检索结果-内蒙古大学图书馆

Laplacian nonlinear logistic stepwise and gravitational deep neural classification for facial expression recognition

引用

Multimedia Tools and applications 2024年 1-21页

作者： Binthu Kumari, M. Sivagami, B. Department of Computer Science & amp Applications South Travancore Hindu College Tamil Nadu Nagercoil629002 India Manonmaniam Sundaranar University Tamil Nadu Tirunelveli627012 India

Facial expression recognition is the paramount segment of non-verbal communication and one frequent procedure of human communication. However, different facial expressions and attaining accuracy remain major issues to be focused on. Laplacian Non-linear Logistic Regression and Gravitational Deep Learning (LNLR-GDL) for facial expression recognition is proposed to select righteous features from face image data, via feature selection to achieve high performance at minimum time. The proposed method is split into three sections, namely, preprocessing, feature selection, and classification. In the first section, preprocessing is conducted with the face recognition dataset where noise-reduced preprocessed face images are obtained by employing the Unsharp Masking Laplacian Non-linear Filter model. Second with the preprocessed face images, computationally efficient relevant features are selected using a Logistic Stepwise Regression-based feature selection model. Finally, the Gravitational Deep Neural Classification model is applied to the selected features for robust recognition of facial expressions. The proposed method is compared with existing methods using three evaluation metrics namely, facial expression recognition accuracy, facial expression recognition time, and PSNR. The obtained results demonstrate that the proposed LNLR-GDL method outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural Computing and applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Toxicity Spread in Social Networks: A Similarity-Based Network Approach

引用

Procedia computer science 2025年 259卷 1161-1168页

作者： Ashtapadhi S V Indulekha T S Jayakumar P Department of Computer Science and Applications Amrita Vishwa Vidyapeetham Amritapuri India

The rapid spread of toxic content on social media poses significant societal challenges. Regulating harmful content in social networks is essential to maintain social harmony. This study explores whether the spread of toxic language or sentiments can be analysed using a dataset that includes comments labelled as toxic or non-toxic but lacks user and temporal information. The proposed approach uses similarity-based networks like Cosine, Jaccard, and Soft cosine and the SEIZ epidemiological model to study toxicity dynamics. While the analysis is theoretical due to data limitations, the findings provide valuable insights for planning prevention strategies, designing policies, and understanding the intrinsic properties of data. The results show consistent patterns across different networks, highlighting the important role of skeptics in slowing toxicity spread. This study demonstrates that even with limited data, theoretical modelling using similarity networks and SEIZ can reveal meaningful insights into the spread of toxic behaviour.

关键词： Social network Propogation dynamics SEIZ model Similarity network Sparse data

来源：评论

学校读者我要写书评

暂无评论

Mobile-Based Classification and Detection of Diabetic Retinopathy Using TinyML 2

Mobile-Based Classification and Detection of Diabetic Retino...

引用

2nd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2023

作者： Kumar, Manish Mohan Kumar, H.P. Sultana, Husna Shweta, J.S. M S Ramaiah Institute of Technology Department of Master of Computer Applications Bangalore India Pes College of Engineering Dept of Master of Computer Applications Karnataka Mandya India Government First Grade College Department of Computer Science Karnataka Tumkur India

ISBN: (纸本)9798350314045

This paper presents a comprehensive approach to diabetic retinopathy (DR) classification and detection, encompassing the evaluation of ResNet, RegNet, and WideResNet models for DR severity assessment. Leveraging the Kaggle's APTOS 2019 dataset, we implement and analyze these models using PyTorch, highlighting their efficacy in categorizing DR severity levels. Additionally, we leverage Tiny Machine Learning (TinyML) techniques to develop a mobile-based solution, enabling real-time DR severity assessment on mobile devices. This mobile application showcases the potential of TinyML for early detection and intervention in DR cases, ultimately enhancing patient outcomes. By synergizing advanced deep learning models with TinyML, this study contributes to healthcare technology, enabling timely interventions and improved patient outcomes. © 2023 IEEE.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Optimize EV's Dealing and Charging

A Novel Approach to Optimize EV's Dealing and Charging

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Vijay, Sandip Gobi, N. Sharma, Ambrish Kumar Tula's Institute Department of Computer Science and Engineering Dehradun India Department of Computer Bangalore India Computer Applications Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350357769

It's an interesting idea to investigate the energy market as a potential means of reducing the power costs related to charging electric cars at public charging stations. Through intraday energy markets., several nations allow electricity trading until just before the delivery time. This research utilizes the market as an illustration to investigate the possibility of lowering power prices via intraday market trading. After conducting extensive simulations., the results show that charging schedule optimization combined with intraday trading in the markets may result in cost savings of around 9% when compared to obtaining all needed energy from the energy provider. A further 2% or more of cost savings may be realized by giving the charging station manager the ability to resell energy to the everyday electricity market. The research explores how the intraday electricity market's lead time and trading unit affect total expenses in addition to any possible cost savings. Lead time is shown to have a major impact on feasible power prices., whereas each trading unit has a negligible impact on the total cost dynamics. © 2023 IEEE.

关键词： charging schedule Electric vehicles (EV's) electricity costs mixed-integer linear programming trading

来源：评论

学校读者我要写书评

暂无评论

IoT-based System for Multi-Head Dual Attention Generative Adversarial Network-based Soil Nutrition and Plant Disease Detection in Smart Agriculture 8

IoT-based System for Multi-Head Dual Attention Generative Ad...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Shukla, Arvind Kumar Krishnaraj, Kowsalyadevi Venkatesh, R.J. Santhanalakshmi, M. Iftm University Department of Computer Applications Uttar Pradesh Moradabad India Sona College of Technology Department of Computer Science and Engineering Tamil Nadu Salem India Sri Venkateswara College of Engineering Department of Eee Tamil Nadu Chennai India Department of Computer Science and Engineering Tamil Nadu Dindigul India

ISBN: (纸本)9798350376425

The Internet of Things (IoT) has been increasingly popular in recent years due to its many uses. Regarding the agricultural industry, automated systems for identifying plant diseases offer mixed benefits and some drawbacks. Hence Multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) based plant disease detection in IoT is proposed. In order to address the absence of infrastructure in this area, the proposed approach seeks to identify stress to plants caused by crop diseases, environmental imbalance, and soil fertility. The proposed scheme uses nodes to capture plant leaf images, with a sink node collecting information from an automated module for IoT-based monitoring. The Combined Bilateral Parametric Filtering (CBPF) is used to pre-process the nodes' images so they are appropriate for the plant disease detection. After pre-processing, DenseNet201is proposed for extracting the Statistical features of the images. Then Multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) is proposed for segmenting and classifying the plant leaf as healthy and disease. In order to improve the classification accuracy, Humboldt Squid Optimization Algorithm is proposed. Utilizing criteria such as sensitivity, accuracy, energy of nodes and specificity on various IoT environments, the detection performance is verified overall. According to the simulation findings, the suggested strategy performs better in terms of detection, with an accuracy of 99.46%. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Extractive Summarization on Twi Language Using Text-Rank and Fuzzy Clustering Algorithm 1

Extractive Summarization on Twi Language Using Text-Rank and...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Dhole, Sayak Sagnika, Santwana Dominic, Ampofo Mishra, Bhabani Shankar Prasad Fernando, Aloka Dash, Satya Ranjan School of Computer Engineering Kiit Deemed to Be University India School of Computer Applications Kiit Deemed to Be University India University of Moratuwa Department of Computer Science and Engineering Sri Lanka

ISBN: (纸本)9798350315769

Twi is a dialect of the Akan language spoken in southern and central Ghana by several million people. About 80% of the Ghanaian population speaks Twi as a first or second language. Summarization is a basic natural language processing task, that is a step to further more advance tasks as well as an aid in reviewing information. This paper tackles the problem of summarizing Twi texts. Three extractive summarization techniques - TF-IDF, Text-Rank and Fuzzy C-means Clustering are implemented. We find that Text Rank performs best, while TF-IDF despite being fairly simple performs comparably well to Text Rank. Our work suggests that embedding based approaches are potent and further work should employ their use. © 2023 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Video enabled crowd monitoring system and analysis 3

Video enabled crowd monitoring system and analysis

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Mehra, Gunjan Joshi, Aditya Singh, Aakriti Shuaib, Mohd Diwakar, Manoj Singh, Prabhishek Graphic Era Deemed to be University Department of Computer Applications Dehradun India Graphic Era Deemed to be University Department of Cse Dehradun India School of Computer Science Engineering & Technology Bennett University Greater Noida India

ISBN: (纸本)9798331515911

One of the most victorious strategies for slowing the spread of the COVID-19 virus has been proposed: social isolation. A computer vision-based AI-assisted approach for aiding with social distance norms compliance is utilized. The solution consists of modules for person detection, tracking, and distance violations detection. You are given the option to select a tool-based mode for camera calibration. In this paper, the various measures for determining the likelihood of social distance violations and how to tell them apart from temporary violations from persistent ones are demonstrated. On countless real-world issues, AI/Deep Learning has in the past shown promising results. In this paper, how to observe crowds in public areas and workplaces using Python, image processing, and computer vision is discussed in depth. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bubble Prediction in Stock Markets: Leveraging SVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations based on Support Vector Machine (SVM) and through important technical indicators. Among these are momentum indicators, such as the Relative Strength Index (RSI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from Bollinger Bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out based on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 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 Various Hyperparameters for Predicting Hypertension using Machine Learning Algorithms 8

Analysis of Various Hyperparameters for Predicting Hypertens...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Duggal, Shallu Sood, Shivani Singh, Amanpreet Singh, Harjeet Malarvel, Muthukumaran Lovely Professional University School of Computer Applications Phagwara144411 India Chitkara Institute of Engineering and Technology Chitkara University Punjab 140401 India Department of Computer Science and Engineering India

ISBN: (纸本)9798350367904

Predicting hypertension, or high blood pressure, is crucial because it's a risky condition that frequently doesn't exhibit any obvious symptoms or indicators until major problems arise. By using predictive models for early identification, the risk of uncontrolled hypertension-related cardiovascular events, strokes, and organ damage can be decreased to take quick action. The study aims to predict the diagnosis of hypertension using three machine learning techniques: Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine(SVM). With the focus on improving accuracy and reliability, the various hyperparameters of each individual algorithm are tuned using the cross validation and grid search approaches. After extensive testing and parameter modification, the SVM algorithm was found to be the most accurate predictor, which achieved a significant accuracy of 9 7. 0 0 %. The best hyper-parameters achieved for SVM are c value 4 and kernel as 'rbf'. The models' performance is evaluated using accuracy, specificity, sensitivity, F1-score, or AUC (Area Under the Curve). This study facilitates proactive healthcare measures by offering insightful information to determine the best algorithms for the early prediction of hypertension. © 2024 IEEE.

关键词： Prediction models

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：