检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kate, Priya Pacharney, Utkarsha Datta Meghe Institute of Higher Education and Research Department of Computer Science and Engineering Faculty of Engineering and Technology Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Department of Computer Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

5G technology represents a progressive leap in Wi-Fi conversation, providing unheard-of pace, connectivity, and capacity. Its deployment has profound implications for modern engineering, impacting industries such as telecommunications, healthcare, transportation, and clever towns. With speeds up to one hundred instances quicker than 4G and latency as little as 1 millisecond, 5G permits real-time facts trade, fostering improvements like independent vehicles, far-flung surgeries, and the Internet of Things (IoT). Currently, Engineers are challenged to design infrastructure that will assist the dense community of gadgets related to 5G, necessitating advancements in antenna design, power performance, and statistics security. The era also quickens the adoption of part computing, reducing reliance on centralised facts centres and ensuring quicker processing near the date supply. The transformative impact of 5G extends beyond connectivity. It reshapes the layout and capability of present-day engineering structures, emphasising adaptability, resilience, and scalability. As 5G continues to conform, its function in driving innovation and redefining engineering paradigms becomes increasingly glaring. © 2025 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Restaurant Recommendation System Based on ML Algorithms and Real-Time Web Scraping

Restaurant Recommendation System Based on ML Algorithms and ...

引用

2024 International Conference on Big Data Analytics in Bioinformatics, DABCon 2024

作者： Rudrapati, Mahima Varghese, Benetta Paul, Carissa Jeya Sekar, MacHlin Singh, Priyamvada Fr. C. Rodrigues Institute of Technology Department of Computer Engineering Navi Mumbai India

ISBN: (纸本)9798350378047

As the restaurant industry expands, the sheer number of dining options makes it increasingly difficult for individuals to find establishments that match their preferences. To address this challenge, we present a personalized restaurant recommendation system that leverages both collaborative filtering and content-based techniques, augmented by real-time web scraping. Users provide their past restaurant ratings and desired location, which is used to recommend dining options based on two algorithms: user similarity and Google reviews. If a location is absent in the database, the system dynamically scrapes Google reviews and applies natural language processing (NLP) to extract feature-opinion pairs, identify sentiment, and compute a reliability score. Collaborative filtering identifies user similarities based on historical ratings, while the content-based model combines sentiment analysis, average ratings, review count, and reviewer reliability to generate a comprehensive restaurant score. Recommendations are ranked and accompanied by a detailed breakdown of the contributing factors, offering users transparency in how the suggestions are tailored to their preferences. This approach not only enhances the accuracy of recommendations but also provides a more informed and personalized dining experience. © 2024 IEEE.

关键词： content based filtering data analysis feature opinion mining natural language processing real time data analysis recommendation sentiment analysis web-scraping

来源：评论

学校读者我要写书评

暂无评论

Violence Detection in Indoor Domestic Environment Using Multimodal Information 5th

Violence Detection in Indoor Domestic Environment Using Mul...

引用

5th International Conference on Machine Learning, Image Processing, Network Security, and Data Sciences, MIND 2023

作者： Aravinth, R. Shashwat, T. Yeshwanth, V. Sitara, K. Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tamil Nadu Tiruchirappalli620015 India

ISBN: (纸本)9783031622168

The recognition of violent activities has emerged as a prominent topic within the realm of computer vision research. This issue is of paramount importance within indoor domestic environments, given the heightened vulnerability of individuals residing in such conditions to potential attacks. Consequently, there exists a substantial imperative for the development of intelligent surveillance systems capable of autonomously monitoring individuals and identifying instances of violent behavior. While numerous techniques grounded in handcrafted and deep learning features have been proposed to address this challenge, it is noteworthy that many of these methodologies primarily focus on video data and often disregard the potential insights offered by audio information. In light of this, this paper presents a fusion model for violence detection, which integrates audio and video features to provide a comprehensive and nuanced assessment of potentially violent incidents. Our proposed approach leverages inflated 3D networks and pretrained models from the Visual Geometry Group to extract video and audio features, respectively. Subsequently, these extracted feature vectors are combined utilizing a joint cross-attention fusion model. The results of our proposed model are promising, with an achieved accuracy rate of 73.3%, coupled with a processing speed of 25 frames per second. This research contribution is instrumental in advancing violence detection technology, particularly within indoor domestic environments, where the safety and well-being of individuals are paramount concerns. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automated Pneumonia Detection Using Manta Ray Optimizer with Deep Learning Approaches 2

Automated Pneumonia Detection Using Manta Ray Optimizer with...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Sabaresh, M.M. Shahin, Fidin Sabri Raja, M Senthil SRM Institute of Science and Technology Computer Science and Engineering CTech Department Chennai India SRM Institute of Science and Technology CTech Department Chennai India

ISBN: (纸本)9798350368109

This new method merging various disciplines into each stage, introduces a novel integration of state-of-the-art neural networks (MobileNet, ResNet, and VGG19) with an adaptive nature based on the Manta Ray scheme within the framework approaches helped by Adam optimizer to significantly improve accuracy across chest X-ray images. Integrating physics-motivated model parameter adaptation, based on the fluid-inspired lenticular lens architecture of manta rays (7), into MRO encourages more rapid convergence during training and allows for flexible manipulation in response to distributed behaviors inherent to medical imaging. This combined action not only accelerates convergence but also enhances the global stability of the model, improving classification accuracy and increasing reliability in diagnostics. Furthermore, the interoperability of these approaches highlights how cross-disciplinary research in healthcare technology can not only be transformational but also provide invaluable adjuncts to clinical practice for high-throughput targeted analyses. In an entirely new way, we want to transform traditional medical imaging analysis by bringing pervasively accurate diagnosis into everyday clinical practice while providing better outcomes for patients and leading "the cutting edge"of healthcare delivery. This ultimate workflow does seem to hold the key which can result in far-reaching improvements in health care, especially after making important progress upon the currently existing slower and less efficient healthcare systems. This approach is interdisciplinary and promises revolutionary progress in medical diagnostics. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Automated Leukemia Detection and Classification from Blood Smear Images Using Machine Learning Techniques 2

Automated Leukemia Detection and Classification from Blood S...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Manu, Y.M. Priyanka, M.E. Bgs Institute of Technology Adichunchanagiri University Department of Computer Science & Engineering BG Nagara Mandya India

ISBN: (纸本)9798350372892

Leukemia early detection and identification is a major problem in disease diagnosis because it requires low-cost, precise differentiation of malignant leukocytes in the early stages of the illness. Despite its high frequency, leukemia is difficult to diagnose because of the restricted availability of flow cytometer equipment and the laborious nature of current laboratory diagnostic procedures. Considering machine learning's (ML) potential for illness diagnosis, the purpose of this systematic review is to look into research that uses ML methods for leukemia detection and classification. Leukemia smear image analysis using machine learning (ML) algorithms can improve diagnostic accuracy, shorten diagnosis times, and provide quicker, safer, and more economical diagnostic services. Clinical and laboratory personnel may also use machine learning techniques into their tools and applications in the lab in addition to their present diagnostic techniques. One method that has been suggested is using a machine learning technique, such artificial neural networks, to diagnose and categorize patients' conditions early on. As a result after collection of data model development should be done then data training and at last model should be tested and Ml algorithms should be used to compare results. Tests are conducted on samples from blood images. © 2024 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Framework for Automatic Sarcasm Detection Using Proposed Tensor-DNN-50 Algorithm 4th

A Real-Time Framework for Automatic Sarcasm Detection Using ...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Murthy, Jamuna S. Siddesh, G.M. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819726103

Social media platforms such as Twitter, Facebook, and Instagram are vast repositories of trending global news. They generate an enormous amount of data, offering a valuable resource for both academic researchers and IT marketing teams. These data can be harnessed for various insights and applications. A prominent and pressing research area within this data is the detection of sarcasm and fake news. The internet is rife with misleading and false information, often causing widespread confusion. Current research primarily categorizes news as either real or fake, using machine learning algorithms. However, this binary approach struggles with news that is partially true yet contains elements that could be deemed fake. To address this issue, our work introduces a real-time framework for sarcasm detection, utilizing an innovative deep learning technique called Tensor-DNN-50 for multiclass classification. The TDNN-50 model not only classifies news articles based on authenticity but also quantifies the level of sarcasm within them. Comparative analysis against leading techniques like SVM, att-RNN, and EANN demonstrates the superiority of our proposed algorithm. It achieves an impressive accuracy of 96.4% for two-class classification, 94.32% for four-class classification, and an astonishing 99.1% for seven-class classification. These results underscore the potential of our Tensor-DNN-50 Model in effectively addressing the intricate challenges of sarcasm detection and news classification with unparalleled accuracy across multiple classes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Review of Fintech Management and Security Development 10

A Review of Fintech Management and Security Development

引用

10th IEEE Information technology International Seminar, ITIS 2024

作者： Ritonga, Ali Akbar Zuhri Harahap, Syaiful Sooai, Adri Gabriel Nugroho, Aryo Samsir Prasetyo Adi, Puput Dani Universitas Labuhanbatu Faculty of Science and Technology Department of Informatics Management North Sumatera Labuhanbatu Indonesia Universitas Labuhanbatu Faculty of Science and Technology Department of Information System North Sumatera Labuhanbatu Indonesia Universitas Katolik Widya Mandira Faculty of Computer Science Department of Computer Engineering NTT Kupang Indonesia Universitas Narotama Faculty of Computer Science Department of Information System Surabaya Indonesia Universitas Labuhanbatu Faculty of Computer Science Department of Informatics Engineering North Sumatera Labuhanbatu Indonesia Department of Telecommunication Bandung Indonesia

ISBN: (纸本)9798331521295

This research focuses on the review of Fintech and its development on the IoT Platform and also the risks that can be posed to the IoT network used. Finance is the most essential side of several other sectors which in this case often experience many losses, one of the biggest losses is the existence of hackers and theft of money through the Internet platform or Internet Server. This research reviews how the ins and outs of the flow of funds located on servers or online banks. And ways to overcome hackers and bypass data. Comprehensively reviewed in this research review. This research discusses Cryptocurrency Analysis, Bitcoin, and Ethereum Comparison which are some of the methods used in online-based Finance, which is without currency but has the same value even more than currency if the conversion process is carried out at the bank. In this research, it is comprehensively discussed how methods are carried out in the process of securing data, Cryptocurrency, Bitcoin, and Ethereum are comprehensively discussed to get a lot of data and comparisons and the right steps to deal with crime via the internet. The predicted use of IoT in the Fintech sector is 140 billion connected devices, IoT Loans 110 billion connected devices, and IoT insurance with an estimated 90 billion connected devices, in the approaching 2026. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Exploring Music Similarity through Siamese CNNs using Triplet Loss on Music Samples

Exploring Music Similarity through Siamese CNNs using Triple...

引用

2023 International Research Conference on Smart Computing and Systems engineering, SCSE 2023

作者： Kasif, Gibran Thondilege, Comganesha University of Westminster London School of Computer Science and Engineering United Kingdom Informatics Institute of Technology Department of Computing Colombo06 Sri Lanka

ISBN: (纸本)9798350341454

In the rapidly evolving digital music landscape, identifying similarities between musical pieces is essential to help musicians avoid unintended copyright infringement and maintain the originality of their work. However, detecting such similarities remains a complex and computationally challenging problem. A novel approach to address this issue is a song similarity detection system that utilizes a Siamese Convolutional Neural Network (CNN) with Triplet Loss for effective audio input comparison. The model is trained on a custom dataset from WhoSampled, an extensive database of information on sampled music, cover songs, and remixes. The dataset comprises pairs of audio samples and interpolations, making it suitable for the Siamese CNN approach. Incorporating Triplet Loss enhances the model's performance by learning discriminative features for improved comparison. The performance of this system is assessed using a confidence interval-based metric, achieving a 96.86% accuracy at a 99.7% confidence level in determining the similarity between music samples. The solution provides a helpful tool for musicians to actively compare their creations with existing songs, helping to reduce the likelihood of unintentional plagiarism and possible legal issues. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Single/Multi-band graphene-based disk THz absorbers with single graphene layer: conceptual design

引用

Optical and Quantum Electronics 2024年第11期56卷 1-26页

作者： Mohsen Daraei, Omid Rezaei, Pejman Zamzam, Pouria Bozorgi, S. Amir Amiri, Nafiseh Ebrahimi, Farshad Radpour, Hamed Rastkar Mirzaei, Milad Mohapatra, Saswat Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States Electrical and Computer Engineering Faculty Semnan University Semnan Iran Center for Digital Safety and Security AIT Austrian Institute of Technology Seibersdorf Austria The School of Electrical and Computer Engineering University of Oklahoma NormanOK73019 United States

This article introduces a unified structure for broadband and multi-band graphene-based absorbers. The absorption process relies on multiple circular graphene disks positioned on a glass surface. The absorber’s functionality can be adjusted from broad-band to multi-band by varying its height. To thoroughly assess its performance, we employed two theoretical frameworks: the transmission line model (TLM) and the Finite Element Method (FEM). Additionally, we conducted optical analysis using various incident wave polarizations. To validate our findings, we simulated the structure in the CST Studio simulator. The analysis reveals that the structure achieves over 90% absorption in the broad-band phase. Furthermore, it exhibits five absorption peaks: 28.1%, 99.9%, 98.1%, 94%, and 76% at frequencies of 0.3, 1, 2, and 2.7 THz, respectively, in the multi-band absorption phase. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Terahertz waves

来源：评论

学校读者我要写书评

暂无评论

Towards Building a Global Robust Model for Heart Disease Detection

引用

SN computer Science 2023年第5期4卷 596页

作者： Mali, Bhabesh Saha, Santanu Brahma, Daimalu Pinninti, Ramakrishna Singh, Pranav Kumar Department of Computer Science and Engineering Central Institute of Technology Kokrajhar BTR Assam 783370 India

Heart disease is one of the most menacing non-communicable diseases. Heart disease prediction is one of the most popular topics in the field of biomedical engineering. Almost all the models for heart disease detection are based on centralized training of data where data are concentrated in a single server. Centralized training of the model may give a good accuracy to predict/detect, yet the models are not robust as only a single dataset is used to train and test the model. This is a major problem with centralized training. Therefore, in order to solve this problem of robustness, we decided to use and simulate federated learning (FL) to build a heart disease detection model through which we can use multiple datasets from different regions to train the model. We created four virtual workers where each one is representing a hospital present in a different location containing the local data. We have used the dataset downloaded from IEEE Dataport. It is a combination of five different datasets, including the Cleveland, Hungarian, Switzerland, Long Beach VA, and Statlog Heart Dataset. The final dataset contains 11 input features and the output label. We divided the dataset into training and testing data. The training data are divided into four sub-datasets using both IID (Independent and Identically Distributed) and non-IID approaches. Then, the sub-datasets are sent to these four hospitals differently for both approaches. We have used the artificial neural network as the FL base model. We trained both the IID and non-IID models and then tested the models with test data and got an accuracy of 84.87 and 86.55% for the IID and non-IID approaches, respectively. We have also checked the AUC score, sensitivity, and specificity for the IID and non-IID approaches. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artificial neural network Federated averaging Federated learning Heart disease

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：