检索结果-内蒙古大学图书馆

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Yogi, Kottala Sri Gowda V, Dankan Manoj Kumar, S.B. Nithya, R. Begum, A.Yasmine Suganthi.n Symbiosis Institute of Business Management Hyderabad Symbiosis International University Department of Operations Pune India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Bgsit Adichunchanagiri University Faculty of Engineering Management & Technology Dept. of Ece Karnataka 571448 India Vivekanandha College of Engineering for Women Department of Computer Science and Engineering Tamilnadu Namakkal India Mohan Babu University School of Engineering Department of Electronics and Communication Engineering Tirupati India Dayananda Sagar College of Engineering Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350364569

This paper presents how IoT plays a vital role in improving delivery of healthcare services especially through remote patient monitoring and telemedicine. The proposed system also employs IoT devices aimed at passing various health indicators like;pulse rate, blood glucose levels, blood pressure, and physical activity to continually and objectively provide real-time data in the body. This particular study, the participants with chronic diseases, normal population and elderly people also participated in the test of the system. Some of the findings include;it is possible to measure the daily steps corresponding to the a calorie expenditure, the sleep score ranging between 60-80 and oxygen saturation percentages ranging from 96%-99% in various postures. The system also proved the correlation between the percentage of variation in ambient temperature and the percentage of variation in the pulse rate which was quite sensitive to the changes in temperatures. Based on these observations, it is possible to conclude that IoT-based monitoring can improve patient's conditions as long as underlying issues will be detected at an early stage and necessary actions will be taken in time. The study also also demonstrates the application of telemedicine in making healthcare more accessible especially for the people from rural settings or in developing countries. The results show a good direction regarding the future of the system;however, security issues, privacy relating to data as well as integration are key hurdles in this connection. © 2024 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Low Latency Single-Cycle EOG Classification Using Cascaded ANN & CNN

Low Latency Single-Cycle EOG Classification Using Cascaded A...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Wakim Sajjad Sakib Abdullah Bin Shams Md. Rifatuddin Romel Raisa Tasrin Ridi Mohammad Liton Hossain Dept. of Electronics and Communication Engineering Institute Of Science and Technology Dhaka Bangladesh Dept. of Electrical & Computer Engineering University of Toronto Toronto Canada Dept. of Aeronautical Engineering Military Institute of Science and Technology Dhaka Bangladesh Dept. of Computer Science and Engineering American International University - Bangladesh Dhaka Bangladesh Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Electrooculography (EOG) is a noninvasive method to record the motion of the eye from the electrical potential difference between the cornea and retina. This technique, paired with AI, is extensively utilized predominantly in assistive technologies. The complexity of AI-driven EOG analysis scales with the number and type of expected eye movements. This challenge intensifies when the detection of eye movements relies solely on a single EOG cycle. An essential metric for real-time applications is the latency of an AI algorithm, which refers to the delay in making predictions. The latency should be smaller than the average human visual reaction time for any AI-driven system to promptly respond. The majority of EOG classification studies tend to overlook latency. In this experimental study, we overcome this multi-facet problem by proposing cascaded Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) architectures that have latency smaller than average human reaction time. Also, we developed a generalized & robust signal processing method to correctly identify single EOG cycle and deliver high prediction performances with either ANN or CNN. To demonstrate, we successfully classified nine distinct eye movements based only on single cycle EOG signal, with the performance metrics reaching close to 100% for both ANN & CNN, and latency well below the reaction time.

关键词： Measurement Electrooculography Wheelchairs Signal processing algorithms computer architecture Prediction algorithms Real-time systems Classification algorithms Convolutional neural networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Efficient Energy Management Algorithm for Single Stage SPV Based Water Pumping system Without Batteries

Efficient Energy Management Algorithm for Single Stage SPV B...

引用

2024 International Conference on Sustainable Power and Energy, ICSPE 2024

作者： Krishna, T. Murali Trrad, Issam Harish, Cholleti Nimer, Hamsa Al-Mattarneh, Hashem Monisha Jothi, R. Ravindra, J.V.R. Chaitanya Bharati Institute of Technology Department of EEE Telangana Hyderabad India Jadara University Department of Computer and Communication Engineering Irbid Jordan Yarmouk University Department of Civil Engineering Irbid Jordan New Prince Shri Bhavani College of Engineering and Technology Dept. of CSE Tamil Nadu Chennai India Vardhaman College of Engineering Department of ECE Telangana Hyderabad India

ISBN: (纸本)9798350366051

Solar Photovoltaic (SPV) based standalone water pumping systems especially without batteries are becoming more popular due to its feature. The SPV system output power is always varying and depends on solar irradiance which cannot be regulated and unpredictable. Hence, standalone water pumping system without integrating any storage device is a challenging task. Further, an appropriate control method must be required to regulate speed of the motor according to power available from SPV system. In this paper an induction motor is considered and developed a novel energy management algorithm to operate battery less standalone water pumping system powered by SPV system. To obtain higher efficiency and utilization, maximum power point tracking (MPPT) device is also developed. A single stage water pumping system is developed by integrating control of inverter to MPPT algorithm. The dc-link voltage is also regulated along with speed of the induction motor by proposed control methodology. A multi motor-pump sets are considered for the application of agriculture. In order to get an effective operation, deloading concept is also included in the proposed control method. Various results are demonstrated by performing OPAL-RT modules based hardware-in the-loop. © 2024 IEEE.

关键词： Solar concentrators

来源：评论

学校读者我要写书评

暂无评论

Design of Energy Selective Surface Guided by Theory of Characteristic Modes

Design of Energy Selective Surface Guided by Theory of Chara...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Zihao Ning Mengmeng Li Dazhi Ding Chao-Fu Wang Dept. of Information and Communication Engineering Nanjing University of Science and Technology Nanjing China Dept. of Electrical and Computer Engineering National University of Singapore Singapore

A characteristic mode (CM) guided design of high-performance energy selective surface (ESS) is presented in this paper. Due to the nonlinear nature of loading diodes, the ESS can provide a passband for the low-intensity radiation field (LIRF) and a stopband for the high-intensity radiation field (HIRF). The design of the ESS is guided by the theory of characteristic modes (TCM), investigated by analyzing an equivalent circuit model, and then verified using field-circuit cosimulation. The results confirm that the transmitted power decreases remarkably at input power levels above 15 dBm. Such a property offers great potential as a protective screen for electronic devices from HIRF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implications of Resource Optimization in D2D communication for Efficient Usage of RF Energy: Practice and Challenges

Implications of Resource Optimization in D2D Communication f...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Devasis Pradhan Suma C Rajeswari Celso Barbosa Carva Dept. of Electronics & Communication Engineering Acharya Institute of Technology Bangalore India Dept. of Electronics & Computer Engineering Federal University of Amazonas Amazonas Brazil

In order to meet the requirements of fourth generation (4G) and fifth generation (5G) technologies, the device-to-device (D2D) communication system is crucial. D2D communication makes use of communicating devices that are close by in order to make better use of the resources that are available, reduce latency, increase data rates, and expand system capacity at the same time. D2D's development is driven by the mobile operator's actions to collect short-range communications for network performance enhancement and maintenance of proximity-based services. The number one goal of the observe is to provide a complete evaluate of latest trends in a variety of D2D domain names, aid allocation and optimization for D2D packages for 5G technologies, interference management, strength manipulate strategies, and the invention technique for sustainable verbal exchange in 5G community with effective usage of energy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heart Attack Detection And Alerting system

Heart Attack Detection And Alerting System

引用

communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Aarthi Elaveini Pragadeesh E Bhavesh Aglecha Metha G P Dept of Electronics and Communication Engineering SRM Institute of Science and Technology Chennai India Dept. of Electronics and Computer Engineering SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

This research presents a cutting-edge IOT-based heart attack detection and alerting system. It combines a number of sensors to continuously track vital indicators in the present. The device identifies physiological parameter irregularities that may be signs of a probable heart attack through a carefully crafted algorithm. Instant notifications are sent via IOT-enabled systems to the patient's family and designated healthcare professionals upon identification. The goal of the technology is to drastically shorten response times during critical cardiac episodes, allowing for timely medical intervention. This technology attempts to improve early detection by utilizing sensor data and IoT connectivity, thereby reducing the severity of heart attacks and raising the chance of successful intervention and patient survival.

关键词： Cardiac arrest Medical services Sensor phenomena and characterization Sensor systems Real-time systems Sensors Telecommunication computing Time factors Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

Predicting Lung Cancer with Artificial Neural Network: Analyzing Performance and Feature Importance

Predicting Lung Cancer with Artificial Neural Network: Analy...

引用

Cognitive Computing in engineering, communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Vatsal Mehta Varun M Ashwini Kodipalli Roshan Joy Martis Shridhar B. Devamane Ushasree. A Dept. of AI & Data Science Global Academy of Technology Bangalore Karnataka India Dept. of Electronics & Communication Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science School of Computing Mysuru Dept. of Computer Science & Engineering Gokaraju Lailavathi Engineering College Hyderabad India

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Lung cancer is the primary cause of cancer-related deaths globally. This cancer is majorly observed in smokers, increasing air pollution has also begun to affect non-smokers. Research indicates that exposure to polluted air significantly raises the risk of developing lung cancer, posing a major threat to public health. Despite advancements in medical technology, the mortality rate from lung cancer remains high, highlighting the importance of early diagnosis. Machine learning and deep learning offer promising solutions for early and accurate prediction through advanced data analysis. In our study, we utilized a dataset with 26 attributes for discern lung cancer, categorizing cases into three risk levels: high, medium, and low. We applied various algorithms and develop an Artificial Neural Network (ANN), comparing the overall performance with various machine-learning and deep-learning models. Our results show that the ANN achieved a high accuracy of 94.9% using the Adam optimizer, making it an effective model for lung cancer prediction.

关键词： Deep learning Accuracy Computational modeling Biological system modeling Lung cancer Mortality Artificial neural networks Predictive models Prediction algorithms Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection of Singing Voices With Whisper Encodings

arXiv

引用

arXiv 2025年

作者： Sharma, Falguni Gupta, Priyanka Centre for Artificial Intelligence Banasthali Vidyapith Jaipur India Dept. of Communication and Computer Engineering The LNM Institute of Information Technology Jaipur India

The deepfake generation of singing vocals is a concerning issue for artists in the music industry. In this work, we propose a singing voice deepfake detection (SVDD) system, which uses noise-variant encodings of open-AI’s Whisper model. As counter-intuitive as it may sound, even though the Whisper model is known to be noise-robust, the encodings are rich in non-speech information, and are noise-variant. This leads us to evaluate Whisper encodings as feature representations for the SVDD task. Therefore, in this work, the SVDD task is performed on vocals and mixtures, and the performance is evaluated in %EER over varying Whisper model sizes and two classifiers-CNN and ResNet34, under different testing conditions. © 2025, CC BY-NC-ND.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection of Singing Voices With Whisper Encodings

Deepfake Detection of Singing Voices With Whisper Encodings

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Falguni Sharma Priyanka Gupta Centre for Artificial Intelligence Banasthali Vidyapith Jaipur India Dept. of Communication and Computer Engineering The LNM Institute of Information Technology Jaipur India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Industries Deepfakes Signal processing Encoding Acoustics Noise robustness Speech processing Testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Intrusion Detection in a Limited Labeled Data Scenario: An Active Learning Approach

Enhancing Network Intrusion Detection in a Limited Labeled D...

引用

Computing, Applications and systems (COMPAS), IEEE International Conference on

作者： Md Sharafat Hossain Md Al Amin Hossain Md Shahin Sikdar Md Saiful Islam Institute of Information and Communication Technology Bangladesh University of Engineering and Technology Dhaka Bangladesh Dept. of Information Technology Engineering Selcuk University Konya Turkiye Dept. of Computer Science and Engineering Prime University Dhaka Bangladesh

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

The Internet was originally developed to facilitate easier communication through digital devices. It has made our lives easier by providing means for communication and delivering digital resources anywhere and at any time in the world. However, the internet also exposes users to the risk of criminals exploiting various vulnerabilities in the internet system, launching sophisticated attacks to gain valuable information and hamper users’ lives. Henceforth, an effective intrusion detection system (IDS) is imperative for safeguarding the data and resources of users in the cyber world. This research aims to enhance semi-supervised IDS models by leveraging limited labeled data and unlabeled data and exploring innovative approaches to improve adaptability and accuracy in detecting known and emerging threats, particularly in scenarios with limited labeled data available. Our study uses the UNSW-NB15 dataset, and the results show that our suggested active learning-based semi-supervised model, which was created with 2000 labeled data, is better than the supervised model that uses the same number of labeled data. The proposed model achieved an accuracy score of 97.67% while existing studies achieved an accuracy score of 94.61%.

关键词： Adaptation models Accuracy Computational modeling Active learning Personal digital devices Network intrusion detection Benchmark testing Data models Internet computer crime

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：