Sin Ting Lim

Sin Ting Lim

orcid

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
29 January 2026 in Forests
Verified
Journal Article
Open access
PDF file
ABDULRAHMAN SUFYAN TAHA MOHAMMED AL-DAERIABDULRAHMAN SUFYAN TAHA MOHAMMED AL-DAERI
ABDULRAHMAN SUFYAN TAHA MOHAMMED AL-DAERI
YCYee Kit Chan
Yee Kit Chan
SLSin Ting Lim
Sin Ting Lim
MRMohamad Razmil Bin Abdul Rahman
Mohamad Razmil Bin Abdul Rahman
Mapping individual-tree crowns (ITCs) along with extracting tree morphological attributes provides the core parameters required for estimating thermal stress and carbon emission functions. However, calculating morphological attributes relies on the prior delineation of ITCs. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) framework, this review synthesizes how deep-learning (DL)-based methods enable the conversion of crown geometry into reliable biometric parameter extraction (BPE) from high-resolution imagery. This addresses a gap often overlooked in studies focused solely on detection by providing a direct link to forest inventory metrics. Our review showed that instance segmentation dominates (approximately 46% of studies), producing the most accurate pixel-level masks for BPE, while RGB imagery is most common (73%), often integrated with canopy-height models (CHM) to enhance accuracy. New architectural approaches, such as StarDist, outperform Mask R-CNN by 6% in dense canopies. However, performance differs with crown overlap, occlusion, species diversity, and the poor transferability of allometric equations. Future work could prioritize multisensor data fusion, develop end-to-end biomass modeling to minimize allometric dependence, develop open datasets to address model generalizability, and enhance and test models like StarDist for higher accuracy in dense forests.

30 April 2024 in International Journal on Robotics, Automation and Sciences
Verified
Journal Article
Open access
PDF file
WLWay-Soong LIM
Way-Soong LIM
DLDesmond Ji Kang Lai
Desmond Ji Kang Lai
SLSin Ting Lim
Sin Ting Lim
Boon Chin YeoBoon Chin Yeo
Boon Chin Yeo
Being known as a nutrient-dense food, eggs are high in demand in the marketplace and high-quality eggs are much sought-after. Hence, egg grading is in place to sort eggs into different grades. Experienced graders are required for their knowledge to classify egg grades and as humans are involved, errors when performing manual grading are unavoidable. This study aims to develop a vision-based egg classification system that requires minimal human intervention. The proposed system houses a camera to acquire real-time images of the eggs and these images are served as the input to the algorithm. Based on the 6 geometrical features derived from the geometric parameters of the egg image, the eggs are classified using Support Vector Machine (SVM). The experiment results show the proposed egg grading system with a linear kernel SVM model can yield as high as 92.59% training accuracy.

4 May 2026 in Cogent Engineering
Verified
Journal Article
Open access
LTLi Wah Thong
Li Wah Thong
RTRobin Tan
Robin Tan
SLSin Ting Lim
Sin Ting Lim
FSFahmidul Huq Syed
Fahmidul Huq Syed
SMSharmeeni Murugan
Sharmeeni Murugan

3 October 2025 in Edelweiss Applied Science and Technology
Verified
Journal Article
Open access
PDF file
TXTan Wei Xiang
Tan Wei Xiang
SLSin Ting Lim
Sin Ting Lim
KCKoo Voon Chet
Koo Voon Chet
LSLim Way Soong
Lim Way Soong
This study presents the design and development of an automated apple quality classification and sorting system to overcome key limitations of manual grading, such as inconsistency, inaccuracy, and labor dependency. The primary objectives are to detect and classify fruit quality based on visual parameters such as color, shape, and defects, and to employ a robotic arm that autonomously sorts the apples into predefined quality categories based on the classification results. A YOLOv8 segmentation model was trained and deployed on a Raspberry Pi 4 Model B to perform real-time classification of apples as good or bad. Further analysis using OpenCV was applied to good apples by evaluating red color ratio and fruit size (height and width) to determine premium or standard grade. The hardware setup includes a PiCamera for image capture and servo motors for sorting and rotating apples to support both single-side and multiple-side detection modes. The YOLOv8 system achieved a mean average precision (mAP) of 96.56%. Hardware testing demonstrated improved classification accuracy from 97% using single-side detection to 100% using multiple-side detection across 60 apple samples. A Tkinter-based graphical user interface (GUI) was developed to allow users to control detection modes, view classification outcomes, and monitor sorting actions in real time. This system offers a low-cost and scalable solution for automated fruit sorting. Its adaptability to multiple detection angles and integration with physical sorting mechanisms make it a practical option for small-scale agricultural automation and research environments.

30 July 2025 in International Journal on Robotics, Automation and Sciences
Verified
Journal Article
Open access
PDF file
SLSin Ting Lim
Sin Ting Lim
SPShawn Pereira
Shawn Pereira
LTLi Wah Thong
Li Wah Thong
TKTetuko Kurniawan
Tetuko Kurniawan
This study aims to enhance security by implementing a smart surveillance robot using existing facial recognition technology. The developed robot is equipped with the HUSKYLENS AI vision sensor camera and an ESP32 CAM module to provide a real-time video feed to a connected computer via Wi-Fi. The results demonstrate the successful integration of facial recognition technology into the surveillance robot's functionality. The robot exhibits an acceptable ability to identify and track intruders, underscoring its potential for enhancing security applications. The robot features a height of 12 cm, a width spanning 11.5 cm, a length measuring 19 cm, and a weight totalling 1.3 kg. Operating on a basic configuration of two main wheels, the robot forms a two-wheeled system with three degrees of freedom (DOF). The developed robot demonstrates an ability to identify and track intruders with a tested accuracy of 77.5%, precision of 80%, specificity of 79%, and sensitivity of 76.1%. The compact and low-profile design enables it to operate discreetly in diverse environments, making it particularly well-suited for scenarios where inconspicuous surveillance is needed.