https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4123 Sat, 04 Apr 2026 10:44:10 GMT 2026-04-04T10:44:10Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4775 Title: An Intelligent Traffic Modeling Framework for Managing the Effects of Abrupt Perturbations in order to Prevent Imbalance Leading to Chaos Authors: Rakkesh, S.T. Abstract: Abstract Vehicular traffic congestion continues to remain a critical problem in most urban cities around the world, especially in developing countries. This results in increased delays, driver stress, fuel consumption, air pollution and road accidents. Solutions to this problem have evolved over the years. Initially, the approach was based on the construction of alternative road infrastructure with increased capacity. However, available funds and territorial limitations have proved to be too formidable for continuing the implementation of such solutions. In parallel, traffic lights and roundabouts were introduced in congested intersections, but the increased growth trends of inhabitance in urban cities now demand more advanced and efficient alternative measures to simply augmenting the existing infrastructure. This has paved way for numerous unconventional approaches to be explored by the research community on the field of traffic. Accidents and unexpected roadblocks can occur anytime in a traffic environment. These abrupt external events usually lead the traffic environment to an imbalanced state and result in subsequent congestions formation and chaos around the region where the perturbation has occurred, especially in urban cities of developing nations. This kind of unanticipated incidents often leads to the build-up of long queues of vehicles in urban cities of Sri Lanka due to subsequent congestions formation and sometimes ending in a severe chaos situation. Since traffic environments are highly dynamic and distributed in nature, any solution to solve this unique traffic related problem should also address this dynamicity by vigorously adapting to the changes. Intelligent transportation systems (ITS) have been playing a crucial role in providing excellent solutions for complex traffic problems since last decade onwards. As an emerging new form of wireless networks, vehicular ad-hoc networks (VANETs) have become the trend setter in ITS solutions. VANETs support a large spectrum of decentralized vehicular applications ranging from traffic light optimization solutions to anticipatory vehicular re-routing strategies ensuring contingency in highly volatile situations. Usually, VANET solutions target to build a distributed inter-vehicular communication (IVC) network by extending the in-vehicle communication interfaces which are already available in present-day vehicles. Due to its flexible architectural design principles, VANET is one of the popular choices of x communication strategies used by researchers to build distributed, autonomous and cost-efficient traffic solutions. A unique ITS solution is presented in this dissertation using VANET’s principles to tolerate unanticipated abrupt perturbations which can occur in any traffic environments due to accidents or roadblocks and settle the environment back to an equilibrium state within a reasonable time, preventing subsequent congestions formation and possible escalation into severe chaos. Also, various in-vehicle and inter-vehicular communication strategies have been extensively analyzed and miscellaneous simulation techniques to replicate both microscopic vehicular movements and inter-vehicular communication dynamics discussed in this thesis. The re-routing strategy devised from the study, the proposed VANET solution encompassing multi-faceted vehicle to everything (V2X) communication model and the bidirectionally coupled simulation framework to evaluate both microscopic mobility simulations and the corresponding network level simulations in a synchronized fashion are the core novel scientific contributions of the research work illustrated in this dissertation. Sun, 01 Jan 2023 00:00:00 GMT https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4775 2023-01-01T00:00:00Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4774 Title: A Study on the Cognitive Complexity Metric of a Software Authors: Wijendra, D. R. Abstract: Abstract The cognitive complexity of a software determines the effort required to understand its source code logic. It can be used to indicate understandability and maintainability, which are predominant quality attributes in software development process. Further, personal profile and source code factors can be stated as major factors associated with cognitive complexity. The inclusion of personal profile results cognitive complexity to be a subjective measurement. However, traditional methods of expressing cognitive complexity are limited only to source code factors to express it as an objective measurement. Moreover, a methodology of relating cognitive complexity to indicate understandability and maintainability cannot be observed. As such, this work has studied the mechanisms of applying cognitive complexity in software development and maintenance processes effectively. Accordingly, the procedures of reducing cognitive complexity to improve understandability and maintainability have been introduced. Expression of cognitive complexity by giving more impact in personal profile is a significant achievement of this research work. The usage of software requirements, its logical diagrams, defects tracing, code quality optimization and refactoring have been introduced as cognitive complexity reduction mechanisms. Those mechanisms have been designed using a computational aid. A meaningful cognitive complexity metric has also been introduced to quantitatively indicate cognitive complexity by considering both personal profile and source code factors. The personal factor involvement of the metric has been introduced using a subjective cognitive weight. The components of reducing cognitive complexity have been evaluated with the duration taken to understand a source code. Accordingly, significant duration reduction has been obtained from proposed components comparing to the current practices to process same scenarios. Therefore, the possibility of proposed mechanisms to gain a less comprehension effort and to achieve a less cognitive complexity can be verified. The proposed cognitive complexity metric has been practically and empirically verified through standard software metric frameworks to prove its stability in real applications. Hence, together with the design to attain a lesser cognitive complexity and the metric to quantitatively indicate the subjective user comprehension effort can be used as significant appliances in software engineering. Keywords: cognitive complexity, cognitive complexity metric, cognitive load, cognitive weight, maintainability, subjectivity, understandability Sun, 01 Jan 2023 00:00:00 GMT https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4774 2023-01-01T00:00:00Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4773 Title: Extracting Common Signatures To Classify Human Nervous System Cancer Data with Bioinformatics Approaches Authors: Senadhera, S.P.B.M. Abstract: Abstract Cancer is a major life-threatening issue in Sri Lanka as well as worldwide. Meta-analysis of Human Nervous System (HNS) cancers is a gap in current cancer research. The proposed research is focused on identifying common and unique signatures (patterns) in HNS cancers using bioinformatics approaches. We have used fifteen mutation cancer datasets and four gene expression datasets downloaded from the cBio Portal and analyzed the data comprehensively. In mutation analysis, single nucleotide polymorphisms (SNP) were used. We have used clustering approaches, association rules and community detection methods for filtering biologically meaningful gene clusters. Gene expression data were also analyzed using these methods. We have validated the identified gene clusters with the Mentha Human Interactome using the Reactome pathways and silhouette statistics. The UniProt, Ensemble, PDB and Mentha databases were used for data annotation and validation. We found 5 association rules, 19 MCODE gene clusters, 16 ClusterOne gene clusters and 622 M-Cliques from the HNS cancer profiles. These 669 gene clusters were identified as Human Nervous system cancer (HNS) gene combinations. These signatures and their genes and proteins are visualized as networks. The genetic, protein level information of each gene and actionable drug details for treatment are annotated and visually presented. We have created the HNS interactome based on the network results. There are 569 genes (nodes) and 7282 edges (interactions). Moreover, we have suggested 8 gene panels for HNS cancer detection. Furthermore, we have created an information enriched dataset for HNS cancer mutations. We conclude that there are highly connected sub-networks in HNS cancer. Since tumours have high cross cancer similarity and heterogeneity it is difficult to find a pattern for mutational level and gene expression level only using computational methods. Our methodology is developed as a reusable component which can be used to analyze different types of cancers. Finally, gene signatures can be practically realized as gene panels to test for HNS cancers. Sat, 01 Jan 2022 00:00:00 GMT https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4773 2022-01-01T00:00:00Z https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4772 Title: A Sensor Fusion Framework for Visually Impaired Navigation A Authors: Silva, P.L.C.S. Abstract: Individuals who are differently-able in vision cannot proceed with their day-to-day activities smoothly as other people do. Especially independent walking is a hard target to achieve with their visual impairment. Assistive technology to aid the mobility of blind people is an emerging area where several scientific contributions have been made to assist the navigation of visually impaired people by mainly facilitating the autonomous execution of intelligent environments and accessible context-aware smart navigation aids. However, most assistive navigation aids depend on the measurements acquired by a single type of sensor attached to the user. The amount of research on combining multiple sensors in assistive navigation aids for visually impaired navigation is limited. Most work is targeted at sensor integration but not at sensor fusion. Another observation was a lack of integration of navigational sub-processes such as obstacle detection, localization, motion planning, and context awareness among the navigational aids for visually impaired persons in the literature. This thesis introduces an assistive navigation framework that consists of sub-processes such as object detection, recognition, localization, context-awareness and motion planning based on fusions of homogeneous and heterogeneous sensors to complement the strengths of different sensors to overcome the drawbacks of individual sensor types. The research questions of this thesis were approached via five investigations, correspond to the aforementioned sub-processes of the proposed framework, and are evaluated over several proofs of concept architectures during the investigation path of the thesis. First, obstacle detection consists of a set of sonar sensors that can detect obstacles in visually impaired navigation. Subsequently, the homogeneous fusion between two ultrasonic sensors was carried out to improve ground-level obstacle detection based on an extended Kalman filter. Second, in the sub-processes of obstacle recognition, vision sensor and computer vision allow users to determine the objects around them, which was impossible when using an ultrasonic sensor alone. Third, localization is based on the fusion of measurements acquired by the Global Positioning System sensor and inertial sensor using the error state extended Kalman filter-based state estimation approach. Fourth, the sub-process of motion planning is based on obstacle detection and localization outputs. Fifth, context analysis considers the amount of safety during the navigation, and it is tested using actual scene data collected from a set of sonar sensors and individual subject data obtained from a personalized smartphone application. Finally, iii multi-modal feedback gives feedback to the navigator using audio and tactile cues on these sub-processes. Investigating and determining the optimal use of complementary sensors in terms of the type and number of sensorial channels to aid visually impaired persons in a dynamic real-world setting is a crucial challenge. Hence simulation-based usability evaluation experiments are a pragmatic and cost-effective approach in such studies. This thesis has designed and implemented a three-dimensional simulation-based test-bed for usability evaluations of navigation sub-processes such as obstacle detection, recognition, localization and motion planning. The usability evaluation experiments conducted in a simulated environment led to significant findings comparable to a real-world setting. To analyze and benchmark the results obtained from the three-dimensional simulated environment, it is necessary how visually impaired persons in real-world situations can use the proof of concept prototype. Therefore, evaluation experiments are carried out in a controlled, real-world environment. The real-world evaluation experiment protocol involves selecting a sampling plan, setting up the controlled environments, and conducting the experiments. Finally, results are analyzed under each navigation sub-processes in the controlled, real-world environment. The sub-process of obstacle detection consists of a set of sonar sensors that gives the average frontal obstacle detection with the highest score, 98%, while left and right obstacle detection is 89% and 86%, respectively. The bench-marking of estimated localization data obtained from error state-extended Kalman filter-based fusion of the Global Positioning System sensor and inertial sensor with the ground truth reference shows only a 28.37% relative error percentage. When evaluating feedback, voice feedback has achieved a higher score between 8.5-10 than tactile feedback between 6-8 on the Likert scale grading from 0-10. In conclusion, this thesis presents a novel framework to integrate several navigational sub-processes with sensor fusion. The proposed approach consists of several contributions to field sensor fusion in visually impaired navigation—for instance, a novel homogeneous sensor fusion algorithm based on the extended Kalman filter to fuse multiple sonar sensors. Subsequently, a novel heterogeneous sensor integration approach is proposed to integrate vision and sonar sensors. Moreover, a complementary sensor fusion algorithm based on the error state-extended Kalman filter is introduced to fuse inertial and Global Positioning System sensors for localization. A novel iv hybrid walking context estimation method based on environmental adaptation and personalization is also introduced. The proposed framework can be extended to include more navigational sub-processes with additional sensors to provide an independent navigation experience for visually impaired people, and the proof of concept implementations are scalable to incorporate the extensions of future assistive technologies. Most importantly, to the best of our knowledge, the three-dimensional simulation developed in this thesis is the first simulation that investigated a novel hybrid sensor fusion approach for visually impaired navigation, including the sub-processes of obstacle detection, obstacle recognition, localization, and motion planning in the three-dimensional simulated environment. Fri, 01 Jan 2021 00:00:00 GMT https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4772 2021-01-01T00:00:00Z