BRAC University Institutional Repository
Preserving Knowledge, Advancing Research, Sharing Scholarship
A digital platform for collecting, preserving, and sharing BRAC University’s scholarly, academic, and institutional outputs.
Contribute to the Repository
Faculty members and students are invited to submit their research publications, theses, dissertations, and scholarly works to increase visibility, access, and long-term preservation.
Recent Submissions
EMG controlled bionic robotic arm using artificial intelligence and machine learning
(Institute of Electrical and Electronics Engineers Inc., 2020-06-05) Rupom, Farhan Fuad; Jannat, Shafaitul; Tamanna, Farjana Ferdousi; Al Johan, Gazi Musa; Islam, Md. Motaharul
The fundamental and main goal of gesture recognition research applied to Human-Computer Interaction (HCI) is making systems to identify and classify some specific human gestures and use them to transfer information and control devices. Surface Electromyography (sEMG) based gesture interfaces need quick and accurate detection, and gesture recognition in real time. We have mainly worked with four hand gestures which are Rock, Paper, Spherical grip, All right. This report proposes a solution to do real-time gesture recognition with the use of various machine learning algorithms and allowing its applications in a vast range of human-computer interfaces. We have used sEMG recordings recorded from muscles of hand which will constantly transmit those data to microcontroller. We will collect data from the microcontroller and then store those data in offline server.
Comparison of analytical and non-sequential monte carlo simulation techniques for generation adequacy assessment
(Institute of Electrical and Electronics Engineers Inc., 2020-06-05) Safat Hossain, Syed Sadman; Khan, Asif Ahmed; Chakma, Pranesh; Anjum, Salman; Huda, A. S. Nazmul
Generation system adequacy is employed to estimate the ability of the power system generation units to meet the system load. The main objective of this paper is to calculate and compare the generation adequacy index Loss of Load Expectation (LOLE) of power generating units of Bangladesh using two different probabilistic techniques. The techniques are analytical and non-sequential Monte Carlo simulation techniques. Results obtained are efficient and confirm the accuracy of both methods.
Secured IOTA enabled crypto-platform with discretionary mining capabilities and miner nomination based on first-price sealed bid auction theory
(Institute of Electrical and Electronics Engineers Inc., 2020-06-05) Amin, H.M Sadman; Sufiyan, Zahin; Rafi, Nakhla; Anjum, Syeda Afrida; Rabiul Alam, Md. Golam
The commercial utilization of cryptocurrency as a digital asset in being more and more sought-after on each successive year. Most of the well-renowned crypto platforms nowadays are devised based on the premise of the concept of blockchain. These cryptocurrencies work as an alternative medium of exchange using cryptography to secure the transactions on a distributed ledger. When using regular blockchain-based digital cryptocurrency most of the time the respected crypto-platforms discourage low valued microtransactions from being executed. Because often, the transaction fee may exceed the value of the product or service that is being purchased. As a result, for this particular reason, micropayment systems using digital crypto platforms remain largely underdeveloped. To solve this complication our thesis model was emanated from the notion of IOTA, which is considered as a minerless crypto-platform where the requisition of miners is disregarded thus enabling users to relish the advantages of microtransactions, however with the inclusion of âDiscretionary miningâ. âDiscretionary Miningâ refers to the hypothesis of the availability of mining capabilities at the discretion of the users.
An IoT based interactive LPG cylinder monitoring system with sensor node based safety protocol for developing countries
(Institute of Electrical and Electronics Engineers Inc., 2020-06-05) Ahsan, Ali; Lslam, Mohammad Zahirul; Siddiqua, Rumali; Rhaman, Md. Khalilur
Proper implementation of internet of things (IoT) can help the people of developing countries to turn their conventional life style into a smart one. In this following research paper an IoT based smart LPG cylinder monitoring system has been approached for smoothing the cylinder uses procedure with proper safety. Robust model with custom designed PCB helps the device to be adjusted with the existing LPG cylinder system without any major changes. Mobile application with unique design and versatile functionality along with a central server connect the user with the system through IoT. Uses of different sensors establish safety through gas leakage alarm and also reduce the amount of gas wastage. Depending on the uses of LPG of the end users an automated prediction will be forecasted about the uses of LPG in the future days which ensures an astute system. Simulation based indoor experiments with a couple of outdoor experiments in practical scenarios justify the collected data and the precision of the complete designed system.
Predicting priority needs for rehabilitation of refugees based on machine learning techniques from monitoring data of rohingya refugees in Bangladesh
(Institute of Electrical and Electronics Engineers Inc., 2020-06-05) Choudhury, Joydhriti; Ashraf, Faisal Bin; Shakil, Arif; Raonak, Nahian
Ethnic cleansing of Rohingya ethnicity from the Rakhine state of Myanmar has made life miserable for more than half million persons who had fled away with their life from their own country. They have taken shelter and and have been living in in the resource-poor side of Bangladesh. Immense size of refugee population makes it challenging to accommodate all the needs. In case of refugee rehabilitation, all the refugees are given shelter in small camps. Different camps have different types of people and needs. However, not all the needs can be met altogether. So, prioritizing needs will make the rehabilitation process more effective. In this paper, we have used machine learning techniques to identify an effective model which predicts the needs based on priority. This learned model can be used to predict the prioritized needs for different camps while rehabilitation process goes on. Our experiments disclosed that Random Forest ensemble methods work effectively.