Research

EduBot

  • Title : EduBot: An Educational Robot for Underprivileged Children

  • Publisher: IEEE

  • Abstract: Block based programming is getting increasingly popular in a lot of countries. In this paper we have described a block based self-compiling education robot that uses Blockly to perform programming operations. The system provides a simple affordable platform to practice and learn programming and other STEM modules to enhance competency, efficiency and develop interest of students. STEM education is an interdisciplinary teaching concept that integrates the Arts with the traditional STEM subjects: Science, Technology, Engineering, and Mathematics. It emphasizes practice-based learning instead of, as traditional education does, theoretical knowledge. We have discussed the principles, hardware and other necessary modules incorporated to our system in this paper.

COVID-19 Prediction

  • Title : Analysing and Predicting Coronavirus Infections and Deaths in Bangladesh Using Machine Learning Algorithms

  • Publisher: Submitted to ICICT4SD

  • Abstract: Since December 2019, the novel coronavirus (COVID-19) has been the cause of over 700,000 deaths with more than 10 million people being infected. Bangladesh, the most densely populated country in the world and now under community trans-mission of the COVID-19 outbreak. This has created huge health, social, and economic burdens. Till the 7th of August 2020, Bangladesh has reported over 250,000 infected cases and 3000 deaths. A total of 1.2 million tests has been conducted among which about 20\% of people were infected. To prevent further detriment in our scenario, predicting future consequences are very important. Previous studies have shown that machine learning(ML) models play a very significant role in forecasting the number of infections and deaths due to COVID-19. Some ML model works extremely well in providing precise information to the authorities thus enabling them to make decisions accordingly. However, Bangladesh is still lacking in this regard. To the best of our knowledge, no ML models have been applied or utilized at this point that can help in determining the pandemic circumstance for Bangladesh demographics. In this study, we explore different machine learning algorithms that can provide more accurate estimations for predicting future cases which includes infections and deaths due to COVID-19 for Bangladesh. Based on this the government, public health institutes, and policymakers can make a decision about the lockdown, management, resource mobilization, etc. Our study shows that in predicting the pandemic situations, amidst many forecasting models like Holt's Linear Regression(HLR), Support Vector Regression(SVR), Holt's Winter Additive Model(HWAM), etc. the Facebook Prophet Model(FPM) provided the best result in forecasting with remarkable precision. We believe that using this information the authorities can take decisions that will lead to the saving of countless lives of the people. Additionally, this will also help to reduce the immeasurable economic burden our country is facing due to the present status quo. On top of that our studies will help analysts to construct forecasting models for future explorations.

Women Security

A Safety Device with GPS and Shock Generator to Enhance Security for Women

  • Journal Name: International Journal of Soft Computing And Artificial Intelligence (IJSCAI)-IJSCAI

  • Abstract

Safety violation of women are increasing in a alarming rate which has become a national concern. There are many rules and regulations to ensure security of women. But in most of the cases victim do not get justice for lack of evidence and culprits roam scott-free. So an advanced system to seek help and alert people has become a crying need. This paper proposes a smart device which will be integrated with watches so that it can be easily carried. The device comprises of an A9 GPRS/GSM module which incorporates GSM and GPS modules both a buzzer, a pulse sensor to measure pulse rate etc. In emergency situations SMS with victim’s location will be sent to the predefined contacts and nearby police stations. And victim can defend herself by applying shock to the oppressor. Keywords - Women Safety, A9 Module, Audio Recorder, Shock Generator.