Research Papers - Dept of Information Technology
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593
Browse
31 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Step-by-Step Process of Building Voices for Under Resourced Languages using MARY TTS Platform(IEEE, 2022-12-09) Senarathna, M; Pulasinghe, K; Reyal, SThis paper presents a comprehensive guide for creating synthetic voices to support under resourced languages for the MaryTTS platform. Although researchers have extensively contributed in the domain of speech synthesis, the lack of a thorough documentation hinders the voice building process for languages not yet supported by MaryTTS, complicating the implementation process for users with inadequate knowledge in the field of Text-to-Speech (TTS). The step-by-step process discussed in this study is further demonstrated with the creation of a synthetic voice for the Sinhala language, with unit selection as the voice building approach. A Sinhalese voice was generated with an intelligibility score of 91.7% upon evaluation with Diagnostic Rhyme Test (DRT). Comparison with ground truth data proved a close approximation to human speech where the intelligibility score was identified as 97.9%, when tested with the same participants. The Mean Opinion Score (MOS) revealed a naturalness level of 2.993, indicating a moderately high speech quality for the proposed system in comparison with the ideal score of 4.972.Publication Open Access SeizeIT: SEIZURE victims are no longer leashed(Institute of Advanced Engineering and Science, 2019-09-18) Wimalarathne, M. A. J. I; Ubeysingha, K. U. K; Imbulana, I. A. D. M; Welikala, W. A. D. R; Pulasinghe, KSeizure is considered to be one of the severe and most common type of neurological disorders. Despite the availability of numerous anti-seizure drugs, it is often difficult to control the disease completely and effectively. Lack of close supervision and failure in providing urgent medical care during and after seizure episodes, leads to serious injuries or even death. On the other hand, the use of wireless sensor networks in everyday applications have rapidly increased due to decreased technology costs and improved product reliability. Therefore, developing a wearable device to monitor seizure may complete the anamnesis, help medical staff in diagnosing and acute treatment while preventing seizure related accidents. There are number of seizure detection systems available in the market. Still their performance is far from perfect. This paper explores an application of biomedical wireless sensor networks, which attempts to monitor patients in a completely non-invasive and non-intrusive manner. It describes a wearable device together with seizure prediction and alerting system, which is designed to address some issues with seizure detection systems in the market. Its functional block diagram and operating modes are detailed. Possible application areas of the device are also discussed.Publication Embargo Machine learning based automated speech dialog analysis of autistic children(IEEE, 2019-10-24) Wijesinghe, A; Samarasinghe, P; Seneviratne, S; Yogarajah, P; Pulasinghe, KChildren with autism spectrum disorder (ASD) have altered behaviors in communication, social interaction, and activity, out of which communication has been the most prominent disorder among many. Despite the recent technological advances, limited attention has been given to screening and diagnosing ASD by identifying the speech deficiencies (SD) of autistic children at early stages. This research focuses on bridging the gap in ASD screening by developing an automated system to distinguish autistic traits through speech analysis. Data was collected from 40 participants for the initial analysis and recordings were obtained from 17 participants. We considered a three-stage processing system; first stage utilizes thresholding for silence detection and Vocal Activity Detection for vocal isolation, second stage adopts machine learning technique neural network with frequency domain representations in developing a reliant utterance classifier for the isolated vocals and stage three also adopts machine learning technique neural network in recognizing autistic traits in speech patterns of the classified utterances. The results are promising in identifying SD of autistic children with the utterance classifier having 78% accuracy and pattern recognition 72% accuracy.Publication Open Access Picture Archiving and Communications System (PACS) for Government Hospitals in Sri Lanka(eHealth Asia 2015At: Colombo, 2015-10) Amarathunga, S. D. D; Jayasundara, P. P. A. S; Somaweera, E. G. P. P; Weerasena, P. D. C; Pulasinghe, K; Samarathunga, S. A. U. SIn this modern world, Healthcare medical imaging system plays and important and central role in critical factor for the quality of diagnostic and treatments. Picture archiving and Communication System (PACS) is the backbone of the analysis of medical images as it is well adapt with several standards such as DICOM and HL7.Publication Open Access Web Based Voice Controlled Advanced PACS to Diagnose Lungs Cancer and Related Anomalies(www.ijisrt.com, 2019-10) Ratnasingam, T; Sayanthan, A; Velummylum, E. S; Archchana, K; Pulasinghe, K- PACS (picture archiving and communication system) is a medicinal imaging technology that is utilized basically in medicinal services associations to safely store and dissect carefully transmit electronic pictures. PACS a needed asset in contemporary hospitals, has demonstrated its key position in the department of radiology for archiving and collecting medical images, followed by its inclusion with the department of radiology. In this paper we have included work 3D displaying of DICOM pictures, calculation of segmented cancer part with fine calculations, voice recognition for a program to get and translate correspondence or to comprehend and complete spoken directions, and forecast of malignancy utilizing examinations of cancer symptoms.Publication Open Access Remote Doctor: Tele Medicine Unit(https://www.ijert.org/, 2017-02) Lakshani, D. G. K; De Silva, W. K. S; Bandara, U. R. R. I. S; Samarasinghe, R. W. H. V; Kahandawaarachchi, K. A. D. C. P; Pulasinghe, KRemote Doctor is a solution for transfiguration of telecommunication for healthcare industry to address the prominent aspects identified among the rural hospitals in Sri Lanka such as inadequate specialist consulting, poor medical record storage, poor capacity planning, time consuming prescription writing and report viewing. The proposed telemedicine system inscribes with video conferencing and report sharing among the physician and the patient, automated prescription, taking snapshots and video clips of necessary details such as wounds, ulcers and incision, annotate them and storing them by compressing without damaging the quality of the images and videos. The system has been developed using PHP, JavaScript, Html5, quickBlox API, Web Speech API, WebRTC technology and Sphinx toolkit. The Remote Doctor will be utilizeed in government hospitals to communicate with rural communities.Publication Open Access Voice Communication in Performing a Cooperative Task with a Robot(Springer, Tokyo, 2002) Pulasinghe, K; Watanabe, K; Kiguchi, K; Izumi, KThis paper investigates the credibility of voice (especially natural language commands) as a communication medium in sharing advanced sensory capacity and knowledge of the human with a robot to perform a cooperative task. Identification of the machine sensitive words in the unconstrained speech signal and interpretation of the imprecise natural language commands for the machine has been considered. The system constituents include a hidden Markov model (HMM) based continuous automatie speech recognizer (ASR) to identify the lexical content of the user's speech signal, a fuzzy neural network (FNN) to comprehend the natural language (NL) contained in identified lexical content, an artificial neural network (ANN) to activate the desired functional ability, and contral modules to generate output signals to the actuators of the machine. The characteristic features have been tested experimentally by utilizing them to navigate a Khepera® in real time using the user's visual information transferred by speech signalsPublication Open Access A Fuzzy-Neural Network Based Human-Machine Interface for Voice Controlled Robots Trained by a Particle Swarm Optimization(Korean Institute of Intelligent Systems, 2003-09-25) Watanabe, K; Chatterjee, A; Pulasinghe, K; Izumi, K; Kiguchi, KParticle swarm optimization (PSO) is employed to train fuzzy-neural networks (FNN), which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. The system has been successfully employed in a real life situation for navigation of a mobile robot.Publication Open Access Syntactic Approach to Predict Membrane Spanning Regions of Transmembrane Proteins(Springer, Berlin, Heidelberg, 2005-03-30) Pulasinghe, K; Rajapakse, J. CThis paper exploits “biological grammar” of transmembrane proteins to predict their membrane spanning regions using hidden Markov models and elaborates a set of syntactic rules to model the distinct features of transmembrane proteins. This paves the way to identify the characteristics of membrane proteins analogous to the way that identifies language contents of speech utterances by using hidden Markov models. The proposed method correctly predicts 95.24% of the membrane spanning regions of the known transmembrane proteins and correctly predicts 79.87% of the membrane spanning regions of the unknown transmembrane proteins on a benchmark dataset.Publication Open Access Knowledge Management for Effective Clinical Diagnosis in Developing Countries(Journal of Information Technology Review, 2013-05-02) Amararachchi, J. L; Pulasinghe, K; Perera, H. S. CIn the last two decades, the Information and Communication Technologies (ICTs) revolution has redefined the structure of the 21st century healthcare organization. The fundamental challenge faced by the 21st century clinical practitioner in a developing country is to acquire proficiency in understanding and interpreting clinical information so as to update knowledge that leverage the quality of decisions made at the clinics. An additional challenge must be considered by the clinical practitioners to make potentially life-saving decisions whilst attempting to deal with large amounts of clinical data. Since the Clinical Knowledge Management Systems (CKMS) consist of most related Data, Information and Knowledge, it could be utilized to achieve the above challenges. Shortage of medical experts in Health Institutions located in rural and remote areas in developing countries being a huge problem which effects badly to the quality of healthcare. By providing facilities for medical practitioners to access KMS, this problem can be alleviated substantially. A Knowledge Management (KM) solution would allow healthcare institutions to give clinical data context, so as to allow knowledge derivation for more effective clinical diagnosis. It would also provide a mechanism for effective transfer of the acquired knowledge in order to aid healthcare workers as and when required. This study has identified the factors that affect to the knowledge management initiatives. There is a strong association between accessing and using Information/knowledge in clinical activities and quality of healthcare. Moreover, attitudes of Medical Practitioners (MP), Infrastructure facilities, patient Information systems, patient treatment, staff benefits etc., have shown positive effect to the success of Knowledge Management in Health Institutions. The research has used a case study methodology for accomplishing the research objectives. Rural and remote areas in Sri Lanka have been considered for the case study since it is one of the developing countries situated in the Asian region. Based on the outcome of the study, we introduce a KM framework for Healthcare Institutions which would assist HIs to discover and create new knowledge. The framework has been validated using a sample of 15 hospitals situated in the Kandy district in Sri Lanka.