检索结果-内蒙古大学图书馆

6th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2021

作者： Harlapur, Nehabanu H. Handur, Vidya School of Computer Science and Engineering KLE Technological University Hubballi580031 India

ISBN: (纸本)9789811935701

Health care is important to live a happy and healthy life [1]. So Chatbots can be helpful in monitoring current health status before visiting the doctors physically. Doctor Chatbot is a means to communicate with man and machines. A Doctor Chatbot allows a user to ask queries about a health issue in a manner that they would consult a doctor. Doctor Chatbot interprets human input and responds back using Artificial Intelligence [2] and Natural Language Processing. Therapeutic, Educational, Agricultural areas are important domains to consider. Chatbots can now be utilized everywhere and at any time. Every day, a large number of people, both young and elderly, suffer as a result of a heart attack. In the proposed study the main objective is to predict whether a person has heart related issues using Deep Learning Techniques of Machine Learning. As a result accuracy of the prediction is measured. Comparative analysis of SVM, Naive Bayes, KNN algorithm is carried out and SVM outperforms other two algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Understanding the Influence of Student's Emotions in Academic Success 2

Understanding the Influence of Student's Emotions in Academi...

引用

2nd Edition of IEEE Delhi Section Owned Conference, DELCON 2023

作者： Koppad, Sahana Gadad, Jyoti Patil, Preeti Vijayalakshmi, M. Kle Technological University School of Computer Science and Engineering Hubli India Kle Technological University Centre for Engineering Education Research Hubli India

ISBN: (纸本)9798350322064

Humanity has evolved, changing how one perceives and experiences emotions. Darwin states that emotions serve a purpose because they wouldn't have developed if they were purely incidental. Typically, emotions are triggered by an interior or exterior experience that has either a positive or negative meaning for the person in question. Emotional intelligence (EI) is the ability to deal with a situation consciously. Emotional intelligence is not likely a significant predictor of work success. Emotions and moods are distinct;the former is more robust and less long-lasting. It has been observed that students have a lot to deal with emotionally (academic/non-academic). This observation necessitates researchers to understand how emotional intelligence affects students' academic performance. The current study focuses on how engineering students' academic performance is significantly influenced by emotional intelligence. The study used a quantitative research approach. The study is to investigate the impact of EI on the academic performance of 5th-semester undergraduate engineering students at kle technological university in India. For collecting the data, a purposive sampling strategy was used. The information was gathered through a questionnaire asking students about their emotional intelligence. A sample size of 159 was obtained and analysed. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation Using U-Net Architecture for Change Detection on Hyperspectral Imagery

Semantic Segmentation Using U-Net Architecture for Change De...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Bidari, Indira Chickerur, Satyadhyan Kadam, Srishti School of Computer Science & Engineering Kle Technological University Karnataka Hubballi India

ISBN: (纸本)9798350313987

Modern research focuses on the creation of cutting-edge image processing methods designed for the analysis of vast amounts of spatial and temporal data gathered from satellite imagery. These techniques have a primary objective to enhance the clarity and precision of satellite images, consequently unveiling insights into previously undiscovered changes in land cover. Recent strides in image processing, with a particular focus on the utilization of Fully Convolutional Neural Networks (FCNNs) have become essential tools. The primary goal is to evaluate the performance of the U-Net architecture in recognizing changes in multi-temporal satellite images and associating objects inside land-covered regions. Multi-Class Change Detection (MCD) is expanded upon by Semantic Change Detection (SCD). It holds a central role in this endeavor, offering detailed insights into modifications occurring in specific geographic locations, as well as changes in land cover and land use. This high-fidelity change data holds wide-ranging applications and significantly enriches our comprehension of dynamic environmental shifts. © 2023 IEEE.

关键词： Hyperspectral Image Satellite Imagery Semantic Change Detection U-Net architecture

来源：评论

学校读者我要写书评

暂无评论

Unveiling Complexity: Synergizing Deep Learning and Computational Fluid Dynamics for Blood Flow Analysis

Unveiling Complexity: Synergizing Deep Learning and Computat...

引用

2023 IEEE Technology and engineering Management Conference - Asia Pacific, TEMSCON-ASPAC 2023

作者： Hiremath, Uma M Chickerur, Satyadhyan Kle Technological University Vidyanagar School of Computer Science and Engineering Karnataka Hubballi India

ISBN: (纸本)9798350384659

Deep learning and healthcare have recently seen major advancements. The study introduces an innovative framework for analyzing and forecasting blood flow behavior in complex anatomical structures using computational fluid dynamics (CFD) simulations and deep learning methods. The synergy enhances accuracy and efficiency in characterizing blood flow patterns, turbulence, and hemodynamic parameters. In the proposed study, a comprehensive dataset of patient-specific vascular geometries and corresponding hemodynamic conditions is employed to train a deep neural network. The neural network is designed to learn the intricate relationships between input geometry, flow conditions, and the resulting blood flow patterns obtained from CFD simulations. By undergoing a series of iterative training stages, the neural network becomes proficient in precisely forecasting blood flow attributes, consequently leading to a substantial reduction in the computational workload typically associated with conventional CFD simulations. Furthermore, the developed framework provides valuable insights into the impact of various physiological factors on blood flow dynamics. The deep learning model's ability to generalize from the training data allows for the exploration of a wide range of scenarios, contributing to a deeper understanding of the underlying mechanisms governing blood flow behavior. The study shows that the developed neural networks accurately predict blood flow attributes, supported by architecture-specific accuracy scores. Notably, the neural network attains an overall accuracy of 0.9970, outperforming other architectures, such as LSTM (0.9779), GRU (0.9916), and RNN (0.9888). To affirm the efficacy of the CFD-deep learning framework, thorough comparisons are conducted between the model's predictions and conventional CFD simulations. The results demonstrate a notable convergence between the two methods, validating the accuracy and reliability of deep learning predictions. © 2023 IEE

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

GAN: A Novel Approach for Cartoonizing Real Images 3

GAN: A Novel Approach for Cartoonizing Real Images

引用

3rd International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2023

作者： Sushmitha, P. Hanchinamani, Gururaj Madanbhavi, Lalitha Baligar, Vishwanath P School of Computer Science and Engineering Kle Technological University Karnataka Hubballi580031 India

ISBN: (纸本)9798350306989

Recent years have seen significant advancements in image processing, especially in transforming authentic images into cartoon-like visualizations. This study introduces a new technique for creating high-quality cartoon images that simulate hand-drawn illustrations using a robust framework called Generative Adversarial Networks. The proposed method integrates generative adversarial networks' capabilities with unique loss function and style transfer approaches to achieve precise and visually appealing cartoon-styled outcomes. The loss function combines adversarial and content-based losses to capture crucial elements while maintaining the desired cartoon-like appearances. Additional components such as style transfer and edge detection enhance the cartoonization process. Based on experiments conducted on several datasets, the proposed strategy has proven effective and adaptable in producing high-quality cartoon images that retain the artistic essence and accurately depict the original data. This research has the potential to benefit various applications, including character design, animation, and digital storytelling, by providing artists and designers with a powerful tool for converting real-world pictures into fascinating cartoon renderings. Moreover, this work offers insightful guidance for professionals and researchers interested in cartoonification and its related applications. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Blood Flow Analysis in MRI Images 3

Deep Learning Based Blood Flow Analysis in MRI Images

引用

3rd International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2023

作者： Hiremath, Uma M Chickerur, Satyadhyan School of Computer Science and Engineering Kle Technological University Vidyanagar Karnataka Hubballi India

ISBN: (纸本)9798350306989

The study, deep learning algorithms, and compu-tational fluid dynamics (CFD) are combined to analyze blood flow patterns in MRI images. Due to complicated physiological structures and turbulent flows, traditional approaches for blood flow analysis in medical imaging frequently face challenges. In the current study, a deep learning architecture is suggested to accurately extract flow data from MRI scans, offering thorough insights into vascular behavior. Following the extraction, the data are merged into a CFD simulation, allowing for accurate hemodynamic modeling. The combination of deep learning and CFD improves the precision and effectiveness of blood flow analysis, paving up the possibility of potential developments in cardiovascular disease diagnosis and treatment planning. The suggested method employs deep learning-based techniques for flow analysis, ROI extraction, and image pre-processing. It's significant that the method presents a possible classification system for both normal and abnormal aortas. Fundamental flow characteristics, such as velocity, pressure, and turbulence, may be calculated using CFD and are crucial for understanding the underlying flow patterns. It is now possible to analyze and identify a variety of aortic issues with the aid of MRI images and the integration of CFD and deep learning, improving diagnosis and patient care. Experimental findings show the effectiveness with which the suggested method captures complex flow patterns and advances our knowledge of vascular dynamics. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Classification of Usual and Atypical Ductal Hyperplasia using Deep Learning

引用

Procedia computer science 2025年 260卷 561-569页

作者： Puneet Pandit Shrinivas D Desai Gururaj N Bhadri Student School of Computer Science & Engineering KLE Technological University Hubli - 580031 Professor School of Computer Science & Engineering KLE Technological University Hubli – 580031 Professor Department of Mathematics KLE Technological University Hubli - 580031

Breast Cancer is the leading cause of death among women. In the diagnosis of preinvasive breast cancer, some of the intraductal proliferations pose a special challenge. One such challenge includes the classification of usual ductal hyperplasia (UDH), atypical ductal hyperplasia (ADH), and ductal carcinoma in situ (DCIS). Prognosis and diagnosis of intraductal breast lesions pinpointing invasive and non-invasive cancer lesions is a monotonous task due to their similar structures in biopsy samples of breast. Expert’s differential diagnosis between breast ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) is of great importance in arriving at an optimal treatment plan. In this research work, we present AI based solution to classify the most confusing stages of breast cancer, that is Usual ductal hyperplasia (UDH), Atypical ductal hyperplasia (ADH) and Ductal carcinoma in situ (DCIS) in breast biopsy. Statistical analysis is carried out to justify the results. Data set having images of normal mammary glands, invasive ductal lesions, non-invasive ductal lesions which include Usual ductal hyperplasia (UDH), Atypical ductal hyperplasia (ADH), Ductal carcinoma in situ (DCIS) in breast biopsy specimens are employed in this study. Statistical analysis is performed to provide the statistical evidence of experiments. Analysis of Variance (ANOVA) as a feature selection method is used to select best features. The proposed method has performed quite significantly, where scores are statistically and medically acceptable. The highest accuracy recorded is 83.33%. When tested for robustness, the accuracy has dropped down to 65.25% allowing one to carry out further investigations.

关键词： Deep Learning Classification Intraductal lesion Invasive ductal carcinoma (IDC) Dimensionality curse Analysis of Variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

Sign Language Detection Using YOLOv10 5

Sign Language Detection Using YOLOv10

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Madanbhavi, Lalitha Hireraddi, Devaraj Nagaral, Nitin Patil, Kushalagouda Dongrekar, Girish Iraddi, Mahendra Aralimatti, Arundati Patil, Chetan Kle Technological University School of Computer Science Karnataka Hubli India R. V. College of Engineering School of Computer Science Karnataka Bengaluru India

ISBN: (纸本)9798350376685

Communication barriers pose significant challenges for individuals who are deaf, impacting their ability to interact seamlessly in society. American Sign Language (ASL) serves as a vital communication medium within this community, yet it remains largely unfamiliar to the general populace. This gap hampers access to essential services and social interactions. Leveraging advancements in deep learning and computer vision technologies, this project introduces a real-time ASL letter detection system utilizing the YOLOv10 model, renowned for its efficiency and accuracy in object detection. The system captures live video feed via a webcam, detects ASL letters, and provides visual feedback through annotated video frames. Our model, trained on a custom dataset encompassing diverse hand positions, orientations, and lighting conditions, demonstrates high accuracy and robustness. The methodology includes data collection and preprocessing, model architecture and training, and real-time detection implementation. Evaluation metrics such as precision, recall, mean Average Precision (mAP), and accuracy affirm the model's effectiveness, with an accuracy of 92.86%. This system offers significant potential for applications in education, healthcare, and public services, promoting inclusivity and accessibility. Future work aims to enhance the model's performance by expanding the ASL dataset's size and diversity, thereby improving its ability to generalize across various real-world scenarios. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An ensemble framework of decision trees for class imbalance using partitioning

引用

International Journal of Innovative Computing and Applications 2024年第1期15卷 1-13页

作者： Kadappa, Vijayakumar Guggari, Shankru Veerabhaskar, Rajeshwari Devi Doddapoojari Department of Computer Applications B.M.S. College of Engineering Bengaluru560019 India School of Computer Science and Engineering KLE Technological University Hubballi580031 India Department of Electronics and Communication Engineering Global Academy of Technology Bengaluru560098 India

Decision tree classifiers are widely used in machine learning and data mining due to their intuitiveness. However, they do not perform well for class-imbalanced data due to bias creation towards the majority class. Therefore, handling class-imbalanced data is an active research area in many applications of machine learning. Feature set partitioning paradigm is proven to be effective for classification by many researchers. In this paper, we extend the ideas of partitioning to propose a decision tree ensemble to overcome class-imbalance issues. The framework consists of balancing the data, partitioning the feature set, building local decision trees, then combining decisions. Some instances of the proposed framework (e.g., Ferrer diagram-based approach) are used to validate the performance of the framework. An empirical study is carried out using university of California Irvine (UCI), Knowledge Extraction Evolutionary Learning (KEEL), and other datasets. The performance of the instances of the proposed framework demonstrates improved performance compared to other benchmark machine learning approaches. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Sobriety Period Prediction of Relapsed Alcohol Dependent Patients using Machine Learning Approach 2

Sobriety Period Prediction of Relapsed Alcohol Dependent Pat...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Sunitha Hiremath, P.G. Sidnal, Adarsh Jain, Sayam Pais, Vivek V. Jadhav, Rohan Motagi, Anushree Kle Technological University School of Computer Science and Engineering Karnataka Hubli India Sdm De-Addiction and Research Centre Ujire India

ISBN: (纸本)9798350306415

Purpose: To analyze the factors contributing to the relapse of persons with alcohol dependencies and to predict their sobriety period by considering male patient's data from a De addiction ***: To carry out this work,329 relapsed male patient's data was collected through the case sheets and descriptive statistics;Bivariate and multivariate logistic regression was applied to determine the prominent factors associated with relapse and their correlation by the Pearson and Spearman correlation coefficients. The sobriety period of the patients taken as the class variable, but the number of patients in each class was varying. This class imbalance was overcome by using Synthetic Minority Oversampling ***: More than 92% (303) of patients were found to be relapsed once. Among the 303 patient records, the sobriety period of 33 patients was less than a 1 month, 28 in 1-3 months, 22 in 3-6 months, 36 in 6-9 months, 70 in 9-12 months and 114 in more than a year. Around 82.8% of patients were at very high risk, 8.91% at high risk,3.96% at medium risk and 4.29% at low risk of alcohol consumption. The risk factors for relapse were Craving (r=0.13, p=0.02) and peer pressure (r=0.137, p=0.016). The Factors for sobriety were found to be motivation factor (r=0.106, p=0.007), the influence of camp and willingness for treatment (r=0.05, p © 2024 IEEE.

关键词： alcohol risk level relapse sobriety

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：