Browsing by Author "Chitraranjan, C"

Now showing 1 - 7 of 7

item: Conference-Full-text
An automated decision-making framework for precipitation-related workflows
(Faculty of Information Technology, University of Moratuwa., 2020-12) Adikari, AMH; Bandara, HMND; Herath, S; Chitraranjan, C; Karunananda, AS; Talagala, PD
Due to weather’s chaotic nature, static workflow managers are ineffective in integrating multiple Numerical Weather Models (NWMs) with cascading relationships. Unexpected events like flash floods and breakdown in canal water control systems or reservoirs make decision-making in workflow management further complicated. To enable dynamic decision-making, we need to update part or entire workflow, terminate unfitting NWM executions, and trigger parallel NWM workflows based on recent results from NWMs and observed conditions. Most of the existing weather-related decision support systems cannot trigger or create workflows dynamically. They are also designed for specific geography or functionality, making it challenging to customize for regions with different weather patterns. In this paper, we present an automated decision-making framework for precipitation-related workflows. The proposed framework can manage complex weather-related workflows dynamically in response to varying weather conditions, automatically control and monitor those workflows, and update workflow paths in response to unexpected weather events. Using significant flood-related datasets from the Colombo catchment area, we demonstrate that the proposed framework can achieve 100% accuracy in dynamic workflow generation and path updates compared to manual workflow controlling. Also, we demonstrate that unexpected event identification and pumping station controlling workflow triggers could be improved with advance rule sets.
item: Thesis-Full-text
Evaluation of VGG & ResNet very deep convolutional neural networks for detecting lung cancer in CT scans
(2018) Perera, WPHD; Chitraranjan, C
Lung cancer is the second most common destructive cancer in the world. It is important to detect Lung cancer at its earliest possible time because this dreadful illness spreads in a rapid pace weakening and killing the entire body of a human. The lung cancer identification process is not easy as its symptoms are visible to outside mostly at its final stage. Lung cancer nodules are detected by radiologists through CT (Computed tomography) scans, but there is a high probability to fail to spot where the actual lung cancer nodule is because, the lung lesions are low in contrast. Therefore, there should be a Computer Aided Diagnosis (CAD) system to assist radiologists in identifying lung nodules efficiently, accurately so the results given by the CAD systems can be taken as a second opinion to detect lung nodules for radiologists. Accurate CAD systems can improve the quality and productivity of radiologists’ image interpretation. There are many research subjects ongoing in medical imaging and diagnostic radiology. But it is needed to continuously improve the accuracy and the consistency of radiological diagnoses because still there are high false positive rates associated with CAD system results. Current CAD systems have been developed using two main different approaches. First is the conventional old framework which detects lung cancer nodules using manual feature extraction and conventional image preprocessing approach. New approach is the Deep Neural Network architecture which automatically and directly uncovers features from the training data. In this approach the three steps, feature extraction, selection and supervised classification have been realized within the optimization of the same deep architecture. This research evaluates two existing very deep learning architectures, Resnet-50 and VGG19 for learning high-level image representation to achieve high classification accuracy with low variance in medical image binary classification tasks. The classification accuracy was performed with two different datasets, NDSB and LUNA16+LIDC. For NDSB dataset the Restnet-50 model outperformed VGG19 model by giving the accuracy, sensitivity and specificity as 68%, 73%, 65% respectively. And for LUNA16+LIDC dataset 80.3%, 79.8%, 80.6% results were obtained for accuracy sensitivity and specificity out performing again the VGG19 network architecture.
item: Conference-Abstract
GI-Net: anomalies classification in gastrointestinal tract through endoscopic imagery with deep learning
Gamage, C; Wijesinghe, I; Chitraranjan, C; Perera, I
Recently, gastrointestinal(GI) tract disease diagnosis through endoscopic image classification is an active research area in the biomedical field. Several GI tract disease classification methods based on image processing and machine learning techniques have been proposed by diverse research groups in the recent past. However, yet effective and comprehensive deep ensemble neural network-based classification model is not available in the literature. In this research work, we propose to use an ensemble of deep features as a single feature vector by combining pre trained DenseNet-201, ResNet-18, and VGG-16 CNN models as the feature extractors followed by a global average pooling (GAP) layer to predict eight-class anomalies of the digestive tract diseases. Our results show a promising accuracy of over 97% which is a remarkable performance with respect to the state-of-the-art approaches. We analyzed how prominent CNN architectures that have appeared recently (DenseNet, ResNet, Xception, InceptionV3, InceptionResNetV2, and VGG) that can be used for the task of transfer learning. Furthermore, we describe a technique of reducing processing time and memory consumption while preserving the accuracy of the classification model by using feature extraction based on SVD.
item: Conference-Abstract
GI-Net: anomalies classification in gastrointestinal tract through endoscopic imagery with deep learning
Gamage, C; Wijesinghe, I; Chitraranjan, C; Perera, I
Recently, gastrointestinal(GI) tract disease diagnosis through endoscopic image classification is an active research area in the biomedical field. Several GI tract disease classification methods based on image processing and machine learning techniques have been proposed by diverse research groups in the recent past. However, yet effective and comprehensive deep ensemble neural network-based classification model is not available in the literature. In this research work, we propose to use an ensemble of deep features as a single feature vector by combining pre trained DenseNet-201, ResNet-18, and VGG-16 CNN models as the feature extractors followed by a global average pooling (GAP) layer to predict eight-class anomalies of the digestive tract diseases. Our results show a promising accuracy of over 97% which is a remarkable performance with respect to the state-of-the-art approaches. We analyzed how prominent CNN architectures that have appeared recently (DenseNet, ResNet, Xception, InceptionV3, InceptionResNetV2, and VGG) that can be used for the task of transfer learning. Furthermore, we describe a technique of reducing processing time and memory consumption while preserving the accuracy of the classification model by using feature extraction based on SVD.
item: Article-Full-text
Glioma survival analysis empowered with data engineering -A survey
(IEEE, 2021) Wijethilake, N; Meedeniya, D; Chitraranjan, C; Perera, I; Islam, M; Ren, H
Survival analysis is a critical task in glioma patient management due to the inter and intra tumor heterogeneity. In clinical practice, clinicians estimate the survival with their experience, which can be biased and optimistic. Over the past decades, diverse survival analysis approaches were proposed incorporating distinct data such as imaging and genetic information. The remarkable advancements in imaging and high throughput omics and sequencing technologies have enabled the acquisition of this information of glioma patients ef ciently, providing novel insights for survival estimation in the present day. Besides, in the past years, machine learning techniques and deep learning have emerged into the eld of survival analysis of glioma patients trading off the traditional statistical analysis-based survival analysis approaches. In this survey paper, we explore the prognostic parameters acquired, utilizing diagnostic imaging techniques and genomic platforms for survival or risk estimation of glioma patients. Further, we review the techniques, learning and statistical analysis algorithms, along with their bene ts and limitations used for prognosis prediction. Consequently, we highlight the challenges of the existing state-of-the-art survival prediction studies and propose future directions in the eld of research.
item: Thesis-Full-text
Recruit best candidates with machine learning
Selvantharajah, T; Chitraranjan, C
In this research, I propose a robust approach for predicting personality traits of job candidates using machine learning. Relationship between personality traits and job performance has been studied extensively during the past few decades and thus this relationship can be utilized to overcome limitations in choosing the right candidates. The proposed approach uses scenario-based analysis using machine learning techniques. Candidates will be asked to take part in scenario-based written conversations and their personality traits will be extracted from these conversations using machine learning techniques. Exacted personality traits of the candidates will be compared with the required job related characteristics in order to evaluate the fitness for the position for which candidates are applying. In order to categorize personality traits of candidates, the Five Factor model is used. Existing methods of evaluating personality traits such as standard set of questionnaires are susceptible to candidates providing false information and also time consuming. Besides candidates’ qualifications, knowledge and experience, candidates’ personality traits also used to rank the candidates and shortlist them for face-to-face interviews. Thus, this technique not only allows recruiting right candidates to right position but also reduces significant amount of time and cost spent on evaluating candidates’ suitability for given a job position by reducing the number of interviews to conduct. Further, this proposed system can be incorporated into existing e-recruitment system thus leveraging its effectiveness. Therefore, it is beneficial for companies since the proposed system helps to reduce cost and time consumption in the recruitment process while assisting them to choose more suitable candidates for a particular job position.
item: Thesis-Abstract
Vision-based forward collision warning application for vehicles
(2023) Rajakaruna, PNSA; Chitraranjan, C
Driver Assistance Systems (DAS) have become an important part of vehicles, and there is a considerable amount of research in this area. Most accidents happen due to driver inattention caused by driver distraction and drowsiness. Driver Assistance Systems aim to minimize these conditions and increase road safety. Vision-based driver assistance plays a major role in DAS, where camera-based collision warning stands out as one of the most effective and accurate types. Our implementation is a collision warning system that utilizes a single monocular camera and performs 3D vehicle detection for better accuracy and performance. It is a low-cost, near real-time collision warning system that can be implemented on both new and old vehicles. For 2D vehicle detection, we employ YOLO, and then we estimate 3D bounding boxes based on the 2D bounding boxes. To track the vehicles, we use the Deep SORT algorithm. The application will generate a Birds Eye View (BEV) graph based on the 3D bounding box estimation. This BEV graph will represent a much more accurate position and orientation for vehicles in a 3D plane. Based on this data, the collision prediction algorithm will determine the possibility of a collision and output a warning signal. The collision prediction algorithm relies on the distance between the vehicle with the camera and other vehicles in each frame.