Accepeted paper

    Abdullah I. Al-Shoshan College of Computer, Qassim University, Qassim, Saudi Arabia

    An approach for modeling linear time-dependent auto-regressive moving-average (TDARMA) systems using the time-frequency (TF) distribution is presented. The proposed method leads to an extension of several well-known techniques of linear time-invariant (LTI) systems to process the linear, time-varying (LTV) case. It can also be applied in the modeling of non-stationary signals. In this paper, the well known modified least square (MLS) and the Durbin's approximation methods are adapted to this non-stationary context. A simple relationship between the generalized transfer function and the time-dependent parameters of the LTV system is derived and computer simulation illustrating the effectiveness of our method is presented, considering that the output of the LTV system is corrupted by additive noise.

    Md. Salah Uddin1, Md Asif Iqbal2, Armanur Rahman3,1National Research University Higher School of Economics (NRU HSE), Faculty of Computer Science, School of Software Engineering, Kochnovskiy Proezd 3, 125319, Moscow, Russian Federation, 2 Financial University under the Government of the Russia federation Preparation engineering faculty Leningrad sky prospect 49 ,YBK-1 Moscow, Russia, 3 BJIT Limited, Level-5, Road-2/C, Block-J, Baridhara, Dhaka-1212, Bangladesh

    Human visual system is one of the wonders of the world. They are skilled at adopt various kinds of human face detection. But when same things come for computer, it’s not easy to detect face from image. There are more than billions of species in this world. Among them detection human face is little tough. Besides an image does not contain only face, maximum area of the image does not contain faces. Using the technique of data mining and deep learning algorithm predicts an image contain human face. Deep learning, in particular convolutional neural network (CNN), has achieved promising result in face detection recently. In real world face detection large visual variations, such as those due to pose, expression and lighting effect. CNN can take image as direct input and powerful to rotation, translation and scaling deformation of images. By manually acquiring some facial feature from an image is difficult and time consuming where CNN could extract effective facial feature automatically. So, choosing CNN for face detection is benefited. Thus, object detection has become one of the most important in computer vision field, especially IoT devices like surveillance and biometrics device. In this research, we built an advanced discriminative model to accurately detect faces from an image weather input image does contain human face or not. The target of this paper is to propose an IoT based smart door system with CNN where if the device found human face only then door will open.