Akm Ashiquzzaman

Mr. Akm Ashiquzzaman

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
14 April 2021 in Sensors
Verified
Journal Article
Open access
PDF file
SOSeungmin Oh
Seungmin Oh
AAAkm Ashiquzzaman
Akm Ashiquzzaman
DLDongsu Lee
Dongsu Lee
YKYeonggwang Kim
Yeonggwang Kim
Jinsul KimJinsul Kim
Jinsul Kim
In recent years, various studies have begun to use deep learning models to conduct research in the field of human activity recognition (HAR). However, there has been a severe lag in the absolute development of such models since training deep learning models require a lot of labeled data. In fields such as HAR, it is difficult to collect data and there are high costs and efforts involved in manual labeling. The existing methods rely heavily on manual data collection and proper labeling of the data, which is done by human administrators. This often results in the data gathering process often being slow and prone to human-biased labeling. To address these problems, we proposed a new solution for the existing data gathering methods by reducing the labeling tasks conducted on new data based by using the data learned through the semi-supervised active transfer learning method. This method achieved 95.9% performance while also reducing labeling compared to the random sampling or active transfer learning methods.

10 August 2018
Verified
Book Chapter
Closed access
PDF file
AAAkm Ashiquzzaman
Akm Ashiquzzaman
ATAbdul Kawsar Tushar
Abdul Kawsar Tushar
ARAshiqur Rahman
Ashiqur Rahman
FMFarzana Mohsin
Farzana Mohsin

6 May 2020 in IEEE Access
Verified
Journal Article
Open access
AAAkm Ashiquzzaman
Akm Ashiquzzaman
HLHyunmin Lee
Hyunmin Lee
TUTai-Won Um
Tai-Won Um
Jinsul KimJinsul Kim
Jinsul Kim
The modern development of ultra-durable and energy-efficient IoT based communication sensors has much application in modern telecommunication and networking sectors. Sensor calibration to reduce power usage is beneficial to minimizing energy consumption in sensors as well as improve the efficiency of devices. Reinforcement learning (RL) has been received much attention from researchers and now widely applied in many study fields to achieve intelligent automation. Though various types of sensors have been widely used in the field of IoT, rare researches were conducted in resource optimizing. In this novel research, a new style of power conservation has been explored with the help of RL to make a new generation of IoT devices with calibrated power sources to maximize resource utilization. A closed grid multiple power source based control for sensor resource utilization has been introduced. Our proposed model using Deep Q learning (DQN) enables IoT sensors to maximize its resource utilization. This research focuses solely on the energy-efficient sensor calibration and simulation results show promising performance of the proposed method.

7 November 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAAkm Ashiquzzaman
Akm Ashiquzzaman
HLHyunmin Lee
Hyunmin Lee
KKKwangki Kim
Kwangki Kim
HKHyeyoung Kim
Hyeyoung Kim
Jae Hyung ParkJae Hyung Park
Jae Hyung Park
Jinsul KimJinsul Kim
Jinsul Kim
Current deep learning convolutional neural network (DCNN) -based hand gesture detectors with acute precision demand incredibly high-performance computing power. Although DCNN-based detectors are capable of accurate classification, the sheer computing power needed for this form of classification makes it very difficult to run with lower computational power in remote environments. Moreover, classical DCNN architectures have a fixed number of input dimensions, which forces preprocessing, thus making it impractical for real-world applications. In this research, a practical DCNN with an optimized architecture is proposed with DCNN filter/node pruning, and spatial pyramid pooling (SPP) is introduced in order to make the model input dimension-invariant. This compact SPP-DCNN module uses 65% fewer parameters than traditional classifiers and operates almost 3× faster than classical models. Moreover, the new improved proposed algorithm, which decodes gestures or sign language finger-spelling from videos, gave a benchmark highest accuracy with the fastest processing speed. This proposed method paves the way for various practical and applied hand gesture input-based human-computer interaction (HCI) applications.

1 December 2017
Verified
Conference Paper
Closed access
ATAbdul Kawsar Tushar
Abdul Kawsar Tushar
AAAkm Ashiquzzaman
Akm Ashiquzzaman
MD Rashedul IslamMD Rashedul Islam
MD Rashedul Islam
Hand signs and signals are the staple form of expression for the hearing and speech impaired people. Human Computer Interaction technology enable people to interact with computer machine using hand gestures. Common sign languages use separate hand signals to communicate different decimals. Recent developments in Deep Convolutional Neural Networks (DCNN) have opened the door to recognize and classify this visual form of gestures more accurately. In this paper, a layer-wise optimized neural network architecture is proposed where batch normalization contributes to faster convergence of training, and introduction of dropout technique mitigates data overfitting. Batch normalization forces each training batch toward zero mean and unit variance, leading to improved flow of gradients through the model and convergence in shorter time. Dropout forces neurons of neural network to regularize, resulting in reduced overfitting. A constructed numerical hand gesture data set is used for validating the claims based on American Sign Language system. The proposed model is shown to surpass other methods in classifying these numerical hand signs successfully.

16 October 2025 in Applied Artificial Intelligence
Verified
Journal Article
Open access
AAAkm Ashiquzzaman
Akm Ashiquzzaman
JKJinsul Kim
Jinsul Kim
CKChihoon Kim
Chihoon Kim