检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Sharvesh, R. Sharan Ram, M. Anandhi, S. Rajalakshmi Engineering College Computer Science and Engineering Chennai India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

According to the World Health Organization, at least 2.2 billion people have impaired vision. It is crucial to note that in at least 1 billion of these cases, vision impairment could have been prevented or is yet to be addressed. There exists a wide range of retinal irregularities ranging from Glaucoma to Diabetic Retinopathy (DR), each with its symptoms and causative. With vision impairment booming in number, it is important to put a system in place which can digitize the optic tests done to detect various retinal irregularities. This paper strives to be a better iteration of the pre-existing models in place, in terms of accuracy and F1 score using processed retinal fundus images with Discrete Wavelet Transform (DWT) and Flower Pollination Algorithm (FPA) in Deep Learning (DL) based Ensemble Learning model using Convolutional Neural Networks (CNNs). Additionally, the integration of the output results into a cloud-based application for storage and statistical analysis makes it a better solution for easy retrieval, future reference and visualization. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Autism Spectrum Disorder by Imperialistic Competitive Algorithm and Logistic Regression Classifier

引用

computers, Materials & Continua 2023年第11期77卷 1515-1534页

作者： Shabana R.Ziyad Liyakathunisa Eman Aljohani I.A.Saeed Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl Kharj16274Saudi Arabia Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah41411Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl Kharj16274Saudi Arabia

Autism spectrum disorder(ASD),classified as a developmental disability,is now more common in children than ever.A drastic increase in the rate of autism spectrum disorder in children worldwide demands early detection of autism in *** can seek professional help for a better prognosis of the child’s therapy when ASD is diagnosed under five *** research study aims to develop an automated tool for diagnosing autism in *** computer-aided diagnosis tool for ASD detection is designed and developed by a novel methodology that includes data acquisition,feature selection,and classification *** most deterministic features are selected from the self-acquired dataset by novel feature selection methods before *** Imperialistic competitive algorithm(ICA)based on empires conquering colonies performs feature selection in this *** performance of Logistic Regression(LR),Decision tree,K-Nearest Neighbor(KNN),and Random Forest(RF)classifiers are experimentally studied in this research *** experimental results prove that the Logistic regression classifier exhibits the highest accuracy for the self-acquired *** ASD detection is evaluated experimentally with the Least Absolute Shrinkage and Selection Operator(LASSO)feature selection method and different *** Exploratory Data Analysis(EDA)phase has uncovered crucial facts about the data,like the correlation of the features in the dataset with the class variable.

关键词： Autism spectrum disorder feature selection imperialist competitive algorithm LASSO logistic regression random forest

来源：评论

学校读者我要写书评

暂无评论

Density-Based Traffic Control System Using IoT and Machine Learning

Density-Based Traffic Control System Using IoT and Machine L...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Tabassum, Husna Mohammed Ameer, M. Alam, Mohammed Murshid Sharieff, Mohammed Yaseen Ahamed, Naveed Anjum, Ayesha Hkbk College of Engineering Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350359688

Traffic congestion is a critical issue in cities due to the increasing population and automobiles. Traffic jams create delays, tension, increased fuel usage, and air pollution, with megacities particularly affected. Real-time road traffic density estimates are vital for better signal control and traffic management. The current traffic management system lacks emphasis on live scenarios, leading to inefficiencies. Our project, implemented using Python OpenCV and a pre-trained YOLO model, aims to prevent congestion. Image processing captures lane footage, and processed data dictates traffic LED commands for signal management and uses sensors and cameras to determine vehicle count and understand the actual crowd of vehicles on each road in real-time. Machine Learning, an intelligent computer system, helps us analyze all this data and make decisions to improve traffic flow based on the current vehicular count. We also provide features for detecting emergency vehicles and giving them more priority over other vehicles to pass through. Additionally, the paper enhances pedestrian safety by incorporating a virtual speed bump when the light is red. It also prioritizes emergency vehicles, improving the efficiency of public services, and introduces a solution called the Density-Based Traffic Control System (DBTCS), which combines the power of the Internet of Things (IoT) and Machine Learning (ML) to revolutionize how we manage traffic. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Alzheimer's Prediction System using Deep Learning for Early Diagnosis 4

AI-Powered Alzheimer's Prediction System using Deep Learning...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Makka, Shanthi Reddy, V. Nikhil Gnaneshwar, R. Kumar, M Abhishek Vardhaman College of Engineering Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350364729

Alzheimer's disease represents a major global health problem characterized by a progressive neurodegenerative disorder that disrupts memory and cognition It helps in diagnosis of the disease at an early stage and resulting in better treatment. MRI has quickly become a valuable diagnostic modality, providing an insightful look at the anatomy of the brain. The work takes advantage of deep learning, particularly neural networks, for analysing MRI data to improve the diagnosis of Alzheimer's. These new methodologies will hopefully give clinicians and caregivers accurate information about when to identify incidence of Alzheimer's at an early stage. We are also creating a simple web-based application which people can use to upload new images easily, allowing the rapid automated analysis of their MRIs to facilitate early diagnosis more *** approach promises to contribute to more timely interventions and better patient outcomes. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Analysis Using Integrating NLP, AI, and Facial Expression Recognition for Enhanced Emotion Detection

Multimodal Emotion Analysis Using Integrating NLP, AI, and F...

引用

2024 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems, SPICES 2024

作者： Babu, Alby Dharshini, T. Gayathry Krishnan, V.S. Ummu Haiman, V.P. Joseph, Annie Julie Rajesh, K.R. College of Engineering Poonjar Computer Science and Engineering Kottayam India

ISBN: (纸本)9798350376135

This paper introduces SAGA (Smart AI Guided Assistant), a pioneering Artificial Intelligence (AI) personal assistant that integrates advanced Emotional Intelligence (EI) capabilities with sophisticated Natural Language Processing (NLP) techniques. Designed to function as an interactive companion, SAGA offers comprehensive task management and support, paralleling existing personal assistants, yet distinguishes itself through its ability to understand and respond to user emotions. By leveraging cutting-edge methodologies in emotion detection, speech analysis, and NLP, SAGA accurately interprets user emotions, thus providing personalized emotional support. Furthermore, SAGA's multi-modal interaction capabilities, which encompass both voice commands and audio-visual feedback, facilitate seamless communication with users. This paper delineates the architecture, development process, and evaluation metrics of SAGA, thereby underscoring its potential to transform the AI personal assistant landscape by prioritizing emotional intelligence and fostering user-centric interactions. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Price Wise a Deep Learning Approach to Stock Price Prediction 1

Price Wise a Deep Learning Approach to Stock Price Predictio...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Bansal, Anshika Singh, Abhishek Roy, Shweta Agarwal, Kadambri Abes Engineering College Computer Science & Engineering Ghaziabad India

ISBN: (纸本)9798350377002

Financial markets depend heavily on stock price prediction, which affects both market behaviour and investment decisions. Given the complexity and volatility of financial markets, traditional methods of stock price forecasting sometimes encounter difficulties. Due to their capacity to extract complex patterns from large datasets, deep learning techniques have become more and more popular in recent years. The use of deep learning models to forecast stock values is examined in this research study, and their effectiveness is compared among various deep learning models. The study employs a diverse dataset encompassing historical stock prices. LSTM based models such as Long-Short Term Memory (LSTM), Bidirectional Long Short-Term Memory(Bidirectional-LSTM), Stacked Long Short-Term Memory(Stacked-LSTM) and Tree based models such as Random Forest, ADA Boost, XG Boost are employed to predict future prices. Using historical stock price data, the models are trained and verified, and a variety of performance indicators are used to evaluate how accurate are the predictions. In this research study, we found that stacked LSTM performs better among various other models. © 2024 IEEE.

关键词： Prediction models

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

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

Enhanced Potato Leaf Disease Detection via Modified Swin Transformer Architecture 15

Enhanced Potato Leaf Disease Detection via Modified Swin Tra...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bajpai, Abhishek Tiwari, Naveen Rajput, Piyush Sahu, Shalinee Singh, Deepak Computer Science and Engineering Rajkiya Engineering College Kannauj India

ISBN: (纸本)9798350370249

Potatoes are a primary agricultural product in India, with stable production hinging on effective disease prevention. Detecting whether potato leaves are healthy or afflicted by diseases such as early or late blight is crucial. This study introduces a novel method based on the Swin Transformer for identifying these diseases. In the last few years, there have been notable developments in the use of advanced deep-learning algorithms to classify and detect diseases in potato leaves within the industrial sector. Based on transformer architecture, the Swin Transformer model has notably improved classification tasks, efficiency and accuracy. The research utilized a deep learning method with the Swin Transformer to detect diseases in potato leaves. The model's performance was assessed using precision, recall, accuracy, and F1 score. After training, the method achieved a notable accuracy of 99.38%. These findings highlight the efficacy of the Swin Transformer model in identifying potato leaf diseases, offering exciting prospects for agricultural research. © 2024 IEEE.

关键词： Agriculture computer Vision Crop Deep learning Plant diseases potato leaf disease detection Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Building a Smarter Shield: Using Ensemble Learning for Multi-Class DDoS Attacks 15

Building a Smarter Shield: Using Ensemble Learning for Multi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vijayalakshmi, M. Susmanth Srinivas, A. Ramanathan, S. Thiagarajar College of Engineering Computer Science and Engineering Madurai India

ISBN: (纸本)9798350370249

Nowadays in this increasing population IBD has become a viral topic that is mainly discussing and implementing topics in both digital and intelligent industry fields. The security problems that widely occur in the signal processing of data streams is a most challenging problem in industries, detection of DDoS attacks in intelligent industrial applications is also highly dangerous. To ensure the security networks, DDoS attack detection is commonly used. Some are failed to detect unknown attacks;they are classical detection that are commonly known as signature-based attacks or explicit-behavior-based attacks. These are very hard to fulfill the requirements of SD-IOT networks. To detect DDoS attacks, the two machine learning algorithms implemented in this paper are Extra Tree and Random Forest. Extratree performed well. Random Forest's Accuracy is 95.15% and Extratree is 95.59%. To get this accuracy we used UNSW_NB15 as a Dataset. After a target variable has been identified, the data will be divided into two sets: one for training and another for testing. Further it is applied to classification methods. Finally, apart from accuracy precision, recall, and F1-measure is found out. © 2024 IEEE.

关键词： Random forests

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：