检索结果-内蒙古大学图书馆

1st International Conference on Cognitive Computing and engineering Education, ICCCEE 2023

作者： Rathor, Sandeep Tiwari, Ashish GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350332803

The global prevalence of visual impairment and blindness due to diabetic retinopathy can be significantly reduced through improved diabetes management. Diabetic retinopathy (DR) screening is crucial as it can prevent vision loss. In recent years, personalized screening intervals considering various risk factors have been proposed, showing promising cost-effectiveness ratios. However, limited funding hampers the implementation of widespread screening programs in many countries. A groundbreaking advancement in screening methods is the application of Deep Learning, which revolutionizes the detection and classification of diabetic retinopathy while reducing costs. By automating the analysis of retinal images, Deep Learning techniques enable efficient and accurate identification of DR, enabling timely intervention and treatment. Moreover, emerging research suggests that retinal imaging can not only detect existing diabetic retinopathy but also identify individuals at risk, expanding the scope of screening beyond the detection of sight-Threatening diseases. This paves the way for proactive measures to prevent or mitigate the progression of DR. Therefore, this research aims to develop a Deep Learning-based system for diabetic retinopathy detection using image processing techniques. By leveraging the power of Deep Learning algorithms and advanced image analysis, this study seeks to improve the accuracy, efficiency, and accessibility of DR screening, ultimately enhancing patient outcomes and reducing the burden on healthcare systems. © 2023 IEEE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Optimising Feature Selection: A Comparative Study of mRMR-Boruta/RFE Hybrid Approach 6

Optimising Feature Selection: A Comparative Study of mRMR-Bo...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Sharma, Manu Sharma, Dilip Kumar GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350346961

Feature selection is an essential component in the data preprocessing pipeline, particularly when dealing with datasets that possess a vast array of dimensions. In this paper, we present a time efficient wrapper technique Boruta to improve the overall complexity of our feature selection process. We have combined this wrapper technique with the filter class Minimum Redundancy Maximum Relevance (mRMR) to enhance the selection of relevant features. Additionally, our scope includes refining a previously proposed hybrid model that combines filter class Minimum Redundancy Maximum Relevance (mRMR) known for faster processing speed with wrapper class Recursive Feature Elimination (RFE) known for its high classification accuracy. We demonstrated the effectiveness of our approach on a variety of datasets and showed that our model is able to identify a smaller and more interpretable subset of features while generating better performance. Our results suggest that the combination of preprocessing and hybrid feature selection model is a promising approach to process a dataset with high dimensions.. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Heart Failure Prediction Using XGB Classifier, Logistic Regression and Support Vector Classifier

Heart Failure Prediction Using XGB Classifier, Logistic Regr...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Jain, Vinod Agrawal, Mayank GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350396485

Heart updated failure is a very serious medical issue nowadays. It causes a lot of deaths all over the world. The bad lifestyle, bad eating habits, unusual food timings are some of the factors responsible for this disease. Artificial intelligence and machine learning is a technology which is used by many researchers for prediction of diseases. Machine Learning (ML) algorithms provide some models which are first trained on a training data and then can be used to test the input data. These models are very helpful in prediction of heart disease. In this work XGBoost, Logistic Regression and Support Vector Machine ML models are used to predict heart disease. Cross validation method is used in this work which improved the prediction accuracy of all the three models. Outcoming results ensure that the XGBoost classifier is the best ML model for heart disease prediction as compared to Logistic Regression and Support vector Machine. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of Finance Risk with Clustering Algorithm Using VIKOR Method 1

Analysis of Finance Risk with Clustering Algorithm Using VIK...

引用

1st International Conference on Cognitive Computing and engineering Education, ICCCEE 2023

作者： Varshney, Neeraj Agrawal, Rishi GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350332803

This paper proposes a new approach to business valuation that considers financial and non-financial weights, taking into account both drivers and simultaneous installation of many MCDMs (many criteria decision-making) methods. The case study selected the world's leading road freight companies to determine the weight of the drivers and compare the companies using various methods. Unpredictability, performance, and innovation were the three subjective interesting measurements used to evaluate patterns. This paper proposes a hybrid interval type-2 ambiguous multi-dimensional decision-making model that utilizes the VIKOR method to solve problems with conflicting and random criteria and different units. The system created aims to find a compromise solution to the conflict that is acceptable to the decision-maker assuming that they want a closer solution and are willing to evaluate more alternatives. In this paper, linguistic values are used to evaluate and weigh the established criteria. The proposed model uses vague set theory and VIKOR to create a step-by-step multi-criteria decision-making (MCDM) model. A numerical example was provided to illustrate the application of the proposed model using various methods alternatives as clustering algorithms, financial risk analysis, Data Envelopment Analysis (DEA), and VIKOR for all implication parameters. From the results, COBWEB ranks first, whereas Graphpartitioning ranks the lowest. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Cartoon Face Detection and Recognition with Emotion Recognition

Cartoon Face Detection and Recognition with Emotion Recognit...

引用

2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Agrawal, Subhash Chand Tripathi, Rajesh Kumar GLA University Department of Computer Engineering & Applications Mathura India

ISBN: (纸本)9798350348910

In the past few years, we have witnessed a high attentiveness in cartoon media, power-driven by the strong demands of the industry. The first step to understanding this media, cartoon face recognition and detection is a very important but less explored work with fewer datasets proposed. The paper, we have proposed has two methods for face recognition and face detection for different cartoon characters that appear in comics, cartoons, games, etc. Cartoon face recognition and detection is a more difficult and challenging task than human face detection because of the many difficult scenes involved. If we aim at the characteristics of cartoon faces, huge differences within the intra-faces exist. In order to identify the emotions from cartoon images, we have employed a Deep Neural Network (DNN) approach in this paper. Two cartoon characters, 'Tom' and 'Jerry,' who each exhibit diverse emotions like surprise, happiness, sadness, and rage, were used to create the dataset. The DNN method that successfully distinguishes cartoon characters splits their face masks and names the ensuing emotions with an accuracy score. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach based on Probability Color Distribution and Color Models to Detect Salient Object 14

A Novel Approach based on Probability Color Distribution and...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Tripathi, Rajesh Kumar Chand Agrawal, Subhash Gla University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350335095

A salient object is the most important object in the scene which attracts to the human visual system. Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. This paper presents a novel approach consisting of an algorithm based on RGB and HSV color models, and probability color distribution for detecting an appropriate salient object. Firstly, the proposed algorithm removes the background pixels of the image by subtracting the average mean of RGB channels from all the channels. Thus, fewer contributing regions from the channels are removed;still, a few non-salient regions remain. Then, the mean of the RGB component is subtracted from each RGB image respectively to remove less prominent pixels of each component and a most probable salient region is obtained after combining. This image is converted into HSV color. Hue and saturation have a strong representation of the salient object. The mean of HSV is computed to remove the non-salient region. The small mean image of HSV is multiplied by the maximum mean image of RGB to obtain higher probability color regions representing the salient region. Then, the salient region is pipelined to probability color distribution computation for non-salient region removal and finalizing correct detection of the salient object. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Acre-Scale Grape Bunch Detection and Predict Grape Harvest Using YOLO Deep Learning Network

引用

SN computer Science 2024年第2期5卷 250页

作者： Sneha, N. Sundaram, Meenakshi Ranjan, Rajeev School of Computer Science and Engineering REVA University Yelahanka Bangalore India School of Computer Science and Applications REVA University Yelahanka Bangalore India

To provide the harvesting weight of grapes in real time to the farmer in the form of acres or square feet of land, the proposed system provides an estimate of grape harvest in the form of kilograms. Some of the challenges in the field where crop harvest may vary due to differences in soil, the size of grapes, maturate of the grapes, color, disease, etc. The proposed system uses YoloV5, a real-time object detection system, to detect the grape bunches, and the total bunch count is based on several images collected from the forms. The total area of acres is divided into bins, which are in turn divided into sectors. The grape data are collected from the Dodballapur district;Karnataka, which consist of 4000 grape images and manual annotation was performed on each image to classify the grape bunch and leaves. Pre-trained YoloV5 is used to detect the grapes by extracting visual features from the training images. The visual images are fetched and used to build a detection network using YoloV5. The research presents three-object detection-pre-trained YOLO models such as YoloV3, YoloV4, and YoloV5, which perform detection of grape bunches. Three models are trained on grape bunches and were compared with precision, F1 Score, and recognition recall value, achieving good results with YoloV5 along with counting grapes, which helps in knowing the harvesting status of the bunch 98%. The recall and F1 Scores are 90.2, 91.25, 95.63 and 92.21, 92.68, 93.21 for YoloV3, YoloV4, YoloV5, respectively. The network also calculates the total bunches in each image, and multiplied with average gram of a bunch and provides the final kilograms expected from each acre for the set of images collected for the particular acre. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Agriculture Grapes harvest prediction YoloV3 YoloV4 YoloV5

来源：评论

学校读者我要写书评

暂无评论

Poze with Vogue 14

Poze with Vogue

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Agrawal, Subhash Chand Tripathi, Rajesh Kumar Kishan, Jai Agarwal, Mridul Gla University Department of Computer Engineering & Applications Mathura India

ISBN: (纸本)9798350335095

We present a poze and attire recommendation system that guides a user in how to best pose while taking a picture and provides the best alternatives for their attire as well as for their poses. Given an input image the system provides most attractive poses and trending fashion attire. Recommendation results in the system are influenced by the appearance and initial pose of the input image. Additionally, the user study indicates that the performance of the recommendation system is moderately correlated with the degree of conformity among the recommendations provided by different photographers. This suggests that the system takes into account factors such as image appearance and pose to generate tailored recommendations. It likely analyzes these aspects to determine the most suitable suggestions for a given image. In this project we have used human pose estimation model that provides thirty-three body point coordinates of an individual in a particular image. We have used a dataset containing insights from images using the above stated model. We have used both supervised and unsupervised learning for getting the best suggestions according to the user. At present, there are many image editing tools that provides some filters, and image enhancement techniques that can be used to beautify the already clicked image but there is no such application that provides posture suggestions while capturing the image. Therefore, this application is the first one in the field. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Investigation of Hazard Wastes using Weight Sum Method (WSM) 1

Investigation of Hazard Wastes using Weight Sum Method (WSM)

引用

1st International Conference on Cognitive Computing and engineering Education, ICCCEE 2023

作者： Agrawal, Rishi Varshney, Neeraj GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350332803

This paper is a common one in many objective optimizations. Conceptually, weight loss is both an independent method and a component of other methods. As a result, the sum of the weighted information about the characteristics of the system has a long-Term impact. However, there are many published applications for this method, and in depicting Barito's optimal collection of literature, its shortcomings have been remedied. There is no detailed discussion of ideological significance or techniques to increase the efficiency of the system's primary expression of preferences. Home is dangerous Municipal solid waste (WSM), disposal managers, and policies are a problem for classmates. When comparing special collection to general disposal, the difficulty of the projects is an important fundamental factor. If used properly, this is a project that can withstand many adverse conditions, whether centralized, periodic, or voluntary. User convenience compared to special collection programs will significantly improve. With a population of 271,960, San Luis Obispo County, California, specifically for HHWM (Household Hazardous Waste and Materials), established a mandatory retail withdrawal scheme. First District: medical sharps, fluorescent lamps, latex paint and home batteries. The project's transfer facility is located near the district's retail localities as assortment points for transportation purposes. Recently, global environmental burden has made increasing automobile weight loss more desirable. Weight of vehicle body structures is one of the common concepts for reducing stress scattering and including load scattering. These approaches Weight loss and increased stiffness and strength are aimed at increasing. For this reason, it is important to understand whether the load is scattered within the structure. Alternative: health and safety, human health care, complementary service, quality of service, own vehicle fleet, economic factors, problem-solving capability, and service time

关键词： Hazards

来源：评论

学校读者我要写书评

暂无评论

Emotions Classification Framework based on Facial Expressions 6

Emotions Classification Framework based on Facial Expression...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Tomar, Surendra Pratap Bhardwaj, Harshit Shekhar, Shashi GLA University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9798350346961

This article addresses the use of face feature extraction using a neural network in combination to identify various classification emotions (happy, sad, angry, fear, surprised, neutral etc.). When communicating, People have the ability to performing There are countless variations in the intricacy, intensity, and meaning of facial expressions. The limitations of the current feeling are investigated in this study. identification method that uses brain activity. In this research, I have used an existing simulator to produce findings that are 94% accurate. This method is simpler and then using a device that monitors brain activity for emotion recognition. The intended system is dependent on the human face since, as we are all aware, the face also conveys emotions or brain activity. Neural networks were utilized in this paper to achieve better results comparisons towards the end of the paper.. © 2023 IEEE.

关键词： Emotion Recognition

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：