检索结果-内蒙古大学图书馆

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Velavendan, R. Shubram, S. Shyam Sundar, V. Padmavathi, B. Kavitha, D. Easwari Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350387933

Addiction to alcohol and tobacco is still a major worldwide health issue that requires innovative approaches to early detection and monitoring. This review of the literature provides a thorough summary of recent research projects in the area of tracking systems for alcohol and tobacco use that are both intrusive and non-intrusive for correct classification. The main goal of this research is to investigate how different IOT-based models might improve the precision and effectiveness of alcohol and smoking detection. The measurement of several IoT models used in tracking systems for alcohol and smoking makes up a sizeable section of this work. The study assesses the benefits and drawbacks of each model. Additionally, how effectively it can identify individuals who smoke or drink and how well it can work with various datasets. This research intends to direct future research efforts and encourage the development of more precise and effective tracking systems for smoking and alcohol use, ultimately resulting in improved public health outcomes. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Recommendation System For Social Platform Using Deep Learning Techniques 8

Recommendation System For Social Platform Using Deep Learnin...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Nishchal Narayan, S. SriVidya, M.S. Rv College of Engineering Dept. of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505462

This paper explores advanced techniques in developing a Friends Recommendation System on social media platforms, specifically Facebook. By leveraging user behavior data such as the number of followers, followings, and mutual friends, the system aims to provide accurate friend suggestions. This recommendation methodology can be applied across various domains, including search engine recommendations (Google, Explorer, Microsoft Edge), music recommendations (Wynk), video recommendations (YouTube), movie recommendations (Amazon Prime), and product recommendations (Flipkart, Amazon). The study employs similarity coefficient calculations like Jaccard Distance and Cosine Similarity, alongside ranking measures such as PageRank. Furthermore, the system's performance is evaluated using advanced deep learning techniques, including Graph Neural Networks (GNN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). Comprehensive experimentation involves measuring the F'l-Score and comparing the accuracy of various machine learning and deep learning algorithms to identify the most effective methods for friend recommendations. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Forecasting Stock Price by LSTM-CNN Hybrid Model and Compares Deep Learning Models 1

Forecasting Stock Price by LSTM-CNN Hybrid Model and Compare...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Arora, Aditi Upadhyay, Yashaswi Shukla, Satvik Saket Abes Engineering College Dept. of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350377002

The The accurate forecasting of stock prices holds significant importance in devising effective trading strategies and making informed decisions about stock transactions. The inherent volatility in stock prices, driven by factors like geopolitical tensions, corporate earnings, and commodity costs, underscores the need for precise predictions. Domestic factors such as central bank policies, governmental decisions, inflation, and global market uncertainties also trigger stock price fluctuations. Estimating this volatility is a complex challenge for traders. A novel approach is presented in this research, proposing a hybrid model that integrates two distinct algorithms - Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN). This model harnesses diverse data representations from stock time series to enhance price prediction accuracy. Comparative analyses are performed with alternative models like LSTM (Long Short-Term Memory), CNN (Convolutional Neural Networks) and Naïve Bayes to ascertain the most effective prediction paradigm with minimal error. The study demonstrates that combining temporal and image features extracted from the same dataset diminishes prediction errors compared to using these features independently. The hybrid model outperforms singular prediction models, highlighting a high enhancement. Among the individual models, the LSTM model exhibits superior performance in terms of prediction accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Visualizing Causes of Poverty in India: A Data-Driven Approach Using HPCC Systems 8

Analyzing and Visualizing Causes of Poverty in India: A Data...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Skanda, P.R. Shobha, G. Shetty, Jyoti Rv College of Engineering Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331505462

Poverty in India is a complex issue with multiple causes. This paper mainly focuses on three of the main causes for poverty: Education, Unemployment and Consumer Price Index. This study makes use of data received from the National Informatics Center (NIC) of India to predict poverty across the various states of India. Through applying preprocessing techniques and employing the HPCC Systems Visualization bundle, the research shows that Bihar is facing a higher level of poverty, whereas Mizoram exhibits converse trend. Subsequently, the HPCC ML-Core bundle is applied to conduct linear regression analysis for predicting poverty scores. This predictive model demonstrated an accuracy of 97%. Lastly, the difference between a single-node and 8-node cluster is presented for runtime performance which clearly shows that the 8-node cluster has an advantage for similar computational tasks and thus makes it suitable. © 2024 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

VisualBlend - A Mixed Approach on Forensic Image Generation and Recognition 6

VisualBlend - A Mixed Approach on Forensic Image Generation ...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Unnikrishna, Pillai Midhun Pulkuzhiyil, Vinayak Krishna, Jyothika Wilson, Naveen Kumar, Veena A. Saintgits College Of Engineering Dept. of Computer Science and Engineering Kottayam India

ISBN: (纸本)9798350381689

An extensive use case of Generative Adversarial Networks (GANs) that not only combines artistic creativity with technological innovation but also significantly improves identification precision, filling in critical gaps in the smooth integration of textual descriptions with visual representations. The motivation is rooted on the difficulties that currently exist in accurately identifying human face sketches by directly transforming them into images, an area where prior approaches were inadequate. Our special dual-function technology is designed to get beyond these obstacles and provides a fresh approach for forensic investigators, artists, and sculptors. It has the ability to convert text to image as well as sketch to image. This easy transformation of textual and drawing data represents an integrated combination of creativity and technology that is set to have an impact on a number of disciplines, such as suspect identification and crime scene reconstruction. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Text-Summarization and Language Simplification:End-to-End Approach for Content Comprehension 1

Enhanced Text-Summarization and Language Simplification:End-...

引用

1st International Conference on Trends in engineering Systems and Technologies, ICTEST 2024

作者： Riza Ayisha, P. Mathew, George Government Engineering College Dept. of Computer Science and Engineering Thrissur India

ISBN: (纸本)9798350307795

Text summarization is the process of shortening a large body of text in a document to form a shorter while preserving its most important information. With the exponential growth of digital data, there is a need for automated text summarization to help users quickly comprehend the content. The use of machine learning techniques, particularly deep learning models, has shown great promise in generating high-quality summaries. Among these models, BERT (Bidirectional Encoder Representations from Transformers) has emerged as a state-of-the-art method for various natural language processing (NLP) tasks, including text summarization. In this paper, we propose to implement a text summarization system using the BERT model. Apart from the normal text summarization, we will be implementing a Language Simplification model that simplifies complex sentence structures or use simpler vocabulary while preserving the original meaning. This model transforms convoluted or verbose sentences into shorter and more straight-forward constructions The paper aims to develop an end-to- end summarization system that takes a long document as input and generates a summary of the most important information contained in the document. For example, like taking the entire news from an online portal and generates it summary. © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

A Study of Various Optimization Algorithms and Entropy Measures for Image Segmentation 18

A Study of Various Optimization Algorithms and Entropy Measu...

引用

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

作者： Gonthina, Nagamani Prasad, L. V. Narasimha Institute of Aeronautical Engineering Dept. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9789380544519

One of the most challenging jobs in image processing techniques is image segmentation. To identify the objects of interest in an image, we segment the image into different parts and extract the interesting objects. Previous studies have addressed various techniques for image segmentation, like clustering, thresholding, watershed, neural networks, etc. However, a segmentation technique alone cannot achieve better-segmented results. Much research is being carried out by combining the segmentation technique with either an optimization algorithm or entropy measures to enhance the efficiency of segmented results in the segmentation process. So, there is a need to study various segmentation techniques combined with optimization algorithms or entropy measures. Recent studies focused only on segmentation techniques, entropy measures, or optimization algorithms rather than on these combinations. This paper presents various works based on optimization techniques and entropy measures combined with clustering and thresholding techniques of image segmentation. From the study it is observed that most of the work is carried out in combining thresholding-based image segmentation techniques with optimization algorithms and entropy measures. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Entropy measures Image segmentation Optimization algorithms Segmentation techniques

来源：评论

学校读者我要写书评

暂无评论

A METHOD TO ESTIMATE THE EARLY AGE COMPRESSIVE STRENGTH OF CONCRETE BEFORE DEMOLDING USING A PIN PENETRATION DEVICE

Journal of Structural and Construction Engineering

引用

Journal of Structural and Construction engineering 2023年第803期88卷 18-26页

作者： Nishiwaki, Tomoya Takasugi, Fumiya Narantogtokh, Bayarjavkhlan Hara, Shoumi Maliha, Maisha Dept. of Architecture and Building Science Graduate School of Engineering Tohoku University Japan Dept. of Architecture and Civil Engineering Faculty of Engineering Tohoku University Japan Dept. of Architecture Graduate School of Engineering The University of Tokyo Japan

This study proposed a method to estimate the compressive strength of early-age concrete before demolding using a pin penetration device. Small holes were prepared on molds to apply for this method. A strong correlation was obtained between pin penetration dept. and compressive strength despite the materials and mix proportions difference. This method was applicable between 5 and 15 MPa compressive strength, which is the demolding criterion. Within the experimental results, the penetration dept.s of 12.5, 9.5, and 8.5 mm (Flat), and 13.0, 10.0, and 9.0 mm (Sharp) were sufficient to demolding criteria of 5, 10, and 15 MPa, respectively. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： Compressive strength

来源：评论

学校读者我要写书评

暂无评论

Flood Prediction System with Voting Classifier 2

Flood Prediction System with Voting Classifier

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Akshitha, K. Vijay Anand, M. Saveetha Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372847

Flood prediction plays a vital role in reducing the influence of natural disasters among the communities and the infrastructure. This paper presents a machine learning approach for flood prediction using a voting classifier, combining information from turbidity, gauge height, and discharge as key features. The dataset, comprising historical records of these parameters, serves as the foundation for training and evaluating the predictive models. In our work, we employ a voting classifier, integrating Random Forest and Gradient Boosting algorithms to harness the strengths of diverse models. The ensemble approach aims to enhance prediction accuracy and robustness by aggregating the predictions of individual classifiers. The choice of features turbidity, gauge height, and discharge is motivated by their relevance in capturing hydrological dynamics associated with flood events. The dataset is preprocessed to handle missing values, normalize features, and encode the target variable. The voting classifier is being trained upon a subset of data, and its accomplishment is estimated on a discrete test set. Various metrics, including accuracy, are employed to assess the model's predictive capabilities. Results indicate promising performance in flood prediction, showcasing the potential of ensemble methods for such applications. This system assures an accuracy of about approx. 99% and alert notification will be sent to the residents of flood predicted areas. Hence, this contributes to the ongoing efforts in leveraging machine learning techniques and also provides an alert notification for enhancing disaster preparedness and response with proper communication. © 2024 IEEE.

关键词： Turbidity

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis on Skin Cancer Classification Using Transfer Learning 3

A Comprehensive Analysis on Skin Cancer Classification Using...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Renu, Israt Zerin Haque, Md. Momenul Paul, Subrata Kumer Mou, Mahmuda Shirin Rahman, Md Nahid Gupta, Sudipta Sen Paul, Rakhi Rani Rabindra Maitree University Dept. of Computer Science and Engineering Kushtia7000 Bangladesh Qadirabad Dept. of Computer Science and Engineering Dayarampur Natore6431 Bangladesh University of Rajshahi Dept. of Computer Science and Engineering Rajshahi6205 Bangladesh

ISBN: (纸本)9798350388282

Skin cancer, a prevalent and potentially life-threatening disease, necessitates accurate and timely diagnosis for effective treatment. In addressing this critical healthcare challenge, this research proposes a novel approach to skin cancer classification. The study identifies the need for enhanced diagnostic accuracy and introduces a solution by integrating the efficiency of transfer learning, specifically utilizing the EfficientNet V2 architecture. The proposed methodology leverages pre-trained convolutional neural networks (CNNs) to extract high-level features from dermatological images, which are subsequently input into a sophisticated classifier, forming a robust framework for precise skin cancer classification. The research employs a diverse dataset comprising 3297 images sourced from the publicly available Skin Cancer ISIC archive dataset, ensuring comprehensive coverage of benign and malignant skin lesions. During the training phase, the proposed EfficientNet V2 transfer learning approach outperforms conventional methods, achieving an impressive accuracy of 84%, surpassing both Inception V3 (82%) and a generic CNN model (81%). Interpretability analysis is conducted to elucidate the decision-making process of the EfficientNet V2 model, providing insights into the key features influencing its predictions. This transparency is crucial for building trust in the model's recommendations and facilitating its seamless integration into clinical workflows. The EfficientNet V2 transfer learning approach emerges as a promising and effective solution for advancing skin cancer classification systems, contributing significantly to the ongoing efforts to improve diagnostic accuracy in dermatology. © 2024 IEEE.

关键词： Decision making

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：