检索结果-内蒙古大学图书馆

Human activity recognition based on hybrid learning algorithm for wearable sensor data

Measurement: Sensors 2022年 24卷

作者： Athota, Ravi Kumar Sumathi, D. Ph.D. Research Scholar School of Computer Science and Engineering VIT-AP University AP Vijayawada India Associate Professor Grade-2 School of Computer Science and Engineering VIT-AP University AP Vijayawada India

Human Activity Recognition (HAR), based on sensor devices and the Internet of Things (IoT), attracted many researchers since it has diversified applications in health sectors, smart environments, and entertainment. HAR has emerged as one of the important health monitoring applications and it necessitates the constant usage of smartphones, smartwatches, and wearable devices to capture patients' daily activities. To predict multiple human activities, deep learning (DL)-based methods have been successfully applied to time-series data that are generated by smartphones and wearable sensors. Although DL-based approaches were deployed in activity recognition, they still have encountered a few issues when working with time-series data. Those issues could be managed with the proposed methodology. This work proposed a couple of Hybrid Learning Algorithms (HLA) to build comprehensive classification methods for HAR using wearable sensor data. The aim of this work is to make use of the Convolution Memory Fusion Algorithm(CMFA) and Convolution Gated Fusion Algorithm(CGFA) that model learns both local features and long-term and gated-term dependencies in sequential data. Feature extraction has been enhanced with the deployment of various filter sizes. They are used to capture different local temporal dependencies, and thus the enhancement is implemented. This Amalgam Learning Model has been deployed on the WISDM dataset, and the proposed models have achieved 97.76%, 94.98% for smartwatch and smartphone of CMFA, 96.91%, 84.35% for smartwatch and smartphone of CGFA. Experimental results show that these models demonstrated greater accuracy than other existing deep neural network frameworks. © 2022 The Authors

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Machinability investigation and optimizing process parameters in ECM of stainless steel −12X18H10T for minimizing surface roughness

引用

Materials Today: Proceedings 2023年 81卷 443-448页

作者： A Jerin K Karunakaran Research Scholar Department of Mechanical Engineering School of Engineering Vels Institute of Science Technology and Advanced Studies (Deemed to be University) Vels University Chennai TN India Research Supervisor & Associate Professor Department of Mechanical Engineering School of Engineering Vels Institute of Science Technology and Advanced Studies (Deemed to be University) Vels University Chennai TN India

The tool and die applications are preferred the unconventional machining processes as they are popular in machining the difficult to cut type complex contour/ profile. The complex profile machined on hard material. Some special materials like Stainless Steel 12X18H10T withstand its inherent properties even it exposes at higher temperature. This investigation aims to expand its application by investigating its machinability in Electro Chemical machining process for surface finish. The process parameters like gap between work material and tool, discharge current, concentration of electrolyte and applied voltage at three levels. The Taguchi approach is used for optimizing the process parameters and confirmation runs also conducted for developing the mathematical modelling. For optimizing number of experiment the Taguchi L9 is utilized for this investigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Crop yield prediction using effective deep learning and dimensionality reduction approaches for Indian regional crops

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2024年 8卷

作者： Subramaniam, Leelavathi Kandasamy Marimuthu, Rajasenathipathi Research Scholar Department of Computer Science Nallamuthu Gounder Mahalingam College (NGMC) Affiliated to Bharathiar University Pollachi Tamilnadu India Associate Professor Department of Computer Science Nallamuthu Gounder Mahalingam College (NGMC) Affiliated to Bharathiar University Pollachi Tamilnadu India

Crop yield prediction (CYP) at the field level is crucial in quantitative and economic assessment for creating agricultural commodities plans for import-export strategies and enhancing farmer incomes. Crop breeding has always required a significant amount of time and money. CYP is developed to forecast higher crop production. This paper proposes an efficient deep learning (DL) and dimensionality reduction (DR) approaches for CYP for Indian regional crops. This paper comprised ‘3′ phases: preprocessing, DR, and classification. Initially, the agricultural data of the south Indian region are collected from the dataset. Then preprocessing is applied to the collected dataset by performing data cleaning and normalization. After that, the DR is performed using squared exponential kernel-based principal component analysis (SEKPCA). Finally, CYP is based on a weight-tuned deep convolutional neural network (WTDCNN), which predicts the high crop yield profit. The simulation outcomes shows that the proposed method attains superior performance for CYP compared to exiting schemes with an improved accuracy of 98.96 %. The novelty of the proposed approach lies in the combination of DL, DR, and WTDCNN techniques for accurate crop yield prediction, specifically tailored for Indian regional crops. © 2024 The Authors

关键词： Crop yield prediction Deep convolutional neural network Deep learning Machine learning Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

GAN-CNN Ensemble: A Robust Deepfake Detection Model of Social Media Images Using Minimized Catastrophic Forgetting and Generative Replay Technique

引用

Procedia computer science 2024年 235卷 948-960页

作者： Preeti Sharma Manoj Kumar Hitesh Kumar Sharma Research Scholar School of Computer Science University of Petroleum and Energy Studies (UPES) Dehradun 248007 India Associate Professor Faculty of Engineering and Information Sciences University of Wollongong in Dubai UAE MEU Research Unit Faculty of Information Technology Middle East University Amman 11831 Jordan

Deep-fake photographs are difficult to discern from real ones, especially when utilized in social media platforms. Anyone can willfully create disinformation about public personalities, politicians, and celebrities using these deep fake photographs. So, it is an important need of society to work for an effective model for its detection. The models for deep fake detection commonly use CNN-based detectors. These detectors experience a drop in performance when used for transfer learning or continual learning techniques. A significant limitation in this process is CNN's catastrophe forgetting defect. For the solution of this problem, a Generative replay technique in the form of a GAN-CNN model is implemented that works to minimize this catastrophe forgetting issue that further helps for better detection. It involves generating and storing samples from previous tasks and then replaying them during the training of new tasks which makes CNN more robust to identify deep fakes. The GAN model used in this work is traditional DCGAN improved with necessary adjustments to achieve training stability. It is observed that the model attained a good accuracy of 98.67%(training),70.08% (testing) and minimum loss with a value of 0. 0337 for 100 epochs. Also, it acquired good precision values of 68% and 72%, Recall values are 74% and 66%, and F1 scores of 71% and 69% for classes 0 and 1 respectively. The model outcome is found stable and reliable in deep fake detection under dynamic training conditions. Optimum values of evaluation parameters ensure the model's capacity to learn new tasks preserving the existing task-learning knowledge.

关键词： Deep Learning CNN GAN Catastrophe forgetting CNN continual learning Lifelong learning GAN-CNN deep fake detector

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Cloud Architecture Using Machine Learning 4

Intrusion Detection in Cloud Architecture Using Machine Lear...

引用

4th International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

作者： Govinda Rajulu, G. Santhoshkumar, R. Venkatesan, D. Kalvikkarasi, S. Santosh Kumar Patra, P. St. Martin's Engineering College Department of Computer Science and Design India St. Martin's Engineering College Department of Artificial Intelligence and Data Science India St. Martin's Engineering College Department of Artificial Intelligence and Machine Learning Department of CSE India Podhagai College of Engineering & Technology Professor in Ece Department India St. Martin's Engineering College India

ISBN: (纸本)9781665474368

The research of Intrusion Detection Systems is known to be among the most challenging aspects of Cloud Security. In the context of the cloud, security breaches such as denial of service, scanning, injection of malicious code, viruses, worms, and the breaking of passwords are becoming increasingly commonplace. In the event that these attacks are not stopped in a timely manner, the company's reputation may be put in jeopardy, and it may sustain financial harm. As a consequence of this, it is essential to safeguard the cloud against dangers of this kind. In this research, we provide solutions to defend cloud systems by incorporating some of the most successful methods of intrusion detection. Within IDS, our primary focus has been placed on two critical aspects: the effectiveness of the detection techniques and the pace of detection. In order to overcome these obstacles, we suggest utilising machine learning in conjunction with parallelization. Approaches based on machine learning gain information from the data itself, hence diminishing the significance of the human expert. In order to identify intrusions, statistical models, safe system approaches, neural networks, and a variety of other methods are utilised. The purpose of this study is to improve the accuracy of intrusion detection in cloud computing by presenting a new approach to intrusion detection that is based on existing intrusion detection systems and the various architectures that those systems employ. © 2022 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection system in distributed cloud computing: Hybrid clustering and classification methods

引用

Measurement: Sensors 2023年 25卷

作者： Samunnisa, K. Kumar, G. Sunil Vijaya Madhavi, K. Research Scholar Department of Computer Science and Engineering JNTUA A.P Anantapur India Professor of CSE & Dean - CSE and Allied Departments Lords Institute of Engineering & Technology Telangana Hyderabad India Professor & HOD of CSE Department JNTUA College of Engineering A.P Anantapur India

Cloud Computing is popular nowadays due to its storage and data access services. Security and privacy are prime concerns when network threats increase. Cloud computing offers organizations and enterprises a scalable, flexible, and cost-effective infrastructure to store data on the Web. An anomaly-based IDS implementation protects the integrity of the data in a database by identifying and quarantining records when something appears to have changed unexpectedly. Machine learning based clustering and classification methods are used for anomaly based IDS attack classification and scalability in advanced networking environments. Machine learning is a fast, efficient, and adaptable approach to develop intrusion detection models that can deal with emerging threats, i.e., known and unknown attacks (including zero-day attacks). This paper proposes an efficient Hybrid clustering and classification models for implementing an anomaly-based IDS for malicious attack type classifications such as normal (no intrusion), DoS, Probe, U2R, and R2L using threshold-based functions, and the results are tested with two different threshold values (e), 0.01 & 0.5. The experiments have been performed on two tested datasets, namely, NSL-KDD and KDDcup99. Detection rate, False alarm ratio, and accuracy have been used to study the performance of the proposed methodology. After applying the proposed approach, the K-means with random forest has been shown at two different threshold values to have a better classification accuracy, detection rate, and false alarm rate of 99.85%, 99.78% and 0.09% on the NSL-KDD dataset and 98.27%, 98.12% and 2.08% respectively on the KDDcup99 dataset. © 2022 The Authors

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Impact of the Intelligent Control System in Assisting Humans Regarding Complex Information Processing 4

Impact of the Intelligent Control System in Assisting Humans...

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Ambika, R. Lahane, Prashant Kumar, G. Rabbi, Fazle Maarif, Muhammad Anas Qureshi, Mohmad Kashif Bms Institute of Technology and Management Department of Ece India Mit World Peace University Faculty of Engineering India Srm Institute of Science and Technology Department of Management India Australian Computer Society Australia Institut Pesantren Kh. Abdul Chalim Pacet Mojokerto Indonesia Sanskriti University Computer Science & Engineering Professor Cum Data Scientist India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Intelligent control system is a control technique that utilises different computing approaches such as fuzzy logic, Bayesian probability, neural networks and machine learning. Information processing is change of information within a manner detectable through an observer. It describes everything that happens in universe from falling of rocks to printing text files from a digital computer system. This paper aimed to analyse the impact of intelligent control systems (ICS) to assist humans with complex information systems. In order to achieve this aim, the paper has conducted a literature review to understand other authors' perspectives. It has discussed concept of ICS and its role in assisting information systems. Additionally, the paper has analysed information processing and other information about it. In order to collect relevant data on selected research topic, paper has conducted a secondary data collection method. It has selected data from secondary resources and analysed data with help of thematic analysis. This data analysis method helped to understand data patterns on selected research topic. Based on data analysis, results found that key methods in intelligence control are fuzzy control, neural network control, and expert control and these controls offer useful and relevant programming regarding complex information systems. Additionally, intelligent control can adapt, learn and plan under a huge uncertainty as well as cope with a huge amount of information. Finally, based on robust discussion, paper has formulated an appropriate conclusion for this research. © 2022 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

IoT based Power and Water Theft Detection in Urban Cities

IoT based Power and Water Theft Detection in Urban Cities

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Praful V. Nandankar G.N.R. Prasad M. Lakshminarayana Mr. Doddabasappa N G. Satish Ramya Maranan Assistant Professor Department of Electrical Engineering Government College of Nagpur Maharashtra India Sr. Asst. Professor Department of Master of Computer Application Chaitanya Bharathi Institute of Technology (A) Hyderabad India Assistant Professor Department of Medical Electronics Engineering M S Ramaiah Institute of Technology Karnataka India Assistant Professor School of Electrical and Electronic Engineering REVA University Bengaluru Karnataka India Associate Professor Department of Electrical and Electronics Engineering Sree Dattha Institute of Engineering and Science Sheriguda Ibrahimpatnam Hyderabad Telangana India Assistant Professor Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai India

Many people in metropolitan areas have experienced problems with energy and water shortages. Some people used modern technologies and advancements to theft water and power illegally. Because the planet absolutely needs both water and power. Currently, the Internet of Things (IoT), smart meters, smart pipelines, and smart homes are being heavily integrated to replace traditional systems for detecting theft activities. This can be digitizing both the meter readings and the data that has been gathered. Wireless technology may be used to collect and analyze the data, which helps to reduce the need for physical labor. In this project, we suggested creating an IoT-based system for water and power theft detection. The proposed project aims to design a system to monitor the amount of power and water used by the people and indicates if water and electricity theft activities happen. This research study offers a user interface system to help people to monitor whether anyone is stealing their water or power. This study employs a hardware like voltage sensors, current sensors, flow sensors, and additionally, the Arduino IoT cloud to enable remote control and monitor the water and power usage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing Recurrent Neural Networks for Sentiment Analysis of Financial News to Enhance Market Prediction and Investment Strategies

Utilizing Recurrent Neural Networks for Sentiment Analysis o...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Ramu Pandiri K. Thilagavathi Aman Mittal Muntader M. Almusawi P. Nagaveni T. Rajesh Kumar Senior Budget Consultant Infomatics Corp Dallas Texas Associate professor Department of Commerce Saveetha school of law(SIMATS) Chennai India Lovely Professional University Phagwara Punjab India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

In this study, an attempt was made to analyze the prospect of Recurrent Neural Networks (RNNs) in carrying out sentiment analysis of financial news in order to improve market prediction and advancement in investment plans. Thus, employing developed NLP methods and neural networks, the study purpose is to develop an automatic solution for identifying the sentiment of financial news articles. The approach that is going to be used includes the data acquisition of great volume of financial news, the data preprocessing, the model training using BiLSTM with BERT embeddings for the sentiment analysis and the combination of the sentiment scores with the other standard financial figures in order to create the novel hybrid market predictor model. The comprehensive analysis shows a high increase in the accuracy of sentiment classification and market prediction and a higher efficiency of the hybrid model over traditional ones. Feedback from the financial analysts substantiates the applicability of the presented system describing it as convenient, precise, and compatible with other systems. In regards to the concerns of the study, hypotheses preoccupy the question of data quality as well as the interpretability of models, focusing on ethical concerns. Finally, the study proves that sentiment analysis based on RNN can give a significant contribution to the illumination of financial activities and help to enhance the effectiveness of the financial investment decision-making process.

关键词： Sentiment analysis Analytical models Solid modeling Accuracy Bidirectional long short term memory Predictive models Data models Stock markets Standards Investment

来源：评论

学校读者我要写书评

暂无评论

Cooperative self-scheduling routing protocol based IOT communication for improving life time duty cycled energy efficient protocol in SDN controlled embedded network

引用

Measurement: Sensors 2022年 24卷

作者： Dhandapani, Anbarasu P, Venkateswari T, Sivakumar C, Ramesh P, Vanitha Department of Electronics Rathinavel Subramaniam College of Arts and Science Sulur Coimbatore India HOD & Associate Professor Department of Electronics Rathinavel Subramaniam College of Arts and Science Sulur Coimbatore India Principal Rathinavel Subramaniam College of Arts and Science Sulur Coimbatore India Professor Department of Mechanical Engineering M.Kumarasamy College of Engineering Karur India Associate Professor Department of Management Studies M.Kumarasamy College of Engineering Karur India

Internet of Things (IoT) is a developing interconnecting medium in a wireless network through internet of communication in network devices like sensors, smart devices and controllers. This interconnect the devices via the internet to make communication. Due to large sectors IoT devices and Software-Defined Networking (SDN) controllers contains energy constraints in improper routing strategies. Specifically in health care industries, the patient monitoring data's consumes higher energy to reduce the lifetime of network communication leads data losses during the IoT devices collecting the information become *** embedded communication are relatively controls through the Software defined network to maintain the energy consumption to improve the lifetime of energy efficient network. But leastpropagation energy losses arise communication losses because of traffic, packet losses, latency beyond with throughput limits. The main problem is Passive Infrared Sensor (PHR) sensor nodes and Relay nodes attain more energy because of non-uniform node displacement in routing in uneven energy drainage. So resolving these problems, in this system propose a cooperative self-scheduling routing protocol based IoT communication for improving energy efficient SDN controlled embedded *** this construct the Neighbor Distance Discovery Protocol (NDDP) to identify the minimum depletion path by identifying Sensor closest route to the relay node. Then construct the Multipath Cooperative Self-Scheduling Protocol (MCSSP) to formalize the non-traffic route. By estimating the energy consumption on each sensor node on routing medium, this considers the prior routing communication rate by calculating average transmission delay, sensor absorption rate, power consumption, node response rate, and packet loss rate. UsingLife Time Duty Cycled Energy Efficient Protocol (LTDCEEP) to calculate the delimit of the feature limits along the network threshold latency energy limits. Based on the

关键词： Internet of things

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：