检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Al-Amain Janin, Fatema Tuj Ahmed Robin, Faizul Ahmed, Shifat Mohi Uddin, Khandaker Mohammad Southeast University Dept. of Computer Science and Engineering Dhaka Bangladesh Hamburg University of Applied Sciences Dept. of Information and Electrical Engineering Hamburg Germany

ISBN: (纸本)9798331529765

Chronic diseases, characterized by long-term effects and persistent symptoms, pose significant challenges to human health and well-being. The hepatitis C virus (HCV) is the cause of chronic hepatitis C, which affects 58 million people globally. It also causes 290,000 deaths annually due to liver cancer and cirrhosis, two conditions connected to HCV. Taking advantage of machine learning (ML) algorithms' ability to analyze large datasets and identify patterns and relationships that aid in diagnosis, this effort focuses on employing algorithms for machine learning to identify and forecast hepatitis C precisely. Various techniques were utilized, including Random Forest, Cat Boost, SVM, and others to create predictive models using blood values from 615 patients, including both hepatitis patients and healthy blood donors. The dataset underwent comprehensive preprocessing, including handling missing values, scaling, and dimensionality reduction via Principal Component Analysis (PCA). Various ML algorithms were evaluated, and the Cat Boost classifier achieved the highest accuracy of 99.17%, recall of 92.00%, precision of 100.00% and F1-score is 96.00%. This study demonstrates the potential of ML in enhancing HCV diagnosis, offering less invasive and cost-effective alternatives to traditional methods, and providing predictive insights for personalized treatment plans. The findings underscore the importance of advanced data preprocessing and feature selection in improving model efficiency. This study adds to the ongoing efforts to lessen the prevalence of hepatitis C worldwide, aligning with the World Health Organization's goal to significantly decrease new HCV cases and related deaths by 2030. © 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

Rapid Construction of Diode Models Based on Physical Mechanism and Machine Learning 12

Rapid Construction of Diode Models Based on Physical Mechani...

引用

12th International Conference on Awareness Science and technology, iCAST 2023

作者： Lin, Kun-Wei Li, Jia-Wei Jian, Wei-Chen Jiang, Zheng-Han Lu, Hsin-Hou dept. Computer Science and Information Engineering Chaoyang University of Technology Taichung Taiwan dept. Electrical Engineering National Cheng-Kung University Tainan Taiwan

ISBN: (纸本)9798350324693

Diodes are crucial components in electronics, with applications ranging from rectification to sensing. Traditional modeling methods are time-consuming due to manual parameter extraction. In this study, two machine learning approaches for the rapid construction of diode models were developed and compared. These two methods named the Turning Point Segmentation (TPS) and Diode Operating Range Segmentation (DORS) are based on machine learning to find turning point segmentation and fixed work interval segmentation. From the experimental results, it is known that finding the turning point with machine learning has better results. In terms of MSE, the train and test sets of TPS (DORS) are 0.008 (0.011) and 0.006 (0.019), respectively. In terms of linearity, the R2-scores of the training set and test set of TPS (DORS) are 0.992 (0.979) and 0.994 (0.961), respectively. In all data simulations, the MSE and R2 of TPS (DORS) are 0.008 (0.013), and 0.993 (0.974), respectively. Both have excellent performance in terms of time consumption. This innovative technique holds promise for revolutionizing electronics engineering and advancing the role of machine learning in modeling complex systems. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Parametric Optimization of WEDM Process for Machining ANSI Steel Using Soft-Computing Methods

Parametric Optimization of WEDM Process for Machining ANSI S...

引用

2023 International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Chen, Yi-Zhen Chiang, Hsin-Han Liao, Jo-An Chen, Yen-Lin Li, Hsiao-Chi National Taipei University of Technology Dept. of Vehicle Engineering Taipei Taiwan National Taipei University of Technology Dept. of Computer Science and Information Engineering Taipei Taiwan National Taipei University of Technology Dept. of Electrical Engineering Taipei Taiwan

ISBN: (纸本)9798350324174

This paper introduces a parametric method for optimizing the wire electric discharge machining (WEDM) process applied to steel machining. The proposed approach employs soft-computing methods to determine the optimal process parameters for achieving maximum material removal rate and minimum surface roughness. This work conducts an analytical investigation to evaluate the feasibility of the proposed approach. © 2023 IEEE.

关键词： Soft computing

来源：评论

学校读者我要写书评

暂无评论

A Sustainable Smart Irrigation and Crop Protection System for Bangladesh 8

A Sustainable Smart Irrigation and Crop Protection System fo...

引用

8th IEEE International Conference on Computational System and information technology for Sustainable Solutions, CSITSS 2024

作者： Ahmed, Khandakar Rabbi Salam, Towfika Miraz, Shafiun Jahan, Israt Hoque, Aminul Al Noman, Abdullah Miyan Research Institute International University of Business Agriculture and Technology Uttara Model Town Dhaka Bangladesh Dept. of Mechatronics Engineering Kazla Rajshahi6204 Bangladesh Dept. of Computer Science and Engineering Rajshahi Bangladesh International University of Business Agriculture and Technology Dept. of Computer Science and Engineering Uttara Model Town Dhaka Bangladesh Asian University of Bangladesh Dept. of Computer Science and Engineering Bangabandhu Road Tongabari Ashulia Dhaka Bangladesh Jahangirnagar University Dept. of Institute of Information Technology Savar Dhaka Bangladesh

ISBN: (纸本)9798331505462

Bangladesh's most crucial sector for development is agriculture. Rainfall has been irregular in recent years due to climate change. In our country, the untimely rain and hailstorms harm crops and vegetables, especially winter vegetables. Surface water is mainly used for agriculture, but its availability constantly declines. Our current key challenge is to save surface water while protecting crops from rain and hail. IoT is cutting-edge technology in many applications, such as smart homes, smart cities, and intelligent traffic management. The IoT may be implemented in so many different industries and sectors. This research work is about smart irrigation with crop protection systems in agriculture. The system's primary parts are the sensors, water pump, servo motors, embedded systems, and internet connectivity. IoT sensors like soil moisture sensors and rain sensors are used in the suggested methodology. The fields of crops have received water from a pump. A motor has covered the crops. The proposed solution is a straightforward Internet of Things setup that sends data to the Arduino after detecting rainfall and soil moisture levels. Depending on the sensor data, the Arduino sends signals to the motor and pump to irrigate the crops and cover crops as necessary, revealing the crops after rain. The system is constructed economically using bamboo, and poly and plastic nets have been utilized to protect the crops from rain and fog. The system's primary effects are increased productivity, decreased crop damage rate, and saved surface water. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

An Overview of Protocols-Based Security Threats and Countermeasures in WLAN 4

An Overview of Protocols-Based Security Threats and Counterm...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Ojha, Nitish Kumar Baray, Elyas Indian Institute of Information Technology Dept. of Information Technology Allahabad211012 India Sharda University Knowledge Park - III Dept. of Computer Science and Engineering Greater Noida201310 India

ISBN: (纸本)9798350335750

WLAN security protocols are the most important section for wireless networks which controls all the security-related issues by securing the network with some pre-defined rules made by wireless-protected access organizations, further which makes it the main target of hacking and threats by interested parties and to be safe from such threats. There should be countermeasures for such threats where there will be a solution for any threat encountered and to mention. WIFI or wireless local area Network is a cost-effective easy deployment Network that makes users take advantage of vast data shared on the internet and by the network without the need for any cable for connections. Here in this overview paper by reviewing many researchers' techniques and works on the WLAN security topic, there are shared threats to WLAN and the ways of taking precautions against those threats as countermeasures and for which the tables are used. For comparison of techniques used by authors and some famous and highly dangerous threats are also defined further. WPA3's new security protocol is also defined with its newly found vulnerabilities and countermeasures except there is a conclusion on the downgrade attack problem with WPA3. Further, there are also countermeasures for that as well, nowadays people think the network is secured with standards defined by the IEEE organization but some know this is not the case so it makes it a more important area for research. © 2023 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

THE CREATION AND ANALYSIS OF THE computer NETWORK MODEL BASED ON ECOLOGY

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2022年第1期84卷 87-104页

作者： Li, Yanjing Dept. of Information Engineering Shijiazhuang University of Applied Technology China

Currently, the ecology was used in the network security by many researchers. But the correspondence between the network and the ecology systems were studied by few researchers which limited the development of cross fields between network and ecology. Due to the rapid development, the structure of computer network is increasingly complicated. The traditional static network model is difficult to characterize the topological properties and dynamic development of computer network. So, based on ecological theory, this paper proposes an ecological computer network model, namely Monomer-Multimer computer network model. The Monomer-Multimer computer network model can not only simulate the computer network, but also describe the dynamic development of computer network from the view of eco-development. In addition, this model is easier to describe the information dissemination mechanism of the computer network. A variety of virus propagation models and anti-virus strategies can also apply to this model. In this paper, the completeness of the Monomer-Multimer computer network model is proven by the complex network and the theory of model completeness. The feasibility of the Monomer-Multimer computer network model is also proven by the Agent. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Ecology

来源：评论

学校读者我要写书评

暂无评论

Cotton Plant Disease Detection and Prevention Using Deep Learning and Image Processing 11

Cotton Plant Disease Detection and Prevention Using Deep Lea...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Kesani, Ruthvija Sunkavalli, Jaya Prakash Shaik, Mahamamad Rafi Yadala, Kusuma Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Information Technology Vijayawada India

ISBN: (纸本)9798350350357

One of the most important aspects of the agricultural economy is the production of cotton, which is threatened by diseases that lower crop quality and yield. Conventional techniques for diagnosing diseases are frequently subjective and labor-intensive. This paper presents a novel method for the automatic detection and prevention of cotton plant diseases that makes use of deep learning techniques. A convolutional neural network (CNN) model is trained using a dataset that includes various photos of both healthy and sick cotton plants. The suggested model offers a dependable and time-efficient solution by exhibiting high accuracy in differentiating between different diseases. Moreover, proactive disease detection is made possible by the integration of real-time monitoring systems, such as drones fitted with high-resolution cameras. Early detection lessens the need for broadspectrum antibiotics by enabling the prompt application of preventive measures, such as targeted therapies. Finally, we conduct a comprehensive computational analysis of eight cutting-edge object detection algorithms on the cotton plant dataset to identify diseases on the leaves and seven cutting-edge classification algorithms on the cotton plant datasets to determine if a leaf has a disease or not. computed results indicate that it has a high degree of object detection accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancing Rehabilitation Through Low Weight Hand Assistive System: Design and Impact Analysis 38

Advancing Rehabilitation Through Low Weight Hand Assistive S...

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Singh, Kushagra Momin, Kafil Abbas Patil, Anshul V Rao, Madhav International Institute of Information Technology Bangalore Dept. of Electronics and Communication Engineering Karnataka India

ISBN: (纸本)9798331522445

This paper introduces a Smart Hand Mobility As-sistive Device designed to aid individuals with impaired hand function due to conditions such as stroke, spinal cord injuries, and neuromuscular disorders. The device enhances daily activities and provides comprehensive rehabilitation support. Leveraging advanced sensor technology, real-time data processing, and adaptive actuation, it detects and amplifies subtle finger movements, facilitating precise hand motions. Unlike conventional methods that are often slow and lack real-time feedback, the proposed design solution offers immediate functional assistance and pro-gressive rehabilitative training. The device integrates seamlessly with a user-centric mobile application offering predefined phys-iotherapy exercises tailored to individual needs. Additionally, the application includes interactive games that engage users in therapeutic activities to improve motor skills and cognitive functions. Experimental evaluations assess the device's efficacy in enhancing grip strength, dexterity, and overall hand function. The system also features multiple control modes, allowing users to select from manual assistance, cyclic movement training, or task-specific routines. Through this approach, our device aspires to significantly elevate the quality of life for individuals with hand mobility impairments, positioning itself as a transformative tool in assistive technology and rehabilitative care. © 2025 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Investigating Principle Component Analysis Impact on the Performance of Machine Learning Classifiers: A Health Informatics Application 25

Investigating Principle Component Analysis Impact on the Per...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Banimustafa, Ahmed Almatarneh, Sattam Bulkrock, Olla Alazaidah, Raed Almahasneh, Hossam Samara, Ghassan Higher Colleges of Technology Computer Information Science Dept. Abu Dhabi United Arab Emirates Zarqa University Data Science & Artificial Intelligence Dept. Zarqa Jordan University of Business and Technology College of Engineering Jeddah Saudi Arabia Princess Sumaya University for Technology Software Engineering Dept. Amman Jordan Zarqa University Computer Science Dept. Zarqa Jordan

ISBN: (纸本)9798331540012

Principal Components Analysis (PCA) is a popular dimensionality reduction and feature selection technique. It works by swiping non-informative features while retaining those that are still potentially useful. However, regardless of its wide applications in statistical analysis, the influence of PCA on the performance of classification algorithms has been rarely studied, particularly in the domain of medical image classification. In this paper, we present a thorough analysis of the influence of applying PCA on the classification of medical images. The dataset used in this study consists of thousands of images that represent four types of blood cells. These images are used to train three machine-learning classifier models after transforming images into numerical vectors using a CNN pre-trained embedding algorithm, where each image is encoded using one thousand numerical vectors. The study involves building three classification models using (1) K-nearest Neighbor (KNN), (2) Logistic Regression (LR), and (3) Random Forests (RF). Each model was built twice, once after the application of PCA to reduce the dimensionality of the embedded features and once with the original embedded features. The performance of each model is evaluated using Classification accuracy, F1, AUC, Recall, precision, and specificity metrics. The recorded performance is then compared to drawing a decisive conclusion. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Recommendation System for Research Grants 7

Recommendation System for Research Grants

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Lokhande, Sharayu Tholia, Rakesh Upadhyay, Mukul Choudhary, Sachin Rathore, Kuldeep Pawar, Shilpa Army Institute of Technology Pune Dept. of Computer Engineering Pune India Army Institute of Technology Dept. of Computer Engineering Pune India

ISBN: (纸本)9798350304268

This research paper proposes the design and implementation of a recommendation system for researchers to simplify the process of finding research grants. Despite the positive impact that researchers and scientists have on the world through their discoveries and innovations, securing funding for their projects remains a challenging and time-consuming task. This paper objects to address the issue by introducing a recommendation system that leverages the architecture of the system, detailed design, project planning, and requirements to suggest grants that researchers may find interesting based on their platform activities. The proposed system will be beneficial for researchers, students, and scientists seeking grants, as it will provide an efficient and user- friendly way of finding grants that fit their interests and project requirements. © 2023 IEEE.

关键词： decision trees GBDT

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：