检索结果-内蒙古大学图书馆

mHAR: a novel convolutional recurrent model for recognizing motion-based human activity

Procedia computer science 2023年 229卷 218-227页

作者： Prabhat Kumar S. Suresh Department of Computer Science Institute of Science Banaras Hindu University Varanasi 221 005 India Department of Computer Engineering & Applications GLA University Mathura 281406 India Department of Computer Applications National Institute of Technology Kurukshetra 136119 India

With sensors built into smartphones and wearable devices, Human Activity Recognition (HAR) makes it possible to identify regular activities. One of the challenges is to access the motion information from activity data and extract the features from this information. A general model trained without motion features may perform poorly while recognizing the contextual patterns in human activities. In this paper, we proposed the mHAR (motion HAR) model for recognizing static, gradual, and dynamic motion activity to address this challenge. We examine the impact of the proposed model against the general non-convolutional and convolutional recurrent networks in terms of accuracy rates and F1 score. As an experimental dataset, the publicly accessible WISDM was employed. Additionally, the findings of the experiments demonstrate that, in contrast to the unbalanced class problem, motion features play a significant role in activity recognition by achieving accuracy rates of 92.29% and an average F1 score of 83.33%.

关键词： Human Activity Recognition (HAR) Deep learning (DL) Motion Features Smartphone Sensors Convolutional Recurrent Non-Convolutional Recurrent

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence Network based-Host Intrusion Detection System for Internet of Things Devices 4

An Artificial Intelligence Network based-Host Intrusion Dete...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Jain, Ashish Srinivasa Rao, B. Chattopadhyay, Saumitra Kumar, Aniruddh Muthuraman, M.S. Manjula, A. Bsss College Department of Computer Applications Madhya Pradesh Bhopal India Gokaraju Rangaraju Institute of Engineering and Technology Bachupally Department of Computer Science and Engineering Telangana Hyderabad India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Electronics Government Polytechnic Aurai Uttar Pradesh Bhadohi India Psna College of Engineering and Technology Department of Mathematics Tamilnadu Dindigul India Jyothishmathi Institute of Technology and Science Karimnagar India

ISBN: (纸本)9798350300093

Internet of Things (IoT) is currently employed in almost all the areas, including applications in smart cities, smart homes, e-Wellbeing, and others. Due to its wider utilization, IoT security has become a serious concern. A secure Intrusion Detection System (IDS) for the Internet of Things is often built using artificial intelligence (AI) and its subsets, deep learning (DL), and machine learning (ML). Industrial IoT devices, which are readily available, are regularly used by researchers and industry experts. This research study investigates the possibility of deploying a DL-Based Host-IDS (DL-HIDS) on specific commercial IoT devices. In this study, an optimized Convolutional Neural Network (O-CNN) based on DL is used. The proposed model's efficiency is evaluated by utilizing performance metrics like recall, precision, accuracy, and f1score. The proposed model's effectiveness is verified by analyzing the promising results obtained from the implementation of the proposed DL-HIDS on various existing models. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Study on Transcontinental Diabetes Datasets Using a Soft-Voting Ensemble Learning Approach 1

引用

6th International Conference on Communication, Devices and Networking, ICCDN 2022

作者： Pradhan, Gaurav Thapa, Gopal Pradhan, Ratika Khandelwal, Bidita Visalakshi, S. Department of Computer Applications Sikkim Manipal Institute of Technology SMU Majitar Rangpo East Sikkim India Department of Computer Science and Engineering Sikkim Institute of Science and Technology Chisopani South Sikkim India Department of Medicine Sikkim Manipal Institute of Medical Sciences SMU Tadong East Sikkim Gangtok India

ISBN: (数字)9789819919833

ISBN: (纸本)9789819919826

Worldwide, diabetes mellitus (DM) is one of the primary causes of illness and death. Diabetes has a well-established hereditary link, which is widely acknowledged. Diabetes is a disease that occurs when the blood glucose level in the body is too high. Diabetes can result in serious cardiovascular problems. According to the WHO, there are 3.7 million fatalities by the age of 70, and cardiovascular disease is increasing day by day which leads to a high death rate (https://***/diabetes/basics/*** [16]). Therefore, the detection of diabetes at an early stage can help patients’ lives. Various research is going under the healthcare sector in the prediction of disease in the field of data mining. Data mining techniques are frequently utilized in early disease diagnosis. In this paper, five diabetes datasets have been used and the main objective is to compare the various machine learning algorithms for detecting and classifying diabetes. The algorithms used for classification are Random Forest, Logistic Regression, Naïve Bayes, XGBoost, and the proposed ensemble approach. The proposed ensemble approach provided better accuracy as compared with individual classification algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Optimized Smart Agricultural Production Systems using Enhanced Parallel Green Anaconda Convolutional Neural Network 8

Optimized Smart Agricultural Production Systems using Enhanc...

引用

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

作者： Meena, S. Gomathi Goyal, Himanshu Rai Lavanya Muthukumar, E. Megha, Mamtaben Kamleshbhai Parikh, Swapnil Peri College of Arts and Science Pg Department of Computer Science and Computer Applications Tamil Nadu Mannivakkam600048 India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun248 002 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Viruthunagar626126 India Nehru College of Management Department of Mba Coimbatore Tamil Nadu Thirumalayampalayam641105 India Natubhai V. Patel College of Pure and Applied Sciences A Constituent College of Cvm University Department of Computer Science Gujarat Vallabh Vidyanagar388120 India Parul University Parul Institute of Engineering and Technology Department of Computer Science and Engineering Post Limda Gujarat Waghodia391760 India

ISBN: (纸本)9798350376425

Smart agriculture, driven by IoT technologies, is becoming increasingly essential due to global population growth and rising food demands. However, challenges such as energy supply constraints and routing issues often result in data transmission failures, high energy consumption, reduced network lifetime, and delays. To address these issues, this study proposes a novel solution: an enhanced smart agricultural production system based on an Optimized Smart Agricultural Production Systems using Enhanced Parallel Green Anaconda Convolutional Neural Network (EPar-GrAnCNN). This system enhances energy management by incorporating the Emperor Penguin Optimizer (EPO) for the formation and selection of cluster heads, aiming to increase power conservation and extend network lifespan. Additionally, the system leverages deep learning techniques, including the Enhanced Parallel Convolutional Neural Networks (EPar-CNN) and Green Anaconda Optimization (GAO), to analyze agricultural data and extract valuable insights. The EPar-GrAnCNN model accurately predicts crop health, the severity of water deficits, and other factors affecting crop growth, guiding farmers in the optimal utilization of resources. computer experiments conducted on the Python platform demonstrate that the proposed approach outperforms existing methods, achieving higher throughput (98.4%), a superior packet delivery ratio (99.3%), and lower energy consumption (0.30 mJ). These results highlight the efficiency of the approach and its potential for further advancement in smart agriculture. © 2024 IEEE.

关键词： Emperor Penguin Optimizer (EPO) Enhanced Parallel Convolutional Neural Network (EPar-CNN) Green Anaconda Optimization (GAO) Internet of Things (IoT) Smart Agricultural Systems

来源：评论

学校读者我要写书评

暂无评论

Predicting Financial Market Movements Through Time Series Analysis and Advanced Machine Learning Algorithms

Predicting Financial Market Movements Through Time Series An...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Amarnath Reddy, B. Kathiriya, Harsh Thapliyal, Nitin Vasuki, S. Sachdeva, Meena Shobana, A. Vignana Jyothi Institute Of Management Department Of Finance & Marketing Hyderabad India Big Analytixs AtlantaGA United States Graphic Era Hill University Department Of Computer Science And Engineering Dehradun India Velammal College Of Engineering And Technology Department Of Ece Madurai India Jims Engineering Management And Technical Campus Department Of Computer Science Uttar Pradesh Greater Noida India Sri Krishna Arts And Science College Department Of Computer Applications Coimbatore India

ISBN: (纸本)9798350371567

A novel approach for forecasting the movements of financial markets is presented in this research. It combines Auto Regressive Integrated Moving Average (ARIMA) time series analysis with Random Forest machine learning techniques. Improving predicting accuracy in ever-changing market conditions is the primary goal of the study. Our suggested model achieves better results than current models using a sample dataset. It achieves an MAE of 1.6, an MSE of 2.8, and an RMSE of 1.67. The R-squared value is 0.797, which means that the model explains a significant amount of the variation. This combined methodology takes advantage of ARIMA and Random Forest's complimentary qualities to identify patterns in financial data, whether they are linear or nonlinear. This research adds to the growing body of knowledge that combines machine learning with time series analysis to provide a powerful resource for those making important financial decisions. To further improve the model's flexibility and utility across varied market situations, future research should focus on parameter tweaking, researching other ensembles, and conducting real-world implementation. Finally, this research establishes the groundwork for a novel hybrid model that might greatly enhance the precision of financial market forecasts in the future. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Machine Learning Techniques on Chronic Kidney Disease Prediction 3

Comparative Study of Machine Learning Techniques on Chronic ...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Panigrahi, Soumyarashmi Adhikary, Dibya Ranjan Das Pattanayak, Binod Kumar Mohanty, Bibhuprasad Dash, Bibhuti Bhusan Patra, Sudhansu Shekhar Siksha 'o' Anusandhan Deemed to Be University Department of Computer Science & Engineering Bhubaneswar India Siksha 'o' Anusandhan Deemed to Be University Department of Electronics & Communication Engineering Bhubaneswar India School of Computer Applications Kalinga Institute of Industrial Technology Bhubaneswar India

ISBN: (纸本)9798350303360

A malfunctioning kidney can cause the increase of waste in the blood, adversely affecting various bodily processes and systems. ML techniques can assist in classifying patients as having chronic kidney disease (CKD) or not. Although previous researchers have conducted several studies, they have often neglected important steps like data preprocessing and feature engineering. In this paper, we have addressed these gaps by implementing various data preprocessing and feature engineering techniques such as Principal Component Analysis (PCA) on the CKD dataset. By carefully selecting features from our dataset, we identified the top-performing classification models which are RFC, SVC (Polynomial Kernel), XG Boost Classifier (XGBC) and Gradient Boost Classifier (GBC) gave the best performance in terms of accuracy. To evaluate the effectiveness of these models, we have utilized various performance metrics. The results obtained have significant contribution to the understanding and management of CKD, ultimately helping in the early detection and treatment of this widespread and critical health issue. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring Reinforcement Learning Algorithms for Autonomous Agents in Dynamic Environments

Exploring Reinforcement Learning Algorithms for Autonomous A...

引用

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Kumar, S. Magesh Swaminathan, Subbiah Sugumaran, D. Saranya, N. Naga Ashokkumar, S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Information Technology Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Information Technology Vel Nagar Tamil Nadu Chennai India Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India

ISBN: (纸本)9798350388602

Reinforcement Learning (RL) algorithms are widely considered to be the enabling technology for deep learning and allow for agents in complex systems to learn in a dynamic environment. In order to present in this paper a break-through training methodology for learning RL agents in the dynamic environment, advised by the following adaptability, robustness, and scalability purposes. Our approach is assessed in an array of the model environments which are open to the users. This framework is labelled as OpenAI Gym environment. We apply different reinforcement learning algorithms in our experiments among which Covering Concurrent and Differentiable in Q-learning, Meta-learning (MAML), Virtual Imitation and Q-learning, and Dyna-Q are the most popular. Meta-learning's performance highlights its power and efficiency in grasping and optimizing decision-making logic in dynamic situations within 20 epochs and reaching the cumulative reward of 500. As a matter of fact, adaptive search strategies, for instance, UCB are another tool that is extremely useful reaching to 490 at 25 epochs after all. Transfer learning techniques like the Progressive Neural Networks shows extremely high power of learning in collecting a reward of 500 and in less than 20 epochs it also converges. Moreover, scalable parallel training methods such as CPDG which are normalized in distribution, have huge scalability and robustness can be applied for large scale dynamic environments. Consequently, it is concluded that the presented approach was very good in giving RL agents the ability to navigate environments and succeed in dynamic settings, thus contributing to the development of autonomous systems not only in the area of RL but also everywhere else. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Bharatanatyam hasta mudra categorization using deep learning approaches 2

Bharatanatyam hasta mudra categorization using deep learning...

引用

2nd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2023

作者： Nandeppanavar, Anupama S. Kallur, Shanta S. Thotad, Puneeth Sankannavar, Vaishnavi A. K. L. E. Institute of Technology Department of Master of Computer Applications Hubballi India Affiliated to Visvesvaraya Technological University Belagavi India K. L. E. Institute of Technology Department of Computer Science and Engineering Hubballi India K. L. E. Institute of Technology Vtu Department of Master of Computer Applications Hubballi India

ISBN: (纸本)9798350314045

The present study explores the precise identification of Bharatanatyam hasta mudras (hand gestures) by applying advanced convolutional neural networks and deep learning methodologies. Specifically, the article employs the Convolutional Sequential Neural Network, VGG-19, and, prominently, ResNet50V2 architectures to analyze a meticulously labeled dataset comprising Bharatanatyam hasta mudra images. With accuracy, recall, precision, and F1-score, key performance metrics are systematically employed for comprehensive performance evaluation, revealing an impressive accuracy rate of approximately 96.44%. Notably, the projected system is a valuable resource for Bharatanatyam practitioners, offering a sophisticated tool for discovering and mastering diverse hasta mudras. Its potential impact extends to dance schools and academies, where the system can be instrumental in teaching and integrating various hasta mudras into choreographic works. Beyond dance education, the article's contribution resonates in the broader context of preserving and promoting Indian classical dance forms. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning based Facial Expression and Emotion Recognition for Human computer Interaction through Fuzzy Logic System 6

A Machine Learning based Facial Expression and Emotion Recog...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Vinutha, K. Niranjan, Manoj Kumar Makhijani, Jagdish Natarajan, B. Nirmala, V. Vijaya Lakshmi, T.R. Department of Information Science and Engineering BMS Institute of Technology and Management Karnataka Bengaluru India Department of Computer Applications Rustamji Institute of Technology Madhya Pradesh Gwalior India Department of Computer Science and Engineering Rustamji Institute of Technology Madhya Pradesh Gwalior India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Tamil Nadu Chennai India Department of Science and Humanities Faculty of Engineering Karpagam Academy of Higher Education Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Mahatma Gandhi Institute of Technology Telangana Hyderabad India

ISBN: (纸本)9798350398496

Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase where many service providers use this feature to find the expression of the people on using their BlogSpot or website or reading any news article. This recognition of facial expression is highly possible with the help of machine learning technology. This research study has developed a facial expression recognizing algorithm using Python programming language with the help of Keras software package. This algorithm is purely based on machine learning approach that enables the programmer to process the facial image and convert it into data that is helpful in prediction of facial expression using the fuzzy logic technique. The fuzzy logic technique is a prediction method that helps programmer to predict the intermediate data by providing the initial and ending conditions. For enabling the facial recognition to process any system or a mobile device the algorithm needs permission to access the camera, once the onto the access is permitted the algorithm retrieves the image from the Vision sensor and with the help of image processing technology of the machine learning algorithm the program the program converts the data from the vision sensor into required facial expression and emotional content. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging XGBoost for Predictive Analytics in Healthcare: Enhancing Disease Diagnosis 7

Leveraging XGBoost for Predictive Analytics in Healthcare: E...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Shrivastava, Anurag Kotiyal, Arnav Habelalmateen, Mohammed I. Rana, Ajay Devi, V.S Anusuya Rao, Bolleddu Devananda Bansal, Saloni Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Amity University Uttar Pradesh Greater Noida India New Horizon College of Engineering Department of Applied Sciences Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Gla University Departyment of Computer Engineering and Applications Uttar Pradesh Mathura India

ISBN: (纸本)9798350350067

In this study, we look at how XGBoost (Extreme Gradient Boosting) may be used in healthcare predictive analytics to improve the speed and precision of illness detection. Thanks to its built-in regularisation algorithms that avoid overfitting and its capacity to handle big datasets, XGBoost has proved useful in a broad variety of prediction applications. It is a scalable and high-performance machine learning algorithm. In order to improve patient outcomes, healthcare providers must ensure that patients are diagnosed with chronic and life-threatening conditions including cancer, heart disease, and diabetes as soon as possible. To test how well XGBoost performs in comparison to more conventional machine learning techniques, the research makes use of healthcare datasets collected from the actual world. The effectiveness of the model in predicting illness outcomes is evaluated using critical metrics including accuracy, precision, recall, and F1-score. Based on the findings, XGBoost is the best classifier for real-time healthcare applications because to its quicker processing efficiency and greater predictive ability. Additionally, the article delves into the model's interpretability and how it may be integrated into clinical decision support systems. By demonstrating how XGBoost may improve diagnostic accuracy and bolster individualised treatment plans, this study adds to the expanding area of AI-driven healthcare. © 2024 IEEE.

关键词： Predictive analytics

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：