Feng Lin

Prof. Dr. Feng Lin

School of Computer Engineering, Nanyang Technological University, N4-2A-05, Nanyang Avenue, Singapore 639798, Singapore
orcid

Research Focus & Metrics

Academic Career Length

30Years (1997-Present)

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

Representative Publications

View All Publications
12 January 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MLMei Chee Leong
Mei Chee Leong
Dilip K. PrasadDilip K. Prasad
Dilip K. Prasad
YLYong Tsui Lee
Yong Tsui Lee
Feng LinFeng Lin
Feng Lin
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is to fuse the convolution layers from 2D and 3D CNNs to allow temporal encoding with fewer parameters than 3D CNNs. We adopt transfer learning from pre-trained 2D CNNs for spatial extraction, followed by temporal encoding, before connecting to 3D convolution layers at the top of the architecture. We construct our fusion architecture, semi-CNN, based on three popular models: VGG-16, ResNets and DenseNets, and compare the performance with their corresponding 3D models. Our empirical results evaluated on the action recognition dataset UCF-101 demonstrate that our fusion of 1D, 2D and 3D convolutions outperforms its 3D model of the same depth, with fewer parameters and reduces overfitting. Our semi-CNN architecture achieved an average of 16–30% boost in the top-1 accuracy when evaluated on an input video of 16 frames.

30 May 2025 in Communications Biology
Verified
Journal Article
Open access
PDF file
SJShuwen Jin
Shuwen Jin
ZZZihan Zeng
Zihan Zeng
XXXiyan Xiong
Xiyan Xiong
BHBaicheng Huang
Baicheng Huang
LTLi Tang
Li Tang
Feng LinFeng Lin
Feng Lin
The rapid advancement of artificial intelligence (AI) has enabled de novo design of functional proteins, circumventing the reliance on natural templates or sequencing databases. However, current protein design models are ineffective in generating proteins without stable structures, such as antimicrobial peptides (AMPs), which are short and structurally flexible yet play critical biological roles. To address this challenge, we present AMPGen, an evolutionary information-reserved and diffusion-driven generative model for de novo design of target-specific AMPs. AMPGen innovates AI tools, including a generator, a discriminator, and a scorer, along with biochemical knowledge-based screening programs. The generator employs a pre-trained, order-agnostic autoregressive diffusion model, which performs axial attention to capture protein evolutionary information from multiple sequence alignments (MSAs). The AMP-MSA conditional input raises the success rate of generated AMPs, which are subsequently filtered based on physicochemical properties and assessed by an XGBoost-based discriminator. The final target-specific scoring is performed with an LSTM-based scorer, resulting in high-quality AMP candidates. In this study, of the 40 de novo designed AMP candidates for verification, 38 were successfully synthesized, and among them, 81.58% demonstrated antibacterial activity. These AMPs designed by AMPGen are absent from existing AMP databases, and exhibit high antibacterial capacity, sequence diversity, and broad-spectrum activity.

8 December 2014 in BMC Bioinformatics
Verified
Journal Article
Open access
YKYadav Kuleesha
Yadav Kuleesha
WPWee Choo Puah
Wee Choo Puah
Feng LinFeng Lin
Feng Lin
MWMartin Wasser
Martin Wasser
Background: During metamorphosis in Drosophila melanogaster, larval muscles undergo two different developmental fates; one population is removed by cell death, while the other persistent subset undergoes morphological remodeling and survives to adulthood. Thanks to the ability to perform live imaging of muscle development in transparent pupae and the power of genetics, metamorphosis in Drosophila can be used as a model to study the regulation of skeletal muscle mass. However, time-lapse microscopy generates sizeable image data that require new tools for high throughput image analysis. Results: We performed targeted gene perturbation in muscles and acquired 3D time-series images of muscles in metamorphosis using laser scanning confocal microscopy. To quantify the phenotypic effects of gene perturbations, we designed the Fly Muscle Analysis tool (FMAj) which is based on the ImageJ and MySQL frameworks for image processing and data storage, respectively. The image analysis pipeline of FMAj contains three modules. The first module assists in adding annotations to time-lapse datasets, such as genotypes, experimental parameters and temporal reference points, which are used to compare different datasets. The second module performs segmentation and feature extraction of muscle cells and nuclei. Users can provide annotations to the detected objects, such as muscle identities and anatomical information. The third module performs comparative quantitative analysis of muscle phenotypes. We applied our tool to the phenotypic characterization of two atrophy related genes that were silenced by RNA interference. Reduction of Drosophila Tor (Target of Rapamycin) expression resulted in enhanced atrophy compared to control, while inhibition of the autophagy factor Atg9 caused suppression of atrophy and enlarged muscle fibers of abnormal morphology. FMAj enabled us to monitor the progression of atrophic and hypertrophic phenotypes of individual muscles throughout metamorphosis. Conclusions: We designed a new tool to visualize and quantify morphological changes of muscles in time-lapse images of Drosophila metamorphosis. Our in vivo imaging experiments revealed that evolutionarily conserved genes involved in Tor signalling and autophagy, perform similar functions in regulating muscle mass in mammals and Drosophila. Extending our approach to a genome-wide scale has the potential to identify new genes involved in muscle size regulation.

30 November 2018 in Sensors
Verified
Journal Article
Open access
PDF file
CLCunguang Lou
Cunguang Lou
CPChenyao Pang
Chenyao Pang
CJCongrui Jing
Congrui Jing
SWShuo Wang
Shuo Wang
XHXufeng He
Xufeng He
HWHongrui Wang
Hongrui Wang
The center of plantar pressure (COP) reflects the dynamic balance of subjects to a certain extent. In this study, wearable pressure insoles are designed, body pose measure is detected by the Kinect sensor, and a balance evaluation system is formulated. With the designed games for the interactive actions, the Kinect sensor reads the skeletal poses to judge whether the desired action is performed, and the pressure insoles simultaneously collect the plantar pressure data. The COP displacement and its speed are calculated to determine the body sway and the ability of balance control. Significant differences in the dispersion of the COP distribution of the 12 subjects have been obtained, indicating different balancing abilities of the examined subjects. A novel assessment process is also proposed in the paper, in which a correlation analysis is made between the de facto sit-to-stand (STS) test and the proposed method; the Pearson and Spearman correlations are also conducted, which reveal a significant positive correlation. Finally, four undergraduate volunteers with a right leg sports injury participate in the experiments. The experimental results show that the normal side and abnormal side have significantly different characters, suggesting that our method is effective and robust for balance measurements.

22 November 2007 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
MRMenaka Rajapakse
Menaka Rajapakse
BSBertil Schmidt
Bertil Schmidt
Feng LinFeng Lin
Feng Lin
VBVladimir Brusic
Vladimir Brusic
Peptides binding to Major Histocompatibility Complex (MHC) class II molecules are crucial for initiation and regulation of immune responses. Predicting peptides that bind to a specific MHC molecule plays an important role in determining potential candidates for vaccines. The binding groove in class II MHC is open at both ends, allowing peptides longer than 9-mer to bind. Finding the consensus motif facilitating the binding of peptides to a MHC class II molecule is difficult because of different lengths of binding peptides and varying location of 9-mer binding core. The level of difficulty increases when the molecule is promiscuous and binds to a large number of low affinity peptides.

10 July 2007 in Journal of Signal Processing Systems
Verified
Journal Article
Closed access
PDF file
MSMaria Stepanova
Maria Stepanova
Feng LinFeng Lin
Feng Lin
VLValerie Chun Ling Lin
Valerie Chun Ling Lin