Noriah Othman

Principal component analysis for detection of NS1 molecules from Raman spectra of saliva

NS1 is an early biomarker for detection of flavivirus related diseases such as Japanese Encephalitis, Murray Valley Encephalitis, Tick-borne Encephalitis, West Nile Encephalitis, Dengue Fever and Yellow Fever. At present, it is detected in the infected blood serum through ELISA and immune-chromatographic lateral flow test. As a preliminary study, we are using PCA to extract NS1 feature from SERS spectra of NS1 adulterated saliva. NS1 characteristic peak at about 1000cm-1 is extracted by the most significant principal component, PC1. Using PCA adhoc stopping rules, data dimension is significantly reduced to more than 90% without losing important features from the original data. Furthermore, PCA score plots of the dataset is also showing clear separation between NS1 adulterated saliva and healthy saliva. This encouraging finding is suggesting the possibility to develop a SERS based automatic classification algorithm for detection of NS1 in saliva. Being a salivary based technique, this will lead to a novel, rapid, non-invasive and non-infectious detection method, dispense of problem arising from blood sampling.

PCA-SCG-ANN for detection of non-structural protein 1 from SERS salivary spectra

With non-structural protein (NS1) being acknowledged as biomarker for Dengue fever, the need to automate detection of NS1 from salivary surface enhanced Raman spectroscopic (SERS) spectra, with claim of sensitivity up to a single molecule thus become eminent. Choice for Principal Component Analysis (PCA) termination criterion and artificial neural network (ANN) topology critically affect the performance and efficiency of PCA-SCG-ANN classifier. This paper aims to explore the effect of number of hidden node for the ANN topology and PCA termination criterion on the performance of the PCA-SCG-ANN classifier for detection of NS1 from SERS spectra of saliva of subjects. The Eigenvalue-One-Criterion (EOC), Cumulative Percentage Variance (CPV) and Scree criteria, integrated with ANN topology containing hidden nodes from 3 to 100 are investigated. Performance of a total of 42 classifier models are examined and compared in terms of accuracy, precision, sensitivity. From experiments, it is found that EOC criterion paired with ANN topology of 13 hidden node outperforms the other models, with a performance of [Accuracy 91%, Precision 94%, Sensitivity 94%, Specificity 96%].

K-Nearest Neigbour: Detection of NS1 from SERS spectra of adulterated saliva

Use of SERS spectra to detect NS1 in saliva is a most current finding that could lead to early, non-invasive, non-blood infectious detection of diseases related to NS1. Since the volume of the SERS spectral data is humongous, hence an automated analysis technique to classify the NS1 adulterated samples is vital to the success of this method. K-Nearest Neighbor (K-NN) is a popular classifier that searches the space for k training records that are nearest to the new record as the neighbors of new records. Our work here intends to find an optimal k-NN classifier for detecting NS1 adulterated salivary samples from the SERS spectra. A total of 128 spectra, each with 1801 Raman shifts were analyzed. The performance of the k-NN classifier, in terms of accuracy, precision, sensitivity and specificity, at different values of nearest neighbour (k) were investigated. Results show that the value of nearest neighbour for the optimal k-NN classifier is between 1 to 11. The optimal k-NN classifier is strictly specific, 100% for all k, and highly sensitive, 89.5% for k between 1 to 11. It has a precision of 100% for all k and an accuracy of 92.3% for k between 1 to 11.

PCA-QDA Model Selection for Detecting NS1 Related Diseases from SERS Spectra of Salivary Mixtures

Of recent, non-structural protein (NS1) in saliva has emerged to be engaging as a detection biomarker for diseases related to NS1 at febrile stage. Non-invasive detection of NS1 in saliva, free from risk of blood infection, further will make the approach more preferred than the current serum based ones. Our work here intends to define an optimal classifier model for Quadratic Discriminant Analysis (QDA), optimized with Principal Component Analysis (PCA), to distinct between positive and negative NS1 adulterated samples from salivary SERS spectra. The adulterated samples are acquired from our UiTM-NMRR-12-1278-12868-NS1-DENV database. Then, PCA extracts significant features from the database after pre-processing, based on three stopping criteria, which are served as inputs to the QDA classifiers. It is found that the PCA-QDA pseudo model with 5, 70 and 115 principal components from the three criterion achieves performance of 100% (Scree), 84.2% (CPV) and 55.3% (EOC) in accuracy. Higher accuracy at 100% (Scree), 97.3684% (CPV) and 97.3684% (EOC) are observed with QDA diagonal model.

PCA-KNN for Detection of NS1 from SERS Salivary Spectra

K-Nearest Neighbor (kNN) has shown its strong capability in pattern recognition, classification and machine learning applications. In this paper, kNN was used to distinguish between Non-structural protein 1 (NS1) positive and NS1 negative dengue patients from salivary Raman spectra. The presence of NS1 was detected in the saliva of dengue infected subjects. It was found Raman active, producing a molecular Raman fingerprint. Surface Enhanced Raman Spectroscopic (SERS) technique was adopted in obtaining the NS1 Raman spectra dataset. Performance of kNN with different K-values, optimized with Scree, Cumulative Percentage Variance (CPV) and Eigenvalue One Criterion (EOC) stopping criteria, was investigated and compared in term of sensitivity, specificity, accuracy and kappa. The best performance is found with the use of CPV stopping criteria and a K-value of 5, which attained an accuracy of 84.5% and kappa of 0.69.

Students’ Experiential Learning in Botanic Garden Leisure Setting

Botanic garden is associated with environment conservation, outdoor recreation and education programme for students. The learning opportunities that take place in the garden functions as a window of knowledge, a platform to build better understanding beside aroused cognitive skills during visitation. This study is aimed to identify the potential of Putrajaya Botanical Garden as a learning environment. The finding showed the male respondents rated higher than the female in all attributes associated with experiential learning at the garden. With good practice of design and management, this garden can continuously serves as successful educational learning environment and achieve its mission. Keywords: Experiential learning; leisure setting; botanic garden; educational learning environment ISSN: 2398-4287

Detection of NS1 from SERS spectra using K-NN integrated with PCA

NS1 is said to be responsible for the reproduction of RNA virus of the flaviviridae family, which is the cause of variants of Encephalitis, Yellow Fever and Dengue Fever. As an antigen, it can be detected in the blood of an infected person, from or before the onset of the symptoms. This makes it a biomarker for early detection of these diseases recently. The K-NN is a non-parametric method that shows strong capability in pattern recognition, classification and machine learning. Here, the K-NN classifier is used to distinguish SERS spectra of the salivary adulterated NS1 samples from the controlled samples. Since the features of SERS spectra is of high dimension, the K-NN classifier is preceded by the PCA to remove the redundant features and noise with Scree Test criterion. The performance of the PCA K-NN classifier is then investigated, using K-values between 1 and 19. The best performance, i.e. accuracy, precision, sensitivity and specificity of 100%, is found with K-value of one to three.

Principal component analysis for detection of melamine adulterated milk products

Melamine is added to diluted milk to increase the nitrogen content confounding the protein concentration in milk. Milk adulterated with melamine can cause acute renal failure, kidneys damage and death. The presence of melamine in milk can be detected using Raman spectroscopy from its unique feature at 676cm-1 Raman shift. In this study, several samples of melamine adulterated milk are prepared in different forms to imitate the possibility on how melamine is illegally added into milk. Using Principal Component Analysis (PCA), dataset of milk and melamine adulterated milk dimension is reduced to several significant principal component which are highly correlated to the melamine and features. The presence of melamine in milk can be visually classified from PCA loading score plots and presented in this paper.

GIS in management of landscape trees: Determining, monitoring and implementing safety measures on potentially hazardous trees

Trees located in the vicinity public areas such as roadsides, recreation areas, and around building should be monitored regularly for structural weakness. Certain conditions can cause a tree to be structurally weakened so that parts or all of it are likely to collapse Landscape trees do not only contribute to the enhancement of scenery but might also become potential hazards risks if, there is no proper management. Nature elements such as heavy rains and strong winds could further increase risks thus endangering public safety and contributing to property damage. A proper management approach to monitor the maintenance of the landscape trees can help to reduce these risks. The development of an effective system for landscape tree management within University Technology MARA (UiTM) Shah Alam campus has been developed in this study. Potentially hazardous landscape trees were identified using the professional Arborist inventory. The condition of trees based on the tree hazard evaluation form modified from the International Society of Arborists (ISA). Geographical database was constructed that include tree location, species, and diameter breast height (DBH), condition, and growth recordings. It was also based on the inventory and later integrated into a system that can be used for the maintenance of trees. The identification of potentially hazardous trees is targeted along the roadside areas of the campus main entrance. They are to be used as a sampling unit in this Study. The selected trees include 61 Peltophorum pterocarpum spp, trees that were planted for over 30 years and that now pose a hazard due to their size, conditions and location of the trees along the road side. The Geographical Information System (GIS) was developed using Visual Basic (VB) software as user interface. The design of GIS software that allow user to capture manipulate and analyze spatial database give a significant help in assisting the documentation and decision making of potential hazard trees.