Searcharxiv⌕ Search

arXiv subjects

Moinul Islam Zaber

Publications and source records attributed to Moinul Islam Zaber.

2 recordsLinked to original sources

Understanding Dhaka City Traffic Intensity and Traffic Expansion Using Gravity Model

Analysis of traffic pattern recognition and traffic congestion expansion in real time are one of the exciting and challenging tasks which help the government to build a robust and sustainable traffic management system specially in a densely populated city like Dhaka. In this paper, we analyze the traffic intensity for small areas which are also known as junction points or corridors. We describe Dhaka city traffic expansion from a congestion point by using gravity model. However, we process real-time traffic data of Dhaka city rather than depend on survey and interview. We exactly show that traffic expansion of Dhaka city exactly follows gravity model. Expansion of traffic from a congestion point spreads out rapidly to its neighbor and impact of congested point decreases as the distance increases from that congested point. This analysis will help the government making a planned urbanized Dhaka city in order to reduce traffic jam.

physics.soc-ph↗

A Novel Disaster Image Dataset and Characteristics Analysis using Attention Model

The advancement of deep learning technology has enabled us to develop systems that outperform any other classification technique. However, success of any empirical system depends on the quality and diversity of the data available to train the proposed system. In this research, we have carefully accumulated a relatively challenging dataset that contains images collected from various sources for three different disasters: fire, water and land. Besides this, we have also collected images for various damaged infrastructure due to natural or man made calamities and damaged human due to war or accidents. We have also accumulated image data for a class named non-damage that contains images with no such disaster or sign of damage in them. There are 13,720 manually annotated images in this dataset, each image is annotated by three individuals. We are also providing discriminating image class information annotated manually with bounding box for a set of 200 test images. Images are collected from different news portals, social media, and standard datasets made available by other researchers. A three layer attention model (TLAM) is trained and average five fold validation accuracy of 95.88% is achieved. Moreover, on the 200 unseen test images this accuracy is 96.48%. We also generate and compare attention maps for these test images to determine the characteristics of the trained attention model. Our dataset is available at https://niloy193.github.io/Disaster-Dataset

cs.CV↗