检索结果-内蒙古大学图书馆

Biomedical signal processing for health monitoring applications: a review

International Journal of Applied Systemic Studies 2023年第1期10卷 44-69页

作者： Sonawani, Shilpa Patil, Kailas Natarajan, Prabhu School of Computer Engineering and Technology Dr. Vishwanath Karad MIT World Peace University India Department of Computer Engineering Vishwakarma University India Department of Computer Science DigiPen Institute of Technology Singapore

Biomedical health monitoring systems are evolving rapidly and using non-invasive and cost effective sensors. These systems can monitor physiological parameters of the body to monitor health conditions and provide feedback. These new generation systems can use advance technologies to build intelligent systems for health monitoring and timely diseases detection and diagnosis. Biomedical signal processing and analysis of the patterns in the signals plays important role in building efficient systems, life sciences and research and is rapidly expanding in this domain. This review paper is significant as no existing review paper is giving complete information on biomedical signal processing phases as a whole. It makes four contributions;first, it gives activity flow for developing biomedical signal processing systems. Second, reviews various recent applications researched and kinds of low cost, non-invasive sensors used for biomedical health monitoring. Third, categorisation and enlisting of signal processing techniques like signal sampling, segmentation, filtering, feature extraction, dimensionality reduction and machine learning techniques in healthcare domain. Fourth, it reviews challenges in using signal processing techniques and gives future perspectives which can be helpful for the researchers to use advance techniques to build intelligent systems for reliable decision making. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Character Classification and Actor Recognition in Yakshagana Images Using Machine Learning Techniques and Facial Makeup Pattern Analysis 8

Character Classification and Actor Recognition in Yakshagana...

引用

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Murthy, Anantha Prathwini Kulkarni, Sanjeev Savitha, G. Nitte Karkala Institute of Computer Science and Information Science Srinivas University Department of Master of Computer Applications India Department of Master of Computer Applications Karkala India Srinivas University Institute of Engineering and Technology Department of Computer Science and Engineering Mangalore India Manipal Institute of Technology Manipal Academy of higher Education Manipal Department of Data Science and Computer Applications India

ISBN: (纸本)9798350350593

Yakshagana, a traditional theater form from Karnataka, India, features a unique combination of vibrant costumes, dynamic dance movements, and elaborate facial makeup, making character and actor identification a challenging task for automated systems. This research work presents a novel approach to classify Yakshagana characters into two primary categories, Vaishnava and Shaiva, and to identify the actors performing these characters using advanced machine learning techniques. Our research employs a Cyclic Gated Recurrent Neural Network (Cyclic GRNN) for classification and identification tasks. For character category classification, we integrate YOLOv3 and Faster R-CNN models, achieving an accuracy of 92.85% with YOLOv3 and 88.285% with Faster R-CNN. The categorization is specifically focused on distinguishing between Vaishnava and Shaiva characters. Additionally, for actor name identification, we utilize a RESNET-50 model, attaining a high accuracy of 95.60%. The results demonstrate the efficacy of Cyclic GRNN combined with state-of-the-art object detection and image classification models in accurately recognizing and categorizing Yakshagana characters and actors. This research contributes to the preservation and digital documentation of Yakshagana by providing robust tools for automated identification, thereby facilitating cultural heritage studies and enhancing audience engagement with this traditional art form. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Endometriosis Labelling using Machine learning 4

Endometriosis Labelling using Machine learning

引用

4th International Conference on Communication, Computing and Industry 6.0, C216 2023

作者： Visalaxi, S. Sudalaimuthu, T. Sowmya, V.J. Department of Computer Science Hindustan Institute of Technology and Science Chennai India Department of Master of Computer Applications Hindustan Institute of Technology and Science Chennai India

ISBN: (纸本)9798350327328

Endometriosis is a disease affecting the women's reproductive system. The lesion-like structure that exists in the women's reproductive organ creates an impact on their fertility. The diagnostic approach of endometriosis was performed by a radiologist using scanning procedures. Those procedures predict the occurrence of endometriosis but not the severity of endometriosis. Amidst the radiologist, machine learning techniques play a predominant role to identify the severity of endometriosis. Among all machine learning techniques, the proposed approach uses a support vector machine. Support vector machine is a contemporary technique for predicting clinical-based data. Support vector machine analyzes the influencing factor that incorporates Adnexal mass, Tube blockage, Lesion size, and lesion color for predicting the severity of endometriosis as well as classifying the endometriosis as Ovarian and Deep Infiltrating endometriosis. The execution was performed and trained accuracy obtained was 85%, test accuracy was 84.5% for radius basis function (rbf) kernel and the cross-validation score was 82.5%. Also, the available data was trained using Random Forest and Linear Regression. Among all three models, the Support vector machine outperforms well with hyper parameter as rbf for the given data to classify the endometriosis and identify the severity of endometriosis. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Experimental Approach to Identify the Optimal Deep CNN Models to Early Detection of Glaucoma from Fundus CT-Scan Images 7

Experimental Approach to Identify the Optimal Deep CNN Model...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Sumitha, S. Gokila, S. Hindustan Institute of Technology & Science Master of Computer Applications Chennai India Hindustan Institute of Technology & Science Department of Computer Applications Chennai India

ISBN: (纸本)9798350397253

Glaucoma is an eye disorder that causes the optic nerve to be affected in glaucoma cause of improved Intraocular fluid Pressure (IOP) in the eye. The only way to prevent blindness is to detect glaucoma early, which can only be done through regular eye examinations. Additionally, earlier diagnosis of glaucoma is challenging to determine and requires several costly vision examination protocols and skillful ophthalmologists. The proposed work's goal is to detect Glaucoma using Convolution Neural Networks (CNNs) to speed up the diagnosis process for timely prevention. CNNs have proven effective in discovering even subtle changes produced by glaucoma. The experimental study using three different Deep Learning (DL) algorithms CNN, MobileNet, and ResNet are carried out to analyses the best model. All these models are pretrained on the image data generator for detecting and classifying glaucoma from the fundus photographs. A Gaussian filter is applied in order to remove noise from the images. Three different datasets ORIGA, SCES, and G1020, which contains images of both healthy and advanced glaucoma, are used to train the model. Also, these databases contain colored images of retina and retinal fundus images that are used for testing, and screening the glaucoma. The proposed method attained the best accuracy of 95% from the ResNet-50 algorithm. Also, each suggested model's performance has been evaluated with the results of each CNN model. Additionally, a custom web application has been developed with CNN-based models to classify Glaucoma. The outcomes show that the CNN algorithms have the ability to develop into a time-saving and cost-efficient tool for analyzing populations intended to prevent irreparable blindness caused by glaucoma. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Utilizing YoLov8 Architecture for Sharp-Edge Segmentation 2

Utilizing YoLov8 Architecture for Sharp-Edge Segmentation

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Pujari, Laxmi Dodawad, Srushti Kashappa Prasanna, H.B. Dept. of Master of Computer Applications KLE Institute of Technology Hubballi India Dept. of Computer Science KLE Institute of Technology Hubballi India

ISBN: (纸本)9798350383867

In computer vision applications, such as object identification, scene comprehension, and robotic manipulation, accurate object segmentation is essential. In complicated contexts, traditional segmentation techniques frequently have trouble distinguishing sharp objects with accuracy. This work declare a novel approach to robust and exact object segmentation utilizing deep learning techniques built around the YOLOv8 architecture using an annotated collection of sharp object photos, the suggested methodology entails preprocessing the images with the CVAT(computer Vision Annotation Tool) tool to create binary masks. The YOLOv8 model is then trained on these annotated photos, and its behavior is compared with conventional segmentation techniques using a various image datasets. With its potential to advance the realm of computer vision, the YOLOv8 architecture presents a promising option for precise and effective sharp object segmentation in real-world scenarios. © 2024 IEEE.

关键词： computer vision deep learning image annotation masks robotic manipulation Sharp object segmentation YOLOv8 architecture CVAT tool

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Automated Lip Reading for Deaf 3

Deep Learning Based Automated Lip Reading for Deaf

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Prathyakshini Prathwini Pratheeksha Hegde, N. Vaishali Rashmi, N. Kumar, Archana Praveen NMAM Institute of Technology Department of Information Science and Engineering Karkala Nitte India NMAM Institute of Technology Department of Master of Computer Applications Karkala Nitte India NMAM Institute of Technology Department of Computer Science and Engineering Karkala Nitte India Manipal Academy of Education Manipal Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350354171

Speech recognition systems play an integral role in numerous applications, from virtual assistants to accessibility tools. This paper offers a new viewpoint to speech recognition utilizing computer vision and deep learning techniques. The proposed system is trained on a sizable dataset comprising 700 video clips of individuals uttering predefined words, add up to approximately 3 GB of data. Leveraging TensorFlow and Keras, model architecture is designed incorporating convolutional and dense layers. The training process yielded promising results, with a training accuracy of 95.7% and a validation accuracy of 98.5%, indicative of robust classification performance. The integration of computer vision enriches the system's ability to extract meaningful features from audio-visual inputs, enhancing its overall recognition accuracy. Proposed method demonstrates significant potential for real-time speech recognition applications in different areas, like human-computer interaction and assistive technologies. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Cai, Congrui Lu, Zhonghai School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Embedded Systems Master Program Sweden School of Electrical Engineering and Computer Science Department of Electrical Engineering KTH Royal Institute of Technology Sweden

ISBN: (纸本)9798350360585

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms. © 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

Hybrid Deep Learning Framework for Femur Bone Osteoporosis Classification: Leveraging Tuna Jellyfish Optimization and Segmentation Techniques 1

Hybrid Deep Learning Framework for Femur Bone Osteoporosis C...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Halesh, T.G. Ashok Kumar, T.A. Sathish, P. Cmr University School of Science and Computer Studies Bangalore India Nitte Meenakshi Institute of Technology Department of Master of Computer Applications Bengaluru India

ISBN: (纸本)9798350352931

Osteoporosis weakens bones, making them more fragile and prone to fractures. This condition can result from changes in bone strength or a decline in bone mineral density and mass. Accurate classification of osteoporosis is crucial for diagnosing skeletal disorders, particularly in aging individuals. This study introduces a novel approach to classify femur bones from X-ray images using a hybrid segmentation method and an enhanced Tuna Jelly Fish Optimizer (TJFO) with Deep Convolutional Neural Networks (Deep CNN). The hybrid method integrates traditional image processing and deep learning for precise femur isolation, while TJFO fine-tunes the Deep CNN's hyperparameters for improved classification. The model's performance was evaluated using metrics like Accuracy, True Positive Rate (TPR), True Negative Rate (TNR), Positive Predictive Value (PPV), and Negative Predictive Value (NPV), showing significant improvements in femur bone classification with balanced results across all metrics. © 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

SafeRoute: Pioneering Online Ride Booking with Pega & ML-Powered Safety Measures 8

SafeRoute: Pioneering Online Ride Booking with Pega & ML-Pow...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Rajalakshmi, D. Immaculate, P.S. Pandi, S. Senthil Pavitra, A. Rehash Rushmi Vijayalakshmi, V. Sharanya, S. Srm Institute of Science and Technology Data Science and Business Systems Chennai India Sri Sai Ram Institute of Technology Chennai Master of Business Administration India Rajalakshmi Engineering College Computer Science and Engineering Chennai India

ISBN: (纸本)9798350367904

The advent of online ride booking services has revolutionized the transportation industry, providing users with convenient and efficient means of commuting. However, ensuring the safety of passengers and drivers remains a paramount concern. This project introduces an innovative solution that leverages Pega, a leading business process management platform, coupled with machine learning algorithms to enhance the safety measures within an online ride booking service. The proposed system integrates seamlessly into the existing online ride booking infrastructure and introduces advanced safety mechanisms based on realtime data analysis. Machine learning models are employed to predict and mitigate potential risks, ensuring a secure and reliable experience for both passengers and drivers. © 2024 IEEE.

关键词： Reservation systems

来源：评论

学校读者我要写书评

暂无评论

Comparison of Transfer Learning algorithm in predicting Alzheimer's disease 1

Comparison of Transfer Learning algorithm in predicting Alzh...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Yashodhar, Archana Kini, Shashidhar Department of Computer Science and Application Mangaluru India Srinivas Institute of Technology Master of Computer Application Mangaluru India

ISBN: (纸本)9798350348057

Many neurogenerative diseases affect today's generation. The causes of this condition are unclear. Alzheimer's disease is one of that diseases, and elderly peoples suffer a lot from this. In this article, we applied several deep learning transfer learning approaches to categorize distinct phases of Alzheimer's disease. Different measures are used to assess each strategy, which leads to better results. © 2023 IEEE.

关键词： Deep learning

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：