MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext Intelligent color vision system for ripeness classification of oil palm fresh fruit bunch

Fadilah N, Mohamad-Saleh J, Abdul Halim Z, Ibrahim H, Syed Ali SS

Sensors (Basel), 2012;12(10):14179-95.
PMID: 23202043 DOI: 10.3390/s121014179

Ripeness classification of oil palm fresh fruit bunches (FFBs) during harvesting is important to ensure that they are harvested during optimum stage for maximum oil production. This paper presents the application of color vision for automated ripeness classification of oil palm FFB. Images of oil palm FFBs of type DxP Yangambi were collected and analyzed using digital image processing techniques. Then the color features were extracted from those images and used as the inputs for Artificial Neural Network (ANN) learning. The performance of the ANN for ripeness classification of oil palm FFB was investigated using two methods: training ANN with full features and training ANN with reduced features based on the Principal Component Analysis (PCA) data reduction technique. Results showed that compared with using full features in ANN, using the ANN trained with reduced features can improve the classification accuracy by 1.66% and is more effective in developing an automated ripeness classifier for oil palm FFB. The developed ripeness classifier can act as a sensor in determining the correct oil palm FFB ripeness category.
Fulltext Using cascade CNN-LSTM-FCNs to identify AI-altered video based on eye state sequence

Saealal MS, Ibrahim MZ, Mulvaney DJ, Shapiai MI, Fadilah N

PLoS One, 2022;17(12):e0278989.
PMID: 36520851 DOI: 10.1371/journal.pone.0278989

Deep learning is notably successful in data analysis, computer vision, and human control. Nevertheless, this approach has inevitably allowed the development of DeepFake video sequences and images that could be altered so that the changes are not easily or explicitly detectable. Such alterations have been recently used to spread false news or disinformation. This study aims to identify Deepfaked videos and images and alert viewers to the possible falsity of the information. The current work presented a novel means of revealing fake face videos by cascading the convolution network with recurrent neural networks and fully connected network (FCN) models. The system detection approach utilizes the eye-blinking state in temporal video frames. Notwithstanding, it is deemed challenging to precisely depict (i) artificiality in fake videos and (ii) spatial information within the individual frame through this physiological signal. Spatial features were extracted using the VGG16 network and trained with the ImageNet dataset. The temporal features were then extracted in every 20 sequences through the LSTM network. On another note, the pre-processed eye-blinking state served as a probability to generate a novel BPD dataset. This newly-acquired dataset was fed to three models for training purposes with each entailing four, three, and six hidden layers, respectively. Every model constitutes a unique architecture and specific dropout value. Resultantly, the model optimally and accurately identified tampered videos within the dataset. The study model was assessed using the current BPD dataset based on one of the most complex datasets (FaceForensic++) with 90.8% accuracy. Such precision was successfully maintained in datasets that were not used in the training process. The training process was also accelerated by lowering the computation prerequisites.
Multiplex PCR for detection of Helicobacter pylori infection in gastric biopsies with lower inflammatory score

Fadilah N, Hanafiah A, Razlan H, Wong ZQ, Mohamed Rose I, Rahman MM

Br J Biomed Sci, 2016 Oct;73(4):180-187.
PMID: 27922429

BACKGROUND: No gold standard has yet been established for the diagnosis of H. pylori infection. A multiplex polymerase chain reaction (mPCR) was developed in this study for rapid, sensitive and specific detection of H. pylori from gastric biopsies.
METHODS: H. pylori infections were determined by in-house rapid urease test (iRUT), culture, histology and multiplex PCR.
RESULTS: A total of 140 (60.9%) from 230 patients were positive for H. pylori infection. H. pylori were detected in 9.6% (22/230), 17% (39/230), 12.6% (29/230) and 60% (138/230) of biopsy specimens by culture, iRUT, histology and mPCR, respectively. mPCR identified H. pylori infection in 100% of biopsies with positive histology and culture. All biopsies with positive iRUT yielded positive PCR except two cases. mPCR also detected H. pylori in additional 116, 101 and 109 biopsies that were negative by culture, iRUT and histology, respectively. Positive samples by mPCR showed lower average in H. pylori density, activity and inflammation scores. The Indians showed the highest prevalence of H. pylori infection compared to the Chinese and the Malays. In addition, Chinese patients with older age were significantly infected compared to other ethnicities.
CONCLUSION: PCR was able to detect the highest numbers of positive cases although the lowest average scores were recorded in the activity, inflammatory and H. pylori density.
Cytotoxic evaluation of biomechanically improved crosslinked ovine collagen on human dermal fibroblasts

Awang MA, Firdaus MA, Busra MB, Chowdhury SR, Fadilah NR, Wan Hamirul WK, et al.

Biomed Mater Eng, 2014;24(4):1715-24.
PMID: 24948455 DOI: 10.3233/BME-140983

Earlier studies in our laboratory demonstrated that collagen extracted from ovine tendon is biocompatible towards human dermal fibroblast. To be able to use this collagen as a scaffold in skin tissue engineering, a mechanically stronger scaffold is required that can withstand manipulation before transplantation. This study was conducted to improve the mechanical strength of this collagen sponge using chemical crosslinkers, and evaluate their effect on physical, chemical and biocompatible properties. Collagen sponge was crosslinked with 1-ethyl-3-(3-dimethylaminopropyl) carbodiimide (EDC) and glutaraldehyde (GA). Tensile test, FTIR study and mercury porosimetry were used to evaluate mechanical properties, chemical property and porosity, respectively. MTT assay was performed to evaluate the cytotoxic effect of crosslinked collagen sponge on human dermal fibroblasts. The FTIR study confirmed the successful crosslinking of collagen sponge. Crosslinking with EDC and GA significantly increased the mechanical strength of collagen sponge, with GA being more superior. Crosslinking of collagen sponge significantly reduced the porosity and the effect was predominant in GA-crosslinked collagen sponge. The GA-crosslinked collagen showed significantly lower, 60% cell viability towards human dermal fibroblasts compared to that of EDC-crosslinked collagen, 80% and non-crosslinked collagen, 100%. Although the mechanical strength was better when using GA but the more toxic effect on dermal fibroblast makes EDC a more suitable crosslinker for future skin tissue engineering.