检索结果-内蒙古大学图书馆

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Sasimekala M M Siva V Shanmuga Shyam B Veeramalai Sankaradass C Selvaganesan R. Ponnusamy Department of Biomedical Engineering Chennai Institute of Technology Chennai Tamil Nadu India Dept. of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Chennai Institute of Technology Chennai Department of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The brain's unchecked and fast cell development fuels a tumor. It may prove lethal if left untreated in the early stages. Accurate segmentation and classification remain difficult despite many noteworthy efforts and promising results. The differences in the tumor size, form, and proportions make brain tumor detection extremely difficult. The primary goal of this study is to provide researchers with a thorough literature review on the use of magnetic resonance (MR) imaging in diagnosing brain malignancies. This study suggested multiple methods for detecting tumors and brain cancer using statistical image processing and artificial intelligence. An assessment matrix for a certain system employing particular systems and dataset kinds is also displayed in this study. The anatomy of brain tumors, available data sets, augmentation techniques, component extraction, and classification between machine learning (ML) and deep learning (DL) models are also explained in this work. Lastly, the study gathers all pertinent information for identifying and comprehending tumors, including their advantages, disadvantages, developments, and future trends. In this study, an attempt is made to classify the tumors using CNNs.

关键词： Deep learning Image segmentation Magnetic resonance Imaging Market research Data models Fuels Data mining Systematic literature review Image classification

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Feature Selection Techniques and Machine Learning Classifiers for Accurate Classification of Pumpkin Seeds

Comparative Analysis of Feature Selection Techniques and Mac...

引用

Information and Communication technology for Sustainable Development (ICICT4SD), International Conference on

作者： Md Abu Ismail Siddique Fariha Haque Md. Shojeb Hossain Shojol Dept. of Electrical & Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

Pumpkin seeds are widely consumed due to their nutritional content and potential health advantages. Accurately categorizing pumpkin seeds based on their diversity and distinct physical properties, such as size, compactness, roundness, and others, is crucial in agriculture, food processing, and research. In this work, two approaches were used to categorize a dataset of pumpkin seeds and establish their relative performance. The first method used a typical machine learning methodology, whereas the second used a filter-based feature selection technique. The filter-based technique used principal component analysis (PCA) and recursive feature elimination (RFE) to extract the most significant features for identifying two varieties of pumpkin seeds. Machine learning classifiers were then used to assess the performance of each strategy. Machine learning classifiers were then applied to evaluate the performance of the approach where Random Forest performed best among all others and achieved 91.80% validation accuracy. On the other hand for the conventional machine learning classifier method, six classifiers were used to evaluate the performance of this approach where the XgBoost classifier performed the best and achieved 95% as training accuracy and 94.87% as validation accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge Node Load Balancing Using Game Theoretic Approaches

Edge Node Load Balancing Using Game Theoretic Approaches

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Rajdeep Haldar Saptadip Rooj Neeraj Sharma Ritambhar Das Arnab Mandal Anjan Bandyopadhyay Dept. of Information Technology Kalinga Institute of Industrial Technology (KIIT) Bhubaneswar India School of Computer Science and Engineering Lovely Professional University Jalandhar India School of Computer Engineering Kalinga Institute of Industrial Technology (KIIT) Bhubaneswar India

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

This paper explores the application of game theoretic approaches to load balancing across edge nodes within distributed computing systems. Focusing on a non-cooperative game model, we aim to enhance system efficiency by strategically optimizing resource allocation and load distribution among autonomous edge nodes. Initial simulations demonstrate that our approach not only addresses the inherent complexities of edge environments but also outperforms traditional load balancing mechanisms in terms of both operational efficiency and system responsiveness.

关键词： Computational modeling Focusing Games Load management Complexity theory Resource management Game theory Distributed computing Load modeling Edge computing

来源：评论

学校读者我要写书评

暂无评论

Temperature Effects on Gallium Nitride Field Emitter Arrays

Temperature Effects on Gallium Nitride Field Emitter Arrays

引用

International Conference on Vacuum Nanoelectronics (IVNC)

作者： Ranajoy Bhattacharyar Pao-Chuan Shih Tomás Palacios Jim Browning Dept. of Electrical & Computer Engineering Boise State University Boise ID USA Dept. of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA

Gallium nitride (GaN) field emitter arrays are being studied for use as vacuum channel transistors (VCTs). In this work, arrays of 150×150 GaN field emitters were characterized before and after heat treatment at 400° C. Collector voltage was kept at 200V DC, and the gate voltage was swept from 0 to 75V. From the I-V measurements, a jump in emission current, a form of conditioning, was observed after a few voltage sweeps resulting in a stable emission current. After heat treatment at 400° C for 10 minutes, ≈ 4 times increase in current was observed, reaching a maximum field emission current of ≈ 10 μA, at 75 V.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task and Process Capturing Toolkit using GUI Automation 4

Task and Process Capturing Toolkit using GUI Automation

引用

4th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2022

作者： Perera, Ravindu Lakshan Bellanthudawa, Hiruni Piyumika Hevavitharana, Nipun Dimantha Ariyasinghe, Kavindu Malshan Wickramarathne, Jagath Perera, Jeewaka Sri Lanka Institute of Information Technology Dept.Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665468350

Automation is one of the best ways to make easier everyone's day-to-day life. When considering the industry, if someone could be able to automate the mechanism of solving computer software issues, that will be helpful to every company. Because most companies are facing difficulties when it comes to giving IT support. Some companies are suffering from a lack of IT supporters because they have to solve the same problem on different computers at the same time. This most likely reduces the efficiency of the company and affects its performance as well. Without the proper knowledge of technology, employees tend to get a lot of technical issues while working with the technology. Here comes the opportunity to automate the IT-related problem-solving mechanism. That will save a lot of time and increase the company's efficiency as well. While carrying out the background research we thought, by automating the IT-related problem it will reduce the allocation of human power and that will directly affect company efficiency. The research team came up with the idea of creating a software product that can export an executable file by capturing selected tasks of the user's screen and its' relevant processes. Task and process capturing toolkit is a software product called the 'ClickMe toolkit'. It can capture relevant processes that are happening in any computer which runs on Windows 10 platform, then make a script called 'ClickMe script', and convert it into an executable file. It can be run on any Windows 10 Platform. © 2022 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature Engineering and Sampling Strategies for Enhanced Diabetic Retinopathy Classification

Hybrid Feature Engineering and Sampling Strategies for Enhan...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： C Vanlalnunpuia Lalhmingliana V. D. Ambeth Kumar R Vanlalawmpuia David Lalmuanpuia Khiangte Ajoy Kumar Khan Dept. of Computer Engineering Mizoram University Aizawl India Dept. of Information Technology Mizoram University Aizawl India Ophthalmologist Eye Care Hospital Aizawl India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

This study presents a machine learning approach for Diabetic Retinopathy (DR) classification, integrating advanced preprocessing, feature extraction, and adaptive sampling. Preprocessing techniques, including CLAHE, gamma correction, and noise reduction, standardize image quality while preserving anatomical details. Class imbalance is addressed with ADASYN, generating synthetic samples in sparse regions for balanced class representation. Feature extraction focuses on clinical markers like vascular density, microaneurysms, exudates, and texture descriptors such as GLCM and LBP. Recursive Feature Elimination (RFE) refines features for better interpretability and reduced computational load. This binary classification framework achieves 92.91% accuracy on test data and a cross-validated ROC AUC of 0.994, demonstrating the effectiveness of hybrid feature engineering and intelligent sampling in DR detection.

关键词： Diabetic retinopathy Adaptation models Accuracy Pipelines Noise reduction Feature extraction Retina Robustness Medical diagnostic imaging Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Smart Job Recruitment Automation Using Location Based Filtering

Smart Job Recruitment Automation Using Location Based Filter...

引用

2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2021

作者： Pandithurai, O. Jayashree, D. Aarthy, D.K. Jaishree, R. Bhavani, K. Dharani, T. Rajalakshmi Institute of Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665428293

Knowledge is both theoretical and practical information, facts and skills we acquire through experience or learning. Our knowledge increases as we gain more experience. To. The employers often receive an enormous number of applications which is usually unstructured resumes that are different to process and analyze manually. The traditional method of recruitment is becoming inefficient. Because of the rapid advancement of Internet technology, many businesses have switched to an online recruitment approach. To overcome the drawbacks there are several automatic recruitment systems have been proposed. The online recruitment system has proved to be more effective in processing Candidate resumes and matching them to their relevant job posts. The effectiveness of the proposed system is need for a location-based services that can recommend users for jobs within their location. The advantage of this system is to reduce the traveling distance, save time, easy process and make offers confidential. Therefore, this website access the location of job seekers. It helps job seekers to apply for the job which is nearby their location and also satisfy the company requisite. © 2021 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis on Voice Based Reviews Using Fuzzy Logic

Sentimental Analysis on Voice Based Reviews Using Fuzzy Logi...

引用

2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2021

作者： Jayashree, D. Pandithurai, O. Prasad, Smisha Suresh, A.S. Vigneshwaran, S. Rajalakshmi Institute of Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665428293

E-commerce websites becoming the future of the market, manufacturers have to keep their products updated to compete among different brands. Improvements according to their customer's needs help them to stay active in the competition. To improve their product, reviews are an important medium in achieving it. Customers also prefer to buy products online depending on the ratings and reviews of a product. Reviews that are written may not deliver all the emotions a customer needs to convey but in the case of a speech review, it almost delivers the information that the customer needs to convey. In this process, the customer submits the review as an audio file which is then converted into a text file using Natural language Processing. The user-driven reviews of a product are processed using sentimental analysis. The proposed system involves fuzzy logic for classifying the reviews into positive, negative, and neutral reviews and for assigning weightage to the words. © 2021 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

An Agent-Based Approach for Modeling Disease Control Strategies Using the SIR Model

An Agent-Based Approach for Modeling Disease Control Strateg...

引用

International Conference on New Trends in Computing Sciences (ICTCS)

作者： Amera Al-Amery Rabiah Al-Qudah Dept. of Data Science and AI Princess Sumaya Univ. for Technology Amman Jordan Dept. of Computer Science and IT Abu Dhabi University Abu Dhabi UAE

ISBN: (数字)9798331523411

ISBN: (纸本)9798331523428

Understanding infectious disease transmission is essential for reducing pandemic impacts. While previous models have assessed the effects of individual intervention strategies, few have examined their combined impact. This study develops an agent-based model integrating multiple interventions within a traditional SIR framework. This study uses an agent-based SIR model to simulate disease spread and assess control strategies such as face covering and quarantine, represented by five different scenarios. Without interventions, infections peak at 50% of the population. Scenarios show that 10% quarantine compliance reduces peak infections by only 10%, while 50% compliance cuts it by 50%. Preventive strategies significantly reduce this impact; for instance, 50% compliance with masks and quarantine lowers peak infections to under 30% and delays the epidemic peak, providing critical time for healthcare preparedness. These findings guide policymakers in designing adaptive strategies to optimize public health and resources.

关键词： Analytical models Adaptation models Infectious diseases Pandemics Computational modeling Market research Delays Public healthcare Bioinformatics Faces

来源：评论

学校读者我要写书评

暂无评论

COBRA: A Continual Learning Approach to Vision-Brain Understanding

arXiv

引用

arXiv 2024年

作者： Nguyen, Xuan-Bac Choudhary, Arabinda Kumar Sinha, Pawan Li, Xin Luu, Khoa Serna-Aguilera, Manuel Dept. of Electrical Engineering and Computer Science University of Arkansas AR United States Dept. of Radiology SUNY Upstate Medical University NY United States Dept. of Brain & Cognitive Sciences Massachusetts Institute of Technology MA United States Dept. of Computer Science SUNY Albany NY United States

Vision-Brain Understanding (VBU) aims to extract visual information perceived by humans from brain activity recorded through functional Magnetic Resonance Imaging (fMRI). Despite notable advancements in recent years, existing studies in VBU continue to face the challenge of catastrophic forgetting, where models lose knowledge from prior subjects as they adapt to new ones. Addressing continual learning in this field is, therefore, essential. This paper introduces a novel framework called Continual Learning for Vision-Brain (COBRA) to address continual learning in VBU. Our approach includes three novel modules: a Subject Commonality (SC) module, a Prompt-based Subject Specific (PSS) module, and a transformer-based module for fMRI, denoted as MRIFormer module. The SC module captures shared vision-brain patterns across subjects, preserving this knowledge as the model encounters new subjects, thereby reducing the impact of catastrophic forgetting. On the other hand, the PSS module learns unique vision-brain patterns specific to each subject. Finally, the MRIFormer module contains a transformer encoder and decoder that learns the fMRI features for VBU from common and specific patterns. In a continual learning setup, COBRA is trained in new PSS and MRIFormer modules for new subjects, leaving the modules of previous subjects unaffected. As a result, COBRA effectively addresses catastrophic forgetting and achieves state-of-the-art performance in both continual learning and vision-brain reconstruction tasks, surpassing previous methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

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：