2692-4048ISSN (Online)
2770-0070ISSN (Print)
Detecting and analyzing emotions from human facial movements is a problem defined and developed over many years for the benefits it brings. During playback, when developing data sets, data sets with methods become more and more complex, and accuracy and difficulty increase gradually. In the given paper, we will use a deep structured learned network using the two mechanisms - Vgg and Resnet50 with deep layers to classify emotions based on input images in complex environments. Besides that, we also use learning methods combining many modern models to increase accuracy. Experimental results show that the two proposed methods have better results than some modern methods in emotional recognition problems for complex input images and some results reported in scientific studies. Particularly combined learning method gives good accuracy - 66.15% on the dataset FER2013
Read MoreDoi: https://doi.org/10.54216/FPA.020101
Vol. 2 Issue. 1 PP. 22-30, (2020)
COVID-19 infection is one of the most dangerous respiratory viruses, and the early detection of this disease reduces the speed of its spread among people. The goal of this virus is to infect the lung by creating patchy white shadows inside the lungs. This paper presents an intelligent method based on the deep learning technique to analyze the medical images of respiratory diseases. Two data set was used in this experiment first dataset is normal lungs taken from the Kaggle data repository. In contrast, abnormal lungs were taken from (https://github.com/muhammedtalo/COVID-19). The results show that the proposed system identifies the COVID-19 cases with an accuracy of 90%.
Read MoreDoi: https://doi.org/10.54216/FPA.020102
Vol. 2 Issue. 1 PP. 05-13, (2020)
Alcoholism may be recognized with the use of (EEG) analyzing signals. None-the-less, the analysis of the multi-channel signals of EEG is a complicated issue that usually needs performing complex computation operations and takes quite a long time to execute. The presented research will propose 13 optimal channel to feature extraction. In this research, an innovative horizontal visibility graph entropy (HVGE) method has been proposed for evaluating signals of EEG from controlled drinkers and alcoholic subjects and comparing against an approach of sample entropy (SaE). Values of HVGE and SaE have been obtained from 1200 records of bio-medical signals. While in classification step using SVM as classifier.
Read MoreDoi: https://doi.org/10.54216/FPA.020103
Vol. 2 Issue. 1 PP. 14-21, (2020)
Facial expressions are the translation of the emotions such as anger, sadness, happiness, disgust felt by a person. Facial expression recognition, classification of expressions which has application in various industries such as hospitality, medical to name a few. There are various datasets available for facial expression recognition, we used FER 2013 dataset to build a classification algorithm. This algorithm classifies the emotions into seven categories namely, angry, disgust, happy, sad, fear, surprise and neutral. In traditional convolutional neural network algorithm the computing time is very large, ensemble learning significantly reduced the computing time and offered a promising accuracy. Features of images were extracted using the convolutional neural network, further these features were implemented using XGBoost and Random Forest to build classification algorithms and an accuracy of 77% and 74% was obtained. This was comparable to the accuracy obtained by traditional convolutional neural network which was 75% also with very less computing time.
Read MoreDoi: https://doi.org/10.54216/FPA.020104
Vol. 2 Issue. 1 PP. 31-41, (2020)
It is not feasible for a single image sensor to convey all of the information essential to comprehend a circumstance thoroughly. The output of many image sensors combined in one place would supply more accurate or comprehensive information on the topic at hand. In recent years, multi-sensor fusion has emerged in the academic world as an emerging topic that has the potential to produce beneficial results. This is because it can aggregate the data from several different sensors. One of the primary objectives is to devise various methods for combining kinematic and visual data to track a moving object. These methods should allow us to achieve this aim. This article looks into the intricacies of various techniques to evaluate the current condition of a target and explores the outcomes of those approaches. These sorts of methods include, for instance, the Kalman filter and its expanded version, the extended Kalman filter. The study of the proposed work is to demonstrate the specifics of the development of an interacting multiple-model Kalman filter to monitor the performance of the moving target in response to a wide variety of tuning parameters. The proposed technique includes the Principal Component Analysis and spatial frequency to integrate the hazy images that were all shot with the same sensor modalities. This action was taken to achieve the aimed-for outcome. The effectiveness of the fusion is evaluated based on the results of several distinct metrics.
Read MoreDoi: https://doi.org/10.54216/FPA.020105
Vol. 2 Issue. 1 PP. 42-60, (2020)