检索结果-内蒙古大学图书馆

6th International Conference on Image Information Processing, ICIIP 2021

作者： Bhardwaj, Sumit Vats, Shubham Bhardwaj, Jyoti Gupta, Punit Singh, Arjun Amity University Department Electronics and Communication India India Govt. PG Degree College Himachal Pradesh India Manipal University Jaipur Department of Computer and Communication Engineering Jaipur India

ISBN: (纸本)9781665433617

Chronic Obstructive Pulmonary Disease is the 2nd most common genesis of Non-Communicable Diseases (NCD)-related deaths in India. Not everyone had the chance to go to a medical facility or hospital for problems/diseases other than COVID-19 amidst lockdown as there was uncertainty of getting infected by COVID-19. To cater this issue this device/software can detect and diagnose diseases such as pneumonia, heart failure, chronic obstructive pulmonary disease (COPD), emphysema, asthma, bronchitis, foreign body in the lungs or airways etc. This process uses methodology of signal, sound and audio processing and image analysis. Normal sound samples of healthy human body would be taken in consideration and then be compared with the samples of the person whom it is tested on, different levels or frequency range of sounds/body noises that a person makes differs in different analysis, for example 'crackles' these are high pitched breath sounds made when the small air sacs get liquid filled and the person may have pneumonia or a heart failure. This not only work as a warning system that is early but also can reduce human workload and can deplete human error while using a stethoscope for the same. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Smart Residential Load Control Technique with Internet of Things and Pattern Recognition Based Load Identification

A Smart Residential Load Control Technique with Internet of ...

引用

IEEE Applied Signal Processing Conference (ASPCON)

作者： Sayan Datta Shreerup Bhowmick Suman Datta Swastik Chatterjee Satwik Ghosh Biswarup Ganguly Arunava Chatterjee Soumyadeep Garai Department of Electrical Engineering Meghnad Saha Institute of Technology Kolkata India Department of Electrical Engineering National Institute of Technology Silchar Silchar Assam India Department of Electrical Engineering Raghunathpur Govt. Polytechnic India School of Material Science and Nano Technology Jadavpur Univeristy Kolkata India

This paper presents a design of a smart home automation system (HAS) for non-intrusive load monitoring (NILM) with load identification. The proposed framework aims to develop an internet-of-things (IoT) based home automation system, where various home devices can be controlled with the help of voice activated remote control. The development of a firmware for smart control is done by minimizing human intervention for preserving the integrity for all electrical appliances in a smart home. NodeMCU based IoT platform has been employed for execution of the automation process. The proposed system possesses various sorts of sensors installed for operating loads based on the discomfort level of the individuals. Moreover, pattern recognition-based load identification is also proposed along with the control of home appliances. Experimental results of the proposed system outperform other IoT protocols in terms of energy consumption and cost reliability. The developed prototype supports user friendly interface with relatively low-cost design and ease of installation. The developed module is a generic one that could be a good contender for helping impaired people.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Life Analysis of the Electric Vehicles using IoT - computer-Based Smart Systems 2

Real-Time Life Analysis of the Electric Vehicles using IoT -...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Neeraja, Bathala Ralte, Hmingthanpuii Jain, Kirti Surlekar, Samarth Ramchandra Arani, Dinesh Ashok Mabborang, Romie C. Government Polytechnic Electrical and Electronics Engineering Dept Telangana Hyderabad India Govt. Mizoram Law College Affiliated to Mizoram University Mizoram India School of Advanced Computing Sanjeev Agrawal Global Educational University Madhya Pradesh Bhopal India National Institute of Technology Department of Electrical- High Voltage Engineering Kerala Calicut India Manglayatan University Uttar Pradesh Aligarh India Pamantasan Ng Lungsod Ng Maynila University of the City of Manila Mathematics Department Manila Philippines

ISBN: (纸本)9798350369960

Most significant automobile manufacturers are now interested in developing Electric Vehicles (EVs). The improvements in battery life and low emissions of EVs have sparked a lot of attention in recent years. Similarly, the growth of the Internet of Things (IoT) made it possible for an increasing number of devices to be connected. However, the autonomy and lack of infrastructure in most locations outside of major cities are one of the consumer concerns regarding adopting EVs. This study's primary objective is to explore how IoT-based systems may be used to analyze real-world usage data for EVs. The systematic literature review was the methodology utilized in this research. This study found that IoT technology has enormous potential for use in advancing and developing the Smart Grid. EVs are a type of dynamic electrical energy storage system that is pretty common due to their excellent electrical properties and flexibility. Still, their mass adoption significantly impacts the grid and poses a risk of damaging their batteries in the event of overcharging or deep discharging. EV batteries require a particular state of charge prediction to reduce the risk of damage, allowing them to have a longer lifespan and protect the devices they power. With the aid of a real-time Battery Monitoring System (BMS) that uses the coulomb counting method for State of Charge (SoC) estimate, a comparison between three techniques-Node-Red, Message Queuing Telemetry Transport (MQTT), and Arduino approach-is studied in this study based on their ease of implementation and overall lack of complexity. © 2023 IEEE.

关键词： BMS IoT MQTT SoC Estimation

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network-Based Fingerprint Reformation for Minimizing Displacement

Deep Neural Network-Based Fingerprint Reformation for Minimi...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Munish Kumar Sandeep Kumar Monali Gulhane Rajender Kumar Beniwal Nitin Shilpha Choudhary Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Department of CSE Symbiosis Institute of Technology (SIT) Nagpur Symbiosis International (Deemed University) (SIU) Pune India Electrical and Electronics Engineering Guru Jambheshwar University of Science and Technology Hisar Haryana India Department of Computer Engg. Govt. Polytechnic Hisar Haryana Department of Computer Science and Engineering(AI & ML) Neil Gogte Institute of Technology Hyderabad India

In the realm of biometric authentication and forensic analysis, the accurate matching of fingerprints is paramount. Fingerprint displacement, caused by factors such as skin elasticity and pressure during touch, has been a significant challenge in achieving precise fingerprint recognition both during the enrollment and the authentication process. This research presents a technique to address this issue by leveraging Support Vector Machines (SVM) for fingerprint transformation and displacement minimization. The proposed methodology involves the extraction of distinctive fingerprint features and the application of SVM-based algorithms to realign and correct fingerprint distortions resulting from displacement. We analyze the effectiveness of SVM in reducing displacement-induced errors and improving matching accuracy. Experimental results demonstrate the potential of SVM-based fingerprint transformation techniques to significantly enhance the robustness and reliability of fingerprint recognition systems. This research contributes to the ongoing efforts in biometrics and forensic science by providing a practical solution to the problem of fingerprint displacement, with potential applications in identity verification, criminal investigations, and security systems. The findings of this study offer a promising avenue for further research and development in the field of biometric authentication, ultimately leading to more accurate and secure identification methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Performance Analysis of Ensemble Learners on BCD Dataset

Predictive Performance Analysis of Ensemble Learners on BCD ...

引用

2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society, TRIBES 2021

作者： Lalotra, Gotam Singh Kumar, Vinod Rajput, Dharmendra Singh Govt. Degree College Basohli Department of Computer Science Jammu and Kashmir India Koneru Lakshmaiah Education Foundation Computer Science and Engineering VaddeswaramAP India School of Inforation Technology and Engineering Vellore institute of Technology Vellore India

ISBN: (纸本)9781665433426

Breast cancer disease (BCD) has now become a worldwide disease in human beings. The breast cancer cases are progressively rising especially in females. Initial detection of this disease can save a patient's life and cost of treatment. There are many clinical diagnosis methods which are used for the detection of breast cancer. Among them supervised machine learning is a very powerful mechanism that helps in predicting the presence or absence of disease based on the laboratory test data of the patient. Presently, numerous machine learning algorithms are available for classifying the disease in patients, but the best amongst all is yet to be explored. Therefore, this research work contributes to find the outperforming model from six non-ensemble methods and four ensemble methods for breast cancer detection. This study claims AdaBoost the most stable and suitable model for BCD prediction with accuracy 97.1%, precision, recall, F1-measure and AUC 95.91 %. © 2021 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Implementation of Trust-Based Novel Approach for Security Enhancements in MANETs

引用

SN computer Science 2021年第4期2卷 257页

作者： Usha, M.S. Ravishankar, K.C. Department of Computer Science and Engineering VTU-RRC Visvesvaraya Technological University Belagavi and NIE Institute of Technology Karnataka Mysuru India Department of Computer Science and Engineering Govt. Engineering College Hassan and VTU-RRC Visvesvaraya Technological University Karnataka Belagavi India VTU-RRC Visvesvaraya Technological University Belagavi India

MANET is completely a unique, self-sustained wireless communication network. It can be created when necessary without any infrastructural support. Mobile ad hoc networks (MANETs) have many nodes with good network communication capabilities. Being self-organizing in nature, the secured way of transferring the data is an important issue in case of multi-hop wireless networks in real-time systems. Hence, trust confirmation among MANET nodes is the major concern beneath bandwidth limitations, energy and dynamic topology. The malevolent nature prompts the insecure data transfer by reducing the degree of trust among the nodes, leads to a lot of energy consumptions and decreases the network link lifetime. Hence proposed, a unique Novel Energy Efficient Trust Aware Routing (NETAR) for traditional AODV protocol to improve the three degrees of trust among the nodes in MANET using neighbour-node trust rate estimation, bandwidth calculation, energy and malicious behaviour predictions with certain performance measurements to improve the Network Link Life Time (NLT) like Packet Delivery Ratio (PDR), end to end delay, false positive and throughput. The NS2 simulator tool is used. The simulation results show the improved performance of the proposed NETAR protocol compared to the existing protocols. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Ad hoc on-demand distance vector (AODV) MANET security Mobile ad hoc networks (MANETs) NETAR (novel energy-efficient trust aware routing) Trust management

来源：评论

学校读者我要写书评

暂无评论

Crop Monitoring and Automatic Weed Detection using Drone

Crop Monitoring and Automatic Weed Detection using Drone

引用

2021 International Conference on Control, Automation, Power and Signal Processing, CAPS 2021

作者： Hafeez, Abdul Tiwari, Vikas Verma, Vinod Kumar Ansari, Akhtar Saleem Husain, Mohammed Aslam Singh, S.P. Khan, Ahmad Neyaz Rajkiya Engineering College Dept. Electrical Engineering Ambedkar Nagar India Govt Polytechnic Ambedkar Nagar India Integral University Department of Computer Science Lucknow India

ISBN: (纸本)9781665445771

The effective farming means lossless farming which is a desired need of current scenario, since the cost of farming is increasing continuously. Weeds are a big problem in agriculture because it is major part of agricultural losses. Nowadays, herbicides are sprayed uniformly throughout the field to control the weed. This method is not only expensive but also have bad impacts on environment and human health. Therefore, an automatic system is needed for spot spray. Improvement in drone technology leads to availability of high payload drone that are suitable for pesticides spraying. Embedded system programed with deep learning when use to control the drone then it will be possible to spray the herbicides at desired place. This paper discusses the artificial intelligence (AI) based crop monitoring and weed detection system that are suitable for spot herbicides spraying. © 2021 IEEE.

关键词： Herbicides

来源：评论

学校读者我要写书评

暂无评论

Implementation of ML Algorithm for Mung Bean Classification using Smart Phone

Implementation of ML Algorithm for Mung Bean Classification ...

引用

2022 International Conference on Business Analytics for Technology and Security, ICBATS 2022

作者： Shahid, Muhammad Munir, Kashif Muneer, Salman Mutiullah Jarrah, Muath Farooq, Umer Govt. Se College Department of Physics Bahawalpur Pakistan Khawaja Fareed University of Engineering and Information Technology Department of Computer Engineering Rahim Yar Khan Pakistan Ncbae School of Computer Science Lahore Pakistan Khawaja Fareed University of Engineering and Information Technology Faculty of Computer Science and Information Technology Rahim Yar Khan Pakistan Skyline University College University City Sharjah School of Information Technology Sharjah1797 United Arab Emirates Lahore Garrison University School of Computer Science Lahore Pakistan

ISBN: (纸本)9781665409209

This work is an extension of my work presented a robust and economically efficient method for the discrimination of four Mung-Beans varieties based on quantitative parameters, Due to the advancement of technology day by day users try to find the solutions to their daily life problems using smartphones but still there is limited resources are available in smartphone concerning computing power and memory so there is need to find the best classifier which can classify the Mung-Beans using already suggested features in previous work with minimum memory requirements and computational power. For achieving the goal of this study, we take the experiments on various supervised classifiers which have simple architecture and calculations and give the robust performance on the most relevant 10 suggested features are selected by Fisher Co-efficient, Probability of Error, Mutual Information, and wavelet features. After the analysis, we replace the Artificial Neural Network and Deep learning with such a classifier which gives approximately the same classification results as the above classifier but is efficient in terms of resources and time complexity. This classifier is easily implemented in the smartphone environment. © 2022 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Cluster radioactivity in trans-lead region: A systematic study with modified empirical formulas

arXiv

引用

arXiv 2022年

作者： Jain, A. Sharma, P.K. Jain, S.K. Deegwal, J.K. Saxena, G. Department of Physics School of Basic Sciences Manipal University Jaipur Jaipur303007 India College Jaipur302004 India Govt. Women Engineering College Ajmer305002 India Govt. Polytechnic College Rajsamand313324 India Govt. Women Engineering College Ajmer305002 India Department of Physics Faculty of Science University of Zagreb Bijenicka c. 32 Zagreb10000 Croatia

The possibility of cluster emission from trans-lead (86≤Z≤96) region of periodic chart has been explored comprehensively by employing few empirical formulas which are modified by adding angular momentum (l) or isospin-dependent (I = (N - Z)/A) or both terms for the calculation of cluster decay half-lives. These modified versions of the formulas are found with lesser χ2 per degree of freedom and root mean-square error, in addition to the smaller values of some other statistical parameters, while compared to their corresponding old versions on available 61 experimental data of cluster radioactivity. By applying the modified version of the formula given by Balasubramaniam et al. [PRC 70 (2004) 017301], the most accurate formula among these, half-lives of several clusters i.e. isotopes of Be, B, C, N, O, F, Ne, Na, Mg, and Si are predicted systematically for the several isotopes in the trans-lead region. The contest of cluster emission with α-decay has been investigated in form of branching ratio which brings several potential cluster emissions into the probable decay modes of these nuclei. The accurate prediction of half-lives of such clusters is expected to be crucial for the future experimental observations where α-decay is observed dominantly. © 2022, CC0.

关键词： Isotopes

来源：评论

学校读者我要写书评

暂无评论

Preserving Data Integrity and Security in IoT-Enabled Wireless Sensor Networks: Employing an Intrusion Detection System Strategy

Preserving Data Integrity and Security in IoT-Enabled Wirele...

引用

Smart Power Control and Renewable Energy (ICSPCRE), IEEE International Conference on

作者： M. Vaithiyanathan Naduvathezhath Nessariose Jose C.S. Sasireka Pooja Mishra T. Prabahar Godwin James Nookala Venu Department: Information Technology Sri Sai Ram Engineering College Regent Strategic Solutions Rochester USA Department Of Computer Science and Engineering SRM Institute of Science and Technology Management and Research DY Patil Institute of Engineering Pune Department Of Computer Science and Engineering Sri Sairam Institute of Technolgoy Centre for IoT Madhav Institute of Technology & Science (MITS) A Govt. Aided UGC Autonomous Institute Gwalior Madhya Pradesh India

ISBN: (数字)9798350377002

ISBN: (纸本)9798350377019

The proliferation of IoT-enabled wireless sensor networks (WSNs) has ushered in a multitude of applications but has also heightened concerns regarding data integrity and security. This underscores the critical necessity for robust Intrusion Detection Systems (IDS) tailored explicitly for such environments. This study presents an innovative IDS framework designed to safeguard the integrity and security of data within -enabled. Our IDS framework introduces advanced machine learning techniques and anomaly detection algorithms to enable real-time monitoring and analysis, effectively identifying and mitigating potential threats. Through extensive experimentation and validation, we demonstrate the reliability and efficacy of our IDS in detecting various intrusion attempts while minimizing false alarms. Moreover, our framework incorporates adaptive mechanisms to address evolving threats and network dynamics, ensuring continuous protection against malicious activities. By enhancing the resilience of IoT-enabled WSNs against intrusions, our research contributes to bolstering trust and reliability in critical applications.

关键词： Wireless sensor networks Machine learning algorithms Data integrity Heuristic algorithms Intrusion detection Machine learning Real-time systems

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：