检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Kumar, Ayush Singh, Deepanshi Meerut Institute of Engineering and Technology Miet Computer Science and Engineering Meerut India

ISBN: (纸本)9781665474924

The goal of our research is to propose a system that automatically marks the attendance among the students in class using a webcam with Face Recognition. Since traditional ways of taking attendance are not that useful as it is highly time-consuming to mark the attendance of every student by calling their names as well as the use of papers to mark the attendance also affects our environment, therefore our system helps to save time as well as its eco-friendly as no paper is needed, helps to solve problems of fake attendance and proxies. The Haar Cascade & LBPH algorithms are used in this work to develop a Student's Attendance System with facial recognition technology. Face detection and recognition are two steps in realtime human face recognition. As of Haar Cascades algorithm's excellent precision and high real-time permit rate, which is implemented in OpenCV via the Python language, we use it for face detection. The training phase and evaluation phase are two categories taken into consideration in face recognition. The algorithm is trained during the training phase using samples of the image to be learned and the test image is compared across all trained samples in the dataset during the estimate step. By using Local Binary Patterns Histogram(LBPH), the live stream's faces are recognized & the face characteristics are taken out. Face recognition is completed using the Euclidean distance classifier using the LBPH. The control of the system in computer-based communication is significantly impacted by authentication. The system will automatically keep track of students' attendance in a classroom and will give faculty members the ability to conveniently access student data by keeping a log of their clock-in times. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Compound attention embedded dual channel encoder-decoder for ms lesion segmentation from brain MRI

引用

Multimedia Tools and Applications 2024年 1-33页

作者： Ghosal, Palash Roy, Abhijit Agarwal, Rohit Purkayastha, Kunal Sharma, Aaditya Lochan Kumar, Amish Department of Information Technology Sikkim Manipal Institute of Technology Sikkim Manipal University Majhitar Sikkim Rangpo737136 India Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur713209 India Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Majhitar Sikkim Rangpo737136 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute West Bengal Kolkata700108 India

Multiple Sclerosis (MS) lesions’ segmentation is difficult due to their variegated sizes, shapes, and intensity levels. Besides this, the class imbalance problem and the availability of limited annotated data samples obstruct the building of highly efficient deep learning-based models. Though researchers have made many attempts to design efficient deep learning-based models, the maximum Dice Coefficient achieved by their models is fairly below the acceptable level of 0.70. The possible reason may be due to the inability to capture sufficient local and global features of the lesions required for accurate segmentation. In this paper, we present a new deep-learning architecture based on compound attention for MS lesion segmentation from magnetic resonance images that handles the challenges of capturing the local and global variable features of the MS lesions. The proposed model is equipped with a dual-channel CNN encoder-decoder structure employing residual connections in one channel and residual channel and spatial attention in the other. The residual connections alleviate the vanishing gradient problem and pass the fine-grained information through the channels, which is crucial for pixel-wise prediction. The attention mechanism used in a channel helps to capture long-range dependencies. Thus, the complete model leverages rich global and local information through the two channels for lesion segmentation. The problem of data imbalance is handled by using the Focal Tversky loss function. Through rigorous evaluation using 3-fold cross-validation on the MICCAI 2016 challenge dataset, our model demonstrates superior performance, achieving a Dice Coefficient of 0.73, surpassing state-of-the-art models in both qualitative and quantitative assessments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aspect-oriented extraction and sentiment analysis using optimized hybrid deep learning approaches

引用

Multimedia Tools and Applications 2024年第41期83卷 88613-88644页

作者： Kotagiri, Srividya Sowjanya, A. Mary Anilkumar, B. Devi, N Lakshmi Computer Science and Engineering GMR Institute of Technology MR Nagar Andhra Pradesh Razam532127 India Andhra Pradesh Visakhapatnam530003 India Electronics and Communication Engineering GMR Institute of Technology MR Nagar Andhra Pradesh Razam532127 India

Aspect-oriented extraction involves the identification and extraction of specific aspects, features, or entities within a piece of text. Traditional methods often struggled with the complexity and variability of language, leading to the exploration of advanced deep learning approaches. In the realm of sentiment analysis, the conventional approaches often fall short when it comes to providing a nuanced understanding of sentiments expressed in textual data. Traditional sentiment analysis models often overlook the specific aspects or entities within the text that contribute to the overall sentiment. This limitation poses a significant challenge for businesses and organizations aiming to gain detailed insights into customer opinions, product reviews, and other forms of user-generated *** this research, we propose an innovative approach for aspect-oriented extraction and sentiment analysis leveraging optimized hybrid deep learning techniques. Our methodology integrates the powerful capabilities of deep learning models with the efficiency of Reptile Search Optimization. Furthermore, we introduce an advanced sentiment analysis framework employing the state-of-the-art Extreme Gradient Boosting Algorithm. The fusion of these techniques aims to enhance the precision and interpretability of aspect-oriented sentiment analysis. The proposed approach first utilizes deep learning architectures to extract and comprehend diverse aspects within textual data. Through the incorporation of Reptile Search Optimization, we optimize the learning process, ensuring adaptability and improved model generalization across various datasets. Subsequently, the sentiment analysis phase employs the robust Extreme Gradient Boosting Algorithm, known for its effectiveness in handling complex relationships and patterns within data. Our experiments, conducted on diverse datasets, demonstrate the superior performance of the proposed methodology in comparison to traditional approaches. The optimized

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Importance of Data Features Selection: Analyze Students Performance using Optimal Features Logistic Regression Model 14

Importance of Data Features Selection: Analyze Students Perf...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Khan, Javed Akhtar Indur Institute of Engineering & Technology Computer Science & Engineering Telangana Siddipet India

This is an informative article of Data Analytics for data .This article covers the various aspects of Data Analytics such as definition of Data analytics, various terminology used in Data Analytics related to data,Types of Data and various methods of data collection. Motive of this paper is to describe the importance of data quality, describe the data processing and preprocessing task for structured and unstructured data . Perform the observation through student data to find the fact about the data design architecture in term of optimization of processing steps for quality data set a case study. A case student is based on the student performance analysis based on the selected feature among the various existing features in the Data set using the machine learning regression model .Implantation related work in this paper work to produce the student performance using Internal exam and attendance and try to predict the performance of student in External Result . For this I include the Logistic Regression model to produce the result. © Grenze Scientific Society, 2023.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Security Framework for Electronic Health Record in the Cloud Based on Public key Encryption 9

Security Framework for Electronic Health Record in the Cloud...

引用

9th International Conference on Signal Processing and Communication, ICSC 2023

作者： Aruna, A. Sellam, V. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India

ISBN: (纸本)9798350383201

In the modern world, medical data is managed and stored online so that anybody can access it at any time. For maintaining medical records and sharing with other healthcare providers, the majority of hospitals already use EHR (Electronic Health Records) with cloud storage. Medical data confidentiality, authentication, integrity, and access control are just a few of the security and privacy challenges that have arisen as a result of the growth of healthcare technology and the shift to Cloud computing. In this article, a Medi-locker has been introduced to keep all of the patient's medical records where Both patient and medical practitioners can access healthcare documents at any time, from any location. To maintain the confidentiality and improve the security of the medical data Fully Homomorphic Encryption (FHE), which enables operations to be performed on data that has been encrypted without even decrypting it. The proposed scheme has a high resistance to brute-force attacks when it is compared to other cryptosystem. © 2023 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Context Sensitive Dynamic Slicing of Multi-Agent System 20

Context Sensitive Dynamic Slicing of Multi-Agent System

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Mishra, Alina Meher, S.K. Behera, H.S. Mohapatra, D.P. Veer Surendra Sai University of Technology Department of Computer Science and Engineering India National Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350305593

Dynamic slicing is a method for finding and fixing bugs and testing various software systems based on a particular execution. In case of multi agent systems, we use agents as basic run-time entity to execute the functionality. The slicing criterion is used to identify the statements in a code that modify the values of variables at a specific location in a program, either directly or indirectly. Static slicing, on the other hand, considers all possible program executions instead of a specific execution. In this research work, we designed a method for dynamic slicing Multi-Agent Systems. The first step in our method is to generate a Multi-Agent System software execution trace, which records the order of events and interactions among agents during one execution. We use this trace to create a dependency graph that shows the connections between the statements in the program. Using this dependency graph, we apply a context-sensitive approach that takes into account the context in which statements are executed to produce more precise slices. Our aim is to provide complete debugging and testing methods for Multi-Agent Systems that allow developers to easily locate and isolate program parts that are related to a certain problem or behaviour. © 2023 IEEE.

关键词： Agent Behaviors Agent-oriented Dependence Graph (AoDG) Agents Java Agent Development Framework (JADE) Message Passing Multi-Agent Systems (MAS)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm With Residual Blocks for Chemical Gas Concentration Estimation

引用

Journal of institute of Control, Robotics and Systems 2023年第7期29卷 556-561页

作者： Jang, Hee-Deok Park, Jae-Hyeon Chang, Dong Eui Seo, Hyun Soo Nam, Hyunwoo Department of Electronics Engineering Korea Advanced Institute of Science and Technology Korea Republic of Chem-bio Technology Center Advanced Defense Science and Technology Research Institute Agency for Defense Development Korea Republic of

Chemical warfare agents (CWA) are highly toxic and hazardous substances that cause serious harm to humans, even when used in small quantities. The accurate estimation of the concentration of CWA is crucial to allow effective responses to these types of attacks. In this paper, we propose a deep learning algorithm for chemical gas concentration estimation, referred to as MLP-res, and compare its estimation performance with those of other machine learning algorithms. MLP-res utilizes a structure with residual blocks and demonstrates comparable or even superior performance compared with those of existing machine learning algorithms. Additionally, MLP-res exhibits high-generalization performance even with the use of experimental condition data that were not used for training. These results indicate that MLP-res can accurately estimate the concentration of chemical gases in actual environments. © ICROS 2023.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Modeling and Prediction of COVID-19 Trajectory using Ensemble Learning 14

Modeling and Prediction of COVID-19 Trajectory using Ensembl...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Parmar, Shabnam Rani, Rinkle Kalra, Nidhi Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India

In this research work, For the event of a model that may predict and forecast death or recovery because of Covid-19 symptoms, different styles of requisite symptoms should be captured correctly, and enough data should be available to coach models of ensemble learning for accurate results. This virus may be passed from an infected person’s lips and nose to tiny liquid particles through the air by activities like coughing, sneezing, speaking, or inhalation. Ensemble Learning helps to improve machine learning results by mixing different models. it’s very useful for prediction and forecasting. In ensemble learning, different sort of algorithms is available consistent with the kind of problem and use cases. It’s part of AI and computers, primary concentrate on a way to use the info and algorithms to simulate in the same fashion as humans learn and focus on how its accuracy will be increased successively. During this research, various feature selection and extraction techniques on the Covid19 dataset are accustomed select or extracting top features, So the model is trained to employ a patient’s symptoms and other information to predict whether the patient will endure or die from their disease (Covid-19).In this research work, various ensemble algorithms are used such as Random Forest (RF), Gradient Boosting (GB), Adda Boosting (AB), and Bagging (BAG) are used. to try and do a comparative analysis on the accuracy used normal trained data set and K Fold trained data set. Ensemble Algorithms RF, GB, and AB feature selection strategies all produced highly promising results with an accuracy of 97% on Selection Techniques, and with Feature Extraction Techniques RF and Bagging also produced promising results with an accuracy of 96%. © Grenze Scientific Society, 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

EFFECTS OF VARIATION IN SOIL PARAMETERS ON RESISTANCE FACTORS OF BEARING CAPACITY OF PILES

引用

AIJ Journal of technology and Design 2024年第76期30卷 1223-1228页

作者： Suzuki, Hiroko Yasu, Hiroki Suzuki, Yasutsugu Nagai, Hiroshi Dept. of Architecture Chiba Institute of Technology Japan Technical Division Tokyo Soil Research Co. Ltd Japan National Research Institute for Earth Science and Disaster Resilience Japan Graduate School of Engineering Muroran Institute of Technology Japan

This study investigates effects of variation in soil on bearing capacity of piles. Resistance factors of shaft friction and tip resistance are estimated with using N-value measured at several points in a site. The resistance factors decrease with increasing variation of N-value. This trend is more remarkable in tip resistance than in shaft friction. This is because, in tip resistance, the variation of designed values is small and the variation of soil has an impact on resistance factors. In the case, in which soil profile is not uniform, it is important to consider the spatial distribution of soil. © 2024 Architectural institute of Japan. All rights reserved.

关键词： Limit state design Resistance factor Variation Pile Spatial distribution

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Air Defense Recommendation Model based on Fuzzy Inference System 26

An Intelligent Air Defense Recommendation Model based on Fuz...

引用

26th International Conference on computer and Information technology, ICCIT 2023

作者： Islam Arif, Md. Ariful Islam, Zohirul Sharmee, Sharmin Sultana Akhtaruzzaman, M. Military Institute of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Securing the nation's airspace demands the integration of an advanced air defense system. Automation technology can be incorporated to deploy anti-missile rockets, acting as a deterrent against various air-missile threats. This research aims to identify potential threats within a protected area and integrate an automatic system into the air defense measures based on detection. In the event of identifying incoming missiles, decisions will be made by gathering and validating information on specific issues through dedicated radars. Special emphasis is placed on utilizing a Fuzzy system to determine the nature of the threat, distinguishing between scrambling or surface-to-air missile launches based on distance, secondary radar input, and the speed of the airborne object. The paper provides a comprehensive comparison of defuzzification methods, demonstrating their effectiveness in modern air defense systems. The chosen method proves suitable, emphasizing its pertinence to contemporary air defense needs. The Fuzzy system offers insights into optimal times, types, and launch locations for interceptors or surface-to-air missiles (SAMs) within an integrated air defense system. The research evaluates the defuzzification process using five different methods, with MoM method yielding notably superior results. The incorporation of technology is crucial for ensuring the safety of protected areas, key installations, and the dynamic decision-making processes inherent in air defense systems, necessitating the use of fuzzy logic-based systems. © 2023 IEEE.

关键词： Air defense fuzzy inference system fuzzy logic integrated system intelligent system

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：