检索结果-内蒙古大学图书馆

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Khan, Sheharyar Shah, Syed M Adnan Arsalan, Aamir Ahmed, Wakeel University of Engineering and Technology Taxila Department of Computer Science Taxila Pakistan Fatima Jinnah Women University Rawalpindi Department of Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350332391

Wearable gadgets are becoming a major constituent of our society due to a wide range of applications like financial transactions, unlocking automobiles, tracking health and fitness, and many more. Personal data is usually required to manage these services, however, most commercially available wearables devices either lack a user authentication mechanism or employ knowledge-based authentication like passwords, PINs, or pattern locks. In this growing digital age, it is really difficult for an individual to memorize such a huge number of passwords. In this research, we put forward a technique for recognizing users from their walking patterns recorded in real-life settings using a smartwatch accelerometer sensor. Ensemble classification techniques (bagging and boosting) are used for the purpose of user identification using the selected time domain features. Our proposed method attained the highest classification accuracy of 88.35% which transcends the existing user recognition schemes available in the literature. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Object Recognition and Tracking System to Assist Visually Impaired: A Neural Network-Based Deep RBM Technique 1

Object Recognition and Tracking System to Assist Visually Im...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Patil, Sonal Ramagundam, Shashishekhar Sukumar, P. Khan, Mohiuddin Ali Patil, Nisha Deepak Nishant, Neerav G H Raisoni Institute of Engineering and Business Management HoD of CSE-IT Department Jalgaon India Software and Dev Engg4- SDET/ IT COMCAST MonroviaMD United States Department of Computer Science and Engineering Tamilnadu Erode India Jazan University Department of Computer & Network Engineering Jazan Saudi Arabia GCOERC Computer Engineering Nashik India School of Engineering Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350371802

Being able to see is fundamental to almost every aspect of our everyday lives, thus those who are visually impaired confront enormous obstacles. Thanks to recent developments in computer vision and computing, a system that can provide auditory input to visually impaired individuals regarding objects and their environments has been designed. Sequencing is crucial for preprocessing, feature selection, and model training. Although extremely accurate data input is still required for object detection, preparation is getting computationally cheaper. We were partially successful in reducing the image size by employing Gaussian Blur, which imparts a smoother appearance to the photos. We use color descriptors and Fourier transforms for feature extraction. Deep RBM training necessitates precise control over the attributes. In comparison to this method, current RBM and DNN algorithms look antiquated. The results demonstrated a notable enhancement in accuracy, reaching 98.31%. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Wenhao Gu Li Gu Ziqiang Wang Ching Yee Suen Yang Wang Department of Computer Science and Software Engineering Concordia University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.

关键词： Training Metalearning Adaptation models Handwriting recognition Visualization Technological innovation computer vision Text recognition Computational modeling Layout

来源：评论

学校读者我要写书评

暂无评论

Enhancing Viewer Engagement: Exploring Generative Long Short Term Memory in Dynamic Ad Customization for Streaming Media 5

Enhancing Viewer Engagement: Exploring Generative Long Short...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Ramagundam, Shashishekhar Karne, Niharika Troy University Software Development & Engineering in Content Discovery & Ai Department of computer Science Computer Science Montgomery Campus AL United States C & Rs Platform services DT Amtrak United States University of south alabama Department of electrical engineering Electrical engineering United States

ISBN: (纸本)9798331504403

In Ad customization, several approaches are employed to improve the relevance level of the message for monitoring the user performance according to the prior search history (e.g., retargeting) or by gathering particular information related to the customer (e.g., micro-targeting). Occasionally, the consumers view the ad developed by the other user, in this situation, the ads are viewed as something that can be related by the user. The quantity of information that is gathered openly or secretly can affect the user choice for the content displayed. However, the users remain as recipients of a strategy, that decides the best ad content. Therefore, an exploring Generative Artificial Intelligence-based Dynamic Ad Customization model for enhancing viewer engagement from streaming media is developed. In this paper, the Generative Long Short-Term Memory (GenLSTM) model is developed for examining customized advertising then includes the customization of specific message elements by individuals, variation in the level of ad customization, and in some cases perceived collaboration with others. Here, the customization classification is defined based on the modification in the marketing mix element that is created by the customer proactively as opposed to the company. In regards to customized advertising, 'ad is something that happens with the viewer'. The customization increases based on the sense of task engagement, strength of the perceived customer relationship with the company, attitude toward the ad, and perceptions of company trust/integrity. Finally, the experimental analysis is conducted based on the relationship with the company, company care, company trust, and task engagement to attain the overall impact on ad customization. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Enhancing ASD Diagnosis with Contrastive and Non-Contrastive Models from Neuroimaging Data 4

Enhancing ASD Diagnosis with Contrastive and Non-Contrastive...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Jha, Abhishek Mehta, Ishita Khan, Kainat Katarya, Rahul Delhi Technological University Department of Mechanical Engineering New Delhi India Delhi Technological University Department of Software Engineering New Delhi India Delhi Technological University Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350352931

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition which impacts social interaction, communication, and behavior. This study introduces a self-supervised learning approach for ASD prediction using resting-state functional MRI (rs-fMRI) scans from the ABIDE I dataset, employing contrastive and non-contrastive models. The contrastive model enhances learning by maximizing agreement between augmented views of the same scan, while the non-contrastive model reconstructs input data through an autoencoder. Both models, pre-trained on ImageNet, were fine-tuned for ASD classification using Resnet18. Our results show that the contrastive model achieved 97.6% accuracy, with a precision of 95.7%, recall of 99.2%, and F1 score of 97.4%. The non-contrastive model reached 95.4% accuracy, with precision, recall, and F1 scores of 99.3%, 96.46%, and 97.82%. These findings highlight the performance of self-supervised learning in ASD diagnosis, showcasing robust pattern-capturing capabilities for neuroimaging data. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

On the Implications of Human-Paper Interaction for software Requirements engineering Education 34

On the Implications of Human-Paper Interaction for Software ...

引用

34th International Conference on software engineering and Knowledge engineering, SEKE 2022

作者： Kamthan, Pankaj Department of Computer Science and Software Engineering Concordia University Montreal Canada

ISBN: (纸本)1891706543

It is broadly accepted that requirements engineering is one of the most important phases of a software project, and requires tools to be effective. For a variety of reasons, paper as a tool has lasted for millennia and remains ubiquitous. This paper makes a case for a contextual, conscientious, and evidence-based use of paper in a competency-oriented approach to software requirements engineering education (REE). It argues that the prophecies for the obsolescence of paper are premature, there are unique benefits in the use of paper, and the decision to use paper should be based on [0, 1] rather than (0, 1). In this regard, a need-centered conceptual model for human-paper interaction is proposed. The characteristics of paper that make it historically unique are reported and the affordances of paper relevant to REE are discussed. The REE-related activities that benefit from viewing paper as a boundary object and using different types of paper are highlighted and illustrated by means of examples. In advocating polyliteracy, the potential for a convergence of paper and digital media towards a harmonic coexistence is underscored. © 2022 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-World Facial Expression Recognition: A Deep Learning Approach based on Attention Mechanisms 3

Enhancing Real-World Facial Expression Recognition: A Deep L...

引用

3rd International Conference on computer science, Electronic Information engineering and Intelligent Control Technology, CEI 2023

作者： Wu, Kai Chen, Zhuang Chongqing University of Posts and Telecommunications Department of Software Engineering Chongqing400065 China Chongqing University of Technology Department of Computer Science and Engineering Chongqing China

ISBN: (纸本)9798350372052

Occlusion and pose variation are the biggest interference factors in real-world face expression recognition (FER). Faces are likely to be occluded by items such as sunglasses, ducktails, and scarves, which can significantly change the visual appearance of the face, while varied poses can lead to partial information loss and inaccurate localization. In this paper, we propose a new deep learning network model for facial expression recognition, firstly, an attention mechanism module is added on top of the residual neural network, which includes spatial and channel attention modules for suppressing unimportant feature information and highlight the key information. Second, a regional attention mechanism is added for adaptively extracting feature vectors from localized unobstructed facial regions, which are combined with global feature information to learn more comprehensive and detailed potential key information. The proposed method achieved good results on two facial expression datasets, FER2013 and RAF-DB, obtaining an accuracy of 74.37 and 89.12, respectively. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Deep Learning and Machine Learning Methods for Water Quality Prediction 3

A Comparison of Deep Learning and Machine Learning Methods f...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Srinivasa Gupta, N. Valarmathi, B. Hiwanj, Ishaan Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798331527549

Predicting water quality is essential to preserving human health and environmental sustainability. Traditional water quality assessment methods often face scalability and real-time monitoring limitations. With accuracies of 62%, 72%, 83%, 69%, 63%, 66%, 71%, 63%, and 64%, respectively, the current techniques utilized were Logistic Regression, Decision Trees, Random Forest Regressor, Extreme Gradient Boosting, Naive Bayes, K-nearest neighbors, Support Vector Machine, AdaBoost, and Bagging [9]. This study addresses these challenges by leveraging Adaptive Synthetic Sampling (ADASYN) to balance the dataset and evaluating model performance on datasets of 5,000 and 10,000 entries per class. A robust dataset obtained from Kaggle was used, with five models – Long Short-Term Memory (LSTM), Feed Forward Neural Network (FFNN), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Random Forest – evaluated and compared. The proposed methods demonstrate significant improvements in accuracy, with XGBoost achieving the highest accuracy of 95.53%, followed by Random Forest at 93.98%. This work underscores the importance of advanced machine learning techniques in addressing the limitations of traditional methods, enhancing accuracy, scalability, and adaptability in water quality prediction. These findings contribute to advancing environmental monitoring and management practices with reliable, data-driven insights. © 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

Earthworm Optimization with Improved SqueezeNet Enabled Facial Expression Recognition Model

引用

computer Systems science & engineering 2023年第8期46卷 2247-2262页

作者： N.Sharmili Saud Yonbawi Sultan Alahmari E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Computer Science and Engineering Department Gayatri Vidya Parishad College of Engineering for WomenVisakhapatnamAndhra PradeshIndia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11564Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass *** techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or *** execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image ***,many studies presented an endwise structure for facial expression recognition by utilizing DL ***,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)*** presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing *** addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)***,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE ***-ranging experimental analysis is carried out to examine the performance of the proposed *** experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.

关键词： Facial expression recognition deep learning computer vision earthworm optimization hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

A reliable method for data aggregation on the industrial internet of things using a hybrid optimization algorithm and density correlation degree

引用

Cluster Computing 2024年第6期27卷 7521-7539页

作者： Heidari, Arash Shishehlou, Houshang Darbandi, Mehdi Navimipour, Nima Jafari Yalcin, Senay Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Pôle Universitaire Léonard de Vinci Paris France Department of Computer Engineering Kadir Has University Istanbul Turkiye and Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Energy System Engineering School of Engineering and Natural Sciences Bahçeşehir University Istanbul Turkey

The Internet of Things (IoT) is a new information technology sector in which each device may receive and distribute data across a network. Industrial IoT (IIoT) and related areas, such as Industrial Wireless Networks (IWNs), big data, and cloud computing, have made significant strides recently. Using IIoT requires a reliable and effective data collection system, such as a spanning tree. Many previous spanning tree algorithms ignore failure and mobility. In such cases, the spanning tree is broken, making data delivery to the base station difficult. This study proposes an algorithm to construct an optimal spanning tree by combining an artificial bee colony, genetic operators, and density correlation degree to make suitable trees. The trees’ fitness is measured using hop count distances of the devices from the base station, residual energy of the devices, and their mobility probabilities in this technique. The simulation outcomes highlight the enhanced data collection reliability achieved by the suggested algorithm when compared to established methods like the Reliable Spanning Tree (RST) construction algorithm in IIoT and the Hop Count Distance (HCD) based construction algorithm. This proposed algorithm shows improved reliability across diverse node numbers, considering key parameters including reliability, energy consumption, displacement probability, and distance. © The Author(s) 2024.

关键词： Reliability

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：