ICT Focus

Mongolian Sign Language Recognition Model

2022-08-10T09:38:41+00:00

Sign language is a gesture-based manual used by people with hearing impairment and spoken language disorder to communicate with others. There is no universal sign language — the most used one is the American Sign Language. Mongolian Sign Language (MSL) has hand signs for letters of the alphabet, numbers, and other commonly used words. There are an estimated 16000 MSL signers. The lack of means to translate MSL into the Mongolian language, such as professional interpreters or translator applications, hinders MSL signers’ freedom of expression and political and public participation. Here, we created an MSL recognition system model that uses a camera to capture the letter symbols for the MSL alphabet and translates them into written Mongolian words. The proposed model uses two machine learning models that 1) recognize input, sorts, and filters, and 2) process Mongolian language. The model had an F1 score of 0.8678, given 51 distinct hand gestures. The natural language processing model that forms words had sufficient performance, though it can be improved in further works.

Quadcopter Stabilization using Neural Network Model from Collected Data of PID Controller

2022-08-14T06:54:15+00:00

There are a lot of methods for the stabilization of quadcopters and the newest are based on AI. A neural network is a simplified model that imitates the human brain's processes. In the research paper, we present a neural network control model for quadcopter stabilization. A single hidden layer network model was estimated to investigate the dynamics of the UAV. A control system with a classical PID controller was used to train the neural network model. This method is used for examining how the neural network imitates the stabilization of the quadcopter in real flight mode. The novelty of the work was to design of small size 3 layers NN model that runs in real-time in a quadcopter. The PID and machine learning controllers' operation results were compared to each other and
shown in the experiment.

Biomolecular Network-based Study of a Parasitic Disease and Therapeutic Drugs

2022-09-02T02:01:03+00:00

Computational drug repurposing methods, particularly biomolecular network-based disease-drug-target interaction models, are essential tools for integrating large-scale heterogenous molecular information and revealing functional mechanisms, as well as for main regulatory modules of interactants which can be useful in developing new drugs. In the present study, a drug-centric network for a parasitic disease (Echinococcosis) and therapeutic drugs have been considered. A complex network with more than 12,000 vertices and more than 33,000 edges representing interactions of 84 echinococcosis-related genes with associated proteins was built and analyzed. The networks of disease similarity and drug similarity were constructed based on the complex network. As a result, three drugs (D08356, D00701, and D00506) associated with three candidate diseases through three pathways and a protein complex have been extracted. This effort tries to predict the anti-echinococcosis effects of the drugs’ combinations with benzimidazole.

A Heterogeneous Graph Model for Repurposing Drugs against Echinococcosis

2022-09-19T11:55:44+00:00

Through this research work, we aimed to use a graph model to determine important drug substances that are proper for the Echinococcosis hydatid disease. Also, that model can be used in convergence with other similar diseases due to the genes of the Echinococcus granulosus that causes this parasitic disease, and to analyze it by applying graph algorithms to the established model. Furthermore, there is an urgent need to create a basic model for machine learning and artificial intelligence methods in health and pharmaceuticals. Also, the collection of genes and proteins registered in the official internationally recognized gene-disease databases, as well as the data of drugs and pharmaceutical products used for the specific disease, is the first step in the understanding and development of interdisciplinary science. In this paper, we define a heterogeneous graph with multiple types of nodes and edges as a basic model for future studies, as well as the methods and algorithms used in the study, considering the interrelationship between Echinococcus granulosus genes, proteins, diseases, and drugs.

The Analysis of FSO Link Performance in Ulaanbaatar

2022-09-20T14:51:31+00:00

Recently, developed countries are leading in telecommunications technology, and many studies are being conducted to transmit information through the free space (FSO) or atmosphere using optical frequency light waves. The natural factors that most affect the propagation of optical light waves are fog, rain, and snow. Ulaanbaatar is the capital of Mongolia and has an extreme and variable climate. This paper is devoted to analyzing FSO link performance during data transmission in Ulaanbaatar during heavy rain months (July-August) and simulation using OptiSystem software. Marshall and Palmer's model was used for data transmission using FSO link performance to estimate the rainfall reduction, and several factors such as BER rate and Q factor were investigated. We have made a detailed assessment of the result of rainfall on the FSO system in Mongolia based on the technical data on the weather in Ulaanbaatar in 2018, 2019, and 2020 for the three meteorological station servers of the world weather online site www.worldweatheronline.com.

Preface - Volume 1, Number 1

2022-09-29T10:00:04+00:00

No Abstract in English