检索结果-内蒙古大学图书馆

Enhancing CNN for Forensics Age Estimation Using CGAN and Pseudo-Labelling

Computers, Materials & Continua 2023年第2期74卷 2499-2516页

作者： Sultan Alkaabi Salman Yussof Sameera Al-Mulla Institute of Informatics and Computing in Energy Universiti Tenaga NasionalMalaysia College of Engineering and IT University of DubaiUAE

Age estimation using forensics odontology is an important process in identifying victims in criminal or mass disaster ***,this process is done manually by human ***,the speed and accuracy may vary depending on the expertise level of the human expert and other human factors such as level of fatigue and *** improve the recognition speed and consistency,researchers have proposed automated age estimation using deep learning techniques such as Convolutional Neural Network(CNN).CNN requires many training images to obtain high percentage of recognition ***,it is very difficult to get large number of samples of dental images for training the CNN due to the need to comply to privacy acts.A promising solution to this problem is a technique called Generative Adversarial Network(GAN).GAN is a technique that can generate synthetic images that has similar statistics as the training set.A variation of GAN called Conditional GAN(CGAN)enables the generation of the synthetic images to be controlled more precisely such that only the specified type of images will be *** paper proposes a CGAN for generating new dental images to increase the number of images available for training a CNN model to perform age *** also propose a pseudolabelling technique to label the generated images with proper age and *** used the combination of real and generated images to trainDentalAge and Sex Net(DASNET),which is a CNN model for dental age *** on the experiment conducted,the accuracy,coefficient of determination(R2)and Absolute Error(AE)of DASNET have improved to 87%,0.85 and 1.18 years respectively as opposed to 74%,0.72 and 3.45 years when DASNET is trained using real,but smaller number of images.

关键词： Dental forensics age estimation generative adversarial network pseudo-labelling convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of CPU Power Consumption for Detecting DGA Botnet Command and Control Communication

Statistical Analysis of CPU Power Consumption for Detecting ...

引用

2024 IEEE International Conference on computing, ICOCO 2024

作者： Ibrahim, Zul-Azri Ismail, Saiful Adli Rahim, Fiza Abdul Abas, Muhammad Hazim bin Khairul Anuar, Muhammad Idris bin Azwan, Aiman Harith Bin Institute of Informatics and Computing in Energy College of Computing and Informatics Universiti Tenaga Nasional Selangor Kajang Malaysia Faculty Artificial Intelligence Universiti Teknologi Malaysia Wilayah Persekutuan Kuala Lumpur Kuala Lumpur Malaysia Department of Computing College of Computing and Informatics Universiti Tenaga Nasional Selangor Kajang Malaysia

ISBN: (纸本)9798331530303

Domain Generation Algorithms (DGA) Botnets represent a significant threat to network security due to their ability to mask Command and Control (C&C) communications with botmaster. Traditional detection methods like domain blacklists have struggle to keep pace with the dynamic nature of these botnets. This research explores an alternative detection approach by investigating the use of CPU power consumption as an indicator for detecting DGA botnet in Internet of Things (IoT) devices. The power consumption data was collected and analyzed from a testbed comprising infected Raspberry Pi devices with DGA-based botnets. Statistical methods that include Analysis of Variance (ANOVA) and post-hoc tests, were used to determine if significant differences in CPU power consumption exist across the botnet phases. The results show that CPU power consumption is significantly higher during both the C&C and attack phases compared to normal operation. Additionally, the attack phase exhibits greater power consumption variance, suggesting unstable resource utilization. These findings highlight the potential of using power consumption data as a key metric for identifying botnet activities in IoT systems. ©2024 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Blockchain Scalability for IoT-based Smart Devices -A Generic Model Development 13

Enhanced Blockchain Scalability for IoT-based Smart Devices ...

引用

13th IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2023

作者： Gurunathan, Mathuri Mahmoud, Moamin A. Faisal, Faisal Hadi Universiti Tenaga Nasional College of Graduate Studies Kajang Malaysia College of Computing and Informatics Universiti Tenaga Nasional Institute of Informatics and Computing in Energy Department of Computing Kajang Malaysia

ISBN: (纸本)9798350347319

Blockchain become well known as there is third-party contribution while doing the exchanges or transactions. Blockchain is the innovation for utilizing digital forms of money. It draws in the consideration of specialists and academicians, along with various highlights of Blockchain it is having the significant issue of versatility and scalability which can be classified into throughput, cost, limit, and systems networking. Scalability influences due to some different components like block size and block interval time which likewise may lessen the security. The system may get powerless against various attacks on the off chance that we indiscriminately change the scalability. To address these challenges, this paper con-ducts an intensive analysis of blockchain scalability challenges in the IoT context and subsequently proposes a generic model to enhance scalability. The investigation covers restrictions on different blockchain stages and how system parameters such as throughput, latency, block size, and network influence a peer-topper system's effectiveness, security, and energy consumption. © 2023 IEEE.

关键词： energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Using Drones and Robots for Social Distancing: Literature Review, Challenges and Issues

Using Drones and Robots for Social Distancing: Literature Re...

引用

2024 Panhellenic Conference on Electronics and Telecommunications, PACET 2024

作者： Murad, Sallar Salam Badeel, Rozin Ahmed, Reham A. Yussof, Salman Institute of Informatics and Computing in Energy Kajang43000 Malaysia Department of Communication Technology and Network Seri Kembangan43000 Malaysia

ISBN: (纸本)9798350318845

Since the number of recorded instances of COVID-19 and the number of deaths linked with the virus are both on the rise, it is crucial to maintain an appropriate level of social distance and wear masks to prevent the transmission of coronavirus. The goal of the Social Distancing is to determine if a given pair of persons is keeping a suitable amount of space from one another. Quarantining infected areas and limiting the spread of viruses in both social and physical settings have been made easier with the help of a number of promising robotic technologies that aid people and healthcare experts in the tracking of virus symptoms, the care of infected individuals, and the avoidance of further infection and spread. In this study, we examine the most up-to-date strategies, structures, and tools for utilizing drones in non-social contexts. Additionally, difficulties, problems, and restrictions within the existing literature are addressed. The primary goal of this study is to aid and educate developers and readers interested in deploying drones and robots' technology to battle COVID-19, and to expose the challenges observed in the previous studies to allow the researcher to improve their methods and systems. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Optimization strategies for microgrid based on generation scheduling considering cost reduction and electric vehicles

引用

Soft computing 2024年第13-14期28卷 7893-7903页

作者： Jiang, Yingjie Zain, Jasni Mohamad Nasr, Arman Institute of Information Technology Changchun Automotive Vocational and Technical University Changchun130051 China School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Solar Energy and Power Electronic Co Ltd Istanbul Turkey

One of the main issues in power systems relates to scheduling of energy resources. With the ever-increasing penetration of renewable energies with intermittent power output, this issue has turned into an even more significant problem. Renewable energy sources (RESs) have captured attention due to their low environmental emission and also low running cost. One drawback that may be brought into power systems is the surplus power generation by such generation technologies that should be carefully addressed in power system-related problems. This paper proposes the unscented transform modeling to consider the stochastic behavior of charge and discharge of EVs, random performance of photovoltaic, load demand and wind turbine systems. Due to the unpredictable nature of solar and wind power outputs, as well as plug-in electric vehicle owners' behavior when supplying or receiving power from the grid, a stochastic programming-based approach is proposed to operate microgrids in grid-connected configuration mode. The integration of vehicle to grid (V2G) has a good ability to minimize the operating cost of the MG. An integrated optimization model is presented in this study for optimal operation of the MG with high penetration of PEVs and RESs. Modified sunflower optimization algorithm (MSFO) algorithm is applied in this paper to address the optimization problem. The single-objective stochastic optimization is used for minimizing the total operating cost over the day taking into consideration the uncertainties due to the RESs’ power output intermittency, including wind speed and solar irradiance and load demand forecast error. Several case studies are taken into account to show the efficiency of the optimal operation with PEVs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning Botnet Detection Techniques based on Network Traffic Log

A Review of Machine Learning Botnet Detection Techniques bas...

引用

2022 IEEE International Conference on computing, ICOCO 2022

作者： Ibrahim, Zul-Azri Razali, Rina Azlin Ismail, Saiful Adli Azhar, Iman Hakimi Khairil Rahim, Fiza Abdul Azilan, Ahmad Muzafaraidil Ahmad Institute of Informatics and Computing in Energy College of Computing and Informatics Universiti Tenaga Nasional Selangor Kajang Malaysia Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Wilayah Persekutuan Kuala Lumpur Kuala Lumpur Malaysia Universiti Tenaga Nasional Department of Computing College of Computing and Informatics Selangor Kajang Malaysia

ISBN: (纸本)9781665489966

Cyber-attacks are a common issue in this modern era because of the introduction of high-speed networks and the use of new technologies like Internet of Things (IoT) devices, which fuel the rapid expansion of cyber-attack. One of the common cyber-attacks is botnet attacks. Hackers use botnet attacks to exploit newly discovered vulnerabilities in order to conduct intensive scraping, distributed denial of service (DDoS) attacks, and other large-scale cybercrime. With their adaptable and dynamic character, botnets work with a botmaster to plan their activities, modify their codes, and update the bots regularly to avoid detection. Researchers use numerous techniques to detect the botnet. However, botmasters nowadays have improved due to avoiding security in detection. As the communication can leave traces that allow researchers to detect the botnet's existence, this paper will review 15 related works on botnet detection that utilize machine learning to predict the botnet communication with the command-and-control (C&C or C2) center based on the network traffic log. This paper summarizes the related works based on the dataset, environment, botnet type, features employed, and machine learning techniques. © 2022 IEEE.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

Behavioural Characteristics and Cyberbullying Profiles among Malaysian Youngsters 1

Behavioural Characteristics and Cyberbullying Profiles among...

引用

1st International Visualization, informatics and Technology Conference, IVIT 2022

作者： Anwar, Rina Md. Din, Marina Md. Bakar, Asmidar Abu Abdul Latif, Aliza Rahim, Fiza Abdul Institute of Informatics and Computing Energy Kajang Selangor Malaysia Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Advanced Informatics Department Kuala Lumpur Malaysia

ISBN: (纸本)9781665486484

Cyberbullying is a variation of bullying that involves the use of technology to abuse others. This study examined the relationship between behavioural characteristics and cyberbullying profiles among youngsters. A total of 221 youngsters aged between 15-30 in Malaysia were surveyed, and their raw scores ran through statistical analysis. Findings show that the majority of the participants have never engaged in cyberbullying, but a few of them had experienced cyberbullying. Findings from the survey revealed that the percentages of female participants as cybervictims are higher (63.7%) than male participants (36.3%), while the percentages of male participants as bullies are higher (52.9%) than female participants (47.1%). The most prominent behaviour of cyberbullies is sending mean messages directly to cybervictims and the most prominent behaviour of cybervictims is being excluded from online groups. © 2022 IEEE.

关键词： Computer crime

来源：评论

学校读者我要写书评

暂无评论

Bandgap Modification of ZnO Nanorods for Enhanced Photocatalytic Application

Bandgap Modification of ZnO Nanorods for Enhanced Photocatal...

引用

IEEE International Conference on Semiconductor Electronics (ICSE)

作者： Aini Ayunni Mohd Raub Siti Nur Ashakirin Mohd Nashruddin Mohd Ambri Mohamed Jumril Yunas Institute of Microengineering and Nanoelectronics Universiti Kebangsaan Malaysia Bangi Malaysia Department of Computing College of Computing & Informatics Institute of Informatics and Computing in Energy (IICE) University of Tenaga Nasional Malaysia

ISBN: (数字)9798350378313

ISBN: (纸本)9798350378320

In this paper, we report the bandgap modification of ZnO-based nanorods (ZnO NRs) through carbon-based nanocomposite (ZnO/rGO) and metal doping using Cu, Ni, Bi, Co, and Mg ions as the dopants. The hydrothermal method was used to grow the nanorod's structure by incorporating a metal doping solution during the growing process and rGO coating. The analysis of the synthesized materials shows that metal doping affects the bandgap of the ZnO NRs. The band gaps of pristine ZnO NRs, ZnO NRs/rGO, Cu, Ni, Bi, Co, and Mg-doped ZnO NRs are 3.25, 3.17, 3.07, 3.15, 3.11, 3.18, and 3.14 eV, respectively. Cu-doped ZnO NRs have the most significant reduction in bandgap energy compared to other metal-doped ZnO NRs. Meanwhile, the rGO coating causes bandgap reduction of ZnO NRs from 3.25 to 3.17 eV.

关键词： II-VI semiconductor materials Photonic band gap Absorption Metals Doping Zinc oxide Ions

来源：评论

学校读者我要写书评

暂无评论

Multitask learning for Arabic Dialects Identification and Machine Translation

Multitask learning for Arabic Dialects Identification and Ma...

引用

International Conference on Artificial Intelligence and Its Practical Applications in the Age of Digital Transformation, I2COMSAPP 2024

作者： Dhleima, Mohamed Tourad, Mohamedou Cheikh Telmoud, Cheikh Abdelkader Ahmed Abdelmounaim, Abdali Nanne, Mohamedade Farouk Scientific Computing Computer Science and Data Science Research Unit University of Nouakchott Nouakchott Mauritania Research Team Control and Informatics for Intelligent Systems and Green Energy FST cadi Ayyad Marrakech Morocco

ISBN: (纸本)9783031714283

Multitask learning (MTL) is a popular approach in natural language processing (NLP) to improve the performance of related functions. This paper presents a comprehensive approach to address dialect identification and translation challenges in Arabic NLP. The proposed model utilizes state-of-the-art transformer architectures for both tasks, ensuring robust performance in capturing contextual dependencies and linguistic nuances inherent in Arabic dialects. The primary objectives are to accurately identify Arabic dialects and facilitate their translation to Modern Standard Arabic (MSA) using a shared representation learning approach. The model architecture consists of a shared embedding layer followed by a transformer encoder for each task, employing multi-head self-attention mechanisms for hierarchical contextual information extraction. The model’s performance is evaluated using the F1-score for dialect classification, and the BLEU-score for translation performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Review on Emotional Recognition System Based E-learning: Technology and Challenges

A Review on Emotional Recognition System Based E-learning: T...

引用

2021 International Congress of Advanced Technology and Engineering, ICOTEN 2021

作者： Fadahl Alhaboobi, Zaid Abass Singh Sidhu, Manjit Hilaluddin, Thaharah College of Computing and Informatics Kajang Malaysia National Energy University College of Computing and Informatics Kajang Malaysia

ISBN: (纸本)9781665412247

Multiple technologies have been incorporated with learning management systems (LMSs) in order to facilitate electronic learning (e-learning) experience. Emotional recognition system (ERS) is one of those technologies for providing tutors with learners' emotions related data such as anger, sadness, happiness etc. Additionally, emotions can be recognized using data alike facial, body activities and brain activate. This paper provides an overview of ERS structure referring to the existing state of the art technology. Results showed that great contribution was made in terms of ERS classification score enhancement by using deep learning-based conventional neural networks (CNN) such as AlexNet, GoogleNet, Inception V3, ResNet50 and SqueezeNet classifiers. © 2021 IEEE.

关键词： Brain

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：