Analysis of the text of the FQP for automated standard control of documents

This publication focuses on underdevelopment the possibilities of machine learn-ing to help students prepare their final qualifying paper. Purpose of the study: present the possibilities of machine learning for processing final qualifying paper texts and checking them for compliance with the requirements. The article shows the possibilities of distributing work by topic, which can help students in finding materials on their topic and algorithms for extracting and analyzing text in Rus-sian for further analysis. The research is carried out on the basis of the CRISP DM methodology and describes in detail all the necessary research steps. The pa-per shows the process of extracting text from pdf and docx files; the necessary methods of text preprocessing for further analysis; and demonstrates the capabili-ties of machine learning algorithms using the example of LDA analysis.

ENCODING OF CATEGORIAL FEATURES IN NEURAL NETWORKS

The relevance and areas of application of machine learning are investigated, one of the machine learn-ing algorithms - neural networks, as well as one of the data preparation processes before extracting a mathematical model - the coding of categorical features using the target coding method is consid-ered. Implemented a coding algorithm in the Python programming language

Detection of Malpractice in E-exams by Head Pose and Gaze Estimation

Examination malpractice is a deliberate wrong doing contrary to official examina-tion rules designed to place a candidate at unfair advantage or disadvantage. The proposed system depicts a new use of technology to identify malpractice in E-Exams which is essential due to growth of online education. The current solu-tions for such a problem either require complete manual labor or have various vulnerabilities that can be exploited by an examinee. The proposed application en-compasses an end-to-end system that assists an examiner/evaluator in deciding whether a student passes an online exam without any probable attempts of mal-practice or cheating in e-exams with the help of visual aids. The system works by categorizing the student’s VFOA (visual focus of attention) data by capturing the head pose estimates and eye gaze estimates using state-of-the-art machine learn-ing techniques. The system only requires the student (test-taker) to have a func-tioning internet connection along with a webcam to transmit the feed. The exam-iner is alerted when the student wavers in his VFOA, from the screen greater than X, a predefined threshold of times. If this threshold X is crossed, the appli-cation will save the data of the person when his VFOA is off the screen and send it to the examiner to be manually checked and marked whether the action per-formed by the student was an attempt at malpractice or just momentary lapse in concentration. The system use a hybrid classifier approach where two different classifiers are used, one when gaze values are being read successfully (which may fail due to various reasons like transmission quality or glare from his specta-cles), the model falls back to the default classifier which only reads the head pose values to classify the attention metric, which is used to map the student’s VFOA to check the likelihood of malpractice. The model has achieved an accuracy of 96.04 percent in classifying the attention metric.

Corona Virus Detection and Classification with radiograph images using RNN

We’re working on detecting the symptoms of Corona virus, also known as Covid-19, in this project.COVID-19 is a highly infectious disease that has been declared a Pub- lic Health Emergency and a Pandemic by the World Health Organization.The virus has infected over 25 million people worldwide,which has killed over 840,000 people and threat- ened the lives of millions more. COVID-19 is characterised by a dry cough, sore throat, and a high temperature. It is critical to find quick and accurate results for Covid-19 at this time in order to stop it in its early stages and avoid it from being a problem. Deep learning concepts are being used to analyse and classify symptoms from radiograph im- ages.Chest radiographs are one of the early screening tests to assess the onset of disease since the infection seriously affects the lungs.In this proposal, we used a recurrent neu- ral network model combined with a multi-level thresholding technique to detect Corona virus. One of the machine learn- ing techniques for prediction is the RNN model. A Recur- rent Neural Network is used to decide if the given images belong to Covid-19 during the classification process. This implementation is based on a publicly available dataset of radiograph images.

Stock Prediction Analysis by using Linear Regression Machine Learning Algorithm

Stock market is varying day to day. Many factors such as government policies, industry performance, market sentiment etc are the main cause of up and downs in stock market. To invest money in stock market, study and analysis of stock market is essential. This type of analysis can be done by using Machine learning algorithms. The main objective of this paper is to predict the stock market future values by using linear regression machine learn algorithms based on past values. The methodology is developed and implemented in python on APPLE and TSLA stock.