Md. Khaliluzzaman

Mr. Md. Khaliluzzaman

Computer Science and Engineering, International Islamic University Chittagong, Chittagong, Bangladesh
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MKMd. Khaliluzzaman
Md. Khaliluzzaman
AUAshraf Uddin
Ashraf Uddin
KDKaushik Deb
Kaushik Deb
Md Junayed HasanMd Junayed Hasan
Md Junayed Hasan
Gait recognition, also known as walking pattern recognition, has expressed deep interest in the computer vision and biometrics community due to its potential to identify individuals from a distance. It has attracted increasing attention due to its potential applications and non-invasive nature. Since 2014, deep learning approaches have shown promising results in gait recognition by automatically extracting features. However, recognizing gait accurately is challenging due to the covariate factors, complexity and variability of environments, and human body representations. This paper provides a comprehensive overview of the advancements made in this field along with the challenges and limitations associated with deep learning methods. For that, it initially examines the various gait datasets used in the literature review and analyzes the performance of state-of-the-art techniques. After that, a taxonomy of deep learning methods is presented to characterize and organize the research landscape in this field. Furthermore, the taxonomy highlights the basic limitations of deep learning methods in the context of gait recognition. The paper is concluded by focusing on the present challenges and suggesting several research directions to improve the performance of gait recognition in the future.

15 November 2023 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
JHJiabul Hoque
Jiabul Hoque
MIMd Saiful Islam
Md Saiful Islam
MKMd. Khaliluzzaman
Md. Khaliluzzaman
Conventional irrigation methods frequently generate excessive or inadequate watering, resulting in the wastage of water and energy and diminished agricultural yields. This study presents a novel intelligent irrigation system that incorporates fuzzy logic and the Internet of Things (IoT) to automate the control of water pumps, thereby eliminating the requirement for human intervention. This novel method enables users to effectively preserve water and electricity by mitigating the issues of excessive and insufficient irrigation of crops. The system utilizes climate sensors that are combined with electrical circuits and connected to an Arduino and a fuzzy inference system (FIS) model to consider climate conditions and soil moisture levels. The sensors are responsible for collecting data that are utilized by the FIS model to control the speed of the water pump effectively. The FIS model integrates fuzzy logic to analyse the data obtained by the Arduino. This analysis enables the Arduino to adjust the pump speed by considering a wide range of sensor inputs. The implementation of this autonomous system eliminates the requirement for human intervention and enhances agricultural productivity by accurately dispensing the optimal quantity of water at the proper intervals. The cessation of water supply occurs when the soil moisture levels reach a sufficient state and resumes when the moisture levels fall below predetermined limits, regulated by various environmental circumstances. A comparative analysis examines the suggested technology, drip irrigation, and manual flooding. The comparison results demonstrate that the intelligent irrigation system accomplishes water and energy conservation.

1 January 2024 in Applied Computational Intelligence and Soft Computing
Verified
Journal Article
Open access
MKMd. Khaliluzzaman
Md. Khaliluzzaman
FUFurquan
Furquan
MKMohammod Sazid Zaman Khan
Mohammod Sazid Zaman Khan
JHJiabul Hoque
Jiabul Hoque
Human activity recognition (HAR) has gained significant attention in computer vision and human‐computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self‐attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model’s comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI‐HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001.

1 December 2017
Verified
Conference Paper
Closed access
AAAtif Anis
Atif Anis
MKMd. Khaliluzzaman
Md. Khaliluzzaman
MYMohammad Yakub
Mohammad Yakub
NCNiloy Chakraborty
Niloy Chakraborty
KDKaushik Deb
Kaushik Deb
Digital meter reading recognition from a digital electric meter image is the key step in the field of digital image processing to evaluate the meter readings from different environmental conditions automatically. This work has gain important for the purpose of automatic generation of electric bill from digital electric meter image. In this regard, a digital electric meter reading recognition framework is proposed in this paper. For that initially, the input image is normalized and converted to YCbCr image. As the digital electric meter reading region is resolute with color light, especially green, the reading region is extracted from YCbCr image based on the value of the Cb and Cr. After that, Canny edge operator is employed on the extracted region to find the edge image. In this edge image, the individual digit's edge gaps are filled up through the morphological operation to find individually connected digit edge image. These individual digits are segmented from an edge image through the vertical projection. Furthermore, the individually segmented digits are filled and thinned to detect the shapes of the digits. From these segmented digit shapes the Horizontal and Vertical Binary (HVB) pattern features are extracted. This is the key contribution of this paper. Finally, based on the HVB patterns the digital meter reading sequence is recognized. The experimental result reveals that the proposed framework is practical and effective.

1 September 2017
Verified
Conference Paper
Closed access
MHMohammad Mahadi Hasan
Mohammad Mahadi Hasan
MKMd. Khaliluzzaman
Md. Khaliluzzaman
SHShabiba Akhtar Himel
Shabiba Akhtar Himel
RCRukhsat Tasneem Chowdhury
Rukhsat Tasneem Chowdhury
Hand sign language recognition is one of the fundamental steps to overcome the barrier of communication between a deaf-mute and a normal person in the field of computer vision. In this paper, a hand sign language recognition framework is proposed for various Bangla alphabets using Artificial Neural Network (ANN). For that, initially the input image is normalized and the skin area is extracted on the basis of the YCbCr values corresponding to human skin color. The extracted area i.e., hand sign area is converted into a binary image and the gaps in the binary hand sign area are filled through the morphological operations. After that, the boundary edge of the hand sign area is extracted through the canny edge detector and extracts the hand sign region of interest (ROI). Finally, features are extracted from the hand sign ROI using Freeman Chain Code (FCC). The ANN is used for training and classifies the hand sign images. The proposed method is tested using various hand sign images and results are presented to demonstrate the efficiency and effectiveness.

1 January 2025 in Complexity
Verified
Journal Article
Open access
JHJiabul Hoque
Jiabul Hoque
MIMd Saiful Islam
Md Saiful Islam
MKMd. Khaliluzzaman
Md. Khaliluzzaman
Correct detection of plant diseases is critical for enhancing crop yield and quality. Conventional methods, such as visual inspection and microscopic analysis, are typically labor‐intensive, subjective, and vulnerable to human error, making them infeasible for extensive monitoring. In this study, we propose a novel technique to detect tomato leaf diseases effectively and efficiently through a pipeline of four stages. First, image enhancement techniques deal with problems of illumination and noise to recover the visual details as clearly and accurately as possible. Subsequently, regions of interest (ROIs), containing possible symptoms of a disease, are accurately captured. The ROIs are then fed into K‐means clustering, which can separate the leaf sections based on health and disease, allowing the diagnosis of multiple diseases. After that, a hybrid feature extraction approach taking advantage of three methods is proposed. A discrete wavelet transform (DWT) extracts hidden and abstract textures in the diseased zones by breaking down the pixel values of the images to various frequency ranges. Through spatial relation analysis of pixels, the gray level co‐occurrence matrix (GLCM) is extremely valuable in delivering texture patterns in correlation with specific ailments. Principal component analysis (PCA) is a technique for dimensionality reduction, feature selection, and redundancy elimination. We collected 9014 samples from publicly available repositories; this dataset allows us to have a diverse and representative collection of tomato leaf images. The study addresses four main diseases: curl virus, bacterial spot, late blight, and Septoria spot. To rigorously evaluate the model, the dataset is split into 70%, 10%, and 20% as training, validation, and testing subsets, respectively. The proposed technique was able to achieve a fantastic accuracy of 99.97%, higher than current approaches. The high precision achieved emphasizes the promising implications of incorporating DWT, PCA, GLCM, and ANN techniques in an automated system for plant diseases, offering a powerful solution for farmers in managing crop health efficiently.