检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ganguly, Sayarnil Katham, Sanjana Reddy Agrawal, Sanyam Sinha, Soumen Roy, Rahul Department of Computer Science Engineering Mahindra University Telangana Hyderabad India

ISBN: (纸本)9783031783821

Denoising images corrupted with multiple types of noise is significantly challenging due to their variable noise distribution. These numerous types of noise have a cumulative effect on the image. Therefore, considering only a single or multiple distribution of noise would be ineffective for restoration. Moreover, estimation of the noise is difficult where there is heterogeneity in the combination of the noise. Hence in this paper, we propose a sequence of autoencoders to progressively restore the noisy images. Each autoencoder specializes in the restoration of images affected by a particular combination of noise. These trained autoencoders are arranged in a state-space graph such that all possible combinations of noises can be screened by the autoencoder or their ensembles. The root of the state space graph is the Nth level autoencoder as it is exposed to all kinds of noise. In contrast, the autoencoder at the leaf level is exposed to one type of noise. During restoration of images, the obtained state space tree is searched using a heuristics search algorithm to find the near-optimal ensemble of autoencoders which can denoise the combinations of noises present in an image. Experiments are conducted with diverse combinations of noises to demonstrate the efficacy of the proposed approach. Furthermore, the proposed method is compared with various state-of-the-art approaches. It was observed that the proposed approach had significant efficiency in handling the combination of noise and outperforms various state-of-the-art techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Sensitive Wavebands Identification System for Smart Farming

引用

computer Systems science & engineering 2022年第10期43卷 245-257页

作者： M.Kavitha M.Sujaritha Department of Computer Science and Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641025India

Sensing the content of macronutrients in the agricultural soil is an essential task in precision *** helps the farmers in the optimal use of *** reduces the cost of food production and also the negative environmentalimpacts on atmosphere and water bodies due to indiscriminate dosageof *** traditional chemical-based laboratory soil analysis methodsdo not serve the purpose as they are hardly suitable for site specific soil ***,the spectral range used in the chemical-based laboratory soil analysismay be of 350-2500 nm,which leads to redundancy and *** sensors based on the discovery of spectral wavebands that respondto soil macronutrient concentrations,on the other hand,is an innovative and successfultechnology since the results are dependable and *** goal of thisarticle is to use a supervised neuro-fuzzy based dimensionality reduction approachin the sensor development process to determine sensitive wavebands of ***,the spectral signatures of the soil are collected inan outdoor environment and mapped with its macronutrient *** thisspectral analysis,the spectral reflectance of 424 wavelengths has been obtainedand these wavelengths are evaluated through combined and individual modesas *** wavelengths are selected in each case by minimizing the fuzzy reflectance assessment *** effectiveness of these selected wavelengthsin each mode is validated by modeling the relation between the reduced reflectancespace and each macronutrient concentration using Partial Least Squares Multi Variable Regression(PLS-MVR)*** of optimal wavebands areidentified and the results are compared with the existing systems.

关键词： Sensitive waveband determination macronutrients feuro-fuzzy based dimensionality reduction partial least squares multi variable regression reflectance

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing leather quality assurance through deep learning powered precision in defect detection and segmentation by a comparative analysis of Mask RCNN and YOLO v8

Revolutionizing leather quality assurance through deep learn...

引用

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

作者： Prathyuksha Nair, J. Thangakumar, J. Hindustan University Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

The leather industry confronts persistent challenges in the maintenance of its product quality, often produced with defects that escape from the traditional conventional inspection methods. This research seeks the transformation of leather quality assurance by harnessing the power of deep learning, specifically through the comparative analysis exploration of Mask RCNN (Mask Region Convolutional Neural Network) and YOLO v8 (You Only Look Once version 8) for precise defect detection and segmentation of wet blue leather. In this comprehensive analysis, the performance of Mask RCNN and YOLO v8 are evaluated using an industrial dataset comprising various defect categories. The study encompasses a deep dive into the intricacies of each model's architecture, training processes, and inference speed to provide an obvious understanding of their respective limitations and strength. Findings from the research showcase the efficacy of both Mask RCNN and YOLO v8 in significantly enhancing defect detection accuracy compared to traditional methods. However, distinct differences emerge in terms of computational speed, resource requirements, and the models' ability to handle diverse defect sizes and shapes. This research provides valuable insights for industry practitioners, being in the selection of the most suitable model for specific operational contexts and facilitates the more informed decisions in implementation of deep learning-powered quality assurance systems. By advancing the precision of defect detection and segmentation through deep learning, the experiment results provided an inference of YOLOv8 being the model with more accuracy in detection and segmenting the defects in the leather, also its ability to provide and predict the defects using lesser training data and time, makes it more efficient model for the manufacturing of good quality of leather. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploring Facial Recognition Technologies for Classroom Management 10

Exploring Facial Recognition Technologies for Classroom Mana...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Nidhya, R. Pabi, D. J. Ashpin Divyasree, U. Abhishek, B. Harika, A. Alim, S. Abdul Department of Computer Science & Engineering Madanapalle Angallu517325 India

ISBN: (纸本)9798350353068

The goal of this research is to create a sophisticated system for gathering student data that is suitable for use in classroom settings. The approach begins with taking pictures of every student in the class in a methodical manner. Next, advanced image processing techniques like segmentation are used to extract unique traits, which are subsequently converted into structured pixel values in an array. These extracted characteristics are used to train a model by utilizing machine learning capabilities, including the use of OpenCV, a powerful computer vision toolkit, and facial recognition algorithms. The system is able to anticipate student presence with 99.38% accuracy. Instantaneous insights into students entering the classroom are made possible by real-time person detection implemented with OpenCV. Carefully logging these entries, which include important date and time information, results in a daily compilation that is saved as a text file and forms an extensive database. This database provides insightful information on attendance trends over time in addition to streamlining the recording of attendance. The incorporation of state-of-the-art technologies like machine learning and image processing not only improves the precision of attendance records but also gives teachers a streamlined, automated way to easily manage classroom attendance, which makes the learning environment more advanced and efficient. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Secure Fog Enabled Blockchain Based Healthcare Model 1

Secure Fog Enabled Blockchain Based Healthcare Model

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Awasthi, Charu Awasthi, Satya Prakash Mishra, Prashant Kumar Poornima University Department of Computer Engineering Jaipur India Pranveer Singh Institute of Technology Department of Computer Science & Engineering Kanpur India

ISBN: (纸本)9798350353648

Cloud Computing introduced high latency, mobility, bandwidth, etc., which Fog Computing addressed. Fog Computing streamlines remote IoT device and sensor management. However, Fog-Cloud has security and privacy issues. Blockchain gives trustless security, subsequently its utilization in various fields is developing. We propose an electronic healthcare framework that oversees basic and non-basic patients all the while. Basic and non-basic fog bunches make up the fog layer. Basic patients are treated in basic fog bunches for fast reaction, while non-basic patients are taken care of utilizing blockchain innovation to save patient wellbeing records. The proposed technique reduces key message response time and offloads cloud infrastructure with minimal IoT ecosystem changes. The results demonstrate that the suggested method protects privacy while maintaining network settings. The aim of the research is to create a safe healthcare system that combines blockchain with fog computing. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Analyzing Security Challenges in Cloud-Based E-commerce Systems a Comprehensive Study 3

Analyzing Security Challenges in Cloud-Based E-commerce Syst...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Akrami, Zinatullah Singh Bhathal, Gurjit Punjabi University Computer Science and Engineering Department Patiala India

ISBN: (纸本)9798350381931

Cloud computing enhances defense, public sectors, innovation, and infrastructure. The Korean Military plans to adopt cloud computing for its defense system, but current security measures are inadequate. A secure architecture is necessary, which aligns with U.S. military standards and addresses Korean defense system requirements in a cloud environment. Cloud computing presents cost, efficiency, and scalability benefits but also security concerns. This paper proposes a risk management framework including self-assessment, provider assessment, risk assessment, third-party review, and continuous monitoring. By using this framework, providers can understand user needs and build *** businesses lack online exposure for their products/services. This article proposes cloud-based organic product catalogs as a solution for enabling electronic ordering and transactions with micro *** e-commerce stores struggle with trust due to security risks and inadequate compliance monitoring. This research develops an adaptive assurance model using legislation, ISO standards, policies, security, and availability to enhance trustworthiness. The model employs intelligent cooperative rating techniques and the empirical survey validates its effectiveness. Findings inform the improvement of e-commerce assurance models. © 2024 IEEE.

关键词： ISO Standards

来源：评论

学校读者我要写书评

暂无评论

DataDAO Club - Revolutionizing Investment Management with On-Chain Governance 4

DataDAO Club - Revolutionizing Investment Management with On...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Yadav, Vikash Singh, Ajay Pal Pandit, Vani Yashu, Kumar Kumar, Mithilesh Chandigargh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9798350385793

Decentralized Autonomous Organizations (DAOs) have become a transformative force in the ever-evolving landscape of decentralized finance (DeFi), reshaping traditional investment frameworks. This research thoroughly examines the intricacies of DataDAO Club, an innovative platform that utilizes on-chain governance, Filecoin storage, and smart contracts to redefine the landscape of investment management. The study encompasses an in-depth literature review, delving into the broader context of DeFi, previous DAO research, and the integration of block chain technologies such as Filecoin. The methodology section meticulously dissects the smart contracts deployed on the calibration testnet, showcasing real-world implementation through features like on-chain governance, economic models for dataset value generation, and proof of data storage inclusion (PoDS I). The findings shed light on the platform's impact, emphasizing its role in democratizing access to investment funds, evaluating the efficacy of Filecoin storage deals, and assessing the resilience of the implemented features. This study not only reveals the intricate workings of DataDAO Club but also discusses user interactions, delves into the challenges encountered during development, and proposes potential avenues for future improvements. This research contributes valuable insights to the ever-changing landscape of decentralized finance, offering a nuanced understanding of the practical implementation and impact of DAOs, thereby paving way for continued innovation and exploration in the field of decentralized investment management. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Enhancing Urban Mobility: A Smart Parking System Using IoT and Machine Learning 2

Enhancing Urban Mobility: A Smart Parking System Using IoT a...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Yadav, Narinder Kang, Sandeep Singh Verma, Rajneesh Garg, Varun Singla, Ishdeep Chandigarh University Department of Computer Science And Engineering Mohali India

ISBN: (纸本)9798331519056

Traffic jams & drivers searching for parking can be a real, especially with more people living in cities and the rise in cars. This paper a smart parking guidance system that helps manage parking spots using the Internet of Things (IoT) & some clever machine learning tricks. It's an IoT solution for the tough parking issues we see in big cities. As the number of cars keeps growing, especially during busy times, it becomes harder for drivers to find available spots. So, we present a cool smart parking system which uses Arduino parts and a mobile app. This system sets up on-site slot modules that keep track of the status of individual parking spaces, showing whether they are free or not. Plus, there's a mobile app so users can check spot availability & even reserve spaces ahead of time. This smart parking system could really help cities save money & protect the environment by cutting down on fuel use & pollution. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Analyzing Aggressive Driving Patterns with GPS Data: A Machine Learning Approach 6

Analyzing Aggressive Driving Patterns with GPS Data: A Machi...

引用

6th International Conference on Sustainable Technologies for Industry 5.0, STI 2024

作者： Islam, Md. Ariful Rahman, Md Mijanur Rahman, Md. Orasur Shakib, Md. Nazmus Green University of Bangladesh Department Of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798331531973

Aggressive driving behavior is a critical issue with significant implications for road safety and traffic management. Researchers have extensively studied methods to predict such behaviors, utilizing various data sources and machine learning techniques. This research focuses on predicting aggressive driving behavior using GPS data from the Green University Bus Route Dataset. We developed a novel preprocessing algorithm, along with label encoding and standardization techniques, to prepare the dataset for analysis. Seven machine-learning algorithms were used to guess how often aggressive driving would happen. These were Decision Tree classifiers (DTC), AdaBoost classifiers (ABC), Gradient Boosting classifiers (GBC), Extra Tree classifiers (ETC), Support Vector classifiers (SVC), Gaussian Naive Bayes (GNB), and Random Forest classifiers (RFC). Our results indicate that the GBC, ETC, SVC, and RFC outperform other models, with each one achieving the highest accuracy of 99.445%. This study demonstrates the potential of GPS data to effectively predict aggressive driving behavior, offering valuable insights for improving road safety measures. © 2024 IEEE.

关键词： Aggressive driving behavior Driver behavior prediction GPS data analysis Traffic Safety

来源：评论

学校读者我要写书评

暂无评论

Multi-Organ 3D Reconstruction and Virtual Reality Visualization Using Graph-Based Segmentation 4

Multi-Organ 3D Reconstruction and Virtual Reality Visualizat...

引用

4th International Conference of science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Nagendra, Roshni Iyer, Saanchita V Dinakar, Punarv Repalle, Shanmukha Sai Kalyan Likitha, P. Pes University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376111

Virtual reality (VR) is an emerging technology with promising applications in organ visualization. Recognizing that this could be valuable in the field of medical education, we devised a pipeline that utilizes classical MRI scans to reconstruct and visualize the heart and the brain in an immersive virtual reality environment. Our tool mainly focuses on incorporating visual learning into medical education, making it interactive and intuitive for aspiring practitioners. The pipeline comprises three key steps: a novel graph-based organ segmentation technique, 3D reconstruction, and VR visualization. The segmentation and reconstruction results were validated through high SSIM and PSNR scores, which showcases that structural details from the MRI are preserved with minimal noise. The visualization results were presented to aspiring medical students and professionals as part of a survey, and their positive responses highlighted the potential impact of our research. © 2024 IEEE.

关键词： Virtual environments

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：