检索结果-内蒙古大学图书馆

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Kailasam, Khushi Singh, Jaswant Gopika, G.S. Sreekrishna, M. Supriya, S. Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Fabric defect detection plays a crucial role in the textile manufacturing industry's quality control process since it guarantees that customers will receive perfect products. Deep Learning (DL) models have demonstrated a great deal of promise in recent years for accurately identifying fabric defects. The proposed fabric defect identification method combines the best features of two architectures: You Only Look Once (YOLOv4) and Region-based Convolutional Neural Network (R-CNN). While YOLOv4 offers quicker and more effective detection, R-CNN generates region recommendations that allow accurate localization of fabric defects. There are two stages in the proposed system. Initially, region proposals are detected using the R-CNN feature extractor and then a convolutional neural network is used for defect classification. YOLOv4 is used for performing object detection in the second step, where the flaws are concurrently classified and localized. The tests carried out on a fabric defect dataset show that the proposed method outperforms the R-CNN and YOLOv4 models separately. The proposed system is appropriate for real-Time fabric flaw detection applications in a variety of sectors due to its high detection accuracy and quick processing time. This study demonstrates how well R-CNN and YOLOv4 together work for fabric flaw detection, providing hope for future developments in the area. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Small object detection in diverse application landscapes: a survey

引用

Multimedia Tools and Applications 2024年第41期83卷 88645-88680页

作者： Iqra Giri, Kaisar J. Javed, Mohammed Department of Computer Science Islamic University of Science & Technology Pulwama India Computer Vision & Biometrics Lab Dept. of IT Indian Institute of Information Technology Allahabad India

The importance of object detection within computer vision, especially in the context of detecting small objects, has notably increased. This thorough survey extensively examines small object detection across various applications, consolidating and outlining the available methodologies. Traditional papers on small object detection have focused on specific domains. However, this survey paper incorporates insights from a multitude of domains, providing a comprehensive understanding of the versatility and applicability of small object detection techniques. This paper sheds light on the key challenges faced and delves into potential solutions to address the challenges, offering insights into viable solutions to enhance small object detection performance, setting it apart from existing literature. The strategies identified in our survey encompass a spectrum of approaches, categorized as transformer-based, CNN, and traditional methods. Also, this paper collates prevalent datasets relevant to small object detection, simplifying access to these resources. Further, it provides a succinct overview of diverse evaluation metrics used for performance assessment in this field, enhancing understanding of the effectiveness and proficiency of these methods. This survey paper not only consolidates established knowledge but also highlights innovative viewpoints, providing a comprehensive and enlightening compilation that contributes to the advancement of small object detection in the field of computer vision. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

IRIS-A WEARABLE DEVICE FOR MONITORING MOVEMENT DISORDERS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2023年第1期85卷 41-52页

作者： Oprea, Flavia Pătru, Cristian Rosner, Daniel Radovici, Alexandru University POLITEHNICA of Bucharest Dept. of Computer Science Romania

Neurodegenerative diseases affect brain neurons by progressively losing structure or function, including death of neurons. To improve or sustain a patient’s quality of life, monitoring their condition and constantly adjusting their treatment based on their home state is crucial. At the moment, there is no objective measurement for monitoring neurodegenerative diseases and the decisions that are being made are biased. This project aims to realize a solution that monitors people with movement disorders and helps the doctors in the process of diagnosing and changing the medication of their patients. We created the IRIS application along with the IRIS wearable devices that analyze the data needed to diagnose and monitor people with movement disorders, such as Parkinson’s Disease. The parameters combined can help the doctors and patients in the process of diagnosing and monitoring movement disorders. The product is able to objectively assess a patient and to offer the data in a processed manner so that the doctor can prescribe new medication to control the symptoms of the patient. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-rule-decided small cell offloading for rate-adaptive SVC-DASH video streaming over the vehicle environment

引用

computer Communications 2023年 212卷 1-20页

作者： Huang, Chung-Ming Wang, Han-I Dept. of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

This paper proposed an SVC-DASH video streaming method over the vehicular environment based on the Multi-access Edge Computing (MEC) architecture. For the streaming concern, a control scheme using the Segment-Set-based buffer-aware bitrate adaptation with the backward quality's increment control was proposed;for the mobility concern, a Small Cell Video Streaming Offloading (SC–VSO) control scheme adopting the multiple attribute fuzzy-based decision for deciding whether it can offload the video streaming traffic from a macro cell to a small cell or not was proposed. To have the suitable bitrate adaptation and stable quality variation, three factors that the proposed streaming control scheme considers are (i) estimated bandwidth, (ii) buffer occupancy and (iii) quality variation. Since the vehicle is moving across many types of Base Stations (BSs), the proposed mobility control scheme can decide whether to have SC-VSO or not before vehicle X entering into the ahead small cell's signal coverage based on (i) the network situations of the corresponding macro and small cell and (ii) the reported context from vehicle X using the proposed fuzzy logic mechanism. The performance evaluation results shown that the proposed method has the higher video quality and better quality stability for video streaming over the vehicle environment. © 2023 Elsevier B.V.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Optical Mark Recognition with Object Detection and Clustering 6

Optical Mark Recognition with Object Detection and Clusterin...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Tabassum, Kaifa Rahman, Zhalok Shahjalal University of Science and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385779

OMR, or optical mark recognition, is the automated analysis of human-marked documents. Presently, many competitive examinations rely on multiple-choice questions, and the answers to these questions are recorded in OMR sheets. In this study, we present an automated answer detection system from an OMR sheet image using computer vision techniques. Typically, evaluating an OMR sheet from an image involves scanning, extracting data, and interpreting the results through various image processing techniques. However, traditional approaches have limitations. They cannot detect empty responses or recognize multiple choices properly without a specified layout or total number of questions stated. We took a unique approach by employing an object detection model, YOLOv8n, to detect and classify OMR marks. To address overlapping bounding boxes, we implemented the DBSCAN clustering algorithm to effectively group the columns and determine question order. Our system is designed to work with multiple layouts, as it can detect columns through clustering. Furthermore, it can identify unanswered questions as well as multiple marked options. To train and evaluate our model, we created a custom dataset with five different OMR sheet layouts. We achieved a remarkable precision of 96.5%, a recall of 99.8%, and an mAP (mean average precision) of 97.3%. These results demonstrate the efficacy of our approach to OMR sheet analysis. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Real Time Monitoring and Configuration Interface for Smart Home Device Management Using Streamlit and Pygame

Real Time Monitoring and Configuration Interface for Smart H...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Mani, G. Suma Krishna, G. Venkata Praveena, M.D. Anto Asha, P. Selvan, Mercy Paul Sathyabama Institute Of Science And Technology Dept. Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

One of the helpful tool for measuring and managing home power consumption is one of the clever and creative tool for tracking the usage of Home Power Management System. The Goal of this system is to lower the power bills, also promote energy efficiency, and provide the users active control over how much energy they use. Smart meters, an intuitive and user-friendly smartphone app, and real-time energy monitoring sensors are some of the system's essential parts and these are the key parts of the system. Installing smart meters makes it possible to accurately track the power usage and provide data to the system. Users can be able to see their energy usage instantly and make smart decisions when real-time energy monitoring equipment is included. Further, the system uses advanced smart technology, analytics and machine learning algorithms to provide clients customized suggestions on how to save energy consumption. Homes may save a lot of money on electricity bills, help the environment, and have more control over how much energy they use by using our Smart Home Power Management System. © 2024 IEEE.

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

Application of computer Vision Approach for Automation and Classification of Fashion Store

Application of Computer Vision Approach for Automation and C...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adebayo, Aminat Abiodun, Moses Kazeem Awoniran, Ifeoluwa Temitayo Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Adeniyi, Jide Kehinde Rueben Aremu, Dayo Alhikman University Dept. of Computer Science Ilorin Nigeria Landmark University Dept. of Computer Science Omu-Aran Nigeria Bowen University Dept. of Computer Science Iwo Nigeria University of Ilorin Dept. of Computer Science Ilorin Nigeria

ISBN: (纸本)9798350358155

The fashion industry has long been interested in utilizing computer vision techniques to automate tasks such as recognizing different types of clothing items in images. This study proposed a novel convolutional neural network (CNN) architecture for the classification of fashion outfits into three categories: shoes, sunglasses, and trousers. The proposed CNN architecture is based on state-of-the-art deep learning techniques and is trained on a fairly large-scale dataset of fashion images. The effectiveness of the proposed CNN architecture is evaluated through extensive experiments and analysis. The result demonstrates that the proposed CNN architecture achieves a high accuracy rate of 0.99 on each diagonal value of the confusion matrix. This indicates that the proposed CNN is capable of accurately classifying each item type with high accuracy. Additionally, the study investigates the impact of various hyperparameters on the performance of the proposed CNN architecture and found that the model which uses a 7x7 filter size and 64 filter number yields higher accuracy compared to other filter combinations. The study demonstrates the potential of CNN in automating fashion item recognition, which can lead to improved efficiency and accuracy in the fashion industry. It can also form the basis for developing more advanced computer vision systems for the fashion industry. © 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

A Number of Conceptual Scalable Node-Organizing Multi-Tiered Blockchain Architectures for IoT 17

A Number of Conceptual Scalable Node-Organizing Multi-Tiered...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Elsaadany, Riham Bégin, Guy Computer Science Dept. Canada

ISBN: (纸本)9798350351637

The high volume and rapid pace of transactions generated by IoT devices pose challenges for current blockchain designs, which typically employ flat or two-tiered node organizations. These models often lack the scalability, throughput, and consensus efficiency required for the IoT environment. This study proposes a multi-tiered clustered design concept that enhances blockchain scalability and efficiency. We compare our approach with flat and two-tiered models to demonstrate its viability. Central to our design is a node lookup and message routing mechanism, coupled with a consensus-accelerating protocol. Transaction, block verification, and creation processes involve a logarithmically bounded number of nodes per tier, improving consensus time and scalability as tier levels increase. The design concept maintains a balance between consensus decentralization and node overhead capacity, ensuring scalability and security. This design concept can be implemented using various algorithmic approaches to produce multiple proposed architectures, all leveraging the consensus-accelerating protocol. Simulations performed on one of the architectures provide solid proof of concept, demonstrating improved performance over flat and two-tier models. The proposed mechanisms provide general-purpose scalability, load balancing, node lookup, and message routing solutions, and are application- and consensus-algorithm-agnostic. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A Novel Method to Detect Oral Carcinoma Using Box Annotation Based on YOLO Model

A Novel Method to Detect Oral Carcinoma Using Box Annotation...

引用

2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems, iCACCESS 2024

作者： Laila, Shahara Ema, Romana Rahman Galib, Syed Md. Jamil, Abu Rafe Md Uddin, A. F. M. Shahab Jashore University of Science and Technology Dept. of Computer Science and Engineering Jashore Bangladesh

ISBN: (纸本)9798350350289

Oral carcinoma affects millions of individuals globally and is a major public health problem due to its high fatality rate. Treatment effectiveness depends on early detection and improves survival rates. An effective method for automated oral cancer screening is deep learning. The paper's primary goal is to use deep learning techniques to advance the state of oral cancer diagnosis, specifically YOLOv5 and YOLOv7. We aimed to achieve accurate detection by leveraging bounding box annotations for both two distinct types of data: collected clinical data and benchmark data of oral carcinoma. The proposed methodology encompasses data collection, preprocessing, expert-driven bounding box annotation and the use of cutting-edge deep learning models for lesion identification, YOLOv5 and YOLOv7. Bounding box serving as expert annotations are meticulously added to pinpoint cancerous regions within the images. Subsequently, a comprehensive evaluation is conducted, measuring the performance of both models based on precision, recall rate (sensitivity) and mean average precision (mAP). Our findings reveal that YOLOv5 outperforms YOLOv7 in terms of oral cancer detection, demonstrating superior precision and recall rates. In the evaluation of this research, the YOLOv5 model demonstrated strong performance metrics on both clinical and lip and tongue cancer datasets. For the lip and tongue cancer dataset, the YOLOv5 model achieved a precision of 97.2%, a mAP (mean Average Precision) of 97.7% and a recall of 96.3%. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Effective Polyp Segmentation in Medical Imaging: A Semi-Supervised Approach with Progressive Supervision 3

Effective Polyp Segmentation in Medical Imaging: A Semi-Supe...

引用

3rd International Conference on Big Data, Information and computer Network, BDICN 2024

作者： Ye, Shunlong Ji, Zexuan Nanjing University of Science and Technology Dept. of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350363821

Medical imaging plays a pivotal role in diagnosing and monitoring various diseases, and accurate polyp segmentation is essential for early disease detection and treatment planning. However, the scarcity of well-Annotated medical imaging data hampers the development of effective segmentation models. Semi-supervised learning stands out as a critical approach to address this issue. Traditional semi-supervised medical image segmentation models leverage strong-weak perturbation consistency losses to provide supervision signals. While these losses are effective in promoting consistency, they often exhibit a drawback, that is the dominance of strong perturbations during early training stages. This dominance hinders the model's ability to extract meaningful features, ultimately impacting its overall performance. In response to these challenges, we introduce a novel training method applied to polyp segmentation. We employ a progressive approach, gradually introducing strong-weak perturbation supervision signals. This gradual guidance empowers the model to focus on learning relevant features from the beginning of training, mitigating the issue of early dominance and enhancing its performance. Our method is evaluated on two widely-used polyp segmentation datasets and surpasses state-of-The-Art methods, demonstrating substantial improvements in segmentation accuracy. © 2024 IEEE.

关键词： Self-supervised learning

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：