检索结果-内蒙古大学图书馆

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： Chen, Liqiong Xu, Zhengyu Shanghai Institute of Technology Department of Computer Science and Information Engineering Shanghai China

ISBN: (纸本)9798350369564

Recommender systems exist with the aim of helping users discover personalized and useful content and products in a sea of information. Recommender systems have long faced challenges such as data sparsity and cold start. In this study, we propose a recommendation model based on Knowledge Graph Convolutional Network and LDA (KGCN-LDA), which first constructs a collaborative knowledge graph, and deep mines the auxiliary entity information in the collaborative knowledge graph using graph convolutional network(GCN). In the knowledge graph, GCN is used to deep mine the auxiliary entity information in the collaborative knowledge graph, while LDA mines the potential features in the semantic information, and finally, the user and entry embeddings obtained from the two parts are concatenated to generate the final recommendation results. In order to evaluate the effectiveness of the proposed model, we conducted experiments on a public dataset, and the results show that the proposed method significantly outperforms several existing methods in terms of precision, recall and F1. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Human Activity Recognition in Smart Homes using Deep Learning and Edge Computing for Real-Time Processing 5

Privacy-Preserving Human Activity Recognition in Smart Homes...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mariappan, K. Gopal, Baskar Parthasarathy, J. Sreekanth, G.R. Nanmaran, R. Jegajothi, B. SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India College of Engineering University of Technology & Applied Science Nizwa Oman Computer Science & Engineering Jayalakshmi Institute Of Technology Dharmapuri India Information Technology Nandha Engineering College Erode52 India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India SRS Tech Solutions Chennai India

ISBN: (纸本)9798331530013

The rapid advancement of smart home technologies necessitates efficient human activity recognition (HAR) systems while ensuring user privacy. This research presents a novel architecture that integrates deep learning and edge computing for real-time HAR, emphasizing privacy protection. By employing differential privacy methods and federated learning, the approach minimizes personal data exposure risks. Using the UCI HAR dataset, the model achieves an accuracy of 96.50%, with precision, recall, and Fl-score metrics of 95.75%, 96.20%, and 95.97%, respectively. The results indicate high accuracy and adaptability to varying smart home environments, while edge computing ensures minimal latency. This work highlights the importance of balancing performance and privacy in HAR systems, paving the way for secure smart home applications. Additionally, it points to the potential of deep learning in medical diagnostics, suggesting future research could enhance diagnostic capabilities across various medical imaging modalities, including CT scans and MRIs, to improve healthcare outcomes. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Time-series Models vs ML Tools for yearly average Indian Rainfall Forecasting 8

Comparative Analysis of Time-series Models vs ML Tools for y...

引用

8th International Conference on Computing in engineering and technology, ICCET 2023

作者： Maniyal, Vishal Sharma, Teek Parval Department of Computer Science and Engineering National Institute of Technology HP Hamirpur India

ISBN: (纸本)9781839539237

Rainfall forecasting plays a critical role in various aspects of human life such as in water management, disaster preparedness, and disaster management. Its impact on agriculture can be well understood by the fact that most farmers plan agricultural activities based on rainfall patterns. This paper focuses on annual rainfall forecasting for India using time series models and machine learning tools. Rainfall and temperature data of India for the period of 1901-2013 are preprocessed. Exploratory analysis is done to understand the underlying pattern in the dataset. Auto-correlation function (ACF) and partial auto-correlation function(PACF) are plotted and analyzed. Time series models are developed using autoregressive integrated moving average (ARIMA), vector autoregressive (VAR) techniques. VAR(6), ARIMA (2, 1, 1), Long Short Term Memory (LSTM), and XGBoost are used to forecast annual rainfall, and comparative analysis is performed using measures such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The vector autoregressive model on comparative analysis gives the lowest RMSE, MAE, and MAPE values thereby shows significant improvement over the rest of the models. © The Institution of engineering & technology 2023.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Twitter Spam Detection Using Different Machine Learning Techniques 1

引用

2nd International Conference on Signal and Data Processing, ICSDP 2022

作者： Venkatesh, G. Reddy, D. Santosh Kavitha, C. Jinila, Y. Bevish Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Information Technology Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9789819914104

ISBN: (纸本)9789819914098

Vehicle reconciliation strategies have been involved a few times in spam channels to incorporate approaching/active messages, for example, spam and spam bunches. This technique expresses that each bunch contains little miniature groups, and each miniature group is dispersed. Notwithstanding, this thought ought not be trifled with, and the miniature group might have a lopsided dispersion. To build the respectability of the main strategy for appropriating the Internet class, we suggest supplanting the Euclidean space with a succession of models that incorporate into the miniature bunch connected with the circulation. Here, the Naïve Bayes (INB) classification has been carried out to carry out miniature bunches across the line. While these INBs can decide the distance and limits of micro clusters, Euclidean space considers the overall worth of the group and misdirects the bigger micro cluster. In this report, DenStream is upheld by a committed framework called INB DenStream. To represent the presentation of INB-DenStream, current techniques, like DenStream, StreamKM + +, and CluStream, have been utilized in the Twitter chronicle, and their exhibition has been estimated as far as quality, honesty as a general rule, memory as a rule, F1 measurements., markers, and complex estimations. The relatively close outcomes show that our techniques outflank its rivals in the set figures. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Image Classification of Ischemic Stroke Blood Clot Origin using Stacked EfficientNet-B0, VGG19 and ResNet-152 3

Image Classification of Ischemic Stroke Blood Clot Origin us...

引用

3rd International Conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Rao, Masabathula V S Raghavendra Puligundla, Surya Ekkala, Nikhil Sai Chebrolu, Srilatha National Institute of Technology Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798350300710

Stroke continues to be the second-leading cause of mortality globally. Over 700,000 Americans suffer from an ischemic stroke every year as a result of a blood clot clogging a brain artery. The chances of the patient surviving a second stroke where recurrent strokes account for 23% of all incidents, are decreased. The motivation of this work is to help physicians better understand the causes of blood clots in fatal strokes, making it simpler for doctors to recommend the most effective post-stroke therapeutic management and lowering the risk of a second stroke. Whole slide digital pathology images capture the blood clot of the patient who has suffered from ischemic stroke. The objective of this work is to classify the blood clot origin in the case of ischemic stroke. Its a binary classification problem where the classes are Cardioembolism and Large artery atherosclerosis. Deep learning models can be applied to classify the stroke origin efficiently. This work proposes a stacked deep learning model with VGG19, ResNet-152, EfficientNet-B0 to classify the stroke origin. Experiments have been conducted on Mayo Clinic - Strip AI dataset from Kaggle. Comparisons have been made with these individual models and also combinations of these models and found that the proposed model is achieving lower loss value. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Predicting Density in Post-Rift Lithologic Sequence from Well Log Data Using Multilayer Perceptron Neural Network 2

Predicting Density in Post-Rift Lithologic Sequence from Wel...

引用

2nd International Conference on Informatics, ICI 2023

作者： Roy, Avik Arora, Anuja Jaypee Institute of Information Technology Department of Computer Science Engineering and IT Noida India

ISBN: (纸本)9798350343830

Estimating the density log is essential in analyzing reservoir characterization of oil and gas exploration. Density and Sonic logs assist in generating the acoustic impedance logs that further help in the impedance volume generation and inversion analysis. In the past different empirical methods (such as Gardner's equation, and Faust Equation) have been proposed to estimate density logs from the other recorded well log data like Sonic and Resistivity Logs. The current study demonstrates that if the Gamma Ray (GR) log is present in a well in addition to the Sonic log, it may be applied to estimate the density logs, improving the acceptance and accuracy of the prediction. The approach takes data from the F3 North field of the Netherlands and estimates density using both gamma and sonic logs. Data from four wells have been used in the study. The model is prepared using training data of three wells and one well is used for testing purposes. The result shows significant improvement by adding GR logs instead of using only Sonic logs while predicting Density with the Neural Network Algorithm. The study gives confidence in using GR logs in addition to Sonic logs for better predictability of Density with Neural Network Algorithms. © 2023 IEEE.

关键词： Acoustic impedance

来源：评论

学校读者我要写书评

暂无评论

Identification of Characteristics of Mewari Poems 6

Identification of Characteristics of Mewari Poems

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Jain, Shubham Dutta, Kamlesh National Institute of Technology Hamirpur Computer Science and Engineering Department Hamirpur India

ISBN: (纸本)9798350346961

Poetry is a type of literature that is used to convey a man's feeling, sentiments and imaginations. It is formed by a beautiful amalgamation of thoughts and notions in the form of words and tones. Mewari in particular is a major dialect of the Rajasthani language and is spoken by a vast majority of population in the Mewar region. It possess a great importance because many literature works created in Mewari glorifies about the great kings like Maharana Pratap, Maharana Kumbha, etc. Thus the cultural significance of this language increases exponentially. Despite having this huge significance very little work has been done in the field of Mewari language in the field of Natural Language Processing, be it identification, classification or extraction. Like Hindi, the Mewari language is written in Devanagari lipi. This paper aims to identify various elements of a Mewari literature like rhymic extent, negative tone, mood and number of a poem. The idea is to extract the data and match it with various parameters to find the hidden elements. Although, decent amount of work has been done in the field of poetry classification and analysis in different languages but this will be the first work being done on Mewari dialect. Various preprocessing operations were performed and it successfully predicted the Rhyme, Negative Tone, Mood and Number with accuracy of 83.75, 90,70 and 70.7 percentage respectively.. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor

引用

Visual Computing for Industry,Biomedicine,and Art 2022年第1期5卷 25-43页

作者： Harmandeep Singh Vipul Sharma Damanpreet Singh Department of Computer Science and Engineering IKG Punjab Technical UniversityJalandharPunjab 144603India Department of Computer Science and Engineering Sant Longowal Institute of Engineering and TechnologySangrurPunjab 148106India

This paper introduces a comparative analysis of the proficiencies of various textures and geometric features in the diagnosis of breast masses on *** improved machine learning-based framework was developed for this *** proposed system was tested using 106 full field digital mammography images from the INbreast dataset,containing a total of 115 breast mass *** proficiencies of individual and various combinations of computed textures and geometric features were investigated by evaluating their contributions towards attaining higher classification *** state-of-the-art filter-based feature selection algorithms(Relief-F,Pearson correlation coefficient,neighborhood component analysis,and term variance)were employed to select the top 20 most discriminative *** Relief-F algorithm outperformed other feature selection algorithms in terms of classification results by reporting 85.2%accuracy,82.0%sensitivity,and 88.0%specificity.A set of nine most discriminative features were then selected,out of the earlier mentioned 20 features obtained using Relief-F,as a result of further *** classification performances of six state-of-the-art machine learning classifiers,namely k-nearest neighbor(k-NN),support vector machine,decision tree,Naive Bayes,random forest,and ensemble tree,were investigated,and the obtained results revealed that the best classification results(accuracy=90.4%,sensitivity=92.0%,specificity=88.0%)were obtained for the k-NN classifier with the number of neighbors having k=5 and squared inverse distance *** key findings include the identification of the nine most discriminative features,that is,FD26(Fourier Descriptor),Euler number,solidity,mean,FD14,FD13,periodicity,skewness,and contrast out of a pool of 125 texture and geometric *** proposed results revealed that the selected nine features can be used for the classification of breast masses in mammograms.

关键词： Mammography Breast cancer Machine learning Classification

来源：评论

学校读者我要写书评

暂无评论

Study of MobileNets Model in Federated Learning

Study of MobileNets Model in Federated Learning

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Negi, Vipul Singh Chinara, Suchismita National Institute of Technology Department of Computer Science and Engineering Rourkela769008 India

ISBN: (纸本)9798350304602

The challenges of handling decentralised data lead to the demand for research on secure gathering, efficient processing, and analysing of the data. In decentralised systems, each node (device) can make independent decisions, reducing the complexity and challenges of dealing with extensive data. Privacy has become a significant concern for our society due to the rise in the number of Edge/IoT devices, the lack of presence of a centralised system, etc. To solve this conundrum, federated learning was proposed. Federated learning works on the sharing of parameter values rather than the data. Worldwide, 10.2 Billion non-IoT and 19.8 billion IoT devices will be active in 2023. These devices lack security when it comes to using traditional machine learning. However, federated learning models solve this problem using techniques such as Secure Aggregation and Differential Privacy, which provide security for the devices and efficient communication between them. The challenges arise from heterogeneous devices, leading to the client selection problem, unbalanced data, and many more problems. The Proposed work focuses on using the MobileNets series of model architecture for federated learning using the FedAvg Strategy. MobileNets architecture has always been robust and reliable when it come to devices with resource constraints. An older generation system is used to show that federated learning is a viable technique for decentralized machine learning. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation 3

Antarlekhaka: A Comprehensive Tool for Multi-task Natural La...

引用

3rd Workshop for Natural Language Processing Open Source Software, NLP-OSS 2023

作者： Terdalkar, Hrishikesh Bhattacharya, Arnab Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur India

ISBN: (纸本)9798891760455

One of the primary obstacles in the advancement of Natural Language Processing (NLP) technologies for low-resource languages is the lack of annotated datasets for training and testing machine learning models. In this paper, we present Antarlekhaka, a tool for manual annotation of a comprehensive set of tasks relevant to NLP. The tool is Unicode-compatible, language-agnostic, Web-deployable and supports distributed annotation by multiple simultaneous annotators. The system sports user-friendly interfaces for 8 categories of annotation tasks. These, in turn, enable the annotation of a considerably larger set of NLP tasks. The task categories include two linguistic tasks not handled by any other tool, namely, sentence boundary detection and deciding canonical word order, which are important tasks for text that is in the form of poetry. We propose the idea of sequential annotation based on small text units, where an annotator performs several tasks related to a single text unit before proceeding to the next unit. The research applications of the proposed mode of multi-task annotation are also discussed. Antarlekhaka outperforms other annotation tools in objective evaluation. It has been also used for two real-life annotation tasks on two different languages, namely, Sanskrit and Bengali. The tool is available at https://***/Antarlekhaka/code. © 2023 Association for Computational Linguistics.

关键词： Natural language processing systems

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：