scholarly journals Efficient Learning of Healthcare Data from IoT Devices by Edge Convolution Neural Networks

2020 ◽  
Vol 10 (24) ◽  
pp. 8934
Author(s):  
Yan He ◽  
Bin Fu ◽  
Jian Yu ◽  
Renfa Li ◽  
Rucheng Jiang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Learning Model ◽  
Streaming Data ◽  
Smart Devices ◽  
Generative Adversarial Network ◽  
Healthcare Data ◽  
Smart Healthcare ◽  
Iot Devices ◽  
Deep Learning Model

Wireless and mobile health applications promote the development of smart healthcare. Effective diagnosis and feedbacks of remote health data pose significant challenges due to streaming data, high noise, network latency and user privacy. Therefore, we explore efficient edge and cloud design to maintain electrocardiogram classification performance while reducing the communication cost. These contributions include: (1) We introduce a hybrid smart medical architecture named edge convolutional neural networks (EdgeCNN) that balances the capability of edge and cloud computing to address the issue for agile learning of healthcare data from IoT devices. (2) We present an effective deep learning model for electrocardiogram (ECG) inference, which can be deployed to run on edge smart devices for low-latency diagnosis. (3) We design a data enhancement method for ECG based on deep convolutional generative adversarial network to expand ECG data volume. (4) We carried out experiments on two representative datasets to evaluate the effectiveness of the deep learning model of ECG classification based on EdgeCNN. EdgeCNN shows superior to traditional cloud medical systems in terms of network Input/Output (I/O) pressure, architecture cost and system high availability. The deep learning model not only ensures high diagnostic accuracy, but also has advantages in aspect of inference time, storage, running memory and power consumption.

scholarly journals DiPLIP: Distributed Parallel Processing Platform for Stream Image Processing Based on Deep Learning Model Inference

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1664
Author(s):  
Yoon-Ki Kim ◽  
Yongsung Kim
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Parallel Processing ◽  
Real Time ◽  
Large Scale ◽  
Learning Model ◽  
Streaming Data ◽  
Model Inference ◽  
Processing Platform ◽  
Deep Learning Model

Recently, as the amount of real-time video streaming data has increased, distributed parallel processing systems have rapidly evolved to process large-scale data. In addition, with an increase in the scale of computing resources constituting the distributed parallel processing system, the orchestration of technology has become crucial for proper management of computing resources, in terms of allocating computing resources, setting up a programming environment, and deploying user applications. In this paper, we present a new distributed parallel processing platform for real-time large-scale image processing based on deep learning model inference, called DiPLIP. It provides a scheme for large-scale real-time image inference using buffer layer and a scalable parallel processing environment according to the size of the stream image. It allows users to easily process trained deep learning models for processing real-time images in a distributed parallel processing environment at high speeds, through the distribution of the virtual machine container.

scholarly journals Recognition of Vehicle License Plates Based on Image Processing

2021 ◽  
Vol 11 (14) ◽  
pp. 6292
Author(s):  
Tae-Gu Kim ◽  
Byoung-Ju Yun ◽  
Tae-Hun Kim ◽  
Jae-Young Lee ◽  
Kil-Houm Park ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Recognition Rate ◽  
Super Resolution ◽  
Learning Model ◽  
Distortion Correction ◽  
License Plate ◽  
Generative Adversarial Network ◽  
Perspective Distortion ◽  
Deep Learning Model

In this study, we have proposed an algorithm that solves the problems which occur during the recognition of a vehicle license plate through closed-circuit television (CCTV) by using a deep learning model trained with a general database. The deep learning model which is commonly used suffers with a disadvantage of low recognition rate in the tilted and low-resolution images, as it is trained with images acquired from the front of the license plate. Furthermore, the vehicle images acquired by using CCTV have issues such as limitation of resolution and perspective distortion. Such factors make it difficult to apply the commonly used deep learning model. To improve the recognition rate, an algorithm which is a combination of the super-resolution generative adversarial network (SRGAN) model, and the perspective distortion correction algorithm is proposed in this paper. The accuracy of the proposed algorithm was verified with a character recognition algorithm YOLO v2, and the recognition rate of the vehicle license plate image was improved 8.8% from the original images.

scholarly journals Design and Implementation of an Infrared-Based Sensor for Finger Movement Detection

2019 ◽  
Vol 6 (4) ◽  
pp. 29-44
Author(s):  
Agbotiname Lucky Imoize ◽  
Aanuoluwapo Eberechukwu Babajide
Keyword(s):  
Deep Learning ◽  
Learning Model ◽  
Smart Devices ◽  
Finger Movement ◽  
Movement Detection ◽  
Depth Sensing ◽  
Xbox Kinect ◽  
Infrared Cameras ◽  
Deep Learning Model ◽  
Static Nature

With the increasing interest in smart devices and convenient remote control, the need for accurate wireless means of control has become imperative. This gives rise to research in the field of gesture and finger movement detection. This design focuses on exploring techniques involved in hand and finger movement detection, using the depth-sensing infrared cameras embedded on Xbox Kinect Module. The generated 3-D images are first filtered along the z-axis, then two distinct techniques; Haar-Like Features, and Deep Learning using a Convolution Neural Network, are performed on the images to detect hands. Useful metrics like, Precision, Recall, F1-Score and Accuracy are then used to evaluate the efficiency of these techniques. The results show that while the deep learning model is the most accurate with a weighted accuracy of 1.0 (due to the absence of noise in the images) in contrast with 0.97 observed for the Haar-Like features, the Haar-like features technique runs faster due to its static nature. These findings point to the conclusion that the deep learning model is a better technique for detecting hands despite its longer running time.

scholarly journals A Novel Deep Convolutional Neural Network for Tuberculosis Detection

2021 ◽  
Vol 9 (VI) ◽  
pp. 1135-1139
Author(s):  
Syed Farhan Hyder Abidi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mycobacterium Tuberculosis ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Learning Model ◽  
Deep Convolutional Neural Network ◽  
Deep Learning Model

India accounts for the world’s largest number of cases in TB, with 2.8 million cases annually, and accounts for more than a quarter of the global TB burden. Tuberculosis (TB) is caused by the bacterium (Mycobacterium tuberculosis) which most commonly affects the lungs. TB is transmitted from person to person through the air. When people with TB cough, sneeze or spit, the germs are propelled into the air. This paper showcases a methodology which uses a Deep Learning Model (dCNN) for the detection of Tuberculosis in the lungs. The accuracy obtained by the methods for the model is desirable and dependable, which is increasingly productive in contrast to the accuracy shown by other neural networks.

Sign in / Sign up

Export Citation Format

Share Document