Evolution of Big Data in Medical Imaging Modalities to Extract Features Using Region Growing Segmentation, GLCM, and Discrete Wavelet Transform

Big data refers to the massive amount of data from sundry sources (gregarious media, healthcare, different sensor, etc.) with very high velocity. Due to expeditious growth, the multimedia or image data has rapidly incremented due to the expansion of convivial networking, surveillance cameras, satellite images, and medical images. Healthcare is the most promising area where big data can be applied to make a vicissitude in human life. The process for analyzing the intricate data is mundanely concerned with the disclosing of hidden patterns. In healthcare fields capturing the visual context of any medical images, extraction is a well introduced word in digital image processing. The motive of this research is to present a detailed overview of big data in healthcare and processing of non-invasive medical images with the avail of feature extraction techniques such as region growing segmentation, GLCM, and discrete wavelet transform.

Slantlet transform used for faults diagnosis in robot arm

<p class="JESTECAbstract">The <span>robot arm systems are the most target systems in the fields of faults detection and diagnosis which are electrical and the mechanical systems in many fields. Fault detection and diagnosis study is presented for two robot arms. The disturbance due to the faults at robot's joints causes oscillations at the tip of the robot arm. The acceleration in multi-direction is analysed to extract the features of the faults. Simulations for planar and space robots are presented. Two types of feature (faults) detection methods are used in this paper. The first one is the discrete wavelet transform, which is applied in many research's works before. The second type, is the Slantlet transform, which represents an improved model of the discrete wavelet transform. The multi-layer perceptron artificial neural network is used for the purpose of faults allocation and classification. According to the obtained results, the Slantlet transform with the multi-layer perceptron artificial neural network appear to possess best performance (4.7088e-05), lower consuming time <br /> (71.017308 sec) and higher accuracy (100%) than the results obtained when applying discrete wavelet transform and artificial neural network for the same </span>purpose.</p>

Technical Vision System for in-Room Access Control

Access systems with face recognition is widely used today. They are used in many enterprises and institutes where it is necessary to control the flow of passing people. Facially recognizable technical vision systems are important because they can be used to store specific individuals faces and use them for access control. As a result of analysis of same modern systems the variant of system there are additional functions is offered. The system consists of ESP-EYE module, with build-in wi-fi and Bluetooth modules, chip sensor camera “ OV2640” and LED display, which dasplays a notification for a person about granting or denying access, notifications are in two collors: geen and red respectively.. Also it has an emergency power supply in case of unforeseen situations. Wi-fi is used as a means of transmiting data from camera to the server. This transmition method of data transmition has several advantages over Bluetooth. It allows to the system to transfer data at a much higher speed and over a grater distance, it is also more secure, provides access to the internet and allows to control the system remotely. All the listed advantages of this method of transmition give us a great variability in the operation and placement of the system. To recognize people system use a comparison method. It compares the person’s face with a database and, after processing it produces the result. To optimize and speed up this process, the system uses a method of image compression based on discrete wavelet transform. This method is the transmission of a signal through several filtres, usualy two. First, the signal is passed through a low-pass filter whis a pulse response g, resulting in an output signal in the form of a convolutional sum. At the same time the signal is decomposed by a high pass filter. The LPF gives an approximate shape of the output signal, and the HPF – the signal of difference or additional detail. Discrete wavelet transform in an oriented basis makes it possible to construct transformation matrices with a given number of filters ”m”, where “m” is in the general case a prime positive number. The simplest way to compare the two images is by substracting the brightness values of the two matrices and estimating the resulting matrix of differences using standard deviation. The use of standard deviation in combination with fiberboard in OB allows to speed up the process of face recognition in the system by discarding unncessary details, the absence of which minimaly harms the accuracy of the results. The advantages of this system are that it is less expensive, in compareson with existing analogs, less energy-consuming, easy to assemble and install, uses a relatively simple and at the same time quite accurate method of identidying a persons identity.