Kai Liang Lew

Mr. Kai Liang Lew


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
14 February 2024 in Journal of Informatics and Web Engineering
Verified
Journal Article
Open access
PDF file
KLKai Liang Lew
Kai Liang Lew
CKChung Yang Kew
Chung Yang Kew
KSKok Swee Sim
Kok Swee Sim
STShing Chiang Tan
Shing Chiang Tan
Medical imaging plays an important role in modern healthcare, with Computed Tomography (CT) being essential for high-resolution cross-sectional imaging. However, Gaussian noise often occurs within the CT scan images and makes it difficult for image interpretation and reduces the diagnostic accuracy, creating a significant obstacle to fully utilizing CT scanning technology. Existing denoising techniques have a hard time balance between noise reduction and preserving the important image details, failing to enable the optimal diagnostic precision. This study introduces Adaptive Gaussian Wiener Filter (AGWF), a novel filter aims to denoise CT scan images that have been corrupted with various Gaussian noise variance without compromising the image details. The AGWF combines the Gaussian filter for initial noise reduction, followed by the implementation of Wiener filter, which can adaptively estimate noise variance and signal power in localized regions. This approach not only outperforms other existing techniques but also showcases a remarkable balance between noise reduction and image detail preservation. The experiment evaluates 300 images from the dataset and each image is corrupted with Gaussian noise variance to ensure a comprehensive evaluation of the AGWF’s performance. The evaluation indicated that AGWF can improve the Signal-to-Noise Ratio (SNR) value and reduce the Root Mean Square Error (RMSE) and Mean Square Error (MSE) value, showing a qualitative improvement in CT scan imagery. The proposed method holds promising potential for advancing medical imaging technology with the implementation of deep learning.

16 October 2024 in Journal of Informatics and Web Engineering
Verified
Journal Article
Open access
PDF file
KSKok Swee Sim
Kok Swee Sim
ALAlex Kai Jie Low
Alex Kai Jie Low
KLKai Liang Lew
Kai Liang Lew
The swift expansion of e-commerce and supply chain operations has significantly enhanced the efficiency of warehouse management systems, establishing them as vital components in augmenting organizations' competitiveness. This paper delves into warehouse sorting systems to enhance the sorting process, reduce error rates, and simplify internal warehouse procedures. It aims to develop a scalable, adaptable, and efficient warehouse sorting system that can maximize sorting efficiency while effectively responding to changing market demands through the use of advanced automation technologies. The study provides an in-depth review of the literature that has explored the Automated Storage and Retrieval System (ASRS) within the context of warehouse operations. It offers a comprehensive introduction to the operational systems of warehouses, detailing each type of ASRS along with the technologies that can improve the efficiency and accuracy of these systems. Moreover, the paper thoroughly investigates and classifies the ASRS design decision problem and compares multiple types of ASRS. The analysis aims to delineate the distinctions among various ASRS configurations, assessing their scalability, adaptability, and their impact on operational efficacy in warehouse environments Through this comparative review, the paper emphasizes the potential enhancements in sorting processes that modern ASRS can provide, ensuring that warehouse operations can rapidly adapt to market changes and demands. The goal is to highlight best practices and technological innovations that can lead to more responsive and efficient warehouse management systems. This exploration contributes to a better understanding of how cutting-edge automation and adaptable system designs can significantly influence the efficiency of warehouse sorting processes.

30 November 2024 in JOIV : International Journal on Informatics Visualization
Verified
Journal Article
Open access
KLKai Liang Lew
Kai Liang Lew
KSKok Swee Sim
Kok Swee Sim
ZTZehong Ting
Zehong Ting
The introduction of deep learning technology has greatly benefited the neuroscience field by improving the electroencephalogram (EEG) signal analysis. These technologies have greatly improved the understanding of complex brain activity by interpreting the signal as normal or abnormal. The EEG signal requires expertise to interpret the pattern, and only then can the EEG signal be differentiated as normal or abnormal. However, some variations always complicate the analysis of the EEG signal by creating noise in the signal. This paper introduces a deep learning model, NeuroNetFlex (NFF), to classify the EEG signal as normal or abnormal. The NNF is designed to classify the EEG signal by using multiple combinations of modules such as one-dimension convolutional neural networks (1D-CNN), Squeeze-and-Excitation (SE) blocks, and the parallel processing fusion of recurrent neural networks (RNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) layers are used to analyze the temporal features of the EEG data and learn the signal pattern. The performance of the NNF was evaluated using evaluation metrics such as accuracy, precision, recall, and f1 score. The model achieved an accuracy of 75.33%, a precision of 76.39%, a recall of 75.33%, and an F1 score of 75.08% with a training time of 16.88 minutes, outperforming the existing models. These results demonstrate the promising potential of the NNF to significantly improve the analysis of brain activities

31 March 2025 in International Journal on Robotics, Automation and Sciences
Verified
Journal Article
Open access
PDF file
ZAZoobiya Aalam
Zoobiya Aalam
SASaman Aziz
Saman Aziz
KLKai Liang Lew
Kai Liang Lew
CLChia Shyan Lee
Chia Shyan Lee
The integration of artificial intelligence (AI) in emotion recognition has significantly transformed human-computer interaction and revolutionized fields such as medicine, education, and entertainment. This paper reviews 30 papers on the detection of emotional signs through various biometric inputs, including electroencephalography (EEG), electrocardiography (ECG), facial expressions, and speech patterns. Despite advancements in AI-driven emotion recognition systems, challenges persist, particularly in data variability, computational inefficiency, and ethical dilemmas associated with privacy, security, and algorithmic bias. Recent innovations in feature extraction techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have enhanced the precision of emotional state recognition across multiple input channels. The transition to edge computing has further enabled real-time processing with low latency, facilitating integration into wearable devices and IoT ecosystems. Multimodal systems, which leverage data sources such as physiological signals, facial expressions, and speech, show great promise but face challenges related to inclusivity and system fragility. To address these issues, the study recommends for robust training datasets, ethical guidelines, and hardware optimizations. Incorporating contextual information and accounting for individual differences can improve recognition accuracy and user trust. However, ethical concerns remain critical, emphasizing the need for strict standards of privacy, security, and equitable access to ensure AI emotion recognition systems are trustworthy and inclusive. Overall, this paper highlights the potential of AI-driven emotion recognition systems while underscoring the importance of continuous research to address technical and ethical challenges, paving the way for broader applications in pattern recognition, cognitive studies, and specialized tools.

19 November 2020
Verified
Book Chapter
Closed access
PDF file
KLKai Liang Lew
Kai Liang Lew
KSKok Swee Sim
Kok Swee Sim
TCTan Shing Chiang
Tan Shing Chiang
FAFAZLY SALLEH ABAS
FAZLY SALLEH ABAS

16 October 2024 in Journal of Informatics and Web Engineering
Verified
Journal Article
Open access
PDF file
KSKok Swee Sim
Kok Swee Sim
KTKok An Teo
Kok An Teo
CTChean Khim Toa
Chean Khim Toa
KLKai Liang Lew
Kai Liang Lew
This paper proposes a virtual reality based Left Brain System named BrainUp World to improve left brain thinking. The left-brain system was employed with mobile virtual reality technology, hand motion tracking and haptic feedback system. The implementation of these systems is to enhance the experience and sense of embodiment. BrainUp World includes virtual reality-based brain training games to improve a person’s attention level, reasoning skill, auditory cognition, arithmetic skill, sequencing skill and memory. The hand tracking system was utilized with an IR camera to capture the hand orientation and return the gesture data to the VR application. A low-cost and lightweight haptic glove was invented which provides the sense of touch using vibrations while interacting with VR contents. An experimental study was conducted to assess the efficacy of BrainUp World compared to traditional PC-based training approaches. Participants were randomly assigned to either the VR-based or PC-based training group and underwent 6 different games to test a person’s attention level, reasoning skill, auditory cognition, arithmetic skill, sequencing skill, and memory. The results revealed a statistically significant improvement in left brain function in the VR-based training group compared to the PC-based group, with a T-score growth of 4.73. Analysis using ANOVA confirmed the significance of this difference (p-Value = 0.04). Notably, the study also identified age-related differences in thinking fluency, highlighting the importance of personalized cognitive training interventions. In conclusion, BrainUp World demonstrates the potential of VR technology in promoting left brain development, as evidenced by empirical findings from the conducted study. By offering immersive and interactive cognitive training experiences, VR-based systems hold promise for enhancing various aspects of cognitive function associated with left hemisphere dominance. Further research in this area is encouraged to explore the full potential of VR-based interventions for cognitive enhancement.