检索结果-内蒙古大学图书馆

The Analysis of Neural Network Models to Distinguish AI generated faces from Real faces

Procedia computer Science 2024年 233卷 295-306页

作者： Joshita Malla Harshini Vemuri SreeDivya Nagalli S Abhishek T Anjali Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Rolls-Royce Inc Bangalore India

The rise of Artificial Intelligence (AI)-generated faces that are identical to actual ones is both a technological innovation and a major concern. While considering the implications, some of the existing security systems are unable to differentiate between a high-quality deep-fake and an actual intruder's face. For instance, the risks are quite high at an airport security checkpoint, where facial recognition is the first line of security against unauthorized entry. The primary concern here is how trustworthy the computer programs and algorithms will be in recognizing counterfeits among a plethora of actual and artificially generated faces. This necessitates the need to introduce machine learning approaches to differentiate between actual and fraudulent faces, particularly when AI-generated faces are involved. Effective artificial intelligence systems must be adaptive and change quickly in the face of more complex threats rather than simply recognizing them. AI-generated faces are becoming more convincing by the day, increasing the risk of their exploitation. This poses the need to ensure that the technology on which people rely should be robust and trustworthy in critical situations, whether it is a security checkpoint or an e-commerce site. In this perspective, this study has attempted to develop and implement Artificial Intelligence-powered solutions to detect the artificial faces while ensuring reliability for critical functions in an age where reality constantly blends with fiction.

关键词： Artificial Intelligence Deep Fake Deep Learning Facial Recognition Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Iot Based Condition Monitoring of Electrical Equipment 2

Iot Based Condition Monitoring of Electrical Equipment

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Raja, J. Kalyani, N. Singh, Mukul Kumar Garg, Akriti Sarojwal, Atul Devi, S. Rukmani Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering School of Computing Tamil Nadu Chennai600062 India School of Computing Sastra Deemed University Tamil Nadu Thirumalaisamudram613401 India Mahatma Jyotiba Phule Rohilkhand University Department of Electrical Engineering Uttar Pradesh Bareilly243006 India Simats Deemed to be University Department of Computer Science Saveetha College of Liberal Arts and Sciences Tamil Nadu Chennai600124 India

ISBN: (纸本)9798350364699

In recent years, the surveillance of the health of electrical appliances has been transformed by the Internet of Things (IoT). This investigation offers a comprehensive account of a system that employs the Internet of Things (IoT) to conduct predictive maintenance and analysis of electrical equipment. The network of interconnected sensors in the proposed system enables the real-time monitoring of a variety of operating characteristics, including temperature, current, voltage, and vibration. Upon the identification of equipment health indicators, the data collected by these sensors is transmitted to a centralised cloud platform. Sophisticated analytics and machine learning algorithms analyse the data on this platform to detect any patterns. The system's predictive warnings and real-time insights facilitate the implementation of preventive maintenance, reduce downtime, and enhance the reliability and efficacy of electrical equipment. The article explores the benefits of utilising Internet of Things (IoT) condition monitoring in industrial and utility settings. It also addresses pertinent topics, including system architecture, data processing methodologies, and other pertinent topics. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Verdant Visions: Exploring the Frontier of Peppermint Disease Detection through CNN and Random Forest 11

Verdant Visions: Exploring the Frontier of Peppermint Diseas...

引用

11th IEEE International Conference on Cloud computing in Emerging Markets, CCEM 2023

作者： Kaur, Arshleen Kukreja, Vinay Chandran, Nisha S. Jain, Vishal Garg, Navin Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School Of Computing Graphic Era Hill University Uttarakhand Dehradun248002 India Department of Computer Science and Engineering Sharda School Of Engineering and Technology Sharda University U.P. Greater Noida India Computer Science and Engineering Graphic Era Deemed to be University Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350360059

—Using Convolutional Neural Networks (CNNs) and Random Forest algorithms, the authors of this study present a powerful hybrid model for the automated identification of peppermint illnesses. The CNN architecture consists of two primary convolutional layers for character extraction, a max-pooling layer for reducing dimensionality, and a final pair of convolutional layers for fine-tuning the extracted features. For the ultimate classification tasks, this framework is combined with the Random Forest algorithm. The table below highlights the model's performance evaluation, showing its efficacy across a variety of disease types including Verticillium dahliae, Puccinia menthae, Erysiphe, Mint anthracnose, Peronospora, & Root Rot. All three measures (accuracy, recall, and F1-score) are consistently above 92% for this model. Verticillium dahliae, for example, achieved a 92.74% precision, and a 95.18% recall, with an F1 score of 93.94%. Other classes also perform exceptionally well, demonstrating the model's generalizability. Precision, recall, or F1-score all converge around 95% on the macro, micro, or weighted averages, demonstrating a balanced, high-performing model. Across all illness types, the model exhibits an impressive accuracy of 0.98 to 0.99, thus establishing its dependability and practicality. Excellent performance across a variety of measures confirms that the hybrid approach is highly effective in identifying peppermint illnesses. Its precision and reliability suggest it could be used in practice to improve disease management during peppermint cultivation. ©2023 IEEE.

关键词： Pepper

来源：评论

学校读者我要写书评

暂无评论

Accurate and Efficient Human Activity Recognition Through Semi-Supervised Deep Learning

引用

IEEE Sensors Journal 2025年第12期25卷 23105-23116页

作者： Long, Xianlei Wang, Ping Gu, Fuqiang Yan, Jinjin Yu, Fangwen Li, Yan Chen, Chao Guo, Songtao Chongqing University College of Computer Science Chongqing400044 China Harbin Engineering University Qingdao Innovation and Development Center Qingdao266400 China Tsinghua University Department of Precision Instrument Beijing China Macquarie University School of Computing Sydney Australia Chongqing University State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing400044 China

In recent years, deep learning has been widely used for human activity recognition (HAR) based on wearable sensor data due to its excellent performance. However, deep learning approaches often need a large amount of labeled data to train the model. The collection of huge amounts of labeled activity data is usually labor-intensive and even cost-prohibitive, limiting the practical use of these methods. An effective way to address this issue is to use semi-supervised learning methods. Yet, most existing semi-supervised approaches fail to fully make use of unlabeled data to improve deep learning models' accuracy and generalizability. In this work, we propose an innovative Adaptive Confidence Semi-supervised HAR (ACS-HAR) method that can dynamically adjust the selective confidence threshold based on the model's learning state, thereby making more efficient use of unlabeled data. Experimental results on six public datasets demonstrate that our method outperforms traditional supervised methods by up to 5.20% accuracy and state-of-the-art semi-supervised methods by up to 3.30% *** release our code at https://***/objwww/ACS-HAR. © 2001-2012 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Deep Learning - YouTube Video Recommendation Process

Two-Stage Deep Learning - YouTube Video Recommendation Proce...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Balakrishna, Cheepu Sharada Mani, D. Basi Reddy, A. Chandrakanth, P. Selvan, R.Senthamil Saispurthi Institute of Technology Department of Computer Science and Engineering Sathupally Mandal India Qis College of Engineering and Technology Department of Computer Science and Engineering Ongole India Mohan Babu University School of Computing Department of Computer Science and Engineering Tirupati India N.B.K.R.I.S.T Vidyanagar Department of Computer Science and Engineering Kota India Annamacharya Institute of Technology and Sciences Department of Electronics and Communication Engineering Tirupati India

ISBN: (纸本)9798350317060

YouTube is one of the most widely used and technically advanced commercial systems of recommendations. It provides an overview of the system and highlights the remarkable gains in efficiency made possible by deep learning. This research uses the traditional 'two-stage' framework for separating and retrieving information. First, a profound model for generating candidates ought to be described, and then a model for ranking candidates ought to be outlined, and both of these should be done in that order. The order in which these two tasks ought to be completed is important. In addition, it offers instruction that can be put into practice as well as valuable insights that have been gleaned from the process of developing, iterating, and managing a large-scale recommendation system that has a significant impact on the experience of the user. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Streamlining Attendance with Fast Face Recognition Model 8

Streamlining Attendance with Fast Face Recognition Model

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sundar, Koushik Ravikumar, S. Jeyalakshmi, J. Eugene Berna, I. Samuel, Prithi Citibank Na Jersey CityNJ United States Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Amrita School of Computing Amrita Vishwa Vidhyapeetham Department of Computer Science and Engineering Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Erode India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur Campus Chennai India

ISBN: (纸本)9798350376425

Facial recognition technology has become increasingly prevalent in today's world, with applications ranging from mobile phones to banking and workplace security. This research proposes a facial recognition-based solution to replace the manual attendance tracking process, streamlining the process and reducing human error. The proposed system integrates facial recognition, registration forms, and a Redis database to automate attendance tracking. By leveraging the ML search algorithm (similarity approach) and the Insight face Python module, the system can accurately identify individuals within a database. The system's implementation involves two phases: the initial phase focuses on integrating facial recognition, registration forms, and database access. The second phase involves utilizing software such as Streamlit and Dashboard to enhance user experience and visualization. This innovative solution offers a more efficient and accurate alternative to traditional manual attendance tracking methods, improving overall efficiency and reducing administrative burdens. By automating the process, the system contributes to a more streamlined and secure environment. © 2024 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Internet of Things routing protocol with mobility awareness and energy efficiency 3

Internet of Things routing protocol with mobility awareness ...

引用

3rd International Conference on Advance computing and Innovative Technologies in engineering, ICACITE 2023

作者： Chauhan, Birendra Kumar Banupriya, M. Venkatagurunatham, K. Sungheetha, Akey Kumari, Ch D V P Karthick, L. Iimt University School of Basic Sciences and Technology Uttar Pradesh Meerut250001 India Hindustan Institute of Technology Department of Computer Science and Engineering Coimbatore India Andhrapradesh Guntur522019 India Adama Science and Technology University School of Electrical Engineering and Computing Department of Computer Science and Engineering Nazareth1888 Ethiopia Aditya College of Engineering Department of Computer Science and Engineering Andhra Pradesh Surampalem533437 India Hindusthan College of Engineering and Technology Department of Mechanical Engineering Coimbatore641032 India

ISBN: (纸本)9798350399264

Internet of things enabled devices are considered one of the technologies for the future and at the same time, the mass use of IoT devices has revolutionised the way of using modern technology. Hence, with the mass implication creating energy-efficient systems without compromising on the data ratio has become mandatory. Thus, the study collected secondary data and conducted a thematic analysis. Such methods of study have emperors the researchers to collect reliable data and with the discussion create a reliable result. For a better understanding, this study has discussed bout different kinds of routing and helps o create an energy-efficient system with better mobility. The discussion is based on different bandwidths of data along with their use at the same time problem of the system is mentioned at the end. Such a critical discussion allows a reader to prepare their own opinion about a system creation which have an energy-efficient topology and that has improved data packet ratio. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Intelligent Trip Planning with Integrated Street View: A Seamless AI-driven Approach

Intelligent Trip Planning with Integrated Street View: A Sea...

引用

Innovations in Power and Advanced computing Technologies (i-PACT)

作者： Siva Sankar A Nirmal Kumar K Sidharth M Dinesh S Abhishek Anjali T Department of Computer Science and Engineering Amrita School of Computing Amritapuri India

The advent and widespread adoption of AI-powered trip planners have revolutionized how travelers engage in travel planning. These intelligent systems leverage artificial intelligence algorithms and data to provide users with personalized, efficient, and immersive planning experiences. In this research the indispensable role played by immersive street view experiences within AI trip planners. Integrating immersive street view experiences within AI trip planners empowers travelers to make well-informed choices, as they can virtually navigate and assess potential destinations, accommodations, and attractions. These intelligent systems leverage artificial intelligence algorithms and data to provide users with personalized, efficient, and immersive planning experiences. The findings reveal that immersive street view experiences significantly elevate the effectiveness of travel planning and decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A survey of energy-efficient strategies for federated learning in mobile edge computing

引用

Frontiers of Information Technology & Electronic engineering 2024年第5期25卷 645-663页

作者： Kang YAN Nina SHU Tao WU Chunsheng LIU Panlong YANG School of Electronic Engineering National University of Defense TechnologyHefei 230009China Department of Computing Hong Kong Polytechnic UniversityHong Kong 999077China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China

With the booming development of fifth-generation network technology and Internet of Things,the number of end-user devices(EDs)and diverse applications is surging,resulting in massive data generated at the edge of *** process these data eficiently,the innovative mobile edge computing(MEC)framework has emerged to guarantee low latency and enable eficient computing close to the user ***,federated learning(FL)has demonstrated its empirical success in edge computing due to its privacy-preserving ***,it becomes a promising solution for analyzing and processing distributed data on EDs in various machine learning tasks,which are the major workloads in ***,EDs are typically powered by batteries with limited capacity,which brings challenges when performing energy-intensive FL *** address these challenges,many strategies have been proposed to save energy in *** the absence of a survey that thoroughly summarizes and classifies these strategies,in this paper,we provide a comprehensive survey of recent advances in energy-efficient strategies for FL in ***,we first introduce the system model and energy consumption models in FL,in terms of computation and *** we analyze the challenges regarding improving energy efficiency and summarize the energy-efficient strategies from three perspectives:learning-based,resource allocation,and client *** conduct a detailed analysis of these strategies,comparing their advantages and ***,we visually illustrate the impact of these strategies on the performance of FL by showcasing experimental ***,several potential future research directions for energy-efficient FL are discussed.

关键词： Mobile edge computing Federated learning Energy-efficient

来源：评论

学校读者我要写书评

暂无评论

Ecoskinomics: Exploring the Ecological Factors Shaping Skin Health

Ecoskinomics: Exploring the Ecological Factors Shaping Skin ...

引用

2023 Innovations in Power and Advanced computing Technologies, i-PACT 2023

作者： Abhishek, S. Anjali, T. Lekshmi, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Department of Dermatology Amrita Institute of Medical Sciences Amrita Vishwa Vidyapeetham Kochi India

ISBN: (纸本)9798350325188

This comprehensive research paper thoroughly investigates the profound implications of environmental factors on skin health. It meticulously examines the multifaceted contributions of pollution, UV radiation, climate change, and lifestyle choices to adverse skin conditions. The research elucidates the intricate processes driving oxidative stress, inflammation, DNA damage, collagen degradation, and immunosuppression generated by these factors through a comprehensive review of scholarly literature and empirical evidence. It underscores the critical importance of enhancing awareness, implementing evidence-based preventive strategies, and fostering lifestyle modifications to mitigate the detrimental effects and promote optimal skin health in an increasingly challenging environmental landscape. © 2023 IEEE.

关键词： Climate Change Hyperpigmentation Premature Aging Skin Disease UV Radiation

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：