检索结果-内蒙古大学图书馆

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Rohit Kumar, Vivek Abes Engineering College Department of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9789380544519

In modern era, the Machine learning especially Supervised Machine Learning is iridescent field where many researchers are shaping their research work. Innovations and new ideas in field are growing fast. Still in various fields like medical, financial and other, we need to enhance the predictions of the Logistic Regression classification models. In this research paper, we focused on the optimization of the supervised Logistic Regression model which can predict more accurately when implemented on clinical dataset. Our purpose is to introduce and implement the fuzzy logic for Features engineering technique to optimize the logistic regression model before training of the Logistic regression, which can predict more accurately in the medical data sets. In this paper, we use Coronary Heart Disease (CHD) for implementing the features engineering using fuzzy logic. Final result showed that Optimized Logistic Regression Model prediction of Ten Years Heart risk is improved with accuracy of. 863 when classical Logistic Regression classification model has been compared with it. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Coronary heart disease Feature engineering Fuzzy logic Logistic regression Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning framework for automatic detection and classification of sleep apnea severity from polysomnography signals

引用

Neural Computing and Applications 2024年第28期36卷 17483-17493页

作者： Raja Brundha, A. Lakshmi Sangeetha, A. Balajiganesh, A. Department of Artificial Intelligence and Data Science Sri Sai Ram Engineering College Chennai India Department of Computer Science Engineering Velammal Engineering College Chennai India

Sleep apnea (SA) is a sleep-related breathing disorder characterized by breathing pauses during sleep. A person’s sleep schedule is significantly influenced by that person’s hectic lifestyle, which may include unhealthy eating habits and their line of work. Polysomnographic (PSG) sleep studies examine sleep-related disorders by recording various biosignals from the human body. However, SA classification methods could be more robust in terms of performance because they rely on feature-engineering strategies or employ a particular signal from PSG recording for diagnosis. This study aims to classify the severity of SA according to the apnea–hypopnea index (AHI) into normal, mild, and moderate-to-severe groups using oxygen saturation (SpO2), electroencephalogram (EEG), and electrocardiogram (ECG) signals. The proposed deep neural network (DNN)-bidirectional long short-term memory (DNN-BiLSTM) framework addresses the issue of low detection accuracy in analysis. The DNN-BiLSTM approach employs features extracted from a multiscale dilation attention 1D convolutional neural network (MSDA-1DCNN) as input for detection and classification purposes. The MSDA-1DCNN network extracts deep features from processed SpO2, EEG, and ECG signals. The developed firefly combined electric fish optimization (FCEFO) algorithm improves performance by optimizing the hidden neuron count of the DNN and the learning rate of the BiLSTM framework. The performance measures proved the effectiveness of the model over conventional machine and deep learning approaches. With the integration of deep features, the proposed DNN-BiLSTM model provides enhanced performance in terms of accuracy and precision. Thus, the proposed approach is progressive and can be used for medical diagnosis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Exploring and Analyzing the Different Models of Video Object Detection

Exploring and Analyzing the Different Models of Video Object...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Gupta, Malvika Kumari, Pragati Gautam, Vikash Kumar, Vatan Computer Science and Engineering ABES Engineering College Ghaziabad India

ISBN: (纸本)9798350376470

Video object detection aims to identify the objects that appear in the frame of video *** challenges in video object detection include the degradation of video frames caused by fast motion,occlusion,scale variations,and the need for real-time processing. To achieve these challenges, we have analyzed var-ious approaches, such as two-stage detectors(e.g.,Faster R-CNN or CNN) and one-stage detectors(e.g.,CenterNet),which adapt to video data, Sequence Level Semantics Aggregation(SELSA) module (working on cluster of frames). The motivation for using deep learning, particularly CNN *** this system is their ability to handle complex scenes,lighting variations, feature extraction,and different object types. The versatile and efficient algorithm for video object detection,offers real-time performance,accuracy, and the ability to detect multiple objects in a single *** this highlights the importance of video object detection and the advancements in technology that make it possible to tackle real-world video analysis tasks effectively. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent and Smart Traffic System Based on Yo-Lo Version-8 through Video Streaming for Longer Distance Level 5

Intelligent and Smart Traffic System Based on Yo-Lo Version-...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Varshney, Apoorv Arya, Disha Katiyar, Arpit Dubey, Anil Kumar Abes Engineering College Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350383522

The creation of intelligent traffic systems is essential in the age of smart cities and developing technologies in order to guarantee effective and secure transportation networks. This study uses the state-of-the-art YOLO (You Only Look Once) v8 deep learning architecture to give a novel solution to the problems of real-time car and pedestrian recognition in video frames. The suggested method is centered on obtaining useful data from video streams, especially when it comes to recognizing cars and pedestrians in individual frames. In this context, we show that YOLO version 8 is accurate and effective through a series of thorough trials and assessments. YOLO version 8 is used for object recognition after pictures from video frames are captured as part of the research method. Our technology can quickly recognize and track automobiles and people by using real- time visual analysis. We also look at how this technology may be used in driverless cars, traffic control, and spying. The report also explores the technological aspects of YOLO version 8, emphasizing its advancements over earlier versions, including increased resilience, speed, and accuracy. We go over the process of training and fine-tuning needed for best results when it comes to traffic monitoring. We demonstrate the system's capacity to properly recognize cars and pedestrians, even in difficult settings like changing illumination conditions and occlusions, by thorough testing and validation on many datasets. The findings demonstrate how this technology has the ability to completely transform traffic management and improve road safety. Finally, using YOLO version 8 for real-time car and pedestrian recognition in video frames, this research study provides an intelligent traffic system. The technology exhibits encouraging outcomes, laying the path for further advancements in intelligent transportation, traffic optimization, and public safety. © 2024 IEEE.

关键词： Object Detection Pedestrian Detection Vehicle Detection Video Analysis YOLOV8

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Graph Neural Network Framework with Attention Mechanism for Computational Offloading in the Internet of Vehicles

引用

computer Modeling in engineering & sciences 2025年第4期143卷 225-254页

作者： Aishwarya Rajasekar Vetriselvi Vetrian Department of Computer Science and Engineering College of Engineering GuindyAnna UniversityChennai600025India

The integration of technologies like artificial intelligence,6G,and vehicular ad-hoc networks holds great potential to meet the communication demands of the Internet of Vehicles and drive the advancement of vehicle ***,these advancements also generate a surge in data processing requirements,necessitating the offloading of vehicular tasks to edge servers due to the limited computational capacity of *** recent advancements,the robustness and scalability of the existing approaches with respect to the number of vehicles and edge servers and their resources,as well as privacy,remain a *** this paper,a lightweight offloading strategy that leverages ubiquitous connectivity through the Space Air Ground Integrated Vehicular Network architecture while ensuring privacy preservation is *** Internet of Vehicles(IoV)environment is first modeled as a graph,with vehicles and base stations as nodes,and their communication links as ***,vehicular applications are offloaded to suitable servers based on latency using an attention-based heterogeneous graph neural network(HetGNN)***,a differential privacy stochastic gradient descent trainingmechanism is employed for privacypreserving of vehicles and offloading ***,the simulation results demonstrated that the proposedHetGNN method shows good performance with 0.321 s of inference time,which is 42.68%,63.93%,30.22%,and 76.04% less than baseline methods such as Deep Deterministic Policy Gradient,Deep Q Learning,Deep Neural Network,and Genetic Algorithm,respectively.

关键词： Internet of vehicles vehicular ad-hoc networks(VANET) multiaccess edge computing task offloading graph neural networks differential privacy

来源：评论

学校读者我要写书评

暂无评论

Handwritten Equation Solver: A Game-Changer in Mathematical Problem Solving 13th

Handwritten Equation Solver: A Game-Changer in Mathematical ...

引用

13th International Advanced Computing Conference, IACC 2023

作者： Gupta, Anmol Pathak, Disha Mohini Sharma, Rohit Srivastava, Somya Computer Science Department ABES Engineering College Ghaziabad India

ISBN: (纸本)9783031566998

Handwriting is something which changes from person to person. Finding two people with same handwriting isn’t an easy job and not everyone can recognize all kinds of writing. But, in the growing era of technology and the modern world with the introduction of the domains like OpenCV – image processing and recognition isn’t a tough job. Further, with the growing dependency on technology and the ease of access, students can now solve equations at the comfort of their home. The job is simple, one just has to click picture of a problem written on the page, scan it, and the algorithm does it job. The system can recognize various handwritings and works on a large dataset. This Handwritten Equation Solver system, will aim towards dealing with various handwritings and solving equations with aiming towards the maximum possible accuracy that could be achieved using the various techniques and to find out the most appropriate out of all the proposed techniques. In this study, we initially take a binary image convert it into binary format using preprocessing and eliminating the noise. We use different segmentation and classification techniques have been used to find out the most accurate technique that will give the maximum possible accuracy. We found out that the highest accuracy came in K-Means segmentation and KNN classification technique which are 92.714 and 92.857% respectively. The proposed methodology uses all the techniques of OpenCV. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Prediction of Chronic Kidney Disease Using ML Techniques 5

Prediction of Chronic Kidney Disease Using ML Techniques

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Shukla, Anupam Robin, Fabian Narvaria, Harshit Joshi, Anju Computer Science and Engineering Abes Engineering College Ghaziabad India

ISBN: (纸本)9798350383522

The study of chronic kidney disease of human body is now a significant topic of interest in the domain of biosciences because of the emerging cases of the disease. One of the most dangerous illnesses in the modern world is chronic kidney disease, for which an accurate diagnosis method needs to be developed to identify and stop the disease at an early stage. A condition known as chronic kidney disease causes a person's kidneys to malfunction and eventually become damaged. This leads to the condition where the kidney is unable to filter the blood and remove the waste as they do. Now-a-days machine learning algorithms have become a major tool in which the disease gets diagnosed based on the certain values like blood pressure, urine value and many such things. This leads to the early detection of the disease so that the patient can consult his required doctor and with the help of which his disease could be cured. The application and the study of the applied algorithm will help us to detect the disease will be explored in this study. These algorithms' outputs have a higher degree of accuracy, sensitivity, and specificity and can be used to predict the presence of chronic kidney disease in the necessary human being. The findings will demonstrate how technology can aid in the better management of chronic kidney disease and how this can enhance decision support systems for healthcare in general. © 2024 IEEE.

关键词： Decision tree GUI data-driven detection Smart disease detection Machine learning methodologies SVM

来源：评论

学校读者我要写书评

暂无评论

Fruit and Vegetable Classification and Freshness Detection using Machine learning

Fruit and Vegetable Classification and Freshness Detection u...

引用

2024 MIT Art, Design and Technology School of Computing International Conference, MITADTSoCiCon 2024

作者： Akshi Varshney, Poorvi Avasthi, Sandhya Agarwal, Kadambri ABES Engineering College Department of Computer Science and Engineering Ghaziabad India ABES Engineering College Department of CSE Ghaziabad India

ISBN: (纸本)9798350362879

Freshness is a key factor in determining a fruit or vegetable's quality, and it directly influences the physical health and coping provocation of consumers. It ascertains the nutritional value of the specified fruit or vegetable. This paper proposes a well-organized and precise fruit and vegetable classification and freshness detection method. The proposed method employs state-of-The-Art deep learning models, specifically convolutional neural networks (CNNs), to analyze images of fruits and vegetables captured through high-resolution cameras. The dataset used for training and evaluation is extensive and diverse, encompassing a wide variety of fruits and vegetables in various conditions. The freshness of a fruit or vegetable can be ascertained by looking at a variety of features, including color, texture, shape, and size. Fresh produce, for instance, is colorful and free of mold or brown spots. Traditional methods for assessing the quality of fruits and vegetables are both time-consuming and error-prone. These methods include inspection and sorting. It is possible to reduce these issues by utilizing automatic detection techniques. In light of this, we proposed an automated fruit-vegetable freshness detection approach that first recognizes whether the image is of a fruit or vegetable, after which it classifies it into one of three freshness categories: rotten, fresh, or mixed. To identify and categorize fruits and vegetables, two deep learning models are employed: You Only Look Once (YOLO) and Visual Geometry Group (VGG-16). The suggested method's qualitative analysis indicates superior performance on the fruit-vegetable dataset. © 2024 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

CineSense -Your Goto Movie Recommender 15

CineSense -Your Goto Movie Recommender

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kumar, Jatin Agrawal, Khushi Bhardwaj, Dev Gupta, Radhika Khanna, Anshul Department of Computer Science ABES Engineering College Ghaziabad India

ISBN: (纸本)9798331300579

Nowadays, with so many films, web series, and TV shows available on digital platforms, it may be exceedingly difficult for consumers to sift through the large library of content and discover something that suits their tastes and preferences. "Cine Sense," a movie recommendation system, stands at the forefront of this transformative endeavour. Modern machine learning techniques are skilfully integrated into "Cine Sense" to form its basis. A unique cinematic experience is guaranteed by the system's ability to recognize user behaviour, preferences, and viewing habits to provide customized learning routes and real-time feedback systems. It represents a harmonious blend of entertainment technology, machine learning, and modern web development principles. React JS, CSS, and Tailwind CSS is used for creating a visually appealing and user-friendly interface. TMDB (The Movie database) API (Application Programming Interfaces) for accessing a vast repository of movie and TV show information. Machine learning models will be integrated for personalized content recommendations based on user behaviour and preferences. © Grenze Scientific Society, 2024.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

Voice Assisted E-Commerce Website 15

Voice Assisted E-Commerce Website

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kumar, Gitansh Matharu, Manmeet Kaur Joshi, Gaurank Chauhan, Jatin Kumar, Ankit Department of Computer Science ABES Engineering College Ghaziabad India

ISBN: (纸本)9798331300579

The way humans interact with computers has evolved thanks to automatic voice-controlled devices. Voice or speech recognition systems enable a user to make a hands-free request to the computer, which then processes the request and returns relevant responses to the user. Voice-controlled technologies have become more efficient and are widely implemented in many sectors to enable and improve human-to-human and human-to-computer interactions after years of development and research in machine learning and artificial intelligence. Web-based technologies enable cutting-edge e-commerce applications to provide interactive and user-friendly interfaces. However, in other cases, people, particularly those with visual difficulties, are unable to completely appreciate the utility of such programs. A voice-controlled system embedded in a web application can improve user experience and functionality. In the current corporate environment, e-commerce is on the rise. Using the Internet as an electronic medium, e-commerce systems facilitate the buying and selling of goods. By enabling contact-free interactions between the user and the machine, voice/speech recognition systems greatly simplify the process. Voice recognition has been the subject of a great deal of research up to this point. The user experience and task completion can be improved by utilizing all of these in online apps. This feature will also improve the web app's accessibility because a significant portion of the population suffers from various forms of visual impairments, and it will be especially helpful to them. © Grenze Scientific Society, 2024.

关键词： Speech 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：