Nimalika Fernando

The University of Texas at Arlington

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

David A. McMeekin

Curtin University

Iain Murray

Curtin University

Iain Murray

University of Edinburgh

Thejaka Mahaulpatha

Sri Lanka Institute of Information Technology

Irendra Koswatta

Sri Lanka Institute of Information Technology

Dananjaya Thathsara

Sri Lanka Institute of Information Technology

Pasindu Chandrasekara

University of Ruhuna

Samantha Thelijjagoda

Sri Lanka Institute of Information Technology

Dilma Vithanage

Sri Lanka Institute of Information Technology

Pedro D. Maia

The University of Texas at Arlington

Cooperative Institutions

Sri Lanka Institute of Information Technology

University of Moratuwa

NHS Greater Glasgow and Clyde

Queen Elizabeth University Hospital

Curtin University

University College London

The University of Texas at Arlington

University of Glasgow

University of Sri Jayewardenepura

University of Sydney

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

A System based on Web-GIS for Post-Disaster Recovery Management

International Conference on Information and Automation (2006)

Nimalika Fernando Sirimeven Waidyasekara Dileeka Días

Managing data related to Tsunami damage, and providing sufficient detailed information to interested parties in the reconstruction and recovery process is a challenge faced by the National Data Center, Sri Lanka. The paper proposes a Web-based GIS system to assist the post - Tsunami recovery process. The data components needed to provide timely information for decision makers were identified from the ambiguous subject domain of the massive-scaled disaster. It facilitates the user to access interactive maps and query information through the maps via a standard Web browser. All tools used are free and open source software which makes the system affordable to a developing country such as Sri Lanka. The Hambantota district was selected for a pilot-scale implementation of the proposed system.

Sri lanka

Web browser

10.1109/icinfa.2006.374155

Cite

Citations (4)

ARROW: A web-based employee turnover analysis tool for effective human resource management in large-scale organizations

T. T. Weeramanthrie C. N. Thilakumara K. N. A. C. Wijesiri Nimalika Fernando Samantha Thelijjagoda

To gain the competitive advantage, organizations need to adapt to the dynamic market. Therefore, many researchers have tried to find different ways for adapting to competitive conditions. Most of these research have finally ended up focusing on the human resource, which is the major and important resource in any organization. Currently human beings are treated as assets rather than resources. The System, ARROW is a unique web application developed to satisfy the requirements of company management in employee understanding process. The main objective of the system, ARROW is to fulfil the gap between employees' past, present and future behavior and the management's ability to understand the behavior of the organization's employees at the HR practices. Natural Language Processing and Data Mining techniques were used to accomplish the main objective.

Arrow of time

Resource Management

10.1109/nitc.2017.8285665

Cite

Citations (9)

List of Selected Articles

Figshare (2020)

Nimalika Fernando David A. McMeekin Iain Murray

This dateset contain (1) List of articles resulted from the original search (2) List of articles selected for full text review (3) List of selected articles with key data extracted

10.6084/m9.figshare.12821786.v1

Cite

Citations (0)

Poster

Nimalika Fernando David A. McMeekin Iain Murray

Way finding abilities of vision impaired (VI) people cannot be expected to be as same as that of people who use the vision as the primary sense so the route determination methods in travel aids for VI people needs to adopted accordingly. This study proposes an indoor route determination model which considers the built environment and user context as the priority factors instead of the distance. It will identify how the elements of a built environment affect the determination of a suitable path which maximizes safety and convenience in an unfamiliar environment and how this path does varies with the individual characteristics of VI people.

Affect

Elderly people

10.1145/2938559.2948799

Cite

Citations (3)

Route planning methods in indoor navigation tools for vision impaired persons: a systematic review

Disability and Rehabilitation Assistive Technology (2021)

Nimalika Fernando David A. McMeekin Iain Murray

Objective Route planning is key support, which can be provided by navigation tools for the blind and visually impaired (BVI) persons. No comprehensive analysis has been reported in the literature on this topic. The main objective of this study is to examine route planning approaches used by indoor navigation tools for BVI persons with respect to the route determination criteria, how user context is integrated, algorithms adopted, and the representation of the environment for route planning.Methods A systematic review was conducted covering the period 1982–July 2018 and thirteen databases.Results From the 1709 articles that resulted from the initial search, 131 were selected for the study. Route length was the sole factor used to determine the best route in the majority of the studies. Routes with less obstacles, less turns, more landmarks and close to walls were selected by the other studies. User variations were considered in few studies. Unique needs of the BVI persons were addressed by few novel algorithms which had integrated multiple parameters and BVI-friendly route modelling.Conclusion Differences between the navigation capabilities of the sighted and the BVI community were not a major concern when deciding the optimum routes in the majority of BVI indoor navigation tools. How to trade-off between factors affecting optimum routes, and how to model suitable routes in complex buildings needs to be studied further, looking from the user perspective.Implications for rehabilitationNavigation differences between sighted and blind and vision-impaired (BVI) communities are not concerned frequently when planning routes in indoor navigation tools of BVI persons.Selecting routes avoiding areas difficult to traverse, close to walls, having landmarks, and less turns are some approaches used to address the unique needs of the BVI community.Assisting for recovery from veering and real-time obstacle detouring are useful features offered by these tools.Identifying and prioritizing different factors contributing to better routes, concerning user variations, and adopting multi-objective route optimization will help to develop improved route planning methodologies for BVI indoor navigation tool

Navigation System

Route Planning

10.1080/17483107.2021.1922522

Cite

Citations (10)

Electronic Patient Record System for a Psychiatry Unit in Sri Lanka

Sri Lanka Journal of Bio-Medical Informatics (2010)

Shamali Dahanayake Nimalika Fernando Varuni De Silva

Electronic patient records improve the quality of patient care in psychiatry units. Many patients with long term illnesses have multiple patient encounters with psychiatric services. Although manual data gathering is available at present, data retrieval is time consuming as files have to be manually searched. Storage of past data is hampered by lack of space. We describe the first electronic patient record system developed for use in a psychiatry unit in Sri Lanka. The system facilitates an electronic storage of data and easy retrieval of information. The system identifies a patient by a unique number and allows different episodes of in-patient and out-patient care to be linked together. The systems' value is enhanced by the generation of reports to assist and improve health administration. Clinical care is enhanced by the ability to view the longitudinal history of a patient. Discharge reports, reports of out-patient attendance and reports of analysis of data are generated by the system. The follow up report identifies outpatients who default treatment enabling community follow up. This would help improve compliance and reduce relapses. This is not currently done as it is not feasible to identify all those who default using a manual record keeping system. Analysis of patients based on different criteria such as diagnosis and treatment will assist in identifying trends and provide a database for research.The system was developed using MySQL database and is hosted on Apache server. As this uses only open source software this can be deployed in both Linux and Windows environment allowing easy and low cost deployment. The system is web based and can be connected to a network expanding the access capabilities. Key Words: Psychiatry; web based system; open source; report generation; electronic patient records; Sri Lanka.Sri Lanka Journal of Bio-Medical Informatics 2010;1(4):214-22DOI: 10.4038/sljbmi.v1i4.2250

Attendance

10.4038/sljbmi.v1i4.2250

Cite

Citations (0)

Modelling indoor spaces to support vision impaired navigation using an ontology based approach.

Nimalika Fernando David A. McMeekin Iain Murray

Source

Cite

Citations (5)

Analysis of goal, feedback and rewards on sustained attention via machine learning

Frontiers in Behavioral Neuroscience (2024)

Nimalika Fernando Matthew K. Robison Pedro D. Maia

Introduction Sustaining attention is a notoriously difficult task as shown in a recent experiment where reaction times (RTs) and pupillometry data were recorded from 350 subjects in a 30-min vigilance task. Subjects were also presented with different types of goal, feedback, and reward. Methods In this study, we revisit this experimental data and solve three families of machine learning problems: (i) RT-regression problems, to predict subjects' RTs using all available data, (ii) RT-classification problems, to classify responses more broadly as attentive, semi-attentive, and inattentive, and (iii) to predict the subjects' experimental conditions from physiological data. Results After establishing that regressing RTs is in general a difficult task, we achieve better results classifying them in broader categories. We also successfully disambiguate subjects who received goals and rewards from those who did not. Finally, we quantify changes in accuracy when coarser features (averaged throughout multiple trials) are used. Interestingly, the machine learning pipeline selects different features depending on their resolution, suggesting that predictive physiological features are also resolution-specific. Discussion These findings highlight the potential of machine learning to advance research on sustained attention and behavior, particularly in studies incorporating pupillometry or other physiological measurements, offering new avenues for understanding and analysis.

10.3389/fnbeh.2024.1386723

Cite

Citations (0)

A framework to develop location based services applications using OGC map services

Nimalika Fernando D. Dias Saraji Wijesekara

A framework to support creation of location based services (LBS) applications using map services is designed and implemented. It provides a means to develop interoperable LBS applications which are independent of service provider, device or data providers. Application developers can use the framework to utilize multiple map servers following Web Map Service (WMS) and Web Feature Service (WFS) standards in creating the LBS applications. Mobile phone users can access the applications created by the framework through mobile Internet. A cascading map server and a application database is used at the application server. The LBS applications developed by the framework can provide directory assistance services on wide spectrum of mobile phones ranging from mid-range to smart phones. Thus many LBSs which have hitherto been denied to mid-range phones are made possible, exploiting their available resources. The results of a sample implementation of the framework, issues and suggestions for improvement of the design are also presented.

Location-based service

10.1109/iciafs.2010.5715717

Cite

Citations (4)

M37 Deploying live AI-based risk prediction models for use in a COPD MDT: acceptability, feasibility and utility data from the DYNAMIC-AI clinical trial

Anna Taylor Leo Hickey Emily Walker Nimalika Fernando Kimberley Goldsmith

Introduction

We have developed performant, fair, explainable and actionable AI-based risk prediction models to enhance COPD care. The DYNAMIC-AI observational cohort clinical investigation (NCT05914220) is evaluating the patient acceptability, technical feasibility, safety and utility of deploying our published 12-month mortality and 3-month readmission model risk scores and features to clinicians using the Lenus Stratify 'AI insights' app.

Methods

Participants were recruited between April 2023 – January 2024 through the established COPD digital support service, with patient information and consent flow within the service patient app. Model risk score thresholds that stratify the cohort into low and high-risk are determined collaboratively by clinician and data science team, and these are adaptable depending on clinical team capacity, nature of intervention(s) that may be triggered, and relative weighting of sensitivity and specificity (figure 1). Acceptability has been measured by recruitment numbers. Feasibility is measured by the number of model scores provided for review to the COPD MDT.

Results

130 patients consented to participate, with 14 people declining consent. 12-month mortality model inferencing was successful on 121 of 130 participants, with non-accessible electronic healthcare data preventing inferencing for 9 participants. 60 12-month mortality and 44 3-month readmission model pairs of inference scores and follow-up clinical events are available to date, with high concordance between model validation and prospective outcomes. There have been no adverse events or device deficiencies. MDT experience in DYNAMIC-AI has noted direct actionable utility of high-risk scores, with emerging respiratory failure and prescribing model features as insights that could prompt proactive clinical interventions.

Conclusions

Providing AI insights to a COPD MDT is acceptable to patients and technically feasible. Early experience in live clinical use suggests considerable potential for reorientation of COPD care. In addition to the opportunity realised by proactively highlighting high-risk patients with addressable unseen care-quality gaps, these risk prediction models can be used in population management and other transformation initiatives and calibrated to optimise the use of limited clinician resource (see figure 1). Secondary objectives including prospective model performance and clinical experience will continue to be captured during the 12-month follow up phase of the DYNAMIC-AI clinical trial.

10.1136/thorax-2024-btsabstracts.465

Cite

Citations (0)