Vikneswaran Vijean
Thumbnail Image
Preferred name
Vikneswaran Vijean
Official Name
Vijean, Vikneswaran
Alternative Name
Vikneswaran
Vikneswaran, V.
Vijean, V.
Main Affiliation
Scopus Author ID
54785424700
Researcher ID
D-2539-2015

Research Output

Filters

33
Reset filters

Settings
Now showing 1 - 10 of 33
  • Publication
    Recognition of plant diseases by leaf image classification using deep learning approach
    ( 2023-02-21)
    Goy S.Y.
    ;
    Chong Y.F.
    ;
    Teoh T.K.K.
    ;
    Lim Chee Chin
    ;
    Vikneswaran Vijean
    Plant health is important in maintaining the sustainability of the foods crop. The key to prevent the loss of yield of plant crops is the identification of plant diseases. The process of monitor plant health manually is challenging as it required expert knowledge which is expensive and time-consuming. Hence, the image processing techniques can be useful for the detection and classification of plant leaf disease. In this project, the leaf images of 5 plant types in the PlantVillage dataset are used for plant type and plant disease classification. The original images are resized to the required input sized and the proposed background removal methods (improved HSV and GrabCut segmentation) are performed to reduce the background noise. The segmented images are then given to proposed models (AlexNet and DenseNet121) for training and classification. For plant type classification, DenseNet121 got a better validation accuracy of 99% compared to AlexNet with 91.2%. After that, the leaf image is given to plant disease models according to their species. All the plant disease models training with DenseNet121 can achieve high validation accuracy of 99%, 99%, 100%, 100% and 97% for apple, grape, potato, strawberry and tomato. Lastly, a user-friendly graphical user interface (GUI) is developed.
  • Publication
    Cloud based analysis and classification of EEG signals to detect epileptic seizures
    ( 2021-03-25)
    Rushambwa M.C.
    ;
    Gezimati M.
    ;
    Govindaraj P.
    ;
    Palaniappan R.
    ;
    Vikneswaran Vijean
    ;
    Ghulam Nabi F.
    Epileptic seizures are explained as the abnormal electrical activity occurring in the brain due to an internal or external triggering factors. EEG (Electroencephalograph) is used to record brain activity and can be used to detect the seizures before, during or after they occur. These signal characteristics, however differ from patient to patient due to the different emotional and physical wellbeing of the various individuals. In normal circumstances, anti-epileptic medication is used to treat patients but very few systems have been developed to manage and track the seizures. In most extreme and rare cases, some patients undergo invasive surgery to treat the seizures and this is common in seizures that are caused by tumors or physical brain damage. Non-invasive surface electrode EEG measurement gives an estimate of the seizure onset but more invasive intracranial electrocorticogram (ECoG) are required at times for precise localization of the epileptogenic zone. This project aims at designing and implementing a device that can be used to detect and monitor the attention and meditation values of a person in real time. The system measures the EEG waves of the brain, performs feature extraction, classification and sends the control command over wireless to a remote controller. The remote controller in turn issues commands with corresponding brain wave frequency and sends it to the cloud for remote analysis and classification.
  • Publication
    Non-invasive Detection of Ketum Users through Objective Analysis of EEG Signals
    ( 2021-11-25)
    Nawayi S.H.
    ;
    Vikneswaran Vijean
    ;
    Ahmad Faizal Salleh
    ;
    Rashid R.A.
    ;
    Planiappan R.
    ;
    Lim C.C.
    ;
    Fook C.Y.
    ;
    Saidatul Ardeenawatie Awang
    Ketum leaves are traditionaly used for treatment of backpain and reduce fatigue. However, in recent years people use ketum leaves to substitute traditional drugs as they can easily be obtained at a low cost. Currently, a robust test for ketum detection is not available. Although ketum usage detection via test strip is available, however, the method is possible to be polluted by other substances and can be manipulated. Brain signals have unique characteristics and are well-known as a robust method for recognition and disease detection. Thus, this study has been done to distinguish between ketum users and non-users via brain signal characteristics. Eight participants were chosen, four of whom are heavy ketum users and four non-users with no health issues. Data were collected using the eegoSports device in relaxed state. In pre-processing, notch filter and Independent Component Analysis (ICA) were used to remove artifacts. Wavelet Packet Transform (WPT) was used to reduce the large data dimension and extract features from the brain signal. To select the most significant features, T-Test was used. Support Vector Machine (SVM), K-Nearest Neighbour, and Ensemble classifier were used to categorize the input data into ketum users and non-users. Ensemble classifier was found to be able to predict the testing instances with 100% accuracy for open and closed eyes task with Teager energy and energy to standard deviation ratio as the features.
  • Publication
    Intelligent fall detection system using traditional and non-traditional machine learning algorithm based on MQTT
    ( 2021-07-21)
    Cheong C.Y.
    ;
    Lim C.C.
    ;
    Chong Y.F.
    ;
    Vikneswaran Vijean
    ;
    Ahmad Faizal Salleh
    ;
    Affandi M.
    The population of elderly people exposed to the risk of fall increases each year as reported by World Health Organization (WHO). Fall detection system presented normally is high cost, large size and not efficient. Wearable-based sensor fall detection system developed in this project which were small size, portable and low-cost. The concept of Message Queuing Telemetry Transport (MQTT) applied in this fall detection system to ease the process of data transmission from motion sensor to Raspberry Pi for classification via Wi-Fi. A small size and lightweight microcontroller (Wemos D1 mini ESP 8266) integrated with MPU6050 motion sensor to sense and publish the motion data. Raspberry Pi 3 Model B applied to carry out classification of the motion data. Machine learning algorithms used for classification in comparison were k-Nearest Neighbors (k-NN) and Long Short-Term Memory (LSTM) of Recurrent Neural Network (RNN). LSTM achieved better result at 97% than k-NN at 94%. Smartphone used to publish the notification via an application known as Blynk.
  • Publication
    Bio-Char And Bio-Oil Production From Pyrolysis of Palm Kernel Shell And Polyethylene
    ( 2023-01-01)
    Ibrahim N.R.
    ;
    Razi Ahmad
    ;
    Wan Amiza Amneera Wan Ahmad
    ;
    Vikneswaran Vijean
    ;
    Ragunathan Al Santiagoo
    ;
    Syakirah Afiza Mohammed
    ;
    Khalid A.F.
    ;
    Ani A.Y.
    In recent years, palm kernel shell (PKS) has become a viable feedstock for making biofuels and value-added commodities using a variety of thermal conversion routes. Therefore, significant conservation is required for PKS as a resource for fuel production in biofuel facilities. Thus, this research was intended to elucidate the effects on PKS as a solid fuel through torrefaction and the production of bio-char and bio-oil by single and co-pyrolysis of PKS and polyethylene (PE). The PKS was treated through torrefaction at different temperatures and holding times. The optimum parameters for torrefaction were a temperature of 250 oC and a holding time of 60 min. Then the PKS and PE were pyrolyzed in a fixed-bed reactor at different temperatures and ratios. The product yield was analysed for single and co-pyrolysis of PKS and PE for pyrolysis. The properties of the product composition for single and co-pyrolysis of the PKS and PE were determined by proximate analysis, Fourier transform infrared (FTIR) analysis, and gas chromatography-mass spectrometry (GC-MS). The optimum parameter obtained for biochar and bio-oil production from co-pyrolysis of PKS and PE was at temperature of 500 oC at a ratio of 1:2 (PKS: PE). The ester and phenol compounds were increased around 19.02 to 23.18% and 32.51 to 34.80 %, respectively, while amide and amine decreased around 4.94 to 18.87% and 0.63 to 32.39 %, respectively, compared to the single pyrolysis of PKS. Therefore, the PKS and PE co-pyrolysis significantly increased the amount of phenol and ester compounds while slightly reducing the amount of amide and amine compounds in the bio-oil product. As a conclusion, biomass conservation enables the manufacturing of value-added chemicals.
  • Publication
    Compatibilizers Effect on Recycled Acrylonitrile Butadiene Rubber with Polypropylene and Sugarcane Bagasse Composite for Mechanical Properties
    ( 2023-10-16)
    Zainal M.
    ;
    Ragunathan Al Santiagoo
    ;
    Razi Ahmad
    ;
    Mohammed S.A.
    ;
    Abdul Ghapar Ahmad
    ;
    Vikneswaran Vijean
    ;
    Wan Amiza Amneera Wan Ahmad
    ;
    Allan Melvin Andrew
    Compatibilizers effect on recycled acrylonitrile butadiene rubber (NBRr) with polypropylene (PP) and sugarcane bagasse (SCB) composite for mechanical properties is evaluated. Trans-Polyoctylene Rubber (TOR) and Bisphenol a Diglycidyl Ether (DGEBA) are used as compatibilizers in this study. Three (3) different composites (80/20/15, 60/40/15, and 40/60/15), with fixed filler (15 phr) and compatibilizers (10 phr) content, were carried out. These composites were arranged via melt mixing technique utilizing a heated two-roll mill at a temperature of 180 C for 9 minutes employing a 15-rpm rotor speed. Tensile and morphological properties were evaluated. The result shown average tensile strength dropped by 48.50% as the recycle NBR content rises 20 phr. Nevertheless, subsequent compatibilization reveals that the compositesâ tensile properties were all greater than control composites. The morphology discovered validates the tensile properties, indicating a stronger interaction between the PP/SCB and recycle NBR composites with the addition of compatibilizer DGEBA.
  • Publication
    Potential of pretreated palm kernel shell on pyrolysis
    ( 2023-01-01)
    Razi Ahmad
    ;
    Ragunathan Al Santiagoo
    ;
    Abdul Ghapar Ahmad
    ;
    Syakirah Afiza Mohammed
    ;
    Wan Ahmad W.A.M.
    ;
    Vikneswaran Vijean
    ;
    Ibrahim N.R.
    The impact of pretreatment on palm kernel shell (PKS) with torrefaction for the possibility of pyrolysis is discussed in this study. PKS samples were torrefied at different holding times of 30 and 60 minutes at temperatures of 200, 225, 250, 275, and 300 °C. In a fixed-bed reactor with a constant nitrogen flow rate of 500 ml/min, torrefaction pretreatment was carried out. The elemental composition, mass, and energy yield, as well as proximate analysis, were all performed on the pretreated PKS. The optimised pretreated PKS was pyrolyzed next at a temperature of 400 to 550 °C in a fixed-bed reactor. The outcomes demonstrated that the pretreated PKS had a significant mass and energy yield at a temperature of 250 °C and a holding time of 30 min. PKS's calorific value and carbon content both rose after pretreatment. However, the oxygen and moisture content decreased for pretreated PKS. The maximum bio-oil production of 58% was achieved during the pyrolysis of pretreated PKS at a temperature of 500 °C. At higher temperature of 550 ℃, the bio-oil decreased due to secondary cracking reaction. Consequently, the pretreated PKS has greater potential as effective feedstock for successive proses particularly pyrolysis for bio-oil production.
  • Publication
    Review Article A Review of Optical Ultrasound Imaging Modalities for Intravascular Imaging
    ( 2023-01-01)
    Rushambwa M.C.
    ;
    Suvendi R.
    ;
    Pandelani T.
    ;
    Palaniappan R.
    ;
    Vikneswaran Vijean
    ;
    Nabi F.G.
    Recent advances in medical imaging include integrating photoacoustic and optoacoustic techniques with conventional imaging modalities. The developments in the latter have led to the use of optics combined with the conventional ultrasound technique for imaging intravascular tissues and applied to different areas of the human body. Conventional ultrasound is a skin contact-based method used for imaging. It does not expose patients to harmful radiation compared to other techniques such as Computerised Tomography (CT) and Magnetic Resonance Imaging (MRI) scans. On the other hand, optical Ultrasound (OpUS) provides a new way of viewing internal organs of the human body by using skin and an eye-safe laser range. OpUS is mostly used for binary measurements since they do not require to be resolved at a much higher resolution but can be used to check for intravascular imaging. Various signal processing techniques and reconstruction methodologies exist for Photo-Acoustic Imaging, and their applicability in bioimaging is explored in this paper.
  • Publication
    Comparison between predicted results and built-in classification results for brain-computer interface (BCI) system
    ( 2021-05-03)
    Ong Z.Y.
    ;
    Saidatul Ardeenawatie Awang
    ;
    Vikneswaran Vijean
    Brain-computer interface (BCI) system is a system of receiving information and transferring responses by communication between a computer and human brain. BCI system acts as assistive device to help the severe motor disabilities patients to live like a normal human being. Classification results used to validate the performances of BCI system. Several classification methods have been used in BCI system. However, previous researchers did not compare the classification results with predicted results. In this study, the predicted results were calculated from the questionnaire which collected from participants after completed the experiments. These predicted results were used to compare with the results from classification learner tool. The built-in classification methods included decision tree, support vector machine (SVM), k-nearest neighbor (KNN) and ensemble classifiers. Based on the results, the average difference of predicted results and built-in classification results for cubic SVM is the smallest which is 2.41% and 1.81% for motor imagery 1 and motor imagery 2 respectively. This finding shows that the cubic SVM classifier can detect the mistake that did by the subjects during the experiment.
  • Publication
    Discrimination of healthy controls and selected visually impaired through visually evoked potentials
    ( 2014)
    Vikneswaran Vijean
    This thesis presents a digital signal processing based detection of healthy controls and selected visually impaired through visually evoked potentials (VEP). Visual impairment is a term used by ophthalmologist to describe any kind of vision loss, whether it's partial or total vision loss. Some of the conventionally used techniques for the investigation of vision impairments include fundoscopy imaging, ultrasound imaging, and manual inspection of retina. These techniques have several disadvantages such as poor quality of images produced by the ultrasound imaging, require experts, and are prone to error in manual inspection. The VEP provides an objective method for the diagnostics of vision impairments in patients. VEP is an electrical signal generated by the brain (Occipital Cortex) in response to a visual stimulus. By analyzing these responses, the abnormalities in the visual pathways of a person can be detected. The development of feature extraction and classification algorithms for investigation of vision impairments through VEPs however is still at an infancy level. Therefore, this study was carried out to investigate the time, frequency, and time-scale/frequency characteristics of the single trial transient VEPs, and propose an efficient feature extraction and classification algorithm for distinguishing the vision impairments. Four different feature extraction methods based on time, frequency, wavelet, and Stockwell transform were explored and statistical features were proposed for the VEP analysis. A new feature augmentation technique was proposed to enhance the variation of the data prior to the analysis. Three different feature reduction techniques were used to reduce the dimensional space of the features. Extreme learning machine, least square support vector machine and probabilistic neural networks were employed to evaluate the performance of the features in discriminating the vision impairments. Statistical analysis were used to demonstrate the significance of the preprocessed features, while performance measures such as sensitivity, specificity, positive predictivity, negative predictivity, and overall accuracy was considered for the evaluation of the classifiers. The dataset from two different experimental settings were used in the analysis. The first experiment was conducted to investigate the effect of different sizes of checkerboard stimulus to the resulting evoked responses while the second experiment was perpetrated to investigate the performance of the new colour fusioned checkerboard stimulus in elicitating reliable VEP responses. The experimental investigation elucidate that features derived from the VEP elicited by the proposed stimulus performed well in classifying the vision impairments. Promising 100% accuracy was achieved using the combinations of the proposed stimulus and feature extraction methods.
      1  8