检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Rajesh, L. Mohan, H.S. Bindiya, M.K. Visvesvaraya Technological University Dayananda Sagar Academy Of Technology And Management Department Of Information Science And Engineering Karnataka Bengaluru India Karnataka Bengaluru India Sjb Institute Of Technology Department Of Computer Science And Engineering Karnataka Bengaluru India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318609

A real-time patient monitoring system procesfses a wide range of biomedical parameters and can store and safely capture biomedical parameters. It lowers the diagnosis time of the several diseases that are prevalent in healthcare services. Accurate prediction of biomedical parameters can significantly reduce healthcare costs and assist in effective decision-making. This research proposes a deep learning approach with hybrid optimization for biomedical parameter prediction by using sensors. At first, a healthcare centre with many patients having various disorders is considered. Several biomedical sensors are placed on the patients and these sensors include a respiratory Rate (RR) sensor, Heart rate (HR) sensor, Pulse Rate (PR) sensor, Ambulatory Blood Pressure (ABP)-sensor, and Saturation of Peripheral Oxygen (SpO2). Based on these sensed parameters, biomedical parameter prediction by using sensor based Deep Long Short-Term Memory (DLSTM)is executed. The DLSTM is trained using the proposed Hybrid Adam Coati Optimization(HAdCO). Here, the HAdCO is developed by incorporating of Coati Optimization Algorithm (COA) with Adam Optimizer. Furthermore, the HAdCO-DLSTM is evaluated by utilising metrics, like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Squared Error (MSE). The HAdCO-DLSTM had a minimal value of MAE at 0.0063, MSE at 0.0062, and RMSE at 0.0078. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

SSAT: Scientific Storyboarding Framework Using Artificial Intelligence Techniques

SSAT: Scientific Storyboarding Framework Using Artificial In...

引用

International Conference on Data science, Computation and Security, IDSCS 2023

作者： Hariharan, Nitin Deepak, Gerard Department of Computer Science and Engineering Alagappa Chettiar Government College of Engineering and Technology Tamil Nadu Karaikudi India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9789819709748

This paper introduces a scientific storyboarding framework that uses artificial intelligence for learning and inferencing. It works by classifying a dataset of documents using the Bi-LSTM classifier to identify different instances. The results are then used to create metadata, which is further classified using deep belief networks. Next, the user's topic of interest is pre-processed, and an intermediate ontology model is generated. This model helps build knowledge by gathering information from the World Wide Web using recurrent neural networks. The framework then combines the results from two distinct classifiers—one from the dataset and the other from the user's query. These results are analyzed through explicit semantic analysis to select relevant entities. The monkey algorithm is utilized for optimization, resulting in an optimal solution set. To ensure semantic reasoning and entity regulation, Morisita index and explicit semantic analysis is applied. The proposed SSAT model achieves high percentages of precision, recall, accuracy, and F-measure, specifically 95.58, 96.83, 96.205, and 96.2009397%, respectively. Additionally, the model achieves a low value of FDR (False Discovery Rate) at 0.05%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Approach for Automatic License Plate Detection with Novel Feature Extraction 2

An Efficient Deep Learning Approach for Automatic License Pl...

引用

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

作者： Kothai, G. Povammal, E. Amutha, S. Deepa, V. KPR Institute of Engineering and Technology Coimbatore641407 India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur60203 India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil626126 India

In the domain of traffic management, road toll collection, and parking lot systems, vehicle number plate detection and identification play a pivotal role. Unlike conventional methods that treat license plate detection and character recognition as separate tasks, the system simultaneously addresses both challenges within a single neural network. Our Proposed methodology capitalizes on the efficiency and accuracy of the one-stage object detection algorithm known as YOLO (You Only Look Once) to locate license plates under diverse and challenging conditions. To augment the quality of input images with low resolution or poor clarity, we employ super-resolution generative adversarial networks (SRGANs). The image enhancement process substantially improves the visual quality of captured license plate images, facilitating more precise character recognition. Quantitative assessment of propounded system reveals compelling results. The license plate detection component achieves an outstanding average accuracy rate of 98.5%, surpassing previous methods by 15.2%. This comprehensive approach not only reduces the dependency on manual labour but also elevates processing precision. It seamlessly integrates into existing transportation infrastructure, resulting in heightened operational efficiency, reduced traffic congestion, and enhanced security measures. The rapid evolution of neural networks and deep learning techniques has streamlined the deployment of such applications, revolutionizing the field of traffic monitoring and management with unprecedented ease and precision. One-stage object detector, widely referred to as YOLO, is used to find licence plates in difficult circumstances. © 2024 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Hybrid Routing Techniques for Location Privacy in IoT-Enabled Wireless Sensor Healthcare Networks

引用

SN computer science 2024年第8期5卷 1-10页

作者： Arpitha, T. Chouhan, Dharamendra Shreyas, J. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Ambedka Beedi Karnataka Bengaluru 560001 India Department of Information Technology Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Bengaluru 560064 India

Ensuring patient privacy is critical for healthcare systems reliant on the Internet of Things. While prior work has addressed patient privacy extensively, a comprehensive end-to-end strategy protecting patients’ location and data privacy under the assumption that system entities are untrusted has yet to be developed. In response, this paper proposes a novel hybrid Deep Q-learning Neural Network (DQ-NN) technique tailored to Source Location Privacy (SLP) integrated with Blockchain technology for routing in Internet of Things (IoT)-enabled Wireless Sensor Networks (WSNs). To overcome the shortcomings of the existing systems, the study offers extremely random routing paths between the source and sink nodes. The plan uses strategically selected phantom nodes to transmit packets to the sink node randomly, ensuring the paths are incredibly confusing to the enemy. To attain maximum privacy and optimize energy consumption, the suggested method employs a hybrid DQNN model to select optimal paths among multiple paths generated. Blockchain integration adds an extra layer of security to the routing network. The results of the simulation show that the proposed scheme outperforms other schemes by offering a more extended safety period, optimized energy, and enhanced privacy for the healthcare environment. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain for privacy Hybrid phantom routing Location privacy Neural network solutions Wireless sensor network privacy

来源：评论

学校读者我要写书评

暂无评论

A novel recursive privacy-preserving information retrieval approach for private retrieval

引用

International Journal of Intelligent Information and Database Systems 2022年第3期15卷 269-274页

作者： Bhat, Radhakrishna Kumar, K.M. Mahesh Sunitha, N.R. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bangalore560064 India Department of Computer Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur572102 India

The major drawback of existing information retrieval schemes in preserving user privacy is that they either exhibit computationally bounded privacy with intractability assumptions or perfect privacy with high bandwidth utilisation. Today, the essential requirement is to have a bandwidth efficient perfect privacy preserving information retrieval scheme in order to provide effective and guaranteed service to the information retrieving user. Therefore, in this paper, we have constructed a new single database perfect privacy preserving private block retrieval scheme called ‘pepperPBR’ using quadratic residuosity as the underlying primitive where private block retrieval (PBR) is a natural extension to private information retrieval (PIR). In this paper, user generates O(6k) bit query and server generates O(2ku + o(n)) bit response where n is the database size, o(n) is the non-trivial server communication cost, u is the number of database blocks, k is the security parameter. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Deep-Based Hybrid Model For Enhancing Land Region Prediction Outcomes 2

Deep-Based Hybrid Model For Enhancing Land Region Prediction...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Selvapandian, D. Raja, Laxmi Tharageswari, K. Vm, Senthilkumar Jc, Nikitha Hemalatha, M. Karpagam Academy of Higher Education Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Karpagam Academy of Higher Education Faculty of Engineering Department of Cyber Security Coimbatore India Mahendra Institute of Technology Department of Information Technology Namakkal India Nandha Arts and Science College Department of Information Technology Erode India

ISBN: (纸本)9798331534950

Although satellite data is not a novel approach to mapping wetlands, its accuracy depends on data quality and categorization algorithms, making it a continuous challenge. The increasing accessibility of satellite data and the development of data modelling technologies, such as big data modelling using machine learning (ML) algorithms, have improved the accuracy of this type of mapping. Our work demonstrated a simple, scalable, and reliable wetland classification using linear Support Vector Machine (l-SVM) and unsupervised k-Nearest Neighbor (k-NN) machine learning approaches. Normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), the two primary inputs were modelled using Landsat optical data. Subsequently, l-SVM was used to supervise k-NN data using training data collected from outside observations. The accuracy test results indicate that there is a considerable reduction in error for both optical indices, and all prediction models have an accuracy of about 99%. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Learning for the Examination of Voice Disorders in the Identification of Parkinson's Disease 1

Applying Deep Learning for the Examination of Voice Disorder...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Gupta, Kushagra Jain, Vedant Andrew, J. Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9798350330915

Parkinson's disease is a degenerative neurological condition marked by difficulties with coordination, tremors, and rigidity in the muscles. Positively, speech recordings show potential as a precocious biomarker for Parkinson's disease, able to identify minute alterations prior to the manifestation of other symptoms. The main objective of this research is to create a machine learning model that can analyse speech recordings and reliably determine whether Parkinson's disease is present. Key questions that the model aims to answer include how well it detects early signs of Parkinson's disease, how well it distinguishes between voice samples from healthy individuals and those from early stages of Parkinson's disease, and whether or not accuracy will vary depending on variables like the length or calibre of voice recordings. The primary goal is to use deep learning methods to analyse voice data to detect Parkinson's disease early on. © 2023 IEEE.

关键词： Deep Learning Extreme Gradient Boosting K-Nearest Neighbour Parkinson's disease Standard Scalar Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Hybrid Models for Plant Disease Detection using Transfer Learning Technique 10

Hybrid Models for Plant Disease Detection using Transfer Lea...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Sharma, Pavan Yadav, Rakesh Kumar Rawat, Sur Singh Iftm University Department of Computer Science and Engineering Moradabad244102 India Maharishi University of Information Technology Department of Computer Science and Engineering Lucknow226013 India Jss Academy of Technical Education Department of Computer Science and Engineering Noida201301 India

ISBN: (纸本)9789380544472

Plant diseases can sometimes be so bad that there is no grain harvest at all. Consequently, there is a great need for automatic plant disease identification and diagnosis in the realm of agricultural informatics. Many approaches have been put forth to solve this problem, but deep learning is quickly winning popularity due to its outstanding results. In this study, we assess the transfer learning capabilities of deep convolutional neural networks for the diagnosis of plant leaf diseases. We also consider how well the trained model will perform when applied to the specific task identified by our own data. One of the deep learning methods, the convolutional neural network algorithm (CNN), has been successfully applied to solve computer vision issues such as image classification, object segmentation, picture analysis, etc. In our study, we apply the Densenet201, Xception, InceptionResnetv2, NasNetMobile and VGG-16, hybrid with Support vector machine (SVM) along with a transfer learning approach to recognize diseases in images of different leaves. Instead of starting the training from scratch and arbitrarily initializing the weights, we use the pre-trained networks on the large labelled dataset, ImageNet, to build the weights. The proposed method's validity is supported by experimental findings, and it effectively detects plant diseases. The suggested method significantly outperforms other cutting-edge approaches in terms of performance like (F-scores of 0.93) for VGGG16+SVM, (F-score: 0.97) for DenseNet201+SVM, (F-score: 0.87) for Xception+SVM, (F-score: 0.97) for InceptionResnetv2+SVM, and (F-score: 0.93) NasNetMobile+SVM hybrid model on the dataset of plant images. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Online Retail Customer Segmentation using RFM Quantiles and Clustering Technique

Online Retail Customer Segmentation using RFM Quantiles and ...

引用

International Conference on computer, Communication, Control and Information technology (C3IT)

作者： Mouli Majilya Giridhar Maji Partha Ghosh Soumya Sen A.K.Choudhury School of Information Technology University of Calcutta Kolkata India Department of Electrical Engineering Asansol Polytechnic Asansol India Department of Computer Science and Engineering Academy of Technology Adisaptagram India

ISBN: (数字)9798350389128

ISBN: (纸本)9798350389135

In the fiercely competitive landscape of modern business, making effective decisions is imperative for generating substantial revenue. With organizations employing diverse strategies to stay ahead, leveraging data for informed decision-making is crucial. Understanding individual preferences and purchasing behaviors can be challenging, but machine learning techniques offer a solution by organizing and analyzing vast datasets. Customer segmentation, particularly through K-means clustering, is instrumental in identifying target groups with similar attributes and interests. The present study focuses on customer clustering method-ologies to give businesses a competitive edge. By collecting, analyzing, and visualizing customer data, we aim to develop a data science model that utilizes K-means clustering and the RFM model (Recency, Frequency, Monetary) for existing customers. Utilizing the UK's e-commerce dataset, which delves into customer purchasing behaviors, we aim to group customers into clusters such as high-value customers, mid-range, and those at risk of churn based on RFM scores.

关键词： Analytical models Instruments Decision making Data visualization Organizations Machine learning Data science Data models Electronic commerce Information technology

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Flood Automation System Using IoT and Machine Learning 1

An Intelligent Flood Automation System Using IoT and Machine...

引用

1st International Conference on Recent Developments in Electronics and Communication Systems, RDECS 2022

作者： Verma, Bhumika Yudheksha, G.K. Sanjana Reddy, P. Maheswari, R. Parvathi, R. Vignesh, U. School of Computer Science and Engineering Vellore Institute of Technology Chennai India Manipal Academy of Higher Education India

ISBN: (纸本)9781643683607

Floods are one of the most common and well-known natural calamities that create havoc, causing damage to one's life and economy while adversely affecting the environment. This Research focuses on receiving emergency notifications whenever the situation is critical and also being able to predict the flood in time by automatically measuring the riverbed water level periodically. In this work, the objective is to measure the level using ultrasonic sensors and process the acquired data using ESP8266, where the information will be transferred to ThingSpeak IoT cloud which uses HTTP Protocol over Local Area Network thus enabling it to graphically monitor the world. It checks whether it is not exceeding the threshold limit and when it reaches beyond the limit the system should be able to alert individuals through Telegram and web cloud application, and when the system predicts a flood in the following timeline. Here the Servo Motor acts as a dam gate i.e., it opens when the flood is alerted and closes back once it reaches below the threshold value. For prediction, various machine-learning algorithms such as Random Forest, Support Vector Machine, KNN, Decision Tree, and Logistic Regression were implemented. Due to its high accuracy of about 95%, the logistic regression model was considered suitable for predicting the changes and detecting various possibilities. © 2023 The authors and IOS Press.

关键词： HTTP

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：