检索结果-内蒙古大学图书馆

A Study of Federated Learning with Internet of Things for Data Privacy and Security using Privacy Preserving Techniques

引用

Recent Patents on engineering 2024年第1期18卷 1-17页

作者： Shakeer, Shaik Mahamad Rajasekhara Babu, M. School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

To address the privacy concerns that arise from centralizing model training on a large number of IoT devices, a revolutionary new distributed learning framework called federated learning has been developed. This setup of devices works together to train models without compromising the security of individual data streams. To solve machine learning problems, a federated learning architecture relies on many clients working together through a central aggregator. To protect each device's privacy, we only access the training data at random. Because of its focus on decentralized processing and model transmission, federated learning considerably reduces systemic privacy risks and costs in comparison to conventional centralized machine learning systems. All client data is encrypted before being stored in a local database. Each user's device collects data locally for training during a federated learning session, and then uploads the final model to a centralized server. To provide a comprehensive assessment and inspire more research, this paper explores into the inner workings of federated learning from five different vantage points: data partitioning, privacy approaches, machine learning models, communication architectures, and system heterogeneity. Then, suggestions for further research are given, and a list is compiled of the most recent problems in federated learning. We conclude with an examination of the present applications of federated Learning knowledge. © 2024 Bentham science Publishers.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

Predicting early ASD traits of adults and toddlers using machine learning and deep learning with explainable AI and optimization

引用

Neural Computing and Applications 2025年 1-28页

作者： Rahman, Md. Ashiqur Hossain, Md. Mamun Singh, Sondip Poul Sharmin, Nusrat Dhaka1216 Bangladesh Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka Bangladesh

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication difficulties, repetitive behaviors, and a range of strengths and differences in cognitive abilities. Early ASD diagnosis using machine learning and deep learning techniques is crucial for preventing its severity and long-term effects. The articles published in this area have only applied different machine learning algorithms, and a notable gap observed is the absence of an in-depth analysis in terms of hyperparameter tuning and the type of dataset used in this context. This study investigated predictive modeling for ASD traits by leveraging two distinct datasets: (i) a raw CSV dataset with tabular data and (ii) an image dataset with facial expression. This study aims to conduct an in-depth analysis of ASD trait prediction in adults and toddlers by doing hyper optimized and interpreting the result through explainable AI. In the CSV dataset, a comprehensive exploration of machine learning and deep learning algorithms, including decision trees, Naive Bayes, random forests, support vector machines (SVM), k-nearest neighbors (KNN), logistic regression, XGBoost, and ANN, was conducted. XGBoost emerged as the most effective machine learning algorithm, achieving an accuracy of 96.13%. The deep learning ANN model outperformed the traditional machine learning algorithms with an accuracy of 99%. Additionally, an ensemble model combining a decision tree, random forest, SVM, KNN, and logistic regression demonstrated superior performance, yielding an accuracy of 96.67%. The XGBoost model, utilized in hyperparameter optimization for CSV data, exhibited a substantial accuracy increase, reaching 98%. For the image dataset, advanced deep learning models, such as ResNet50, VGG16, Boosting, and Bagging, were employed. The bagging model outperformed the others, achieving an impressive accuracy of 99%. Subsequent hyperparameter optimization was conduct

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Lung disease classification using deep learning and genetic algorithm

引用

Neural Computing and Applications 2024年 1-16页

作者： Chutia, Upasana Tewari, Anand Shanker Singh, Jyoti Prakash Computer Science and Engineering National Institute of Technology Patna Bihar Patna India

Lung disorders are medical conditions that disrupt the lungs and their capacity to function normally. One fatal lung disease is a collapsed lung where the lung collapses partially or fully due to diseases like pneumothorax and atelectasis. The conventional approach to detecting such diseases is time-consuming, often requiring extensive manual analysis by trained experts, leading to delays in diagnosis and treatment. computer-aided diagnostics have the potential to aid doctors in enhancing the consistency of diagnoses while also optimizing time efficiency. In this study, we enhance each lung X-ray image with three image enhancement techniques (i) contrast-limited adaptive histogram equalization (CLAHE), (ii) discrete wavelet transform (DWT), and (iii) gamma correction (GC) in parallel. A 3-channel convolutional neural network (CNN) then uses those enhanced images to extract features. The extracted features are further optimized using a genetic algorithm to improve the efficiency of the classification models. Our proposed model is validated with a dataset containing 9391 X-ray images to achieve an average precision, recall, and F1-score of 98, 97, and 98% and best accuracy of 99.33% which shows an improvement of 2.03% in terms of accuracy over the existing state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Development of optimized cascaded LSTM with Seq2seqNet and transformer net for aspect-based sentiment analysis framework

引用

Web Intelligence 2025年第Pre-press期Pre-press卷 1-26页

作者： Ramasamy, Mekala Elangovan, Mohanraj Department of Information Science and Engineering Bannari Amman Institute of Technology India Department of Computer Science and Engineering K.S. Rangasamy College of Technology India

The recent development of communication technologies made it possible for people to share opinions on various social media platforms. The opinion of the people is converted into small-sized textual data. Aspect Based Sentiment Analysis (ABSA) is a process used by businesses and other organizations to assess these textual data in order to comprehend people’s opinions about the services or products offered by them. The majority of earlier Sentiment Analysis (SA) research uses lexicons, word frequencies, or black box techniques to obtain the sentiment in the text. It should be highlighted that these methods disregard the relationships and interdependence between words in terms of semantics. Hence, an efficient ABSA framework to determine the sentiment from the textual reviews of the customers is developed in this work. Initially, the raw text review data is collected from the standard benchmark datasets. The gathered text reviews undergo text pre-processing to neglect the unwanted words and characters from the input text document. The pre-processed data is directly provided to the feature extraction phase in which the seq2seq network and transformer network are employed. Further, the optimal features from the two resultant features are chosen by utilizing the proposed Modified Bird Swarm-Ladybug Beetle Optimization (MBS-LBO). After obtaining optimal features, these features are fused together and given to the final detection model. Consequently, the Optimized Cascaded Long Short Term Memory (OCas-LSTM) is proposed for predicting the sentiments from the given review by the users. Here, the parameters are tuned optimally by the MBS-LBO algorithm, and also it is utilized for enhancing the performance rate. The experimental evaluation is made to reveal the excellent performance of the developed SA model by contrasting it with conventional models. © 2024 – IOS Press. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Brain haemorrhage classification from CT scan images using fine-Tuned transfer learning deep features

引用

International Journal of Business Intelligence and Data Mining 2024年第2期24卷 111-130页

作者： Ghosh, Arpita Soni, Badal Baruah, Ujwala Department of Computer Science and Engineering National Institute of Technology Assam Silchar India

Classification of brain haemorrhage is a challenging task that needs to be solved to help advance medical treatment. Recently, it has been observed that efficient deep learning architectures have been developed to detect such bleeding accurately. The proposed system includes two different transfer learning strategies to train and fine-Tune ImageNet pre-Trained state-of-The-Art architecture such as that VGG 16, Inception V3 and DenseNet121. The evaluation metrics have been calculated based on the performance analysis of the employed networks. Experimental results show that the modified fine-Tuned Inception V3 performed well and achieved the highest test accuracy. © 2024 Inderscience Enterprises Ltd.. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Patch Selection: An Improved Patch Sampling for No Reference Image Quality Assessment

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 541-555页

作者： Nandhini, C. Brindha, M. National Institute of Technology Department of Computer Science and Engineering Tiruchirappalli620015 India

Quality degradation due to the compression and the transmission of images is a significant threat to multimedia applications. Blind image quality assessment (BIQA) is a principal technique to measure the distortion and dynamically set the optimal parameters for developing image compression standards, image restoration algorithms, etc. Insufficient training data with quality scores are a challenge for image quality assessment (IQA) tasks. The existing solutions to deep-convolution-neural-network-based BIQA, which rely on patchwise training, struggle to find an ideal set of patches consistent with the human visual system. To address these issues, HIerarchical paTch Selection (HITS) is proposed. HITS keeps the patches with considerable details in each quadrant according to their intensity variance scatter ratio (IVSR). IVSR identifies the best nonhomogeneous patches by computing patch intensity variance. Extensive trials are conducted, and the performance reveals that the proposed approach achieves excellent performance on synthetic and authentic distortion datasets with less memory and processing power. Moreover, the proposed approach outperforms other BIQA methods that adapt patchwise training strategies. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Vision Transformer toward improved non-invasive anaemia detection using palm video

引用

Multimedia Tools and Applications 2024年第38期83卷 85825-85848页

作者： Kesarwani, Abhishek Das, Sunanda Kisku, Dakshina Ranjan Dalui, Mamata Department of Computer Science and Engineering National Institute of Technology Durgapur Durgapur India

Anaemia, a condition characterised by reduced haemoglobin levels, exerts a significant global impact, affecting billions of individuals worldwide. According to data from the World Health Organisation (WHO), India exhibits notably high anaemia prevalence in comparison to other developing nations. The urgency arises for the development of non-invasive, cost-effective, and accurate anaemia screening technologies, primarily due to the substantial costs and logistical complexities associated with invasive screening methods, which impede their broad adoption on a global scale. The current endeavor aims to establish a robust anaemia detection system through the integration of cutting-edge computational methodologies with the traditional yet less precise approach of assessing haemoglobin levels based on observation of palm pallor. The proposed method employs time-domain analysis to establish a correlation between blood haemoglobin concentration and the observed changes in palm colour resulting from the application and release of pressure. This involves employing a custom device to capture and record the complete sequence of palm colour changes using a smartphone camera sensor, followed by data processing and analysis. The Multi-scale Vision Transformer is then employed to extract features from dominant frames. The approach further incorporates the application of a multi-layer perceptron (MLP) network as a regression model based on the reduced feature outcomes. The proposed system accurately estimates blood haemoglobin levels with RMSE, sensitivity, specificity, and accuracy of 0.509, 96.88%, 86.39%, and 92.59%, respectively based on 531 video samples of palm evidence. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Information Freshness for Monitoring and Control over Wireless Networks

引用

Performance Evaluation Review 2024年第3期51卷 62-65页

作者： Tripathi, Vishrant Massachusetts Institute of Technology Electrical Engineering and Computer Science United States

Brief Biography: Vishrant Tripathi obtained his PhD from the EECS department at MIT, working with Prof. Modiano at the Lab for Information and Decision Systems (LIDS). He is currently working on building efficient data center networks at Google. His research interests primarily lie in the optimization of resources in resource constrained networked systems. The main applications of his work are in multi-agent robotics, federated learning, edge computing, cloud infrastructure, and monitoring for IoT. More recently, he has also been working on software defined networking and next-generation wireless networks. In 2022, he won the Best Paper Runner Up Award at ACM MobiHoc. Copyright is held by author/owner(s).

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning Architectures for Enhanced Traffic Sign Recognition: A Comparative Analysis 3

Exploring Deep Learning Architectures for Enhanced Traffic S...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Kumar Gupta, Amit Mathur, Priya Singh, Riya Sharma, Sana Manipal University Jaipur Computer Science and Engineering Rajasthan Jaipur India Poornima Institute of Engineering and Technology Department of Mathematics Rajasthan Jaipur India

ISBN: (纸本)9798350384598

This research paper investigates the efficacy of various deep learning architectures in Traffic Sign Recognition (TSR) tasks, aiming to contribute to the advancement of intelligent transportation systems. A comprehensive comparative analysis is conducted, evaluating the performance of four prominent architectures: AlexNet, DenseNet, VGG, and a generic CNN, using the GTSRB dataset. Results demonstrate that DenseNet achieves the highest accuracy of 95.12%, outperforming other architectures, with remarkable precision, recall, and F1-score values. The generic CNN also exhibits impressive performance, with an accuracy of 97.31% and comparable metrics. Conversely, AlexNet and VGG achieve accuracies of 88.84% and 85.03%, respectively, with varying performance metrics. These findings underscore the effectiveness of DenseNet and the generic CNN in accurately classifying traffic signs, highlighting their potential for real-world implementation. The study emphasizes the importance of selecting appropriate deep learning architectures tailored to specific tasks, and further analysis may explore strategies to optimize model performance and generalization capability. © 2024 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Research on facial expression recognition based on multimodal data fusion and neural network

引用

International Journal of Wireless and Mobile Computing 2024年第1期27卷 47-55页

作者： Han, Yi Wang, Xubin Lu, Zhengyu School of Mechanical Science and Engineering Huazhong University of Science and Technology Hubei Wuhan China Anyang Institute of Technology Department of Computer Science and Information Engineering Henan Province Anyang China School of Computer Science and Information Engineering Shanghai Institute of Technology FengXian District Shanghai China

Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes Convolutional Neural Network (CNN) designed to extract features from facial image, neural network designed to extract features from facial Landmarks and Neural Network (LNN) designed to extract features from Histogram of gradient (HNN), three sub-neural networks to extract data features, using multimodal data feature fusion mechanism to improve the accuracy of facial expression recognition. Experimental results show that, the algorithm has a great improvement in accuracy, robustness and detection speed. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Data fusion

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：