检索结果-内蒙古大学图书馆

2022 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2022

作者： Mahmeed, Yusuf Al Elmedany, Wael Sharif, Mhd Saeed University of Bahrain College of Information Technology Sakhir Bahrain University of East London School of Architecture Computing and Engineering London United Kingdom

ISBN: (数字)9781665451932

ISBN: (纸本)9781665451932

The use of Internet of Things (IoT) devices has been growing over the last few years making these appliances available in every household and organization. This significant rise of usability led to misuse, especially by non-technical people, making it an easy target for attackers to intrude on these networks. Therefore, the conventional thinking of protecting the information technology devices needs to embrace these frequent changes. Open-Source Intelligence (OSINT) is one of the modern techniques that can be used to keep track of these new systems by harvesting publicly available information. Collecting the needed information can be challenging for the IoT devices manufacturing companies and clients. This paper proposes an Open-Source Intelligence tool for IoT devices detection called Eagle-Eye which is integrated with Shodan search engine to perform OSINT queries and display it in user-friendly format. With the use of this tool companies, clients and researchers can automate their task of identifying and searching for different IoT devices statics that can be utilized and analyzed to harden these devices. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Blockchain Vulnerabilities and Recent Security Challenges: A Review Paper

Blockchain Vulnerabilities and Recent Security Challenges: A...

引用

2022 International Conference on Data Analytics for Business and Industry, ICDABI 2022

作者： Alfaw, Aysha Elmedany, Wael Sharif, Mhd Saeed University of Bahrain College of Information Technology Sakhir Bahrain University of East London School of Architecture Computing and Engineering London United Kingdom

ISBN: (纸本)9781665490580

Blockchain is a relatively new technology, a distributed database used for sharing between nodes of computer networks. A blockchain stores all information in automated digital format as a database. Blockchain innovation ensures the accuracy and security of the data record and generates trust without the need for a trusted third party. The objectives of this paper are to determine the security risk of the blockchain systems, analyze the vulnerabilities exploited on the blockchain, and identify recent security challenges that the blockchain faces. This review paper presents some of the previous studies of the security threats that blockchain faces and reviews the security enhancement solutions for blockchain vulnerabilities. There are some studies on blockchain security issues, but there is no systematic examination of the problem, despite the blockchain system's security threats. An observational research methodology was used in this research. Through this methodology, many research related to blockchain threats and vulnerabilities obtained. The outcomes of this research are to Identify the most important security threats faced by the blockchain and consideration of security recently vulnerabilities. Processes and methods for dealing with security concerns are examined. Intelligent corporate security academic challenges and limitations are covered throughout this review. The goal of this review is to serve as a platform as well as a reference point for future work on blockchain-based security. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Exploring 2D representation and transfer learning techniques for indoor localization

引用

Multimedia Tools and Applications 2025年 1-13页

作者： Kerdjidj, O. Himeur, Y. Atalla, S. Copiaco, A. Sohail, S.S. Amira, A. Fadli, F. Mansoor, W. Gawanmeh, A. Centre of Development of Advanced Techniques Algiers Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom School of Computing Science and Engineering VIT Bhopal University Kothri Kalan India Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

Indoor localization (IL) plays a critical role in various applications, including asset tracking, emergency response, and indoor navigation. Traditional methods relying on one-dimensional (1D) representations of received signal strength indicator (RSSI) data often suffer from limitations such as low accuracy, environmental sensitivity, and susceptibility to interference. To overcome these challenges, this paper proposes Scalogram-Based Transfer Learning for Indoor Localization (STL-IL), a novel framework that significantly enhances localization performance. The proposed approach transforms 1D RSSI signals into two-dimensional (2D) representations using scalogram-based time-frequency analysis, coupled with advanced transfer learning (TL) techniques. By leveraging the scalogram method to generate image representations of the data and employing diverse wavelet types. Furthermore, pre-trained deep learning models, including GoogleNet and SqueezeNet, are utilized to achieve state-of-the-art performance. Experimental results demonstrate that the STL-IL system achieves remarkable accuracy levels of 95% and 96% for SqueezeNet and GoogleNet, respectively. The proposed framework not only improves localization accuracy but also enhances robustness in dynamic and challenging environments, making it a promising solution for real-world indoor localization applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Network Tumor Classification System in Brain MRI

Deep Convolutional Network Tumor Classification System in Br...

引用

2022 IEEE International Conference on Electronics, computing and Communication Technologies, CONECCT 2022

作者： Vicente, Roderick Y. Tejada, Ryan R. Fernando, Glenn John O. Cimagala, Roselle P. Austria, Yolanda D. Evangelista, Deanne Cameren P. Ifugao State University College of Computing Sciences Ifugao Philippines Bohol Island State University College of Engineering and Architecture Tagbilaran City Philippines Adamson University Department of Computer Engineering Manila Philippines

ISBN: (数字)9781665497817

ISBN: (纸本)9781665497817

Doctors' availability is one of the concerns of people who want to have an appointment with a specialist. Doctors do have a very tight schedule and cannot consistently have appointments, especially for doctors who specialize in brain tumors as they are not that much in numbers here in the Philippines. Brain tumors are a very rare case among individuals and the 10-year survival rate is about 31%, a very low survival rate compared to other diseases. YOLOv3 or a machine learning model using transfer learning and object detection is used as the approach to classify brain tumors. The detection model has an mAP value of 99%, according to the study's findings. The proposed system applies to hospitals, especially those that conduct brain MRIs to classify what type of brain tumor are we dealing with right after the test. The system has a 51% to 99% precision rate per frame © 2022 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Utilising Machine Learning for Precise State-of-Charge Prediction in Li-Ion Batteries

Utilising Machine Learning for Precise State-of-Charge Predi...

引用

International IEEE Conference on Intelligent Systems, IS

作者： Avinash Khatri Jaswinder Lota Prasanna Nepal Mohammad Hossein Amirhosseini School of Architecture Computing and Engineering University of East London London United Kingdom Department of Electrical and Electronics Engineering Nepal Engineering College Bhaktapur Nepal

ISBN: (数字)9798350350982

ISBN: (纸本)9798350350999

As the popularity of electric propulsion using batteries rises alongside the demand for renewable energy, effective battery management and monitoring are crucial for sustain ability and efficiency in electric vehicles (EVs). The battery monitoring system (BMS) employs IoT/sensor networks to estimate crucial battery metrics like remaining useful life (RUL), state-of-health (SoH), and state-of-charge (SoC), using data on current status, temperature, and voltage. Machine learning (ML) and artificial intelligence (AI) are increasingly utilized to enhance BMS accuracy, addressing challenges like real-time data processing and the accuracy of estimations. This paper investigates the effectiveness of Linear Regression and Random Forest models in estimating SoC. During the hyperparameter tuning phase, the models were optimized using the Grid Search method, and their performance was evaluated at various temperatures: 25°C, 10°C, 0°C, and -10°C. The findings indicate that the models' effectiveness enhances as the temperature increases. The Random Forest model exhibited superior performance at 25°C, achieving an R2 score of 0.99646 and an RMSE score of 0.000264. This paper not only contributes to advancing Li-ion battery monitoring system, but also empowers professionals in this field to harness machine learning capabilities effectively.

关键词： Lithium-ion batteries Analytical models Temperature distribution Accuracy Voltage Predictive models Real-time systems Monitoring Random forests Tuning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Digital Identity and Open Banking Data for Fraud Prevention in the Financial Industry

Leveraging Digital Identity and Open Banking Data for Fraud ...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Nada Khalifa Wael Elmedany Saeed Sharif College of Information Technology University of Bahrain Bahrain School of Architecture Computing and Engineering University of East London United Kingdom

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

Financial institutions, organizations, and customers face great harm as a result of fraud in the industry. The potential risks associated with fraud schemes are increasing, and preventive actions are essential to reduce their level of impact. In order to combat fraud in the financial industry, this research paper investigates the possibilities of using open banking data and digital identification solutions. Digital identification solutions provide trusted ways to confirm people’s identities by combining technology like biometrics and secure authentication processes. Accurate and secure identification verification is made possible by different technologies such as facial and fingerprint recognition. Users and service providers can establish secure and trusted connections through the use of secure authentication protocols like OpenID Connect and OAuth. By strengthening identity verification procedures, these solutions help prevent fraudulent activity. Financial organizations can identify possible fraud possibilities with the help of open banking data that is made available by third party data analytics providers through APIs. Account specifics, transactional data, and consumer behavior patterns are all included in this data. Financial institutions can detect unusual behavior and possible fraud threats by analyzing this data. Proactive detection and improved fraud prevention tactics are made possible by the integration of open banking data. he objective of this research paper is to examine the effectiveness of these technologies in identifying and preventing fraudulent activities and their overall impact on fraud prevention strategies in the financial industry.

关键词： Open banking Data analysis Consumer behavior Prevention and mitigation Authentication Organizations Market research Stability analysis Fraud Security

来源：评论

学校读者我要写书评

暂无评论

Advancements in Sentiment Analysis: Insights, Innovations and Future Directions

Advancements in Sentiment Analysis: Insights, Innovations an...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： MhD Saeed Sharif Madhav Theeng Mohammed Swalih Koya Wael Elmedany School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Kingdom of Bahrain

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

This paper presents a comprehensive study on sentiment analysis utilizing X data to uncover insights, innovations, and future directions. The study aimed to develop and evaluate machine learning techniques for sentiment classification, addressing challenges such as class imbalance and feature engineering. Methodologically, the research involved rigorous data pre-processing, exploratory data analysis, model training, and evaluation. Preliminary analysis indicated tweet length's limited role in sentiment classification while emphasizing platform-specific linguistics. Data pre-processing encompassed tokenization, cleaning, stemming, and stop word elimination, leading to Count Vectorization. The Bag-of-Words approach transformed text into numerical vectors, facilitating model training. Multiple classifiers were tested, with the random forest classifier emerging superior, boasting 99.92% training and 98.44% validation accuracies. The results demonstrate the promising accuracy and resilience of the machine learning models, with the random forest model emerging as a frontrunner. The study highlights practical implications for commercial entities and policymakers and suggests future research directions, including multi-lingual analysis and further exploration of deep learning methodologies. This paper contributes to understanding and applying sentiment analysis in real-world contexts.

关键词： Training Deep learning Sentiment analysis Analytical models Technological innovation Accuracy Data analysis Data models Numerical models Random forests

来源：评论

学校读者我要写书评

暂无评论

Accelerate Bit Manipulation in XiangShan Processer Using RISC-V B Extension and Instruction Fusion

Accelerate Bit Manipulation in XiangShan Processer Using RIS...

引用

2022 International Conference on Cloud computing, Internet of Things, and Computer Applications, CICA 2022

作者： Zhang, Fawang Tang, Dan Cai, Ye College of Computer Science and Software Engineering Shenzhen University Shenzhen China State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing China

ISBN: (纸本)9781510656673

In the field of high-performance computing, some application scenarios make extensive use of bit manipulation. RISC-V foundation issues B extension to reduce the number of instructions during the static compilation. But this extension does not cover the more frequent operations fully. Instruction fusion technology can fuse multiple instructions into one instruction at the decode stage to dynamically reduce the number of instructions. Therefore, this technology can supplement RISC-V B extension uncovered instruction, enhancing the processor’s capabilities for bit manipulation. This paper implements the RISC-V B extension 1.0 version on the Xiangshan processor. For accelerating more bit manipulation, we profiled general benchmarks by the simulator, proposed ten new instructions fusion targets, and implemented a fusion decode unit. Finally, we use Coremark and SPEC CPU 2006 integer to evaluate the performance. The Coremark results show that dynamic instructions reduce by 18.14%, and the performance improves by 12.09%. © 2022 SPIE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Securing IoT Devices Against Emerging Security Threats: Challenges and Mitigation Techniques

引用

Journal of Cyber Security Technology 2023年第4期7卷 199-223页

作者： Aziz Al Kabir, Mohammed Elmedany, Wael Sharif, Mhd Saeed College of Information Technology University of Bahrain Sakhir Bahrain School of Architecture Computing and Engineering UEL London United Kingdom

The increasing prevalence of IoT devices has brought about numerous security challenges due to their relatively simple internal architecture and low-powered hardware warranted by their small footprint requirement. As there are billions of IoT devices in use today, the sheer number of such devices pose a great security challenge as they are often constrained by a number of hardware and software limitations in addition to being designed with a focus on convenience, ease of use, mass production, and low cost, rather than security. The seemingly exponentially increasing number of such devices make it harder to keep track of–and patch–insecure IoT devices. This paper explores the common security threats, attacks, and vulnerabilities relating to IoT devices and highlights the challenges associated with securing them against emerging security threats and cyberattacks. Due to their role as gateways to connected devices and susceptibility to forming botnets or facilitating man-in-the-middle attacks, IoT devices are a lucrative target for cybercriminals. The paper discusses various remediation and mitigation techniques that can be implemented to better secure IoT devices, including access control mechanisms, secure communication protocols, and regular updates and patches. By better understanding the security challenges associated with IoT devices and implementing effective mitigation techniques, individuals and businesses can ensure the safety, security, and privacy of their connected devices and networks. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Emotion Recognition through Galvanic Skin Response and ECG Analysis for Improved Accuracy and Reliability

AI-Enhanced Emotion Recognition through Galvanic Skin Respon...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Mounagurusamy, Mathan Kumar Kaur, Parvinder Bdair, Mohammad Pavithra, G. Thenappan, S. Kalpanadevi, G. Srm University Department of Computing Technologies Kattankulathur Campus Tamil Nadu Chennai India Chandigarh College of Engineering and Technology Department of Electronics and Communication Engineering Chandigarh India School of Architecture Computing & Engineering University of East London London United Kingdom Bannari Amman Institute of Technology Department of Aiml Tamil Nadu Sathyamangalam India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Tamil Nadu Chennai India K. Ramakrishnan College of Engineering Department of Ece Tamil Nadu Turuchirapalli India

ISBN: (纸本)9798331543617

Traditional methods of emotion detection, including the problem of recognizing seven basic emotions, have issues such as occlusion, noise, and self-reporting. Besides text mining there are voices, facial and gesture recognition algorithms as well. The indicated acoustics-based difficulties are resolved in the proposed system by employing the previously mentioned signals - less forgery and interferences for ECG and GSR. When noise from signals is removed, characteristic properties such as pace fluctuation and skin conductance are obtained. All of these features are organized using modern machine learning models such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN). Measurements of labelled datasets are utilized to verify the system's accuracy levels, and better performance is reported in the dimension of emotion identification resilience. The proposed methodology in this research is more accurate than other existing systems, with an accuracy rate of 90%, recall rate of 88 percent, and F1-Score of 87.5%. Similar to feature metrics, the level of accuracy for particular parameters has improved. HCl technology will improve learning and mental health features such as recognition, emotion, and social interaction. The established goal of physiological ones is to serve as a solid and steady foundation for identifying emotions. © 2024 IEEE.

关键词： Support vector machines

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：