检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Sriram, S. Rk, Hariharathmajan Barathi Babu, M. Pradeep, Amal Karthi, R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Federated learning (FL) is a collaborative learning paradigm where multiple clients are used to build the model without sharing data and preserving privacy. An FL-based linear regression model is designed to predict the length of stay for patients at hospitals using the low-power Arduino Nano 33 BLE Sense microcontroller unit (MCU). FL uses a distributed learning technique that allows model building from decentralized data sources. The Arduino Nano 33 BLE Sense is a compact and energy-efficient MCU providing an ideal platform for implementing FL in resource-constrained environments. FL algorithms aggregate model parameters from multiple Arduino clients and collectively train and build a predictive model to estimate the length of stay at the hospital by patients. Experiments were conducted to understand the performance of FL on clients with data of equal and varying sizes and heterogeneous data from multiple sources. The performance of the algorithm is evaluated based on Mean Absolute Error (MAE), Percentage Decrease in Training error (PDTE), and Percentage Difference with Optimal Testing (PDOT) value. Experimental results show that the number of local epochs and FL rounds affects the convergence of clients to the optimal value. The experimental results demonstrate the applicability of FL on low-power MCUs, preserving privacy which is a core requirement for healthcare solutions. © 2024 Elsevier B.V.. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Real-time Tweets Analysis using Machine Learning and Bigdata 3

Real-time Tweets Analysis using Machine Learning and Bigdata

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Reddy, P Nandieswar Sai Aswath, S. Alapati, Rithvika Radha, D. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350364569

Twitter's exponential increase in data has transformed it into a rich source for machine learning research, unveiling patterns of opinions and behaviors. This research introduces an automated pipeline built on Kafka, adept at handling large volumes of real-time Twitter data. Utilizing the Twitter API, tweets bearing the hashtag #justice are retrieved and efficiently processed via Kafka. PySpark facilitates data analysis by enabling aggregation, Jaccard similarity computation, and k-means clustering. Preprocessing with Python libraries and TF-IDF enhances analysis accuracy. Jaccard similarity aids in comparing tweets across socio-economic categories. Aggregated data is stored in MongoDB for further examination. Additionally, Streamlit offers visualization tools for effortless exploration of Twitter discourse trends. Thus, this project exemplifies the potential of big data and its impact on investigating social justice discourse in the digital age. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Secure ML Evaluation on Encrypted Data with Fully Homomorphic Encryption and Concrete ML 5

Secure ML Evaluation on Encrypted Data with Fully Homomorphi...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Gaddam, Thanmai Chennupalle, Divya Kavitha, C.R. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350376685

In healthcare sector, preserving patient data privacy is vital. The increasing popularity of machine learning (ML) models for classification tasks on sensitive medical datasets calls for the widespread use of strong encryption approaches to protect data. This work looks at employing homomorphic encryption to safeguard healthcare datasets for machine learning (ML) classification tasks. The performance of fully homomorphic encryption (FHE) with Cheon-Kim-Kim-Song(CKKS) on medical datasets is evaluated in terms of the time taken to encrypt/decrypt the datasets used for ML tasks and the time taken to perform fundamental operations like addition and dot product. In this study, ML models such as Logistic Regression, Support Vector Machine, Decision Tree, and XGBoost are trained on two datasets: heart disease prediction and breast cancer prediction, and then tested on unencrypted, quantized, and fully homomorphic encrypted data using scikit-learn and Concrete ML. The models are evaluated using accuracy, precision, recall and f1-score. This paper evaluates the practicality of using homomorphic encryption to maintain the confidentiality of data without significantly affecting performance of ML models, emphasising its potential benefits in healthcare. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Underwater Object Detection Using Deep Neural Networks 5

Efficient Underwater Object Detection Using Deep Neural Netw...

引用

5th IEEE International Conference on computing, Power, and Communication Technologies, IC2PCT 2024

作者： Rasool, Shaik Atheeq Annamalai, R. Natarajan, B. Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amrita School of Computing Chennai India

ISBN: (纸本)9798350383522

The increasing amount of underwater visual data and deep sea research have led to the rise of marine animal identification as a major field for data processing and analysis. The need to protect the ecosystem emphasizes how important this endeavor is, yet it's still difficult because of things like the complexities of underwater backdrops, poor picture and video quality, and the variety of movements that marine life exhibits. This research used deep learning techniques to identify certain marine species and mark their presence with bounding boxes in uploaded images and videos in order to overcome these difficulties. The main goal is to provide workable methods for detecting marine life, so providing crucial backing for further studies in this area. By using the core deep learning frameworks, YOLOv8 and Faster-RCNN, the research was able to improve the efficiency and accuracy of marine life identification by making significant progress in detection time and mean average precision (mAP). This research work not only solves the current problems with finding marine animals but also establishes the groundwork for future research into comprehending and protecting the fragile undersea ecology. © 2024 IEEE.

关键词： Convolutional Neural Net- work Faster R-CNN Object Detection

来源：评论

学校读者我要写书评

暂无评论

Road Surface Analysis through Machine Learning Techniques

引用

IEIE Transactions on Smart Processing and computing 2024年第4期13卷 344-353页

作者： Singh, Prabhat Sharma, Shilpi Kamal, Ahmed E. Kumar, Sunil Department of Computer Science and Engineering Amity School of Engineering & Technology Uttar Pradesh Noida India Department of Electrical and Computer Engineering Iowa State University Ames United States Computer Science and Engineering Amity School of Engineering & Technology Uttar Pradesh Noida India

Roads are an important part of transporting goods and products from one place to another. In developing countries, the main challenge is to maintain road conditions regularly. Roads can deteriorate from time to time. Monitoring the conditions of the roads, which may degrade with time, is very difficult, resulting in a delay in transportation and damage to the vehicles moving on the roads. Poor road conditions cause road accidents. A model is being proposed to monitor the conditions of the road surface by smartphone sensors. Accelerometer, gyroscope, and GPS sensors are deployed in the mobile phones, which will help to collect data on the road conditions. After collecting the data about the road conditions, various machine learning approaches, such as supervised, multi-layered, and multiclass, are applied to data filtration. Road conditions are divided into three categories to achieve this methodology: potholes, deep traverse cracks, and smooth roads. This categorization helped in analyzing the road surface condition through smartphone sensors over all three axes instead of taking it over a single axis. Neural networks helped analyze data or road conditions more accurately than Decision Tree and SVM. Copyrights © 2024 The Institute of Electronics and Information Engineers.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Scalable Model for Text Mining using Sentiment Analysis on PySpark 4

A Scalable Model for Text Mining using Sentiment Analysis on...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Vishal, K.S. Srinidhi, Srivageesh K Shashank, U Someswara Samhitha, Sankepalli Sai Venugopalan, Manju Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350349900

Sentiment analysis, an essential tool for deciphering public sentiment from vast internet data, offers valuable insights to businesses and policymakers. Its adoption is driven by the ability to interpret emotions, providing guidance for product refinement and decision-making. This tool is crucial for understanding user sentiments, empowering businesses to improve customer experiences, shape brand perception, and refine marketing strategies. Organizations benefit from sentiment analysis by leveraging customer insights for informed decision-making and product enhancement, thereby safeguarding positive relationships and brand reputation. The proposed system utilizes both formal and informal datasets and works on models like Logistic Regression, Naive bayes and SVM. Additionally, feature extraction techniques such as hashing and TF-IDF enhance data representation, contributing to the accuracy and F1-score of the employed models. The proposed system makes use of the PySpark platform to elevate the *** the three models utilized, SVM achieved the highest accuracy and F1-score for the Twitter dataset, with an accuracy of 0.76 and an F1-score of 0.76. Similarly, for the Amazon dataset, Logistic Regression exhibited the highest accuracy and F1-score, recording values of 0.89 for both metrics. For comparison and experimental evaluation, the models were executed on a merged dataset comprising both Twitter and Amazon data. In this merged dataset, Logistic Regression outperformed the other models, achieving an accuracy and F1-score of 0.83 for both metrics. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Bharatanatyam Pose Perfection: Deep Learning vs. Meta-Learning & Real-Time Pose Evaluation with MediaPipe and OpenCV 4

Bharatanatyam Pose Perfection: Deep Learning vs. Meta-Learni...

引用

4th International Conference on Ubiquitous computing and Intelligent Information Systems, ICUIS 2024

作者： Sadhana, P. Ravishankar, Nandhitha Palaniswamy, Suja Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331529635

Bharatanatyam is renowned for its ability to narrate stories and express emotions through a complex interplay of facial expressions, hand gestures, and body postures. However, the sheer complexity of these dance movements poses a significant challenge in terms of capturing and evaluating them with precision. This work seeks to leverage the power of computer vision techniques, such as MediaPipe and OpenCV, as well as deep learning and meta-learning models, to create a system that can accurately detect and analyze Bharatanatyam dance poses in real-time. By providing dancers with immediate feedback on their performance, the work aims to enhance the understanding and appreciation of this rich cultural heritage, ensuring that the divine stories and emotions conveyed through Bharatanatyam are presented with the utmost clarity and authenticity for virtual learning as well. The deep learning model (CNN) achieved 95% accuracy while the meta-learning model (Siamese Network) attained 90% accuracy. These results highlight the deep learning model's higher accuracy and the meta-learning model's efficient learning process. By providing dancers with immediate performance feedback, this system enhances the understanding and appreciation of Bharatanatyam, ensuring its cultural narratives are presented with clarity and authenticity. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ProGAN-Based Architectural Style Transfer: Cross-Cultural Adaptation of Indian Architecture 8th

ProGAN-Based Architectural Style Transfer: Cross-Cultural Ad...

引用

8th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2024

作者： Ishvarya, G. Kammari, Kavya Sree Vanraj Thambi, Sharanya Khanna, Manju Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9789819766833

India’s architectural heritage serves as a testament to its rich history and cultural diversity, offering profound insights into its past. Despite dedicated efforts in documentation and photography, the faithful translation of Indian architectural wonders into digital representations remains a formidable challenge. Conventional image generation methods, including state-of-the-art Generative Adversarial Networks (GANs), often struggle to encapsulate the intricate nuances and deep-rooted cultural essence of these architectural masterpieces. This research endeavors to develop a specialized GAN model meticulously crafted for the singular purpose of rendering hyper-realistic and historically accurate images of Indian architectural monuments. The fundamental aspiration is to not only safeguard these invaluable cultural monuments but also to present them to the world in a manner that elicits profound appreciation within the digital landscape. The research aims to train the specialized GAN to iterate through the architectural characteristics of Indian monuments systematically. This iterative approach, driven by an understanding of architectural elements, historical contexts, and cultural symbolism, will enable the GAN to progressively enhance its ability to generate monument images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Architecture Generative adversial networks India Progressive GANs

来源：评论

学校读者我要写书评

暂无评论

A privacy-preserving method for publishing data with multiple sensitive attributes

引用

CAAI Transactions on Intelligence Technology 2024年第1期9卷 222-238页

作者： Tong Yi Minyong Shi Wenqian Shang Haibin Zhu School of Computer Science and Engineering Guangxi Normal UniversityGuilinChina School of Computer Science Communication University of ChinaBeijingChina Department of Computer Science and Mathematics Nipissing UniversityNorth BayOntarioCanada

The overgeneralisation may happen because most studies on data publishing for multiple sensitive attributes(SAs)have not considered the personalised privacy ***,sensitive information disclosure may also be caused by these personalised *** address the matter,this article develops a personalised data publishing method for multiple *** to the requirements of individuals,the new method partitions SAs values into two categories:private values and public values,and breaks the association between them for privacy *** the private values,this paper takes the process of anonymisation,while the public values are released without this *** algorithm is designed to achieve the privacy mode,where the selectivity is determined by the sensitive value frequency and undesirable *** experimental results show that the proposed method can provide more information utility when compared with previous *** theoretic analyses and experiments also indicate that the privacy can be guaranteed even though the public values are known to an *** overgeneralisation and privacy breach caused by the personalised requirement can be avoided by the new method.

关键词： data privacy data publishing

来源：评论

学校读者我要写书评

暂无评论

Hyperparameters’ Optimization of Convolutional Neural Network Using Diversity-Guided Genetic Algorithms for Image Classification 2nd

Hyperparameters’ Optimization of Convolutional Neural Netwo...

引用

2nd International Conference on Advances in Data-driven computing and Intelligent Systems, ADCIS 2023

作者： Somani, Zenith Thangavelu, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819995301

Convolutional Neural Networks (CNNs) are an effective tool for image classification and other computer vision problems. However, getting ideal performance necessitates careful adjusting of hyperparameters, which may be a difficult and time-consuming operation when performed manually. Genetic Algorithms (GAs) are a common approach for hyperparameter optimization;however, they have certain limitations, such as premature convergence and inadequate search space exploration. To overcome these challenges, we present Diversity-Guided Genetic Algorithms (DGGAs), a unique approach for hyperparameter optimisation. DGGAs improve GA performance by introducing diversity preservation mechanisms into the GA architecture. By promoting variation among candidate solutions, DGGAs enable more efficient exploration of the hyperparameter search space, resulting in the discovery of a greater range of high-quality configurations. To test the performance of DGGAs, we performed extensive experiments on the CIFAR-10 dataset, a widely recognized benchmark in computer vision. The experimental results show that our approach achieves competitive accuracy results while maintaining significantly higher diversity among the generated solutions compared to state-of-the-art hyperparameter optimization methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

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：