检索结果-内蒙古大学图书馆

Emerging Research in Computational science (ICERCS), International Conference on

作者： Karthi Vivekanandan B. Kaleeswari P L. Natchiammai Arun Anthonisamy R. Vijayabharathi Manjunathan Alagarsamy Department of Electrical and Electronics Engineering Builders Engineering College Tirupur India Department of Electronics and Communication Engineering Easwari Engineering College (Autonomous) Chennai India Department of Electronics and Communication Engineering Mookambigai College of Engineering Pudukkottai India Department of Computer Science and Business System Panimalar Engineering College Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Trichy India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

Smart home technology has made daily life easier, automated, and managed. IoT devices like smart speakers, cameras, thermostats, and security systems are increasingly integrated, raising security and privacy concerns. This study examines smart home devices’ energy consumption, use trends, device failures, and system efficiency. This research uses smart home devices to identify consumption trends and risks. To better understand smart home ecosystems, the study will evaluate energy consumption, device usage hours, and malfunctions that can affect functionality and security. Using predictive analytics and machine learning, the researchers predict excessive energy usage and device problems. These methods identify trends and irregularities in smart home device operation to improve performance, efficiency, and security. This study investigates how user decisions, usage hours, and device age affect energy consumption, as well as how to identify optimization opportunities. The data analysis study contains statistical summaries and visualisations of device type, usage hours, energy consumption, user preferences, malfunction incidents, and device age. Machine learning algorithms such as linear regression and anomaly detection predict energy usage and locate anomalies. The data illustrate energy and device efficiency trends and recommend improvements to smart home security and effectiveness. This study addresses smart home device vulnerabilities and inefficiencies to improve smart home system optimization. The results offer smart home technology manufacturers and customers ways to improve energy efficiency, device performance, and system security.

关键词： Performance evaluation Energy consumption Data analysis Smart homes Machine learning Market research Energy efficiency Security Object recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

Low-Resolution Face Recognition for CCTV and Edge-Powered Smart Attendance systems

Low-Resolution Face Recognition for CCTV and Edge-Powered Sm...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Nico Surantha Edward Yose Sani Muhamad Isa Department of Electrical Electronics and Communication Engineering Faculty of Science and Engineering Tokyo City University Tokyo Japan Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Attendance systems have become more modern, and one of the biometric systems without physical contact is face recognition. However, many face-based attendance systems still carry out attendance individually and cannot detect multiple faces simultaneously. In addition, capturing facial data in real-time is still a challenge because the relatively large distance between the camera and the individual reduces the ability to recognize faces. The general solution is to use super-resolution to generate better-quality faces while maintaining the main facial recognition features. One technique still being researched is super-resolution generative adversarial networks (SRGAN). SRGAN can enlarge the resolution of captured images and maintain image quality sufficient for face recognition. The attendance system can be easily integrated into edge devices such as the Jetson Nano. This paper proposes automatic and effective attendance systems with the super-resolution technique to detect and recognize faces in low-resolution input. The experimental results show that using face data capture with a resolution of 40 × 40 pixels and a four-fold magnification results in a resolution of 160 × 160 pixels. Combining Face SRGAN with FaceNet architecture as the basis of face recognition can achieve an accuracy rate of 78.19% and an F1-Score of 81.13% with an average processing time of 1.61 seconds per frame on a PC and 14.55 seconds per frame on a Jetson Nano at an average of face recognition per frame of as many as up to 8 faces simultaneously.

关键词： Support vector machines Image quality Accuracy Face recognition Image edge detection Superresolution Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Sleep Monitoring systems based on Edge Computing and Microservices Caching

Sleep Monitoring Systems based on Edge Computing and Microse...

引用

Artificial Intelligence of Things (AIoT), IEEE Annual Congress on

作者： Nico Surantha David Jayaatmaja Sani Muhamad Isa Faculty of Science and Engineering Department of Electrical Electronics and Communication Engineering Tokyo City University Tokyo Japan Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350392296

ISBN: (纸本)9798350392302

The rapid development of Internet of Things (IoT) technology has enabled the widespread deployment of health monitoring systems. Traditionally, the health monitoring system has been limited by centralized processing and storage in the cloud, leading to latency issues and potential data loss. This paper introduces a smart sleep monitoring system based on edge computing, utilizing microservices architecture and caching techniques. The proposed system employs edge computing to enable data processing closer to the source, reducing latency and improving real-time monitoring capabilities. Caching is employed to reduce database load and optimize random access memory (RAM) usage. This research addresses latency and response time challenges on IoT health monitoring platforms in environments with poor network quality while optimizing database load and resource usage on Jetson Nano as the edge computing device. Using Electrocardiogram (ECG) data as input, the proposed system yields impressive performance metrics. The research results indicate that the proposed system can increase throughput by 26.92 KB/s, reduce response time by 18.8 ms, and decrease latency by 20.86 ms compared to the previous work. Message Queuing Telemetry Transport (MQTT) integration reduces CPU usage by approximately 40% and RAM usage by about 81.24%.

关键词： Cloud computing Databases Random access memory Microservice architectures Real-time systems Nanoscale devices Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning for Human-Object Interaction Detection 2

Ensemble Deep Learning for Human-Object Interaction Detectio...

引用

2nd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2022

作者： Mansour, Ahmed E. Mohammed, Ammar Elsayed, Hussein Abd El Atty Ramly, Salwa H. El Ain Shams University Faculty of Engineering Electronics and Electrical Communication Department Cairo Egypt Cairo University Faculty of Graduate Studies of Statistical Researches Computer Science Department Cairo Egypt

ISBN: (纸本)9781665466776

Human-object interaction (HOI) detection is the task of predicting the visual relationships between humans and their surroundings in images and videos by locating and inferring the interactions between human-object pairs. The majority of existing models have approached this task by detecting human and object instances and predicting interactions between them using a single model and relying on visual features to differentiate between different actions. In this article, we propose a novel method for solving the HOI detection problem by employing ensemble voting on simple models that use only spatial features to predict human-object pair actions. Additionally, we solve the false-positive pairs generated by mis-grouping and non-interaction objects in the image using a bipartite matching. Our proposed approach outperforms many state-of-the-art models on the V-COCO dataset while requiring less inference time. © 2022 IEEE.

关键词： Visualization Computational modeling Object detection Predictive models Feature extraction Ubiquitous computing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

QuripfeNet: Quantum-Resistant IPFE-Based Neural Network

引用

IEEE Transactions on Emerging Topics in Computing 2024年

作者： Han, KyungHyun Lee, Wai-Kong Karmakar, Angshuman Yi, Myung-Kyu Hwang, Seong Oun Gachon University Department of Computer Engineering Seongnam13120 Korea Republic of Universiti Tunku Abdul Rahman Faculty of Information and Communication Technology Malaysia Indian Institute of Technology Computer Science and Engineering Kanpur India

In order to protect the sensitive information in many applications involving neural networks,several privacy-preserving neural networks that operate on encrypted data have been developed. Unfortunately,existing encryption-based privacy-preserving neural networks are mainly built on classical cryptography primitives,which are not secure from the threat of quantum computing. In this paper,we propose the first quantum-resistant solution to protect neural network inferences based on an inner-product functional encryption scheme. The selected state-of-the-art functional encryption scheme based on lattice-based cryptography works with integer-type inputs,which is not directly compatible with neural network computations that operate in the floating point domain. We propose a polynomial-based secure convolution layer to allow a neural network to resolve this problem,along with a technique that reduces memory consumption. The proposed solution,named QuripfeNet,was applied in LeNet-5 and evaluated using the MNIST dataset. In a single-threaded implementation (CPU),QuripfeNet took 107.4 seconds for an inference to classify one image,achieving accuracy of 97.85%,which is very close to the unencrypted version. Additionally,the GPU-optimized QuripfeNet took 25.9 seconds to complete the same task,which is improved by 4.15 × compared to the CPU version. © 2013 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Impact of Parameters for the In-situ Measurement of the Electric Field Strength of the SSB Signal in a 5G NR system Using the Frequency-Selective Method in Zero-Span Mode

Impact of Parameters for the In-situ Measurement of the Elec...

引用

International Conference on Smart systems and Technologies (SST)

作者： Vanja Mandrić Slavko Rupčić Bogdan Pavković Josip Ilakovac Department of Communication Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia Department of Computing and Control Engineering Faculty of Technical Sciences University of Novi Sad Novi Sad Serbia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (数字)9798350386394

ISBN: (纸本)9798350386400

Measuring 5G systems is a major challenge for measurement engineers, who need to be aware of all the limitations of the new generation The parameters of the frequency-selective measurement system (spectrum analyzer - ROHDE & SCHWARZ FSH8) were investigated in the measurement of 5G NR SSB signals (3.4 – 3.8 GHz). The focus was on the setting parameters which, according to the literature, have an influence on the measurement: RBW, VBW, SWEEP TIME and the duration of the measurement. All measurements were carried out in zero-span mode. In the second part of the measurement, these SSB synchronization signal measurement results were compared with the 5G signal measurement results at the same location using the NARDA SRM-3006 device equipped with a decoder for the 5G NR system (FR1) to determine the optimal method for measuring these signals with a spectrum analyzer (SA).The measurement results show that the resolution bandwidth (RBW) has the largest variation in the measured electric field (EF) strength values of the SSB 5G NR signal of 17.20 dB (MH/RMS) and 17.70 (RMS/AGV10). It is therefore necessary to pay particular attention to the setting of this measurement parameter. In addition, the video resolution (VBW) shows a significantly lower field strength variation of 2.50 dB, but also the same deviation from the reference value of 2.50 dB (RMS/AGV10). Other analyzed parameters have a negligible influence on the measurement of the EF *** post-processing was performed in the work to determine the final (maximum) value of the EF strength at the points of assumed highest exposure, which is used to assess the impact and compliance with the permissible values according to the relevant standards.

关键词： Time-frequency analysis 5G mobile communication Measurement uncertainty Electric variables measurement Amplitude modulation Time measurement Frequency measurement Decoding Electric fields Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Quantifying the Impact of AI and Machine Learning on Data Access Optimization

Quantifying the Impact of AI and Machine Learning on Data Ac...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Khandari, Harsimrat Sahoo, Girija Shankar Tr, Mahesh Rajeswari, M. Jadhav, Prranjali Meena, Mansingh Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka 562112 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Electrical Engineering Jaipur India

ISBN: (纸本)9798350329773

Quantifying the impact of synthetic Intelligence (AI) and machine getting to know (ML) on information access Optimization (DAO) and its ability to enhance overall performance and performance inside organizations has been a topic of research for decades. This newsletter investigates how such technology is essential in optimizing records access and its effect on the rate and accuracy of operations. We speak about how cutting-edge advances in AI and ML can be utilized to detect patterns in facts, reduce latency, and improve the general quality of data. Furthermore, we discuss how that technology can reduce manual techniques and get rid of errors due to human mistakes, hence enhancing performance and productiveness. Sooner or later, we talk about the main challenges associated with enforcing AI and ML within a company and identify capacity areas of development. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Perspective Analysis of Optical Biosensors in Machine Learning Applications

A Perspective Analysis of Optical Biosensors in Machine Lear...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： B. Naveen Kumar M. V. Panduranga Rao Preeta Sharan K. R. Varun Suresh Kallam M. Kumaresan Department of Computer Science and Engineering Faculty of Engineering and Technology Jain (Deemed-to-be-University) Bengaluru India Department of Electronics and Communication Engineering The Oxford College of Engineering Bengaluru India Department of Mechanical Engineering The Oxford college of Engineering Bengaluru India

Optical biosensors, a novel invention at the intersection of biotechnology and optics, are revolutionizing the field of biomedical diagnostics. Optical biosensors act by identifying variations in light’s wavelength, phase, polarization, or intensity caused by interactions between a sensing element and the target analyte. Optical biosensors outperform other sensor types in sensing applications due to their quick, accurate, and extremely sensitive results. When evaluating optical sensors, total power, core power, efficient area, and indices are the most crucial variables to consider. Recent years have seen notable advancements in machine learning (ML), a branch of artificial intelligence (AI). This review investigates the complementary nature of optical biosensors and machine learning methods. Here, the potential utility of ML for optical biosensors is explored in detail. The advantages and drawbacks of the most popular machine learning methods are listed based on an analysis of the optical biosensing data. It highlights the possible effects of machine learning on improving the sensitivity, selectivity, and adaptability of optical biosensing devices, and it summarizes current advancements in the field. Finally, the study considers the challenges and limitations that associated with current optical biosensing techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Convolutional-Transformer Neural Network Architecture for Diagnosis of Pneumothorax

A Novel Convolutional-Transformer Neural Network Architectur...

引用

International CSI computer Conference, CSICC

作者： Amir Sanati Mansoureh A. Dashtestani Habib Rostami Saeed Talatian Azad Computer Engineering Department Faculty of Intelligent System Engineering and Data Science Persian Gulf University Bushehr Iran

Pneumothorax is a life-threatening and urgent chest disease than can be detected using Chest X-Ray (CXR) image. CXR images are low resolution and diagnosis of pneumothorax based on them is error prone. Deep learning-based computer aided diagnosis systems can improve diagnosis performance of pneumothorax. Convolutional Neural Networks (CNNs) are default networks in deep learning-based medical image process. However, CNNs fail to capture long range features. On the other side, Transformer are proposed to exploit long range feature, but they cannot capture local features. In this paper, we propose a general method with a convolution and a transformer module which can classify CXR images to diagnose pneumothorax by extracting local features, global features and global features attended by local ones using a novel architecture. Results show that the proposed method outperforms base architectures and the other previous works.

关键词： Image resolution Convolution Neural networks computer architecture Feature extraction Transformers Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Construction Equipment Performance with Cloud Data Analysis for Predictive Maintenance 6

Construction Equipment Performance with Cloud Data Analysis ...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational systems, RAICS 2024

作者： Seeni, Senthil Kumar Maheswari, P. Konidhala, Jothibabu Suguna, M. Raja Ishwarya, M.V. Srinivasan, S. Cognizant Technology Solutions Department of Mobile Application Development Buffalo GroveIL United States Srm Institute of Science and Technology Faculty of Management Studies Kattankulathur Chennai India University of Technology and Applied Sciences- Al Musannah Department of Electronics and Communication Engineering South Al Batina Musanna Oman Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Agni College of Technology Artificial intelligence and Data science Department Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350381689

The research uses Internet of Things technology for predictive maintenance in the construction sector. The system addresses incorporating Internet of Things sensors into construction machinery to enable real-time monitoring of operating parameters. The study suggests a proactive maintenance strategy that may anticipate equipment breakdowns by examining the data obtained and using sophisticated prediction models. With this strategy, construction teams can arrange maintenance activities systematically, which cuts down on downtime and helps avoid expensive interruptions. The abstract emphasizes the advantages of this practice, which include reducing unexpected downtime as much as possible, extending the life of equipment, and making the most of available resources. The study proves the usefulness of the IoT-based predictive maintenance approach via empirical investigations and the analysis of case studies. This validates the strategy's efficacy, contributing to enhanced equipment performance and increased work efficiency in the construction industry. © 2024 IEEE.

关键词： Predictive maintenance

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：