Research
Some of the projects I have worked on.
RESEARCH PROJECTS
RoadNote
Navigation apps (i.e., Google Maps, Apple Maps, Waze, etc.) have become an important part of our daily lives and offer several benefits. Map applications show real-time traffic conditions by combining crowdsourced data from their user base or partners using roadside sensors and historical data. Then the prediction model applies to calculate the travel time, route, alternatives of suggested routes, etc. In addition, these applications use official data from local authorities and user feedback or reports to show road closures. However, map applications often fails to reliably accommodate unscheduled road closures, road maintenance, and emergency management. We investigates erroneous situations and found 23 incidences in 15 days long study where maps fail to navigate the closure information. We propose ROADNote, an automated system that accommodates urban sensors and provides closures update to users. ROADNote provides real-time traffic conditions by automated detections using future-generation commodity sensors.
Pedestrians Safety
It is possible to provide timely interventions to Smartphone Zombies to increase situational awareness and reduce the distraction by various smart devices. One of the research projects is the context-aware road safety service for distracted pedestrians. Users are considered distracted if they are actively using the phone, listening to music, or talking to someone on the phone. StreetBit app is a part of the Pedestrian Safety research project to warn distracted people. Users can download the Android version from Google Play and here. We published our work at Accident Analysis & Prevention journal, 2021 and IEEE Internet of Things Journal (IoTJ), 2022.
InSight: Ad-hoc Emergency Warning System
During natural disasters and in an emergency, it is essential to disseminate warnings to nearby people. InSight is a system that uses low-energy Bluetooth beacons and smartphones to locate and circulate any warning marked by an emergency responder. InSight can identify and warn a pedestrian from the hazard location without the Internet and Cellular network.
We published our work at the IEEE Consumer Communications & Networking Conference (IEEE CCNC), 2021.
Security Analysis and Threat Model
Threat modeling is a process to understand system security and identify potential vulnerabilities with a cost-effective mitigation technique. We investigate the security and vulnerabilities of Video Conferencing technology and Contact Tracing applications.
Our article titled "Towards a Threat Model and Security Analysis of Video Conferencing Systems" has published at IEEE CCNC 2021, and "Towards a Threat Model for Contact Tracing Applications" at IEEE WFIoT 2022.
Preemptive Construction Site Safety (PCS2)
Real-time location tracking, trajectory prediction, and prevention of potential collisions between workers and site hazards. PCS2 uses ubiquitous mobile technology (smartphones) for positional data collection and a robust trajectory prediction technique that couples the hidden Markov model (HMM) with risk-taking behavior modeling. Our work published from the Journal of Construction Engineering and Project Management.
ACADEMIC PROJECTS
CloudEncryp: Cloud-based Encryption Service using Mobile Application
The goal of this project was to design and implement a cloud-based encryption service. We developed a mobile and desktop application where the user can log in and select the encryption technique for encrypting the files. The encryption is done on the server-side on Amazon EC2 servers using OpenSSL and the encrypted files are stored in the Amazon S3 buckets. The user can download the encrypted files through the mobile application and the user is charged based on the amount of file that is being encrypted and the encryption technique that is selected.
Technology Used - OpenSSL, Amazon S3, Amazon RDS, Amazon EC2, Android Studio, etc.
CloudBox: A cloud-based file storage service implemented in AWS
The goal of this project is to design and implement a cloud-based storage system. The project contains most of the services of a standard cloud-based storage service such as login, registration, upload, download, share, and delete files in that account.
For the Desktop client, we used Java, AWS java SDK, OkHttp, and JAVA NIO.
For the Web client, we used PHP, MySQL, AmazonEC2, and Amazon RDS.
For Object storage, we used AWS S3 Bucket.
Question Similarity Detection Using Bidirectional LSTM through Natural Language Processing
Identifying the duplicate questions is challenging; the sentence composition and word selection vary among persons. There is a way to find the document similarity based on the degree of overlapping in classic natural language processing. However, duplicate question detection does not perform well, because most of the questions are too small and the degree of overlapping is insufficient. We have implemented an LSTM based architecture that detects the duplicate question if they have the same intent. [Poster]
PROFESSIONAL PROJECTS
Core4VoIP Billing
Core4VoIP is a secure VoIP billing application that empowers service providers with all necessary tools to successfully operate the complete telecom business. This android version of Core4VoIP billing is to manage and monitor child resellers and clients. The application works over any data network and Wi-Fi.
Technology Used - AsyncTask, MySQL, Remote Connection, SHA-256, 2 Factor Authentication, etc.
Core4VoIP Mobile Dialer
Core4VoIP dialer is a SIP dialer for the Android operating system. It is designed to work in low bandwidth areas. The voice goes as IP packets through the Internet. I worked as a team member on this project.
Technology Used - SIP (Session Initiation Protocol), VoIP (Voice over Internet Protocol), VPN, Load Balancing, Geo-Blocking, etc.
Application link - Google Play
Mobile Application for Newspapers
Designed and developed three mobile application for the daily newspaper [Early Versions].
Kaler Kantho - Google Play.
Bangladesh Pratidin - Google Play.
Daily Sun - Google Play