检索结果-内蒙古大学图书馆

A Bilateral Assessment of Human Activities Using PSO-Based Feature Optimization and Non-linear Multi-task Least Squares Twin Support Vector Machine

引用

SN computer science 2024年第3期5卷 315页

作者： Thakur, Ujwala Vidyarthi, Ankit Prajapati, Amarjeet Department of Computer Science Engineering and Information Technology Jaypee Institute of Information Technology Noida Sector-62 Uttar Pradesh Noida 201309 India

Human activity recognition (HAR) is an essential part of many applications, including smart surroundings, sports analysis, and healthcare. Accurately categorizing intricate actions from sensor data is still difficult, though. This method infers an individual’s actions using a variety of sensor data, including magnetometers, gyroscopes, and accelerometers. This work suggests a unique method for classifying human activities by combining a non-linear multi-task least squares twin support vector machine (NMtLSSVM) with particle swarm optimization (PSO) for feature optimization. Utilizing the advantages of both approaches, the suggested strategy achieves excellent resilience and accuracy in activity identification. The suggested method reduces dimensionality and computing costs while maintaining pertinent information using PSO to extract the most important features from the raw sensor data. On the other hand, NMtLSSVM is used to construct a multi-task learning framework that learns several related tasks at the same time and shares information among them. As a result, generalization and resilience can be enhanced beyond single-task models. Two datasets that are available to the public, WISDM, and UCI-HAR, were used to assess the suggested method. The testing findings show that the suggested approach works noticeably better than the most advanced techniques already in use. Overall activities, the outcome achieves an average classification accuracy of 97.8% (UCI-HAR dataset) and 98.5% (WISDM dataset). Furthermore, the PSO-based feature optimization decreased the feature count by 60% without sacrificing efficiency. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Human action recognition Intelligent computing Machine learning classification Performance comparison Sensory data analysis

来源：评论

学校读者我要写书评

暂无评论

Smart Health Monitoring System in Intensive Care Unit using Bluetooth Low Energy and Message Queuing Telemetry Transport Protocol 5

Smart Health Monitoring System in Intensive Care Unit using ...

引用

5th International Conference on Smart Systems and Inventive technology, ICSSIT 2023

作者： Ragavan, K. Ramalakshmi, R. Srirenganachiyar, V. Gnana Priya, G. Jeyageetha, K. Department of Electronics and Communication Engineering Ramco Institute of Technology Rajapalayam India Department of Computer Science and Engineering Ramco Institute of Technology Rajapalayam India

ISBN: (纸本)9781665474672

Smart healthcare monitoring is very essential for people who are in the Intensive Care Unit (ICU) in hospitals which provides continuous monitoring of health parameters, which cannot be afforded outside the hospitals. Because of the ever-increasing population of the world, smart health care has become increasingly crucial. The traditional patient-doctor consultation has lost its usefulness. The effective way of monitoring the patient's health within ICU has great potential to introduce Bluetooth Low Energy (BLE) and Message Queuing Telemetry Transport (MQTT) protocol. The patient's survival can be improved by the daily care of parameters such as heart rate, Hemodynamic, skin temperature, capillary refill, mental status, etc., which can be wirelessly monitored in smart way using BLE and MQTT. In addition, the Short Message Peer to Peer (SMPP) protocol could also be used for alerting the doctors if the sensor values go to a critical level as per the threshold value. It uses BLE and MQTT in monitoring the health of an ICU patient and also it will compare the ZigBee technology, which is already used in monitoring health parameters in following criteria low power, performance, cost, availability etc., with the proposed method. ZigBee will not support android version which is very important to access the smart phones. But the proposed method can support android version with low power consumption. © 2023 IEEE.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

Recognition of Human Emotions Through The Use of Facial Expressions

Recognition of Human Emotions Through The Use of Facial Expr...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Singh, Nongmeikapam Thoiba Chaudhary, Amrita Dhiman, Richa Singh, Akanksha Chanu, Asem Debala Chandigarh University Department of Computer Science and Engineering Punjab India Indian Institute of Information Technology Department of Computer Science and Engineering Assam Guwahati India

ISBN: (纸本)9798350308167

Emotions play a pivotal role in human life, influencing communication, relationships, and productivity. Recognizing and understanding these emotions is crucial, and various methods have been explored, including monitoring brain activity. However, traditional approaches, such as electroencephalography (EEG), are costly and time-consuming, often yielding accuracy rates ranging from 31% to 81%. In this study, we propose an alternative approach: accurately detecting human emotions through facial expressions. Leveraging an existing simulator and neural networks, we achieved remarkable accuracy rates of up to 96%. We present the methodology, including image processing, differential readings, and facial expression detection, and compare our approach to other methods. The study sheds light on the potential of neural network-based systems for high-accuracy emotion recognition from facial expressions, offering a promising avenue for human-computer interaction and intelligent surveillance systems. © 2023 IEEE.

关键词： brain activity emotion recognition facial expression fuzzy logic human-computer interaction neural network

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Optimization for Identifying Effective Drugs in Breast Cancer on an in Vitro Platform 4

Machine Learning-Based Optimization for Identifying Effectiv...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Saxena, Mahima Rao, P.V.V.S. Eswara Choudhary, Amar Reddy, P. Srinivas Sharma, Vipin Kumar Kumar, Vinish Ajay Kumar Garg Engineering College Department of Computer Science Ghaziabad India Sasi Institute of Technology and Engineering Department of Computer Science Tadepalligudem India Department Electronics and Communication Engineering Bengaluru India Cvr College of Engineering Mechanical Engineering Department Rangareddy India Ims Engineering College Department of Mca India Ghaziabad India

ISBN: (纸本)9798350360165

In this innovative quest for more efficient irrigation, we investigate the combined use of sensor technology and machine intelligence to optimize agricultural water usage. We collect precise data on essential variables, including water flow, temperature, humidity, soil moisture, and water level, every 15 days by promptly deploying sensors in the field to monitor them in real-time. We use the vast amount of data available to us to train machine learning models, including Recurrent Neural Networks (RNN), K-Nearest Neighbours (KNN), Artificial Neural Networks (ANN), and Convolutional Neural Networks (CNN), specifically for streams that are anticipated to have a certain distribution. CNN has exceptional precision with a decoding accuracy of 94.5% in visual signal interpretation, surpassing ANN, KNN, and RNN which achieve lower accuracies of 91.1%, 88.7%, and 83.6% respectively. Our investigation uncovers a fluid interaction between sensor data and model training, leading to each model exhibiting unique characteristics. These findings not only showcase the accuracy with which machine learning can distribute water, but they also signify a noteworthy progress in resource-efficient and sustainable agriculture. In addition to generating mathematical discoveries, our research establishes the foundation for advanced irrigation systems that smoothly integrate mechanical and natural processes in agricultural fields. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Predicting the Sale Price of Pre-Owned Vehicles with the Ensemble ML Model 4

Predicting the Sale Price of Pre-Owned Vehicles with the Ens...

引用

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

作者： Kathiravan, M. Ramya, M. Jayanthi, S. Reddy, Vangala Vamseedhar Ponguru, Lokesh Bharathiraja, N. Computer Science and Engineering Chennai India St.Joseph Institute of Technology Computer Science and Engineering Chennai India Mohamed Sathak Aj College of Engineering Department of Computer Science and Engineering Chennai India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350300093

Car price forecasting is a popular study topic because it requires a lot of work and knowledge. Used car pricing forecasting is a major auto industry concern. Machine learning can accurately predict used automobile prices based on many characteristics. Many distinct qualities are considered for accurate predictions. The suggested model uses a dataset that contains vehicle brand and model, year of production, mileage, condition, and other factors that affect used car prices. This study used linear regression, GBT regression, and random forest regression to estimate secondhand car prices. Then, algorithm performance was compared to find which method better fit the data set. Thus, these methods outperform others. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Ocular Eye Disease Prediction Using Machine Learning 15th

Ocular Eye Disease Prediction Using Machine Learning

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Kongala, Lavanya Bikku, Thulasi Preethi, B. Zaveriya Ruman, S.K. Susmitha, P. Sowjanya, B. Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Amrita School of Computing Amaravati Amrita Vishwa Vidyapeetham Andhra Pradesh Vengal522503 India Department of Computer Science and Engineering Vignan’s Nirula Institute of Technology and Science for Women Guntur India

ISBN: (纸本)9783031810794

The human eye, often considered the most crucial sense organ for perceiving and understanding the world, plays a fundamental role in our ability to see and interpret our surroundings. However, vision can be significantly impacted by various ocular eye disorders, which pose significant challenges to our visual capabilities. Among these disorders, one of the most prevalent conditions is cataract, a condition characterized by cloudiness in the lens of the eye, resulting in impaired vision and a blurred perception of objects. Typically, cataracts are more commonly found in individuals of advanced age due to natural aging processes. Identifying and diagnosing ocular eye illnesses can be a complex and challenging task, often requiring sophisticated techniques and tools to aid in the process. In recent research endeavors, automated learning algorithms have emerged as valuable tools for assisting in the detection of ocular eye disorders. These algorithms, such as Convolutional Neural Networks (CNNs), are employed alongside image pre-processing techniques to analyze and interpret ocular data. By leveraging the power of machine learning, researchers have been able to develop and refine predictive models for ocular diseases. To evaluate the accuracy of disease prediction models, various design pattern graphs can be utilized. These graphs serve as visual representations, showcasing the performance and reliability of the algorithms in predicting ocular eye disorders. By employing these advanced technological approaches, researchers and medical professionals can enhance their ability to identify and diagnose ocular conditions, ultimately leading to more effective treatments and interventions for individuals affected by these diseases. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Study of Handwritten Digit Recognition Methods: An Exploration of Deep Learning and Machine Learning Approaches

An In-Depth Study of Handwritten Digit Recognition Methods: ...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Singh, Nongmeikapam Thoiba Tiwary, Priyanshu Chanu, Asem Debala Chandigarh University Department of Computer Science and Engineering Punjab India Indian Institute of Information Technology Department of Computer Science and Engineering Assam Guwahati India

ISBN: (纸本)9798350319200

This article explains how deep learning and machine learning techniques are being utilized to replace humans in a variety of activities, like item classification and sound addition. It emphasizes handwritten text recognition (HTR), which involves computers interpreting handwritten content from sources like paper documents and touchscreens. For recognizing handwritten digits, the study analyzes three algorithms: support vector machines (SVM), multilayer perception (MLP), and convolutional neural networks (CNN). This comparison aims to evaluate the correctness and execution times of different approaches. The evaluation is based on parameters like the dataset used, the number of epochs, algorithm complexity, accuracy, and hardware specifications. The study compares the effectiveness of CNN, Multilayer Perception (MLP), and Support Vector Machines using handwritten digits from the MNIST dataset. It evaluates these algorithms based on criteria such as runtime, complexity, rate of precision, the count of epochs, and the quantity of hidden layers specifically within deep learning techniques. SVM had the highest training data accuracy, but CNN outperformed others on the test dataset. The article's primary goal is to identify the most precise model for recognizing handwritten digits. It achieves this by assessing the performance of different algorithms and comparing them based on various characteristics. © 2023 IEEE.

关键词： convolutional neural networks execution time handwritten digits multilayer perceptron overfitting visualization

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential: A Review of Digital Twins and Integration with Emerging Technologies 1

Unlocking the Potential: A Review of Digital Twins and Integ...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Dinesh Babu, V. Geetha, S.K. Aneeshkumar, M. Revathi, S. Arulprakash Arulprakash, P. Karpagam Institute of Technology Department of Information Technology Coimbatore India Department of Computer Science and Engineering Coimbatore India Arjun Collge of Technology Department of Artificial Intelligence and Data Science Thamaraikulam India Erode Sengunthar Engineering College Department of Computer Science and Engineering Erode India Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350359756

The Digital Twin (DT) is primarily used to digitally represent a physical object, process, or service. Simply put, DT is a clone representation of a physical object in the real world, such as wind farms, objects like a building or even an entire city. The key uses of technology are to collaborate, train, and simulate processes or products. The results of DT vary greatly depending on the sector and application, but a few key advantages include reducing costs and risks before investing in real-world resources and helping to enhance products or processes over their entire life cycles. The integration of the digital Twin with so many various industries, including manufacturing, healthcare, and the growth of urban and rural areas, has enhanced the prominence of this emerging technology. This paper's major goal is to identify ongoing initiatives by numerous engineering fields to apply digital twin technology for sustainable development. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adaptive Gamma Correction with Unsharp Masking and Gaussian filter for Image Contrast Enhancement

Adaptive Gamma Correction with Unsharp Masking and Gaussian ...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Mishra, Pawan Kumar Patni, Jagdish Chandra Saini, Shivika Kishore, Jaydeep Baloni, Dev Verma, Shalini Graphic Era Deemed to Be University Computer Science & Engineering Dehradun India Nagpur Campus Pune India Uttarakhand Technical University Department of Computer Science Dehradun India Manipal University School of Computer Science & Engineering Department of Aiml Jaipur India Quantum University Quantum School of Technology Roorkee India Doon Institute of Engineering & Technology Computer Science & Engineering Rishikesh India

ISBN: (纸本)9798350382723

In this research work image processing is done for direct application of digital images. Image processing is used for the enhancement of process includes with it. Adaptive histogram equalization is an appropriate method for improving the quality of images. This technique is used with gamma correction. Unsharp masking and Gaussian smoothing filters are also applied to improve the visibility as well as to remove the harshness of images. The comparative results of different approaches are also shown in this research work. The proposed method is superior to earlier developed methods by testing on various parameters such as MSE, PSNR, MAE, and AMBE. The suggested strategy maintains brightness in different types of images. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Manhole Monitoring: Autoencoder-Assisted Anomaly Detection 3

Next-Gen Manhole Monitoring: Autoencoder-Assisted Anomaly De...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Krishnan, R. Santhana Gopikumar, S. Muthu, A. Essaki Raj, J. Relin Francis Kumari, D. Abitha Malar, P. Stella Rose Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Civil Engineering Chennai India Scad College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical AndTechnical Sciences Department of Electronics and Communication Engineering Chennai India Rmk Engineering College Department of Computer Science and Engineering Thiruvallur India J.P. College of Engineering Department of Electronics and Communication Engineering Thenkasi India

ISBN: (纸本)9798350375190

In various regions, the maintenance of manholes is imperative, given the potential consequences for public health and safety. Neglecting this responsibility can result in severe outcomes, including loss of lives and the spread of diseases within the community. To address these challenges, an advanced anomaly detection system is proposed, leveraging deep learning with Autoencoders. Notably, the entire system operates on solar power, aligning with a commitment to environmentally sustainable practices. At the core of the system's functionality is the Autoencoder, a deep learning model to differentiate complex manhole conditions. The Autoencoder is trained on normative sensor data, capturing nuanced patterns inherent in routine manhole states. This training enables the Autoencoder to perform real-time anomaly detection by swiftly identifying deviations such as the presence of noxious gases, irregular sewage levels, or unauthorized attempts at access. When anomalies are detected, signaling potential hazards, the Autoencoder triggers alert messages disseminated to municipal authorities via a cloud server. This proactive approach empowers timely intervention, particularly critical in scenarios involving toxic gases, ensuring the safeguarding of maintenance personnel. Additionally, the system integrates an NFC reader, streamlining authorized access for designated personnel while upholding robust security measures. In essence, the incorporation of Autoencoders into the system furnishes an intelligent anomaly detection infrastructure for manhole surveillance. By continually adapting to normative patterns, the Autoencoder enhances the system's capacity to identify and promptly communicate potential risks, thereby improving the overall safety and efficiency of manhole maintenance practices. © 2024 IEEE.

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：