically, DL techniques are extensively utilized to decode the chaotic and nonlinear aspects of Earth systems, and to address climate challenges via understanding weather and climate data. Cutting-edge performance on specific tasks within narrower spatio-temporal scales has been achieved recently through DL. The rise of large models, specifically large language models (LLMs), has enabled fine-tuning processes that yield remarkable outcomes across various downstream tasks, thereby propelling the advancement of general AI. However, we are still navigating the initial stages of crafting general AI for weather and climate. In this survey, we offer an exhaustive, timely overview of state-of-the-art AI methodologies specifically engineered for weather and climate data, with a special focus on time series and text data. Our primary coverage encompasses four critical aspects: types of weather and climate data, principal model architectures, model scopes and applications, and datasets for weather and climate. Furthermore, in relation to the creation and application of foundation models for weather and climate data understanding, we delve into the field’s prevailing challenges, offer crucial insights, and propose detailed avenues for future research. This comprehensive approach equips practitioners with the requisite knowledge to make substantial progress in this domain. Our survey encapsulates the most recent breakthroughs in research on large, data-driven models for weather and climate data understanding, emphasizing robust foundations, current advancements, practical applications, crucial resources, and prospective research opportunities. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

The Effect of Artificial Intelligence on Cybersecurity 2

The Effect of Artificial Intelligence on Cybersecurity

引用

2nd International Conference on Business Analytics for technology and Security, ICBATS 2023

作者： Ali, Atif Khan, Muhammad Arif Farid, Khushboo Akbar, Syed Shehryar Ilyas, Amna Ghazal, Taher M. Al Hamadi, Hussam Cyberjaya Malaysia Federal Urdu University of Science and Technology Karachi Pakistan University of Karachi Karachi Pakistan NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan Center for Cyber Security Faculty of Information Science and Technology Selangor Bangi43600 Malaysia Skyline University College School of Information Technology University City Sharjah 1797 United Arab Emirates College of Engineering and IT University of Dubai PO Box 14143 United Arab Emirates

ISBN: (纸本)9798350335644

Cyber-attacks present a greater threat to individuals and the security of the modern state in the globalized world. Artificial intelligence offers several tools that can be used to improve cybersecurity. Throughout this article, we can observe many benefits and disadvantages of artificial intelligence in cybersecurity at national and international levels. Artificial intelligence makes new opportunities for value creation in businesses, sectors, societies, and the public possible. Research has shown that technology is important in many facets of life. This reason has contributed to its incorporation in many enterprises and sectors. The uses of AI are too many to list. The following study looks at how artificial intelligence (AI) is used in cybersecurity. A developing idea in the technological sector is cybersecurity. information technology has been incorporated into many enterprises. Public and private companies and organizations have had to demand stronger security measures because of this problem. Cyberspace has expanded in response to the need to secure not only personal data but official info as well as technology that is presently accessible. AI was already observed to impact cybersecurity on a broad scale significantly. Because of this, machine learning has been strongly incorporated into modern cybersecurity-related technology. The research study does a literature review and investigates the general effects of AI on *** our results, we have obtained positive findings in attacks with artificial intelligence and have found certain results when obtaining information on attacks using AI. In conclusion, it is necessary to advance in artificial intelligence since the increasing volume and complexity of attacks at the international level require more resources to face them. Cybercriminals will also use artificial intelligence to attack individuals, state infrastructure, and systems. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bandwidth Optimization Techniques for Underwater Fiber Optic Networks

Adaptive Bandwidth Optimization Techniques for Underwater Fi...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Sunil D. Kale Bhavuk Samrat Varalakshmi S Mohit Tiwari Vaishali Singh Umamaheswari. B Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune INDIA Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Faculty of Engineering and Technology Center for Management Studies Bangalore Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

Underwater fiber optic networks provide hyperlinks that permit communiqué among offshore structures, deep-sea bases, and oil rigs. Despite the growing need for better facts costs, the constrained to be had bandwidth in such networks stays a major undertaking for their efficient use. To overcome this task, a variety of adaptive bandwidth optimization techniques were proposed in current years. A number of those strategies involve dynamic modulation and coding, whilst other techniques use adaptive scheduling algorithms. All tactics rely upon dynamic replace of bandwidth allocation to make the only use of the underlying fiber hyperlink. Within the case of dynamic modulation and coding, modifications are made to the physical layer configuration of the hyperlink to conform to converting conditions on the hyperlink. On the other hand, adaptive scheduling strategies use course optimization algorithms to select the maximum green route for records to tour, re-allocating bandwidth as had to accommodate heavy loads. Subsequently, new techniques such as EQUINOX are also being explored to further optimize bandwidth usage on underwater fiber optic networks by means of combining elements of each dynamic modulation and coding and adaptive scheduling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blister Package Classification Using ResNet-101 for Identification of Medication 25

Blister Package Classification Using ResNet-101 for Identifi...

引用

25th International computer Science and engineering Conference, ICSEC 2021

作者： Hnoohom, Narit Maitrichit, Nagorn Chotivatunyu, Pitchaya Sornlertlamvanich, Virach Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakorn Pathom Thailand Musashino University Faculty of Data Science Tokyo Japan University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9781665411974

This research aimed to fine-Tune image classification with deep learning techniques to verify the dispensing of prescriptions in hospitals. The proposed approach will be able to help pharmacies reduce the errors that lead to patients receiving the wrong medications. The image classification model uses a double-side transformed image dataset with download from Highlighted Deep Learning (HDL) paper. The dataset collected two-hundred seventy-Two images for types of medicine blister packs, including 72 images of front-side and backside merged with a horizontal cropped background, which were used for training the model. The blister package image dataset uses a deep learning model with a ResNet-101 pre-Trained model from the TensorFlow framework. The experimental results indicated that the TensorFlow framework achieved higher precision, recall, and F1-score than the Caffe framework. A ResNet-101 model with histogram equalization in the front and backside has the highest accuracy at 100 percent. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Android Malware Detection via Hybrid Lion-Bee Optimization with Bi-Directional Recurrent Neural Network

Android Malware Detection via Hybrid Lion-Bee Optimization w...

引用

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

作者： Sivaram Rajeyyagari Mohamed Ahmed Elfaki Khan Asif Rashid B Kiran Bala Omar Reyad Department of Computer Science College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Department of AI and DS K.Ramakrishnan college of Engineering Trichy India College of Computing and Information Technology Shaqra University Shaqra Saudi Arabia Faculty of Computers and Artificial Intelligence Sohag University Sohag Egypt

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

The number of malicious programs that target the Android OS has significantly expanded with the rise in mobile device usage. It is crucial to identify, prevent, and defeat Android malware assaults since they have long presented a severe threat to Android apps. The emergence of secure Android app ecosystem depends on recognizing and classifying harmful applications into groups are similar to another. Malware families can be categorized in order to recognize harmful activity and to systematically spot dangerous-patterns. Thus, the study suggests a hybrid strategy that combines the attributes discovered from doing static and dynamic malware assessment for enhanced identification and categorization of Android malware. This method more effectively addresses the issue of studying, identifying Android malware. The feature extracted from image sections utilizing the hybrid lion and artificial bee colony (HL-ABC) optimization. RNN were used to classify the retrieved features. Each segment of a malware image file served as a test case for the categorization performance. This is contrasted with other current ways to show the effectiveness of the suggested strategy. Comparing the suggested model to other approaches, the study's findings demonstrate its effectiveness in identifying and classifying Android malware.

关键词： Image segmentation Recurrent neural networks Communication systems Ecosystems Bidirectional control Feature extraction Malware Mobile handsets Integrated circuit modeling Optimization

来源：评论

学校读者我要写书评

暂无评论

Deploying Fuzzy Rough Set and Artificial Immune System Algorithms for Air Quality Prediction 11th

Deploying Fuzzy Rough Set and Artificial Immune System Algor...

引用

11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021

作者： Lasisi, Ayodele Ghazali, Rozaida Ismail, Lokman Hakim Husaini, Noor Aida Department of Mathematical Sciences Faculty of Science Augustine University Ilara-Epe Lagos106101 Nigeria Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Batu Pahat Johor Parit Raja86400 Malaysia Department of Design Engineering and Architecture Faculty of Civil and Environmental Engineering Universiti Tun Hussein Onn Malaysia Batu Pahat Johor Parit Raja86400 Malaysia

ISBN: (纸本)9789811681288

The widespread of air pollution due to emissions of highly detrimental concentrates on human life needs paramount attention. Devising air prediction strategy that accurately analyze air quality level through gathering of useful information allow for relevant organizations to disseminate promptly control measures. This paper proposes the use of artificial immune system (AIS) algorithms consisting of Immunos algorithms (Immunos-1, Immunos-2, Immunos-99), CLONal selection ALGorithm (CLONALG), clonal selection classification algorithm (CSCA), artificial immune recognition system algorithms (AIRS1, AIRS2, Parallel AIRS2) for air quality prediction. The fuzzy rough set selects pertinent data features summarizing interpretations of the data. Comparative simulations reveal that the Parallel AIRS2 produced superlative results to other algorithms with detection rate of 96.40%. Effective prediction performance can be generated with AIS algorithms having highest detection rates and lowest false alarm rates. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Android Malware Detection: Towards Understanding Why the Models Perform So Well?

arXiv

引用

arXiv 2022年

作者： Liu, Yue Tantithamthavorn, Chakkrit Li, Li Liu, Yepang Faculty of Information Technology Monash University Melbourne Australia Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Machine learning (ML)-based Android malware detection has been one of the most popular research topics in the mobile security community. An increasing number of research studies have demonstrated that machine learning is an effective and promising approach for malware detection, and some works have even claimed that their proposed models could achieve 99% detection accuracy, leaving little room for further improvement. However, numerous prior studies have suggested that unrealistic experimental designs bring substantial biases, resulting in over-optimistic performance in malware detection. Unlike previous research that examined the detection performance of ML classifiers to locate the causes, this study employs Explainable AI (XAI) approaches to explore what ML-based models learned during the training process, inspecting and interpreting why ML-based malware classifiers perform so well under unrealistic experimental settings. We discover that temporal sample inconsistency in the training dataset brings over-optimistic classification performance (up to 99% F1 score and accuracy). Importantly, our results indicate that ML models classify malware based on temporal differences between malware and benign, rather than the actual malicious behaviors. Our evaluation also confirms the fact that unrealistic experimental designs lead to not only unrealistic detection performance but also poor reliability, posing a significant obstacle to real-world applications. These findings suggest that XAI approaches should be used to help practitioners/researchers better understand how do AI/ML models (i.e., malware detection) work-not just focusing on accuracy improvement. Copyright © 2022, The Authors. All rights reserved.

关键词： Android malware

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：