检索结果-内蒙古大学图书馆

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

作者： Kavitha, M.N. Saranya, S.S. Pragatheeswari, E. Priya, N. Kaviya Ranjith, S.R. Vanchivel, N. Rahul Kongu Engineering College Department of Computer Science and Design Tamil Nadu India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Kongu Engineering College Department of Csd Tamil Nadu India

ISBN: (纸本)9798331509675

The proposed system aims to enhance student transportation security through real-time face detection and recognition. Leveraging the MTCNN framework for accurate face detection and the FaceNet model for reliable face recognition, the system ensures only authorized students can board designated buses by comparing captured faces with a pre-registered database. In case of mismatches, alerts are triggered to notify drivers and authorities. Additionally, parallel implementation of Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers improves authentication accuracy. The system's deep learning-based architecture ensures robust performance under varying environmental conditions and supports continuous learning for long-term reliability. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning Based Time Series Prediction and Forecasting of Ten Nations’ COVID-19 Pandemic

引用

SN computer science 2023年第1期4卷 91页

作者： Kumar, Yogesh Koul, Apeksha Kaur, Sukhpreet Hu, Yu-Chen Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India Department of Computer Engineering Punjabi University Patiala India Department of Computer Science and Engineering Chandigarh Engineering College Mohali Landran India Department of Computer Science and Information Management Providence University Taichung Taiwan

In the paper, the authors investigated and predicted the future environmental circumstances of a COVID-19 to minimize its effects using artificial intelligence techniques. The experimental investigation of COVID-19 instances has been performed in ten countries, including India, the United States, Russia, Argentina, Brazil, Colombia, Italy, Turkey, Germany, and France using machine learning, deep learning, and time series models. The confirmed, deceased, and recovered datasets from January 22, 2020, to May 29, 2021, of Novel COVID-19 cases were considered from the Kaggle COVID dataset repository. The country-wise Exploratory Data Analysis visually represents the active, recovered, closed, and death cases from March 2020 to May 2021. The data are pre-processed and scaled using a MinMax scaler to extract and normalize the features to obtain an accurate prediction rate. The proposed methodology employs Random Forest Regressor, Decision Tree Regressor, K Nearest Regressor, Lasso Regression, Linear Regression, Bayesian Regression, Theilsen Regression, Kernel Ridge Regressor, RANSAC Regressor, XG Boost, Elastic Net Regressor, Facebook Prophet Model, Holt Model, Stacked Long Short-Term Memory, and Stacked Gated Recurrent Units to predict active COVID-19 confirmed, death, and recovered cases. Out of different machine learning, deep learning, and time series models, Random Forest Regressor, Facebook Prophet, and Stacked LSTM outperformed to predict the best results for COVID-19 instances with the lowest root-mean-square and highest R² score values. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： COVID-19 Facebook Prophet Holt model Prediction Random forest regressor RANSAC regressor Stacked gated recurrent units Stacked long short-term memory XG Boost

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Age Detection: The Impact of Data Augmentation and Balancing on CNN Performance 1st

Enhancing Human Age Detection: The Impact of Data Augmentati...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Alrubaye, Maryam Hameed, Alaa Ali Jamil, Akhtar Department of Artificial Intelligence Engineering Istinye University Istanbul Turkey Department of Computer Engineering Istinye University Istanbul Turkey Department of Computer Science National University of Computer and Engineering Sciences Islamabad Pakistan

ISBN: (纸本)9783031823763

Accurate age detection is a crucial aspect in various sectors including security, marketing, and demographic analysis, where understanding the age of individuals can lead to better service delivery and enhanced user experience. This study explores the enhancement of age detection algorithms using Convolutional Neural Networks (CNNs). Leveraging a unique combination of the UTKFace and Facial-age datasets, our approach introduces an advanced data augmentation and balancing technique. This methodological innovation significantly contributes to optimizing CNN performance in age detection tasks. The proposed technique not only overcomes the common challenges in age estimation but also achieves an accuracy of 90.51%, and a noteworthy F1 score of 89.82%, which demonstrates the model’s accuracy and robustness. The findings of this research hold substantial implications for improving age detection processes, offering a promising direction for future applications in various fields that require reliable age estimation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Modified Feature Extraction to apply PSO for solving Handwritten Digits 20

Modified Feature Extraction to apply PSO for solving Handwri...

引用

20th International Joint Conference on computer science and Software engineering, JCSSE 2023

作者： Samleepant, Jiraphat Ratanavilisagul, Chiabwoot Faculty of Applied Science Department of Computer and Information Science Bangkok Thailand

ISBN: (纸本)9798350300505

Handwritten Digit Recognition (HDR) is a widely used technology that has been demonstrated in various research topics. However, there are many limitations because everyone's handwriting is different, including important handwriting characteristics. The experimental results of the previously proposed methods were unsatisfactory when using limited amounts of the datasets for the training model and inefficient pre-processing. Therefore, we describe a new method for increasing the recognition rate through well-planned pre-processing and enhanced feature extraction for applying Particle Swarm Optimization (PSO). When compared to other techniques, the proposed method performed well when tested against an individual's handwritten digits and the original MNIST database. Our results are a high recognition rate and short runtime. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Empowering patients: Evaluating user experience with the MED-LIST platform 4th

Empowering patients: Evaluating user experience with the MED...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Agarwal, Paras Choudhary, Vishal Agarwal, Swati Tyagi, Shivika Chaurasiya, Nitish Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad India

ISBN: (纸本)9781032911571

In today’s fast-paced world, people have hectic lives. Almost everyone faces the challenge of taking their medicines on time, enduring lengthy waits for lab reports, people face challenges in managing their medical records, misplacing their medical prescriptions, navigating cumbersome appointment booking systems in the clinics, etc. This paper introduces a mobile and a web application designed to provide a complete healthcare system and resolve all the mentioned problems and many more. It will help people to connect to their respective healthcare provider and provide a notification system for medication reminders, streamlined appointment booking with integrated payment functionality, instant lab reports on the phone, disease prediction by symptoms, medicines history and reports history, an intelligent queue management system that predicts appointment times bases on a regression ML model with 85% accuracy, etc. © 2025 the Author(s).

关键词： Reservation systems

来源：评论

学校读者我要写书评

暂无评论

Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality 40

Reasons for the Superiority of Stochastic Estimators over De...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Ohayon, Guy Adrai, Theo Elad, Michael Michaeli, Tomer Faculty of Computer Science Technion Haifa Israel Faculty of Electrical and Computer Engineering Technion Haifa Israel

Stochastic restoration algorithms allow to explore the space of solutions that correspond to the degraded input. In this paper we reveal additional fundamental advantages of stochastic methods over deterministic ones, which further motivate their use. First, we prove that any restoration algorithm that attains perfect perceptual quality and whose outputs are consistent with the input must be a posterior sampler, and is thus required to be stochastic. Second, we illustrate that while deterministic restoration algorithms may attain high perceptual quality, this can be achieved only by filling up the space of all possible source images using an extremely sensitive mapping, which makes them highly vulnerable to adversarial attacks. Indeed, we show that enforcing deterministic models to be robust to such attacks profoundly hinders their perceptual quality, while robustifying stochastic models hardly influences their perceptual quality, and improves their output variability. These findings provide a motivation to foster progress in stochastic restoration methods, paving the way to better recovery algorithms. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Adapting to Evasive Tactics through Resilient Adversarial Machine Learning for Malware Detection 18

Adapting to Evasive Tactics through Resilient Adversarial Ma...

引用

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

作者： Krishna, G. Bala Sravan Kumar, G. Ramachandra, Mummadi Sampurnima Pattem, K. Rani, D. Sandhya Kakarla, Geeta Cvr College of Engineering Department of Computer Science Engg. Rangareddy Ibrahimpatnam India Cvr College of Engineering Department of Computer Science Engg.-Cyber Security Rangareddy Ibrahimpatnam India Sreenidhi Institute of Science and Technology Department of Computer Science Engg. Hyderabad India Sreenidhi Institute of Science and Technology Department of Computer Science Engg. Cyber Security Hyderabad India

ISBN: (纸本)9789380544519

This paper presents the Adaptive Resilience-based Convolutional Network (ARCNet), a sophisticated machine learning framework specifically designed to detect advanced, evasive malware. ARCNet combines convolutional and recurrent neural networks, making it highly adaptable to changing cyber threats. Its core components, the Adversarial Learning Module (ALM), Predictive Analysis Engine (PAE), and Dynamic Adaptation System (DAS), significantly boost its detection power. Tests using a synthetic dataset show ARCNet's superiority over traditional models like the Support Vector Machine (SVM). It achieved 95.2% accuracy under normal conditions (compared to SVM's 89.4%) and maintained 92.5% accuracy even during adversarial attacks (against SVM's 80.3%). Notably, ARCNet's detection rates improved from 78.5% to 86.7% in five months after integrating the DAS. These results confirm ARCNet's efficiency in tackling complex malware challenges, contributing greatly to cybersecurity. The study underscores the importance of evolving and enhancing machine learning methods to keep pace with the rapidly changing landscape of cyber threats. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Block chain Blockchains Challenges of Block chain Consensus algorithm Data privacy Digital signatures Distributed ledger Faces Organizations Smart contracts

来源：评论

学校读者我要写书评

暂无评论

Tri Focus Net: A CNN-Based Model with Integrated Attention Modules for Pest and Insect Detection in Agriculture 3rd

Tri Focus Net: A CNN-Based Model with Integrated Attention M...

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Montashir Fahim, A.S.M. Efat, Anwar Hossain Mahedy Hasan, S.M. Oishe, Mahjabin Rahman Jannat, Nahrin Mitu, Mostarina Department of Computer Science and Engineering Rajshahi University of Engineering and Technology Rajshahi6204 Bangladesh

ISBN: (纸本)9789819739363

Pests and insects pose a significant threat to global agriculture, causing crop damage and quality loss, with a massive annual costs. Early detection of these agricultural challenges is essential for sustainable farming and food security. Challenges in early pest detection include class imbalance, computational limitations, and the need for comprehensive feature learning. In response, our study introduces "Tri Focus Net (TFN)," a hybrid model that seamlessly integrates multiple attention mechanisms, including Channel, Soft, and Squeeze-and-Excitation Attentions, effectively addressing these issues. This combination empowers TFN to discern critical details both globally and locally within images, significantly enhancing feature extraction and robustness. Additionally, we have successfully integrated DenseNet 201 with TFN, further enhancing our model’s feature extraction capabilities and robustness. In our work, we achieved exceptional results, attaining a maximum accuracy of 94.20% for the insects dataset and a perfect 100% accuracy for the pest dataset. Our contribution to agriculture lies in providing a cost-effective, precise, and robust solution for pest and insect detection, underpinning the sustainability of crop health and the agricultural industry. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

A Novel Parallel Hybrid k-Means and HGSO Based Approach for Detecting Fake Reviews in Social Media

引用

SN computer science 2025年第5期6卷 1-16页

作者： Purohit, Rajendra Chowdhary, K.R. Purohit, S.D. Pal, Raju Sharma, Harish Department of Computer Science and Engineering JIET Jodhpur Pali Road Rajasthan Jodhpur 342802 India Department of HEAS (Mathematics) RTU Kota Rawatbhata Road Rajasthan Kota 324010 India Department of Computer Science and Engineering Gautam Buddha University Greater Noida 201308 India Department of Computer Science and Engineering RTU Kota Rawatbhata Road Rajasthan Kota 324010 India

Online reviews play a key role in deciding purchases by the customers. However, the proliferation of fake reviews has made it hard to differentiate between real and fake reviews. Manual classification of reviews is subjective, and traditional methods are limited in accuracy. To address this issue, we propose a novel Parallel Hybrid k-means and Henry Gas Solubility Optimization (H-KHGSO) algorithm for detecting fake reviews in social media. The H-KHGSO algorithm capitalizes on the strengths of k-means clustering to initialize the initial population and Henry Gas Solubility Optimization (HGSO) to find optimal cluster heads. Leveraging Hadoop’s distributed computing capabilities, our parallel approach enhances computational efficiency and accelerates the detection process. To validate the effectiveness of H-KHGSO, experiments on three distinct spam review datasets, including SSR, MR, and YHRR, were investigated against state-of-the-art clustering methods, including PSO, DE, GA, CS, GWOK, and k-means. The comparative analysis confirmed the superiority of the H-KHGSO algorithm. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fake reviews HGSO K-means Parallel computing Social media

来源：评论

学校读者我要写书评

暂无评论

Novel Steganalysis Method for Stego-Images Directly Constructed from Color Images Based on Their Quantum Noise

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-11页

作者： Abdeltawwab, Mohammed R. Taie, Shereen A. El-Bahnasawy, Hany H. Eissa, Amir Department of Basic Science Faculty of Computers and Artificial Intelligence Fayoum University El Fayoum63514 Egypt Department of Computer Science Faculty of Computers and Artificial Intelligence Fayoum University El Fayoum63514 Egypt Department of Physics Faculty of Science Al-Azhar University Nasr City Cairo11884 Egypt

Steganography and steganalysis are two different sides of the same coin. Both are just as important as the other. Image steganography is considered one of the most promising secure data transmission methods because it hides the data in an image file. In contrast, steganalysis tries to attack steganography and retrieve the hidden data that can be a secret message. Many robust and powerful image steganography methods have been presented in the literature. One of these methods is referred to as steganography without embedding (SWEM). It is considered more secure because it adopts the concept of data transmission without embedding or concealing it in the file. Like any new technology, image steganography may have a negative impact and can be misused. There is no steganalysis method for distinguishing and attacking the image file that has been constructed by the SWEM method. To overcome the aforementioned issues, the main contribution of this paper is to propose a new image steganalysis method based on the fast Fourier transform (FFT). The proposed method starts by examining a suspected image using FFT. Then, by calculating the ratio of different parts of the resulting FFT spectrum and comparing the result with a threshold value, we can decide whether the suspected image has been constructed by the SWEM or not. The proposed method overcomes the other existing methods that fail to attack this strong image steganography method. To check the generalizability of the proposed method as a method for distinguishing and attacking the image file that is created by SWEM, we constructed a data set of images, used the SWEM algorithm to construct images with concealed secret messages without embedding, and applied the proposed method and other two common existing steganalysis methods. The results show that the proposed method is able to distinguish these images with a high recognition rate compared to the results of the two methods. (Figure presented.) © Shanghai Jiao Tong University

关键词： Quantum noise

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：