Kazi Mejbaul Islam

Bio: Kazi Mejbaul Islam is an academic researcher from Ahsanullah University of Science and Technology. The author has contributed to research in topics: Anomaly detection & Convolutional neural network. The author has an hindex of 3, co-authored 7 publications receiving 34 citations. Previous affiliations of Kazi Mejbaul Islam include Military Institute of Science and Technology.

Line follower robot: Fabrication and accuracy measurement by data acquisition

Abstract: The line follower robot has great importance in industrial manufacturing process, automation, carrying cartage in a specific direction etc. Importance is given in this paper in investigating efficiency of the robot, response of the sensor, getting actual data of the sensors, feedback of the central processing unit depending on this response, error correction of following line, future aspects of the line follower robot, providing some real time data of the robot and giving the preliminary steps on fabricating a line follower robot. This robot is the basic form of the line follower robots. Much more complex form of line following robot can be manufactured depending on this basic form of line follower robot. More specifically, efforts has been put on acquiring data during test runs so that robots can be manufactured in massive way under specific requirements of purpose.

Handwritten Bangla Numeral Recognition Using Ensembling of Convolutional Neural Network

Abstract: Despite being one of the major languages in the world, research regarding Bengali handwritten numeral recognition (BHNR) isn't enough in comparison with the other prominent languages. Existing methods mostly rely on feature extraction and some older machine learning algorithms. Recent bloom in machine learning due to deep neural network especially using Convolutional Neural Network (CNN) showing promising results in this field with better accuracy. Some recent works show very good accuracy only in recognizing plain simple digits but perform poor in challenging scenario because of lack of large and versatile training dataset. In this work, we've ensembled our best performing proposed CNN models to recognize numerals with high degree of accuracy beyond 96% even in most challenging noisy conditions. Initially 72000+ specimens from NumtaDB (85000+) have been used for training and 17000+ specimens have been used as test dataset. The improvement in performance in challenging scenarios has been observed, when various noisy training specimens have been augmented to create a training dataset of size about 114000 specimens. The performance of our proposed model has been compared with other existing works also and presented here. These finding are based on Computer Vision Challenge on Bengali HandWritten Digit Recognition (2018) competition submissions.

Unsupervised Abnormality Detection Using Heterogeneous Autonomous Systems

Abstract: Anomaly detection (AD) in a surveillance scenario is an emerging and challenging field of research. For autonomous vehicles like drones or cars, it is immensely important to distinguish between normal and abnormal states in real-time. Additionally, we also need to detect any device malfunction. But the nature and degree of abnormality may vary depending upon the actual environment and adversary. As a result, it is impractical to model all cases a-priori and use supervised methods to classify. Also, an autonomous vehicle provides various data types like images and other analog or digital sensor data, all of which can be useful in anomaly detection if leveraged fruitfully. To that effect, in this paper, a heterogeneous system is proposed which estimates the degree of abnormality of an unmanned surveillance drone, analyzing real-time image and IMU (Inertial Measurement Unit) sensor data in an unsupervised manner. Here, we have demonstrated a Convolutional Neural Network (CNN) architecture, named AngleNet to estimate the angle between a normal image and another image under consideration, which provides us with a measure of anomaly of the device. Moreover, the IMU data are used in autoencoder to predict abnormality. Finally, the results from these two algorithms are ensembled to estimate the final degree of abnormality. The proposed method performs satisfactorily on the IEEE SP Cup-2020 dataset with an accuracy of 97.3%. Additionally, we have also tested this approach on an in-house dataset to validate its robustness.

A Deep Convolutional Neural Network for Bangla Handwritten Numeral Recognition

Abstract: Despite being one of the major languages in the world, research regarding Bengali handwritten numeral recognition (BHNR) isn't enough in comparison with the other prominent languages. Existing methods mostly rely on feature extraction and some older machine learning algorithms. Recent bloom in machine learning due to deep neural network especially using Convolutional Neural Network (CNN) showing promising results in this field with better accuracy. Some recent works show very good accuracy only in recognizing plain simple digits but perform poor in challenging scenario because of lack of large and versatile training dataset. In this work, we propose a method where our proposed CNN model which recognizes numerals with high degree of accuracy beyond 96%, even in most challenging noisy conditions. Initially 72000+ specimens were used from NumtaDB (85000+) dataset for training and 1700+ specimens were used as test dataset. The improvement in performance in challenging scenarios is observed, when training specimens are augmented to create a training dataset of size about 114000 specimens. The performance of our proposed model also compared with other existing works and presented here. These findings are based on Computer Vision Challenge on Bengali HandWritten Digit Recognition (2018) competition submissions.

Anomaly Detection in Unsupervised Surveillance Setting Using Ensemble of Multimodal Data with Adversarial Defense

Abstract: Autonomous aerial surveillance using drone feed is an interesting and challenging research domain. To ensure safety from intruders and potential objects posing threats to the zone being protected, it is crucial to be able to distinguish between normal and abnormal states in real-time. Additionally, we also need to consider any device malfunction. However, the inherent uncertainty embedded within the type and level of abnormality makes supervised techniques less suitable since the adversary may present a unique anomaly for intrusion. As a result, an unsupervised method for anomaly detection is preferable taking the unpredictable nature of attacks into account. Again in our case, the autonomous drone provides heterogeneous data streams consisting of images and other analog or digital sensor data, all of which can play a role in anomaly detection if they are ensembled synergistically. To that end, an ensemble detection mechanism is proposed here which estimates the degree of abnormality of analyzing the real-time image and IMU (Inertial Measurement Unit) sensor data in an unsupervised manner. First, we have implemented a Convolutional Neural Network (CNN) regression block, named AngleNet to estimate the angle between a reference image and current test image, which provides us with a measure of the anomaly of the device. Moreover, the IMU data are used in autoencoders to predict abnormality. Finally, the results from these two pipelines are ensembled to estimate the final degree of abnormality. Furthermore, we have applied adversarial attack to test the robustness and security of the proposed approach and integrated defense mechanism. The proposed method performs satisfactorily on the IEEE SP Cup-2020 dataset with an accuracy of 97.8%. Additionally, we have also tested this approach on an in-house dataset to validate its robustness.

Anomaly Detection using Edge Computing in Video Surveillance System: Review

Abstract: The current concept of Smart Cities influences urban planners and researchers to provide modern, secured and sustainable infrastructure and give a decent quality of life to its residents. To fulfill this need video surveillance cameras have been deployed to enhance the safety and well-being of the citizens. Despite technical developments in modern science, abnormal event detection in surveillance video systems is challenging and requires exhaustive human efforts. In this paper, we surveyed various methodologies developed to detect anomalies in intelligent video surveillance. Firstly, we revisit the surveys on anomaly detection in the last decade. We then present a systematic categorization of methodologies developed for ease of understanding. Considering the notion of anomaly depends on context, we identify different objects-of-interest and publicly available datasets in anomaly detection. Since anomaly detection is considered a time-critical application of computer vision, our emphasis is on anomaly detection using edge devices and approaches explicitly designed for them. Further, we discuss the challenges and opportunities involved in anomaly detection at the edge.

Implementation of Line Follower Robot based Microcontroller ATMega32A

Abstract: The development of technology in the field of robotics is very fast, but in the eastern regions of Indonesia, namely the development of the development has not yet felt the impact. Especially in the university's electrical laboratory Musamus Merauke learning media devices for microcontrollers are also not yet available, therefore the author wants to pioneer by implementing the simplest robot design, the line follower robot, where the robot only goes along the lines. This study uses an experimental method, by conducting a research process based on sequences, namely: needs analysis, mechanical chart design, electronic part design and control program design, manufacturing, and testing. The line follower robot based on ATmega32A microcontroller has been tested and the results show that the line follower robot can walk following the black line on the white floor and can display the situation on the LCD. But this line follower robot still has shortcomings in the line sensor sensitivity process depending on a certain speed. At speeds of 90-150 rpm the line follower robot can follow the path, while more than 150 rpm the robot is not able to follow the path.

Sliding mode control of a line following robot

Abstract: Line following robots have ability to track a given path autonomously using feedback mechanisms. The path is usually a black line on a white surface or a white line on a black surface. Today, line following robots are used in medical, industrial and automotive industries. Therefore, the studies on the line following robots have been increased recently. In this study, a robust, non-chattering sliding mode control (SMC) is designed and applied for a line following robot. The mobile robot is designed to sense the straight or curved path with its infrared sensors mounted on the robot. Therefore, these infrared sensors provide continuous streaming of the defined path to guide or direct changes in robot by activating motors on right wheel or/and left wheel. The control strategy is curial to track complex paths accurately and to have a fast, stable and accurate line following robot. Thus, for comparison, conventional proportional-integral-derivative (PID) is also applied to robot. The main purpose of this study is to investigate performance of sliding mode control during path tracking. For this, numerical solution and experimental study were carried out. From the results, it was understood that sliding mode controller is highly efficient in tracking the path.

Two Decades of Bengali Handwritten Digit Recognition: A Survey

Abstract: Handwritten Digit Recognition (HDR) is one of the most challenging tasks in the domain of Optical Character Recognition (OCR). Irrespective of language, there are some inherent challenges of HDR, which mostly arise due to the variations in writing styles across individuals, writing medium and environment, inability to maintain the same strokes while writing any digit repeatedly, etc. In addition to that, the structural complexities of the digits of a particular language may lead to ambiguous scenarios of HDR. Over the years, researchers have developed numerous offline and online HDR pipelines, where different image processing techniques are combined with traditional Machine Learning (ML)-based and/or Deep Learning (DL)-based architectures. Although evidence of extensive review studies on HDR exists in the literature for languages, such as English, Arabic, Indian, Farsi, Chinese, etc., few surveys on Bengali HDR (BHDR) can be found, which lack a comprehensive analysis of the challenges, the underlying recognition process, and possible future directions. In this paper, the characteristics and inherent ambiguities of Bengali handwritten digits along with a comprehensive insight of two decades of state-of-the-art datasets and approaches towards offline BHDR have been analyzed. Furthermore, several real-life application-specific studies, which involve BHDR, have also been discussed in detail. This paper will also serve as a compendium for researchers interested in the science behind offline BHDR, instigating the exploration of newer avenues of relevant research that may further lead to better offline recognition of Bengali handwritten digits in different application areas.