Transport & consumer behaviour · Empirical measurement · Electrical engineering
Empirical researcher in transport and consumer behaviour, working on measurement design: getting behaviour recorded as it happens rather than reconstructed afterwards. Electrical and electronic engineer by training, with six and a half years in applied engineering, four of them in a dedicated research role. Seeking a funded doctoral position starting 2027.
Applied engineering
6.5
years
4 years in a dedicated research role
Peer-reviewed output
5
papers
4 published · 1 accepted for Sept 2026 · +1 in preparation
MSc ICT · CGPA
3.81
/ 4.00
Earned in full-time employment
Primary data collected
35
interviews
Sole-authored, under institutional ethics approval
Profile
I am an empirical researcher whose work is measurement design. My sole-authored 2021 study of health-technology adoption in Bangladesh was designed, ethically approved, collected and analysed end to end by me, on thirty-five in-depth interviews with clinicians, patients and platform staff.
My MSc thesis built deep-learning detection of over-speeding and lane-change manoeuvres from naturalistic traffic footage in mixed, weakly regulated urban traffic, a setting largely absent from a literature trained on regulated European and North American roads. Alongside that, my published work covers applied machine learning on environmental and public-health data, and model interpretability.
Since 2019 I have also designed and run controlled tests inside large algorithmic advertising systems across five markets. That is not a detour. It is sustained practice in randomisation, power and pre-specification of outcomes before the data is seen, and a view of automated decision-making from inside the system rather than from the outside.
I am an electrical and electronic engineer by training, with an MSc in Information and Communication Technology (CGPA 3.81 / 4.00) completed alongside full-time work at Bangladesh University of Professionals. Four peer-reviewed papers, a fifth accepted for presentation in September 2026, one in preparation.
Doctoral directions
Each direction below is already load-bearing somewhere in my record: a thesis, a paper, or six years of operating the systems in question. Written concept notes exist for the first two and are available on request. I am open to a supervisor reshaping any of them.
Tested within-subject rather than between populations, and in mixed traffic where lane discipline is weakly enforced. My MSc thesis built deep-learning detection of over-speeding and lane changes from naturalistic footage of exactly that setting. It detected the behaviours; what it could not answer is whether the vehicle changes them.
For high-cost, infrequent purchases such as vehicles: which stated reasons were present before the decision, and which are constructed afterwards. Relatedly, how optimisation systems reach targeting decisions, and where regulatory assumptions diverge from operational reality. I have run these systems daily since 2019.
Including the comparison between rationing by outage and rationing by connection restriction. This is the decade-long thread: from peak-shaving hydro dispatch in my BSc thesis to learned dispatch policies under chronic generation shortfall today.
With particular attention to tropical siting and the Johor–Singapore cluster. It joins my grid-side training to the environmental modelling in my 2026 conference work, and sits on my doorstep.
Experimental design and controlled A/B testing at population scale · randomisation, power and pre-specification of outcomes before data is inspected · survey instrument design · semi-structured and in-depth interviewing, purposive sampling, thematic analysis · research ethics procedure and institutional approval · negotiation of data and measurement agreements with commercial partners · supervised machine learning, model benchmarking and validation · explainable AI (LIME, SHAP, feature importance) · deep learning for computer vision · Python, including deep-learning implementation.
Publications
ORCID 0009-0009-8360-9690. Author name in bold. Full texts on request. View the CV or download the PDF.
7th Multimedia University Engineering Conference (MECON2026 / DIFCon 2026), Multimedia University, Malaysia, 5–7 May 2026
A predictive framework built on open-source meteorological data to forecast dengue outbreak trends across Malaysia, aimed at early warning and public-health preparedness. Affiliations: Multimedia University, Malaysia; Miraiyo, Bangladesh; Centre for Electric Energy and High Voltage Engineering.
7th Multimedia University Engineering Conference (MECON2026 / DIFCon 2026), Multimedia University, Malaysia, 5–7 May 2026
Benchmarks machine-learning algorithms against seasonal operational features of brick kilns to forecast severe air-quality degradation in Dhaka, a source term that generic pollution models routinely omit.
The 8th ASEAN–UEC Workshop on Informatics and Engineering, held with the 13th UEC Seminar in ASEAN 2026, UEC ASEAN Research and Education Center, University of Electro-Communications, Japan, 5–6 September 2026
A survey of creative professionals on the occupational and ethical consequences of generative AI in Malaysia’s digital-art sector. Primary data collected by questionnaire.
International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), March 2024
Compares LIME, SHAP and conventional feature importance on a decision-tree classifier. Finds high local precision and recall for LIME, a local–global balance for SHAP, and sets out practical selection criteria for interpretability frameworks.
Asian Journal of Multidisciplinary Research & Review (AJMRR), 2(2), 592–621, 2021. ISSN 2582-8088
Mixed-methods study of how AI-driven telemedicine was implemented and adopted in Bangladesh during the pandemic. Thirty-five in-depth interviews with practitioners, patients and platform staff; purposive sampling; instrument designed and all data collected by the author under institutional ethics approval.
In preparation
Replaces the rule-based peak-shaving schedules of my undergraduate thesis with learned dispatch policies under chronic generation shortfall. The same question, fourteen years on, with the methods that were not available the first time.
Bangladesh University of Professionals, Faculty of Science and Technology, Dhaka. Examined March 2022
Deep-learning models applied to naturalistic traffic footage to detect over-speeding and lane-change manoeuvres in mixed, weakly regulated urban traffic, a setting under-represented in driver-behaviour research.
Ahsanullah University of Science and Technology, Dhaka, 2012
Dispatch scheduling to flatten demand peaks in a chronically supply-constrained national grid. Extended a decade later with machine-learning methods (see P6).
Where I have been
Research collaboration, environmental and climate-health machine learning
Multimedia University, Malaysia · Miraiyo, Bangladesh · Centre for Electric Energy and High Voltage Engineering. Supervising collaborator: Ir. Dr. Siow Chun Lim. Output: P1 and P2.
MSc in Information and Communication Technology (CGPA 3.81 / 4.00)
Bangladesh University of Professionals, Dhaka. Completed in full-time employment. Group thesis on deep-learning speed and lane-change detection.
Independent researcher, sole investigator: health-technology adoption
Instrument designed, institutional ethics approval secured, thirty-five in-depth interviews conducted and thematically analysed single-handedly. Published as P5.
Research Engineer
Debonair Electrical & Electronics Ltd., Dhaka. Four years of applied product research and technical evaluation, reported to international suppliers and industrial clients; trained junior engineers.
BSc, Electrical and Electronic Engineering
Ahsanullah University of Science and Technology, Dhaka. Thesis on peak-shaving hydro dispatch and load shedding.
Social Media & Content Manager, Paid Media
Black Swan Business Setup Services, UAE (remote). Paid acquisition across five markets; builds and runs the full measurement stack (GA4, Tag Manager, Conversions API, Looker Studio). Controlled experiments at population scale with outcomes pre-specified before results are read.
Technical Writer · Marketing Manager · Assistant Manager
BuddyBoss, Canada · STUDiLOG · Enzaime Bangladesh. Developer documentation and pre-release testing; the Enzaime role provided the field access behind P5. The MSc was completed in full over this same period.
Support Engineer
Ahsan Automation Ltd., Dhaka. Industrial automation design and implementation; engineering drawing; collaboration with international manufacturers on new products.
September 2026. 13th UEC Seminar in ASEAN and the 8th ASEAN–UEC Workshop on Informatics and Engineering, University of Electro-Communications, Japan. Presenting author on two contributions: the generative-AI survey (P3) and the Dhaka air-quality work (P2). May 2026. 7th Multimedia University Engineering Conference (MECON2026 / DIFCon 2026), Malaysia; co-author of two accepted papers.
Bengali. Native, and a working research capability for fieldwork, interviewing and primary-document access in Bangladesh. English. Full professional proficiency, medium of instruction throughout higher education; IELTS Academic overall band 7.5, certificate lapsed March 2026, retest at short notice if a valid score is required. Hindi. Good working proficiency in speech and comprehension, sufficient for interviewing and South Asian source material. Malay. Basic working familiarity for regional sources.
Contact
If any of the four directions above overlaps with your group’s work, I would value a short conversation. Written concept notes exist for the transport and behaviour directions, and I can send those, full texts of any paper listed here, and my transcripts on request.
I am a Bangladeshi national, currently resident in Malaysia, and available to relocate. I hold a valid long-term pass in Malaysia and am available immediately. My strongest independent evidence is publication P5, a sole-authored, interview-based study designed, approved, collected and analysed end to end by me, together with the MSc thesis on driver behaviour in naturalistic traffic footage and six years of controlled testing at population scale.
The fastest way to reach me is email. I reply within a day.
This browser cannot display the PDF inline.
Open the CV in a new tab