Nabil Ibtehaz

Work place: Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh



Research Interests: Computational Learning Theory, Computer Vision, Evolutionary Computation, Natural Language Processing


Nabil Ibtehaz is a graduate student at the Department of Computer Science and Engineering (CSE), Bangladesh University of Engineering and Technology (BUET), Bangladesh. Currently, he is pursuing his Master of Science in Computer Science and Engineering (MSc CSE). He earned his Bachelor of Science in Electrical and Electronics Engineering (BSc EEE) from the same institution. His core areas of interest are machine learning, natural language processing, computer vision , signal processing , evolutionary algorithms . He has participated in various national and international competitions.

Author Articles
A Regression based Sensor Data Prediction Technique to Analyze Data Trustworthiness in Cyber-Physical System

By Abdus Satter Nabil Ibtehaz

DOI:, Pub. Date: 8 May 2018

A Cyber-Physical System strongly depends on the sensor data to understand the current condition of the environment and act on that. Due to network faults, insufficient power supply, and rough environment, sensor data become noisy and the system may perform unwanted operations causing severe damage. In this paper, a technique has been proposed to analyze the trustworthiness of a sensor reading before performing operation based on the record. The technique employs regression analysis to select nearby sensors and develops a linear model for a target sensor. Using the linear model, target sensor reading is predicted in a particular time stamp with respect to each nearby sensor’s reading. If the difference between the predicted and actual value is within a given limit, the reading is considered as trustworthy for the corresponding nearby sensor. At last, majority consensus is taken to consider the reading as trustworthy. To evaluate the proposed technique, a data set containing temperature reading of 8 sensors for 24 hours was used where first 90% data was used for nearby sensor selection and linear model construction, and rest 10% for testing. The result analysis shows that the proposed technique detects 19, 69, and 73 trustworthy data from 73 records with respect to 3%, 4% and 5% deviation from actual reading.

[...] Read more.
A Partial String Matching Approach for Named Entity Recognition in Unstructured Bengali Data

By Nabil Ibtehaz Abdus Satter

DOI:, Pub. Date: 8 Jan. 2018

In today's data driven, automated and digitized world, a significant stage of information extraction is to look for special keywords, more formally known as 'Named Entity'. This has been an active research topic for more than two decades and significant progresses have been made. Today we have models powered by deep learning that, although not perfect, have near human level accuracy on certain occasions. Unfortunately these algorithms require a lot of annotated training data, which we hardly have for Bengali language. This paper proposes a partial string matching approach to identify a named entity from an unstructured text corpus in Bengali. The algorithm is a partial string matching technique, based on Breadth First Search (BFS) search on a Trie data structure, augmented with dynamic programming. This technique is capable of not only identifying named-entities present on a text, but also estimating the actual named-entities from erroneous data. To evaluate the proposed technique, we conducted experiments in a closed domain where we employed this approach on a text corpus with some predefined named entities. The texts experimented on was both structured and unstructured, and our algorithm managed to succeed in both the cases.

[...] Read more.
Other Articles