Ongoing & Completed Projects

1. Electricity and Consumption

Improving Quality of Power Supply to the Industrial Clusters around Dhaka City

Quality of power supply has three main aspects – Reliability, Power quality, and Commercial quality. The first two are related to the technical aspects of a power system and the last one is related to the quality of service provided to the customers. For Bangladesh, one of the fastest growing economy of the world, the supply of quality electricity is vitally important to meet the growing demand for electricity and to improve the country’s economic condition further. The recent growth of power generation in Bangladesh indicates that the government has successfully met the challenge of expanding the generation capacity. However, significant challenges persist. Rigorous investigation is essential to analyze the existing power supply quality. We also need to evaluate the economic cost of low power quality and how it varies across different industries to take appropriate policies. To overcome these challenges, a complete data base development and a data scientific analysis approach is necessary.

Identifying this knowledge gap, this research proposes a pilot project that aims to incorporate a data driven approach to improve the Quality of Supply (QoS) of our National Power Grid System. To achieve the goal, the study defines a set of Objective Parameters (OP) to monitor the Quality of Supply (QoS) from Big Data Analysis and Sample Survey. Initially, two commercial hubs have been selected for the pilot project, which have a high concentration of commercial industries. Load, complaint, and supply interruption data of two years from two substations and interruption data from four (depending on the availability) industrial customers will be collected and digitized. Power quality data (voltage, frequency data) will be collected by random sampling method through manual inspection from the substations. Following the data preparation, a preliminary analysis will be conducted. Industries will be categorized into different cluster based on OPs. Finally, the study will draw some policy suggestions based on the cluster analysis.

Funded by BEPRC (Bangladesh Energy and power Research Council)

Analyzing current prepaid and past postpaid consumption data of Dhaka south’s electricity users

  • Measuring the change in payment and consumption behavior due to the replacing of conventional postpaid meters to prepaid meters.
  • Analyzing the consumption data of households before and after prepaid meter intervention and comparing them with households who are still using old meters.
  • We found prepaid meters effectively reduced payment delinquency. Further analysis on consumption is still under progress.

S. B. Rabbani, A. A. Ali and M. Zaber, “Does Electric Prepaid Meters Decrease Payment Delinquency? Evidence from Data Centric Analysis of Electricity Consumption in Dhaka, Bangladesh” in IEEE Region 10 Symposium (TENSYMP), Dhaka, 2020

Abstract— Prepaid electricity meters are favored by power distribution companies to improve revenue collection, debt prevention and ensure customer satisfaction. In this paper, we investigate changes in bill payments pattern of customers in Dhaka, Bangladesh who had switched from post to pre-payment meters. We collected postpaid bill and prepaid recharge payment data over there years. We specifically look into payment behavior of residential household customers to understand the effect of prepaid meters on payment delinquency. Analysis of postpaid bill indicate that at least 32% households skipped paying one or more bills over a period of one year. Households consuming 100-300 KWH accounts for almost 51% of the total delinquent households. After prepaid switch, approximately 46% of all households are making prepayments every month. 52% of households who skip paying bill and 45% of households who pay bill after due date, at least once, are now recharging every month. Overall the technological intervention shows considerable reduction of retail debts and a behavioral shift towards on time payment.

2. Land Use / Land Cover

Deep-learning coupled with novel categorization method to classify  the urban environment of the developing world

With advent of high definition satellite images,  high resolution data, novel computational methods such as deep neural network analysis, and hardware capable of high-speed analysis- urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis and visualization. In this paper we propose a novel categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting.  

Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types etc and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose  small-scale classifications, which give limited  information, have poor scalability, and are slow to compute in real time. 

Our proposed method  is divided into two steps-categorization and automation. We categorize the urban area  in terms of informal and formal spaces and take the surrounding environment into account.  50km × 50km Google Earth image of  Dhaka, Bangladesh  was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: a) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total sixteen sub-categories were identified.

For semantic segmentation and automatic categorization, Google’s deep labV3 plus model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 0.60 Mean Intersection over Union (mIoU)

Qianwei Cheng, A K M M  Rahman, Anis  Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, Ryosuke Shibasaki, Moinul Zaber, “Deep-Learning Coupled with Novel Categorization Method to Classify the Urban Environment of the Developing World” has been accepted for “, ICRSETE 2020: International Conference on Remote Sensing, Environment and Transportation Engineering, Paris, France, 2020

Rahman AKMM, Zaber M, Cheng Q, Nayem ABS, Sarker A, Paul O, Shibasaki R. Applying State-of-the-Art Deep-Learning Methods to Classify Urban Cities of the Developing World. Sensors. 2021; 21(22):7469.

Cheng Q, Zaber M, Rahman AM, Zhang H, Guo Z, Okabe A, Shibasaki R. Understanding the Urban Environment from Satellite Images with New Classification Method—Focusing on Formality and Informality. Sustainability. 2022; 14(7):4336.

3. ICT For Education

The Inclusion of ICT Tools in Education: What works, what doesn’t and why do they work?

A Visualization of how usage of ICT Tools by school headmasters is influenced by the attitude towards inclusion and their access to technology. Each bubble represents the “scores” obtained by a school headmaster in terms of his/her access to ICT tools and training, his “Attitude” (i.e. opinion and confidence) towards using ICT tools inside and outside classrooms, and the level (i.e. frequency and intensity) of usage of ICT tools in teaching learning and administrative purposes. The size of the bubbles represent the comparative usage score of the headmasters. The bigger the bubble, the more their usage.

  • We aim to analyze the current state of ICT Inclusion in the schools of Bangladesh.
  • Using the responses to a survey conducted on 33 Headmasters, 46 school teachers, 56 students and 32 ICT Coordinators from around 30 schools in Bangladesh, we aim to identify the obstacles that hinder the widespread use of ICT tools in teaching learning and school management purposes.
  • Based on the survey responses, and data about the schools from various external sources, we cluster the surveyed schools based on various parameters including the academic performance of the school’s students in public examinations, teacher-student ratio, availability of ICT tools and resources in the school, duration of usage of those tools in teaching-learning,
    the level of urbanization of the community surrounding the school, average family income of the community, etc.
  • Based on their responses, we assign a score to the level of access, attitude and usage of ICT facilities for each headmaster, teacher and student who responded.
  • As part of our ongoing research, we are working on devising strategies to make sense of the available data, and find out which underlying factors influence the usage of ICT tools in education in the schools of Bangladesh.

4. Monitoring Air Pollution

Visualization of PM2.5 time series and correlation analysis of cities in Bangladesh

This study is conducted in several cities in Bangladesh toward understanding the characteristics of PM 2.5 such as spatial-temporal characterization, correlation of other particulate matter such as human activities, driving factors and environmental casualties. Significant time-lagged correlations were discovered between the PM 2.5 time series in different city groups throughout the country using the visualization framework. The Heatmaps show that the pooled series correlations are less significant in summer and between cities of greater distance as well as there are seasonal changes in the time lag magnitude and direction of the best shifted correlated particulate matter time series. The geomap visualization demonstrates interactions of air pollution among districts around Dhaka city and the significant effect of wind direction on correlated shifted time series. Clustering on the data gave an insight on the time and zone groups. The visualization framework could help determine the pathway of regional transportation of air pollution and may also be useful in delineating the area of interaction of PM 2.5 pollution for impact analysis.

Cross Correlation Analysis: Determining whether any district has any influence over other districts and selecting the time-lag with maximum correlation

A. Zaman, S. B. Rabbani, R. Ridwanul Haque and M. Zaber, “Seasonal, Temporal and Spatial Variation of Particulate Matter Concentration in Bangladesh: A Longitudinal Analysis,” 2021 IEEE Region 10 Symposium (TENSYMP), 2021, pp. 1-8, doi: 10.1109/TENSYMP52854.2021.9550877.

5. Inland Water Port Connectivity

A Complex Network Analysis of Inland Water Port of Bangladesh

A well-structured inland waterways system should help Bangladesh fulfill SDG goals. In this study, we employ complex network analysis methods to analyze the river-port network of the country. We ascertain different types of ports based on their importance and placement in the connectivity network. Data regarding port location, vessel routes, and schedules were collected from governmental resources. Using the data, a connectivity network was built for further analysis. Different measures of network analysis are used to categorize the ports and the network model has been identified. These categories should help transportation planners and policymakers to better design the inland waterways network of Bangladesh.


F. Tabassum, H. Islam, A. A. Ali and M. Zaber, “A Complex Network Analysis of Inland Waterways Port Connectivity of Bangladesh” in IEEE Region 10 Symposium (TENSYMP), Dhaka, 2020.

6. Nightlights For Economic Condition

What can Nighttime Lights tell us about Bangladesh?

Analyzing the state and growth of various socio-economic indicators is essential for effective developmental planning at a sub-national level. However, in many cases, data regarding such indicators are not publicly available and/or hard to collect. In many other cases, the available data may not be recent enough. In contrast, satellite data is both readily available and up-to-date. In recent times, various studies have been conducted to use different types of satellite data as a proxy to determine the condition of socio-economic indicators in different places around the world. In this paper, we study the efficacy of one such data source, nighttime lights (NTL), for monitoring factors related to sustainable development in the context of Bangladesh.


M. Wahed, R. A. Rizvee, R. R. Haque, A. M. Ali, M. Zaber and A. A. Ali, “What Can Nighttime Lights Tell Us about Bangladesh?” in IEEE Region 10 Symposium (TENSYMP), Dhaka, 2020.