Koh Tieng Wei

Koh Tieng Wei

Auto-generated profile, based on publicly available information

Koh Tieng Wei

Centre for Cyber-Physical Systems, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
25 December 2024 in IEEE Access
Verified
Journal Article
Open access
BQBrandon Liew Yi Quan
Brandon Liew Yi Quan
NWNur Haliza Abdul Wahab
Nur Haliza Abdul Wahab
AAArafat Al-Dhaqm
Arafat Al-Dhaqm
AAAhmad Alshammari
Ahmad Alshammari
AAAli Aqarni
Ali Aqarni
KWKoh Tieng Wei
Koh Tieng Wei
Blockchain is a technology that has been gaining popularity in the recent years thanks to its immutability and decentralized features, various industries have started to integrate the technology with their business models, and this resulted in various types of blockchain networks being developed. This paper reviews the latest academic advancements of sharding techniques in the various types of sharded blockchain networks that have been implemented in the past 5 years to identify their strengths and weaknesses. The increasing volume of transactions in blockchain networks has caused issues in terms of their scalability, transaction efficiency, storage, and security which obstructs the global adoption of blockchain technology. Sharding in blockchain is a solution that aims to solve the issues through its various types of sharding techniques such as network, transaction, or state sharding along with the various types of networks and systems. The general definition of sharding is to partition the network into subsets known as shards which allows them to validate transactions parallelly and thus, resulting in performance improvement and scalability improvement of the existing network. The existing sharding techniques (before 2020) and latest sharding techniques (2020 – 2024) along with their characteristics, advantages, and disadvantages are also discussed. An analysis based on the performance evaluation of recent sharding techniques was done to further understand the impact brought by the techniques. The result of the review sheds critical insights on the advancements in sharding techniques and fosters innovation and facilitates the widespread adoption of sharding-based solutions in the blockchain ecosystem.

24 January 2024 in IEEE Access
Verified
Journal Article
Open access
FYFan Yang
Fan Yang
NINor Azman Ismail
Nor Azman Ismail
YPYee Yong Pang
Yee Yong Pang
Victor R KebandeVictor R Kebande
Victor R Kebande
AAArafat Al-Dhaqm
Arafat Al-Dhaqm
TKTieng Wei Koh
Tieng Wei Koh
Sketch-based image retrieval (SBIR) utilizes sketches to search for images containing similar objects or scenes. Due to the proliferation of touch-screen devices, sketching has become more accessible and therefore has received increasing attention. Deep learning has emerged as a potential tool for SBIR, allowing models to automatically extract image features and learn from large amounts of data. To the best of our knowledge, there is currently no systematic literature review (SLR) of SBIR with deep learning. Therefore, the aim of this review is to incorporate related works into a systematic study, highlighting the main contributions of individual researchers over the years, with a focus on past, present and future trends. To achieve the purpose of this study, 90 studies from 2016 to June 2023 in 4 databases were collected and analyzed using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework. The specific models, datasets, evaluation metrics, and applications of deep learning in SBIR are discussed in detail. This study found that Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN) are the most widely used deep learning methods for SBIR. A commonly used dataset is Sketchy, especially in the latest Zero-shot sketch-based image retrieval (ZS-SBIR) task. The results show that Mean Average Precision (mAP) is the most commonly used metric for quantitative evaluation of SBIR. Finally, we provide some future directions and guidance for researchers based on the results of this review.

20 November 2025 in Ocean Engineering
Verified
Journal Article
Closed access
TKTarwan Kumar Khatri
Tarwan Kumar Khatri
KWKoh Tieng Wei
Koh Tieng Wei
KSKhaironi Yatim Sharif
Khaironi Yatim Sharif

15 July 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
ASAmran Salleh
Amran Salleh
MOMohd Hafeez Osman
Mohd Hafeez Osman
SHSa’aDah Hassan
Sa’aDah Hassan
MSMar Yah Said
Mar Yah Said
KSKhaironi Yatim Sharif
Khaironi Yatim Sharif
KWKoh Tieng Wei
Koh Tieng Wei

5 January 2026 in IEEE Access
Verified
Journal Article
Open access
ZDZeyu Ding
Zeyu Ding
RYRazali Yaakob
Razali Yaakob
KWKoh Tieng Wei
Koh Tieng Wei
AAAzreen Bin Azman
Azreen Bin Azman
SRSiti Nurulain Mohd Rum
Siti Nurulain Mohd Rum
ANAzree Nazri
Azree Nazri
The lesions of tuberculosis (TB) in X-ray images are highly complex, exhibiting a variety of sizes, shapes, and structural variations. Single-scale features are insufficient to fully represent this diversity and complexity, thereby limiting the effectiveness of TB detection. As a result, multi-scale feature fusion has become a widely explored approach in the field of TB detection. However, current multi-scale feature fusion methods still have several limitations. First, the weight allocation in existing methods typically remains at the feature level without extending to local features and channels. This limitation prevents the model from precisely controlling the significance of local features and channels, resulting in coarse feature representations. Second, current methods neglect the contextual information between features at different levels, which further undermines the consistency of the fused features and leads to a lack of semantic coherence. To address the aforementioned issues, this study proposes TB-FusionNet, a multi-scale feature fusion algorithm based on channel and spatial cross-attention mechanisms, for tuberculosis classification. The algorithm first calculates the similarity between local features at different levels to precisely select low-level detail features that are closely related to high-level semantic features, thereby generating a more hierarchical feature representation. Next, the algorithm computes the dependencies between feature channels at different levels, allowing low-level channel features to be appropriately enhanced or suppressed under the guidance of high-level channels, effectively improving the semantic consistency between cross-level features. Through these operations, the model can dynamically adjust the weight distribution of local features and channels according to task requirements, thereby more flexibly adapting to the challenges of complex tasks. Experiments were conducted on the Shenzhen, Montgomery and HSAAS datasets in this study. The results demonstrate that the proposed method outperforms current state-of-the-art approaches, validating its effectiveness and robustness.