检索结果-内蒙古大学图书馆

Behaviour-constrained support vector machines for FMRI data analysis

AIP Conference Proceedings 2023年第1期2523卷

作者： Pardeep Kumar J. Jegan Amarnath K. Somasundaram Thilagavathy A. 1Department of Artificial Intelligence Anurag University Hyderabad Telangana India. 2Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India. 3Department of Computer Science and Engineering Chennai Institute of Technology Malayambakkam Chennai Tamil Nadu India. 4Department of Computer Science and Engineering R.M.K. Engineering College Chennai Tamil Nadu India.

Statistical learning approaches, including SVM, are a powerful tool for studying functional imaging data. These were especially effective in extracting information from useful magnetic resonance imaging signals from the direction and location of visual properties and categories of objects. Computational intelligence methods are developed to decipher neural imagery information as a valuable tool. The distorted signal and the small number of test patterns usually reported in functional brain imaging studies pose problems when interpreting brain data by using predictive learning techniques. To solve this issue, we propose to use previous details focused on human observers’ behavioral success to boost the training of Support Vector Machines (SVMs). During functional resonance screening, we gather behavioral reactions to human participants executing a classified mission. We use the brain imaging method developed based on the behavioral choices of observers as a distance limit for SVM training. We name the behaviourally limited SVM process. Our results show that BCSVM consistently outperforms SVM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parametric heart activity condensed photoacoustic stimulation from MRI images

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： T. Senthil Kumar Maram Ashok M. Suresh Anand Karthikeyan Palaniappan 1Department of Electronics and Communication Engineering GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India. 2Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India. 3Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India. 4Department of Centre for System Design Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India.

In this article, we propose a computer research approach that uses only a few tomographic optoacoustic projections to analyze main components for high-frame volumetric heart imagery is seen herein in the non-invasive imaging of a smoking rodent. This approach is beneficial for discerning periodic movements. The training process allows the heart motion information to be effectively compressed and used in a higher frame rate as prior information for image restoration. Image consistency with report book decrease in the data flow is seen to be safeguarded. We prove that the parametric motion can be effectively obtained under such conditions by focusing on moment data from a single tomographic detector. A visualization of perfusing a contrast agent in vivo indicates the possibility of recording intermittent (quasi) events not recorded in the training process. The proposed method can be used to dramatically improve optoacoustic imaging time resolution and help create more accessible and data efficiency systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a safety system for drainage workers - Li-Fi technology

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： M. Narendra M. Nithya Arun Kumar Pallekonda Yoganand Selvaraj 1Department of Information Technology CMR Engineering College Hyderabad Telangana India. 2Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India. 3Department of Electrical and Computer Engineering Bule Hora University Bule Hora Addis Ababa Oromia Ethiopia. 4Department of Computer Science and Engineering Madras Institute of Technology Chennai Tamil Nadu India.

In underground sewage a few sorts of unsafe things happened to the specialists. Because of inward breath of harmful gases, they experience the ill effects of various kinds of lung illnesses and furthermore because of the great seepage level a few wounds were happened to the waste laborers, now and then it prompts passing. Yet, the evacuation of seepage squanders is a fundamental one to every one individual to lead the solid life. There are various kinds of framework accessible to screen the laborers in underground. The current framework utilizes IoT as a method of correspondence between the laborers and the comparing specialists. Yet, the proposed framework utilizes Li-Fi as a correspondence mechanism for the laborers. In this way, the framework comprises of transmitter and beneficiary, the correspondence happens through apparent light. The framework screens the climate of waste territory and wellbeing level of the specialist and communicate those qualities to the client by means of TX. The specialists have the current circumstance of the underground seepage, so in the event of any issue happens the safety measure can be taken by the comparing authority.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Custom written sentiment analysis supported Twitter data

引用

AIP Conference Proceedings 2022年第1期2464卷

作者： M. Nithya M. Pachhaiammal Priya V. Lalitha S. Samundeswari 1Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India 2Department of Computer Science and Engineering Sri Sairam Institute of Technology Chennai India 3Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India 4)Department of Computer Science and Engineering Sri Sairam Engineering College Chennai India

This paper helps to make the created Twitter Data more understandable. It streams real-time tweets, or can fetch tweets from specific topics or keywords. It then analyses the data using a custom-written sentiment analysis algorithm, and eventually displays the results with a series of dynamic *** data visualizations. It has a wide range of uses, for analyzing the effectiveness so for marketing campaign, to compare two competing topics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification system on diabetes prediction using deep learning approach

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： S. Thaiyalnayaki G. Kalaiarasi M. Nithya R. Padmavathy 1Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai Tamil Nadu India 2Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamil Nadu India 3Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India 4Department of Electronics and Communication Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai Tamil Nadu India

Diabetes is considered one of the deadliest and most persistent diseases that cause glucose levels to increase. Complications can arise if diabetes is left untreated and undiagnosed. Patient visits specialist to determine the results of the patient status are usually to found. No matter how you look at it, the growth of methods to cope with AI is critical. There is a goal in this study to develop a model that can accurately predict the risk of diabetes in a patient population. Decision Tree, SVM, and Naive Bayes are used in this study to detect diabetes. The UCI AI library's Pima Indians Diabetes Database (PIDD) performs experiments. The presentation of each of the three computations is based on various factors, such as precision, accuracy, f-measure, and recall. Precision is measured by comparing instances to categorize the results as normal or abnormal and verify using the Receiver Operating Characteristic (ROC) curves.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mature antibody immune response over SARS-CoV-2 as a pattern recognition with artificial immune system

引用

AIP Conference Proceedings 2022年第1期2481卷

作者： Manita Dhyani Dibyahash Bordoloi Anupriya Sharma Ghai 1Department of Computer Science and Engineering Graphic Era (Deemed to be) University Dehradun Uttarakhand India 248002 2Department of Computer Applications Graphic Era Hill University Dehradun India

A natural immune system has a remarkable ability to recognise self from nonself antigens in human body. The immune system has a natural ability to learn, recognise and respond accordingly to protect human body against viruses and diseases. B-cells produce detectable antibodies and immunoglobulins and are responsible for humoral antibody immunity (IgM, IgG). Memory cells play an important role in this entire reactive process. With the help of these memory cells, the immune system recognises and responds immediately to the second entry of infection.I propose a supervised machine learning method (Immunos -R) to give an approach to build an immune response model to get an accurate antibody immunological response to SARS-CoV-2 without doing in-vitro laboratory *** rate for antibody immunological response (B lymphocytes cells subset) is 96.0% at fourth split and lowest at 8th split 68.0%

关键词：

来源：评论

学校读者我要写书评

暂无评论

RPM prediction model for reducing dimensions by combining PCA, K-means using MLAS in identifying a disease

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： A. P. Bhuvaneswari R. Praveen Sam C. Shoba Bindu 1Department of Computer Science and Engineering Jawaharlal Nehru Technological University Anantapuramu Anantapur Andhra Pradesh India 2Department of Computer Science and Engineering G Pulla Reddy Engineering College Kurnool Andhra Pradesh India

A large population around the world is unaware of the health condition early in their life which can increase their life span. This paper presents an efficient Risk Prediction Model (RPM) for the accurate prediction of the diseases early enough. Medical datasets have a greater number of dimensions for diagnoses and prediction of disease accurately. PCA is applied to the given dataset, as a greater number of features will reduce the model accuracy. The reduced datasets are clustered using the popular K-means algorithm to remove the outliers. Supervised machine learning classification algorithms are used in calculating the accuracy for the clustered medical datasets. Our main goal is to detect the disease early in the life and analyze the risks associated with the disease for a longer span of life. The RPM comprises of PCA, K-means and machine classification algorithms. Experimental results show that RPM model attains an accuracy of 1.94% higher when compared with other published studies. The proposed RPM algorithm yielded outstanding results by automatically predicting the presence of disease with high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task scheduling in geo-distributed big data using ant colony optimization

引用

AIP Conference Proceedings 2022年第1期2405卷

作者： J. Rajkamal P. Ezhumalai 1Department of Computer Science and Engineering Sri Venkateswara Institute of Science and Technology Thiruvallur Tamil Nadu INDIA 2Department of Computer Science and Engineering R.M.D. Engineering College Chennai Tamil Nadu INDIA

Our commercial application main design depends on the big data in grid computing, distributed computing, and fog computing. The significant challenges facing big data is higher time consumption and cost consumption. Scheduling algorithm is used to save time and money to introduced in big data analytics. The proposed work deals with a significant challenge in task planning. The formidable Optimization challenge in the meta-heuristic algorithm is a considerable solution for cloud task planning. An effective task Manager includes the changes in the working of the task algorithm's task and schedule. Work consists of the cloud a task-based policy of the Ant Colony Optimization (ACO) listens to the various programming algorithm such as first in first out and Round Robin arbitrary algorithm. The purpose of this algorithm is to increase the efficiency of the scheduled task within cloud computing. ACO is an arbitrary Optimization technique that selects the various functions from the incoming jobs to virtual machines. Cloud-Sim toolkit package is used to simulate the proposed algorithm. Various experimental studies were carried out with cloud activities using first in first out and Round Robin based on the ACO technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Use of agile software development method to manage academic resources

引用

AIP Conference Proceedings 2022年第1期2481卷

作者： Anupriya Sharma Ghai Divya Kapil Lakshita Sejwal Atika Gupta Swati Devliyal 1Department of Computer Applications Graphic Era Hill University Dehradun India 2Department of Computer Science & Engineering KCC Institute of Technology & Management Noida India 3Department of Computer Science and Engineering Graphic Era University Dehradun India

Agile is a method that moves quickly, lightly, and approachable in developing a software process. The primary goal of agile methodology is to produce high-quality software in a quicker time. It is using this methodology for developing the Academic Resource in a system provided by software for maintaining academic and financial records of data efficiently and conveniently. The administration of any academic association must make records of students registered and the staff of the university on paper and keep them safe, which is a tedious task due to the increase in manual work that reduced the utilization of the efficiency of staff. This paper describes a systematic approach to developing a user-friendly, flexible, and easy-to-maintain environment for academic resources using agile's extreme programming. The execution of the different tasks to develop the system is used to widen the horizons in Agile Methodologies step by step.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Critical success factors for client proposal selection: A vendor perspective in offshore software maintenance outsourcing

引用

AIP Conference Proceedings 2023年第1期2484卷

作者： Atif Ikram b) Masita Abdul Jalil Amir Bin Ngah Ahmad Salman Khan Tahir Iqbal 1School of Informatics and Applied Mathematics Universiti Malaysia Terengganu Malaysia 2Department of Computer Science & Information Technology The University of Lahore Pakistan 3Department of Software Engineering The University of Lahore Pakistan 4Department of Computer Science Bahria University Lahore Campus Pakistan

Offshore Software Maintenance Outsourcing (OSMO) is increasing by leaps and bounds. In offshore outsourcing, most of the highly-paid countries outsource software development and maintenance projects to such developing countries where skilled human resources are available at economical packages. The OSMO clients get quality-oriented services and OSMO vendors earn valuable foreign exchange if the OSMO process is executed successfully. But the existing literature advocates that all the OSMO business deals do not end successfully. The right combination of vendor and client plays a vital role. For a vendor, it is important to find a more suitable client among multiple options. The scope of the current paper is to find out such critical success factors which can help out OSMO vendor to select a more suitable OSMO client among many options. This practice will provide ease to OSMO vendors in the OSMO client selection and decision-making process to select a suitable client. The method used to conduct this study is the Literature Review (LR). The literature review found different critical success factors related to the research question. Some of these factors include the client's contract, the client's required team size, the domain of the required project, the size of the software maintenance project, etc. OSMO vendor organizations can use this information in the decision-making process to select more suitable OSMO clients for successful offshore business. This study also recommends the implementation of any suitable machine learning technique on the critical success factors (founded in the current study) in the decision-making process.

关键词：

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：