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

32
32
Reset filters

Settings
Now showing 1 - 10 of 32
  • Publication
    Assessments of cognitive state of Mitragyna speciosa (ketum) users during relaxation state
    ( 2023-02-21)
    Fadhilah A.W.
    ;
    Vikneswaran Vijean
    ;
    Ahmad Faizal Salleh
    ;
    Rashid R.A.
    ;
    Palaniappan R.
    ;
    Mutusamy H.
    ;
    Helmy K.
    The abuse of Mitragyna speciosa or commonly known as ketum leaves is widespread across Asian countries. Ketum leaves that were originally used as medicine were abused for the purpose of deluding their minds. As it has intoxicated properties that similar to drugs, EEG signals of ketum users may differ from normal people as the ketum may alter the brain signal and the cognitive state of ketum users may decrease. Therefore, this study was conducted to assess the cognitive state between ketum users and non-ketum users in terms of their relaxation state by using brain signal characteristics. A total of 8 subjects were involved in the experimental session. The 8 subjects were divided into two groups which are 4 subjects were ketum users for at least one year while the other 4 subjects were non-ketum users, had enough sleep for at least 6 hours and had no mental disorders. The EEG data was recorded during awaken relaxed state and was filtered using a notch filter and Independent Component Analysis (ICA) to remove the powerline artefacts, eye blinking and eye movement. Stockwell Transform was used to reduce the amount of the large data and extract useful features from the signal. Student's t-test is performed in order to compute the percentages of the differences between the ketum users and non-ketum users in each brain lobe. Mean of Shannon Entropy, mean of Tsallis Entropy, and mean of Hurst Exponent features used were able to elucidate the differences in brain activities between the two groups investigated.
  • Publication
    Data Acquisition System for Web-based Multi-modal Data Repository
    ( 2021-03-25)
    Rushambwa M.C.
    ;
    Mukherjee A.
    ;
    Maity M.
    ;
    Palaniappan R.
    ;
    Vikneswaran Vijean
    ;
    Ghulam Nabi F.
    The multimodal medical data with annotation helps to build different automated algorithms. Each reported work has used a specific disease database and developed a CAD based on the considered database. Therefore, the availability and quality of medical database play the most crucial role in developing any CAD. However, it has been observed that most of the reported studies used public database (created by foreign universities/centers) or private database. Unfortunately, the availability of a national medical database in India is negligible. However, development of such medical database is possible. Such medical database can encourage new research activity and help a large research community. The proposed study focuses on developing an online public medical multimodal database platform. Here, the data acquisition software is build for collecting various information.
  • Publication
    DT-CWPT based Tsallis Entropy for Vocal Fold Pathology Detection
    ( 2020-10-26)
    Farah Nazlia Che Kassim
    ;
    Vikneswaran Vijean
    ;
    Muthusamy H.
    ;
    Abdullah Z.
    ;
    Rokiah Abdullah
    ;
    Palaniappan R.
    The study of voice pathology has become one of the valuable methods of vocal fold pathology detection, as the procedure is non-invasive, affordable and can minimise the time needed for the diagnosis. This paper investigates the Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) based Tsallis entropy for vocal fold pathology detection. The proposed method is tested with healthy and pathological voice samples from Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database and Saarbruecken Voice Database (SVD). A pairwise classification using k-Nearest Neighbors (k-NN) classifier gave 91.59% and 85.09% accuracy for MEEI and SVD database respectively. Higher classification accuracy of 93.32% for MEEI and 85.16% for SVD database achieved using Support Vector Machine (SVM) classifier.
  • Publication
    Investigation on effect of gas concentration in distinguishing conventional plastic and bioplastic for plastic recycling
    ( 2022-12)
    Ragunathan Al Santiagoo
    ;
    Allan Melvin Andrew
    ;
    Wan Amiza Amneera Wan Ahmad
    ;
    Razi Ahmad
    ;
    Syakirah Afiza Mohammed
    ;
    Abdul Ghapar Ahmad
    ;
    Vikneswaran Vijean
    ;
    Mustaffa Zainal
    Distinguishing type of plastic was important for the recycling process. In this project, the effect on gas concentration released from composite was studied to distinguish between conventional plastic and bioplastic. This project involved the fabrication of a composite from polypropylene (PP), empty fruit bunches (EFB), and recycle acrylonitrile butadiene rubber (NBRr), with PP used as a conventional plastic and PP/NBRr/EFB used as a bioplastic. Trans-polyctylene (TOR) was used as a compatibilizer to evaluate the effect on the PP/NBRr/EFB. Tensile testing and SEM were conducted to study the mechanical properties and morphological properties on the PP/NBRr/EFB and the PP/NBRr/EFB/TOR composite. The gas sensor (MQ135) was used in this study to detect the presence of NH3 and CO2 released from heating conventional plastic and bioplastic. From the overall result, composite with TOR as compatibilizer has shown better performance than composite without TOR in mechanical, morphological and gas sensor testing. By using MATLAB software, it shows that from gas sensor testing, it can be verified to distinguish between conventional plastic and bioplastics for plastic recycling. The average classification obtained from the Probabilistic Neural Network (PNN) was 99.29 % accurate.
  • 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
    Optimization of dual-tree complex wavelet packet based entropy features for voice pathologies detection
    ( 2020-07-01)
    Farah Nazlia Che Kassim
    ;
    Vikneswaran Vijean
    ;
    Abdullah Z.
    ;
    Muthusamy H.
    ;
    Rokiah Abdullah
    The Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) has been successfully implemented in numerous field because it introduces limited redundancy, provides approximately shift-invariance and geometrically oriented signal in multiple dimensions where these properties are lacking in traditional wavelet transform. This paper investigates the performance of features extracted using DT-CWPT algorithms which are quantified using k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM) classifiers for detecting voice pathologies. Decomposition is done on the voice signals using Shannon and Approximate entropy (ApEn) to signify the complexity of voice signals in time and frequency domain. Feature selection methods using the ReliefF algorithm and Genetic algorithm (GA) are applied to obtain the optimum features for multiclass classification. It is observed that the best accuracies obtained using DT-CWPT with ApEn entropy are 91.15 % for k-NN and 93.90 % for SVM classifiers. The proposed work provides a promising detection rate for multiple voice disorders and is useful for the development of computer-based diagnostic tools for voice pathology screening in health care facilities.
  • Publication
    Clinical validation of 3D mesh reconstruction system for spine curvature angle measurement
    ( 2023-02-21)
    Shanyu C.
    ;
    Lim Chee Chin
    ;
    Fook C.Y.
    ;
    Azizan A.F.
    ;
    Vikneswaran Vijean
    ;
    Ahmad Faizal Salleh
    ;
    Shafriza Nisha Basah
    Spine curvature disorders are scoliosis, lordosis, and kyphosis. These disorders are mainly caused by the bad habits of the person during sitting, standing, and lying. There are about 3 to 5 out of 1,000 people who are affected by spine curvature disorder. The current conventional method used for diagnose this disorder, such as radiography, goniometry and palpation. However, these conventional methods require human skills and can be time-consuming, resulting to exhaustion of logistic. Therefore, there is a need to solve this problem by creating a Graphical User Interface (GUI) to analyse the human body posture through the 3D reconstructed model of the person. Hence, 3D map meshing reconstruction of the human body method is proposed. This project divided into three parts, which are the development of the GUI for human posture analysis, clinical validation and posture analysis of the 3D model. The 3D model reconstructed from 3D mapping parameters shows 100% accuracy of the assessed point. The lowest difference of angle for the comparison between clinical method (goniometer) and the GUI for male is (A.Pe) 0.930±0.870 and 1.240±0.860 for female (P.Pe). This finding of 3D model assessment system can be helpful for medical doctor to diagnose patient who have spine problem.
  • Publication
    Differential diagnosis tool in healthcare application using respiratory sounds and convolutional neural network
    ( 2023-08-03)
    Palaniappan R.
    ;
    Sundaraj K.
    ;
    Nabi F.G.
    ;
    Vikneswaran Vijean
    This chapter focuses on the classification of respiratory pathology using breathsound signals. The development of a computerised breath-sound analysis system could improve the standard of living of people affected by respiratory-related disease and further also be used as a differential diagnosis tool in affective computing. Accordingly, in this chapter, respiratory sounds recorded according to the Computerised Respiratory Sound Acquisition standard were obtained from subjects with respiratory sounds belonging to five different respiratory pathologies, namely, normal, wheezes, rhonchi, fine crackles, and coarse crackles.
  • 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
    Traffic Sign Classification for Road Safety using CNN
    ( 2024-01-01)
    Haree Krishna P.
    ;
    Ravindran S.
    ;
    Vikneswaran Vijean
    In today's life, Traffic sign identification is a significant domain of environment awareness system. This traffic sign identification is becoming a top priority for modern transportation systems as it is highly essential to maintain the road safety nowadays. While detecting the traffic signs using various target detection techniques, many real-time problems are being faced like easy omission, undesirable light, inaccurate positioning for traffic signs (during detection), disorientation, motion blur, color fade, occlusion, rain, and snow. In view of these problems that the traffic signs cannot be recognized well, many novel target detection technologies are emerging, which in-turn solves these problems. This article introduces a reliable traffic sign categorization system, with the help of OpenCV for image enhancement and a five-layered Convolution Neural Network. The significance of sophisticated traffic sign identification for preventing accidents and promoting road safety is emphasized by this research that classifies traffic signs. The proposed CNN model has proved to achieve a remarkable classification accuracy and flexibility in response to changes in sign and environment, as demonstrated by the outcomes of the experiments. The strength of the proposed model has been tested on the German Traffic Sign Dataset and the experimental results have unfolded the fact that this model has recognized German traffic signs, with a better classification accuracy of 97.3%.