CS&ES Conference - 2011

Permanent URI for this collectionhttp://192.248.9.226/handle/123/19492

Browse

Now showing 1 - 19 of 19

item: Conference-Full-text
Levi – the native bpmn 2.0 execution engine
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Sooriyabandara, E; Pathirage, M; Perera, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
In today's enterprise world, as more and more importance is placed on process automation and IT based governance, organizations tend to model and manage their business processes to achieve increased efficiency and productivity. The proper use of process modeling concepts in business scenarios enables designers to specify process requirements in terms of interactions enacted by human agents. Although Business Process Modeling is possible with languages like Business Process Execution Language (BPEL), they use more of a programing oriented view as oppose to human oriented view. Standardization of the Business Process Model and Notation version 2.0 (BPMN 2.0) provide a way to support inter-operation of business processes at human user level, rather than at the software engine. Although BPMN has being standardized, its wide adoption is limited by the lack of runtimes supporting BPMN. Although there are several BPMN implementations, they convert the BPMN to BPEL or another intermediate representation, which will yield mix results. In this paper, we discuss the design of Levi, a BPMN 2.0 runtime build using the underline constructs of ODE (Orchestration Director Engine), Apache based open source process engine. Unlike most other approaches, Levi supports BPMN natively using a concurrent runtime that supports Join pattern.
item: Conference-Full-text
AxiCo2 Concurrency coordination runtime on top of apache axis2
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Mudannayaka, S; Bandara, L; Gunawardena, V; Weerasooriya, C; Perera, S; Wimalawarne, K; De Silva, R; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
AxiCo2 is an Application Programming Interface (API) designed to simplify the implementation of concurrency in local environment as well as in the invocation of web services. AxiCo2 thereby reduces many inherent difficulties undergone by developers in programming multi-threaded applications. The higher level Application Programming Interface provided by AxiCo2 hides complexities associated with concurrency constructs and web service invocations. As a framework for concurrency and coordination among threads, AxiCo2 provides a means of asynchronous communication among threads which are used for local tasks and service invocations using “Ports” which are subdivided as Local and Service Ports. AxiCo2 has a thread pool within itself eliminating inherent overheads of thread per task approach. Apart from being a high level Application Programming Interface to hide complexities of concurrency, AxiCo2 provides means to the developer to configure applications to respond to partial success through the variety of Receivers provided. This set consists of Join, Choice, Multiple Item and Timeout Receivers which are used in implementing various logical constrains between tasks. AxiCo2 derives benefits both in programmability and performance perspectives.
item: Conference-Full-text
''e-arogya'' an e-health solution for Sri Lankan government hospitals
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Niroshan, GS; Lanerolle, KG; Silva, LCT; Wijekoon, WMUS; Weerawarane, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Sri Lanka is one of the few countries that provide free health services. But majority of hospitals in Sri Lanka still use the traditional paper based methods when registering patients and other administrative functions. The efficiency of the hospitals has decreased largely due to this. “e-Arogya” is introduced as a solution to this problem. This paper explores the possibilities achievable for the introduction of ICT in Sri Lankan healthcare system, problems faced when achieving that, the proposed solution with the use of open source software, and open standards in healthcare, with a new user interface design that follows Human Computer Interaction (HCI) principles.
item: Conference-Full-text
Debas – a sinhala interactive voice response system
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Nallathamby, JD; Kariyawasam, KKR; Pullaperuma, HD; Vithana, DC; Jayasena, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Although there are widely used Interactive Voice Response (IVR) systems in many languages today, there is no Sinhala language IVR system yet. This paper talks about an approach taken in developing a complete Sinhala IVR system. It talks about the research carried out in this area, the process taken, the overall design and implementation aspects and the future work that can be carried out in this area. deBas IVR is a complete Sinhala IVR with automatic speech recognition (ASR) and text-to-speech (TTS) synthesis modules that work in compliance with Media Resource Control Protocol (MRCP). In the ASR component, training the acoustic model is done with SphinxTrain, and decoding with PocketSphinx, which are based on Hidden Markov Models (HMM). In the TTS component, AMoRA Sinhala TTS knowledge base is used, which uses Festival speech synthesis engine and a female diphonic voice, built using Festvox voice building tools. Asterisk is used as the IVR gateway and dial-plan interpreter. MRCPv2 protocol has been followed in developing the speech resources, which uses Session Initiation Protocol (SIP) for establishing controlled connections to external media streaming devices and Real-time Transport Protocol (RTP) for media delivery. The language model of the ASR component has been restricted to digits from 0-9 that are commonly used in IVR systems and the set of words used for our demo application. The word-error-rate and the sentence-error-rate of the ASR component are reported to be 31.4% and 54% respectively, as observed in our experiments. In addition to these, we also introduce a new intonation model that can be applied to any existing Sinhala diphonic voices.
item: Conference-Full-text
Miyaesi: java based implementation for automatic music transcription
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Abeykoon, H; Kaushalya, T; Akram, N; Dissanayaka, A; Weerawarana, S; De Silva, C; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Music Notes play a major role in the music world. They are extremely important for musicians and composers. Sometimes people like to know music notes of an already composed music which raises the need of music transcription. In the past decade up to now researches and engineers have come up with vivid techniques to do music transcription automatically using probability and signal processing. With the advent of computer science which facilitated encoding and recording music in digital format it became an important topic. Nevertheless, implementation specific details are still rare to find addressing Automatic Music Transcription (AMT). In this paper we discuss concepts behind automatic music transcription and how they are applied in the system Miyaesi, an automatic music transcription system implemented using Java programming language. Further, we discuss how time domain signal analysis and spectrum analysis leads to automatic instrument identification.
item: Conference-Full-text
Age progressive person-specific 3d model for Sri Lanka
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Anpaz, AJ; Perera, KKD; Thirunavukkarasu, R; Ajith, C; De Silva, C; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Face Age Progression is a process of predicting the face of a person with advancing years. Automation of such process with the power of the Computing is one of the huge challenges in the world. This paperexploresautomatic age progression in 3D modelespecially in Sri Lankan context where there is no such model exists in present. To implement this, Person-Specific 3D model is reconstructedusinggeneric model and asingle frontal image instead of using 3D scan or different poses of images. Then 3D modelis deformed according to the extracted person-specific features.Aging approach on 2D image isproposed based on IBSDT method. Age is progressed in Person-specific 3D model using aged 2D image, texture mapping and structural changes in the nasolabial fold area.
item: Conference-Full-text
Gviz: a web based client side data visualization framework
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Edirisooriya, MW; Fernando, BPP; Fernando, TAMP; Wickramasinghe, WAWSK; Weerawarana, SM; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Data visualization is widely used in modern day web applications. Although there are popular solutions like Google Visualization API and YUI, they all are dependent on the server side technology. This paper describes a generic framework which runs entirely on the client side of a web application and enables easy integration of different types of visualization components like maps and charts from different visualization providers into a single web based dashboard [1] supporting different types of data providers like XML and JSON [2]. Data is described to the framework using an open standard named Data Set Publishing Language (DSPL) [3]. The framework implements an Event Driven Architecture (EDA) to facilitate the numerous asynchronous workflows happening inside.
item: Conference-Full-text
Mahasen: distributed storage resource broker
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Perera, KDAKS; Kishanthan, T; Perera, HAS; Madola, DTHV; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Modern day systems are facing an avalanche of data, and they are being forced to handle more and more data intensive use cases. These data come from many forms and shapes: Sensors (RFID, Near Field Communication, Weather Sensors), transaction logs, Web, social networks etc. As an example, weather sensors across the world generate a large amount of data throughout the year. Handling these and similar data require scalable, efficient and reliable very large storages with support for efficient metadata based searching. This paper present Mahasen, a highly scalable storage for high volume data intensive applications built on top of a peer-to-peer layer. In addition to scalable storage, Mahasen also supports searching built on top of the Distributed Hashtable (DHT).
item: Conference-Full-text
Mapping dependency relationships into semantic frame relationships
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) de Silva, NHND; Fernando, CSNJ; Maldeniya, MKDT; Wijeratne, DNC; Perera, AS; Goertzel, B; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
We describe the refactoring process of the Natural Language Understanding pipeline of OpenCog Artificial General Intelligence Framework, a method for expanding the concept ontology of the pipeline using statistical learning algorithms. Further an experimental approach to automatically generating a common sense knowledge base specifically with relation to concept relationships derived from the natural language pipeline using data mining techniques is detailed and evaluated.
item: Conference-Full-text
Annebot – an evolutionary artificial neural network framework.
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Mathotaarachchi, MSS; Perera, DC; Udawatte, L; Perera, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
A novel method for selecting the appropriate architecture and learning rule of an artificial neural network for a given application is discussed in this paper. Evolutionary Artificial Neural Networks (EANN) use the adaptation capabilities of genetic algorithms in which the natural selection process is used to attain the optimum network structure and learning algorithm for a specific task. ANNEbot is a framework which allows the combined powers of learning and adaptation of EANNs to be applied in various machine learning tasks. The framework was tested on the Iris Classification problem and the Wisconsin Breast Cancer Diagnosis problem, both of which provided results with above 90% accuracy. ANNEbot was also successfully applied on a robotic application for obstacle avoidance.
item:
Ises: intelligent semantic search framework
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Jayarathne, M; Fernando, D; Arachchi, CD; Haththotuwa, I; Perera, S; Weerakoon, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
With vast amounts of data being produced, present world is overwhelmed with information and searching for appropriate content has turned out to be harder than ever before. Semantics, which typically focuses on the relationship between signifiers, such as words, phrases, signs and symbols, and what they stand for is now being used more and more in search engines to provide the user with more meaningful content. Further it is no more the case that users are interested in search results that the majority of users would agree to, but are more interested in results being personalized to them. In this research paper we present iSeS: Intelligent Semantic Search Framework, which is a search framework that a custom web site or an application can adapt. We focus on using underlying semantics of the content being indexed in providing more meaningful search results personalized to each user. We look into both latent semantic indexing and metadata extraction based methods for providing semantically rich search results. Collaborative filtering and how it is used to personalize search results is also explored in this paper.
item: Conference-Full-text
Innovative framework for human motion tracking for hci
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Sandaruwan, HGL; Kumara, GDT; Dileepa, HGR; Gamage, C; Gunaratna, HD; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Human Computer Interaction is an emerging field in the computer science context, which tends to discover new systems that use user-centered view instead of machine centered view. This research specifically targets the full body motion interaction with computer. Therefore it develops an application which is more biased towards a user centered view. The process of building a new framework for HCI is challengeable and should be done very carefully. The system needs to indicate higher performance gain for measurements such as usability, efficiency, accuracy, and reliability. This paper describes a passive marker based approach which feeds input from web cameras and tracks blue colored markers. Input brings the marker position details with respect to time. Algorithms which regulate this framework are used for the calculation of derived attributes, clustering markers, and the prediction of positions coordinates of markers and initializing markers. They will give a meaningful interpretation to the marker position details. The next task of motion detection is facilitated using the Artificial Intelligence techniques which take preprocessed marker details as input. According to the prediction made, the user will be able to move in an immersive virtual environment. Although the project components were implemented in C++ java, they were integrated using java Native Interface (JNI).
item: Conference-Full-text
Decisionai: a framework to automate the decision making process
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011) Buddhika, KT; Jayamanne, DP; Kohomban, U; Wimalasena, L; WIjegunawardana, PP; Gunasekera, RC; Perera, AS; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
accurate decision making is the key to make a business profitable. Decision support systems are used to make the decision making process accurate and easy. Even though there are many business specific decision support systems they cannot be used for general purpose decision making or outside their domain. DecisionAI provides a framework which can be used in any decision making domain with similar decision types. DecisionAI provides a good solution to many decision making problems in the industry allowing detailed analysis of data with the integrated intelligence.
item: Conference-Full-text
Siddhi: a comprehensive architecture for stream processing
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Suhothayan, S; Narangoda, IL; Gajasinghe, K; Chaturanga, S; Nanayakkara, V; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Complex Event Processing (CEP) is one of the most rapidly emerging fields in data processing. Processing of high volume of events to derive higher level events is a vital part of several applications. The use-cases found in Business applications, financial trading applications, operational analytics applications and business activity monitoring applications are directly related to complex event processing. This paper discusses different design decisions associated with CEP Engines, and proposes to improve CEP performance by using a stream-processing-style pipelines. Furthermore, the paper discusses Siddhi, a CEP Engine that implements pipelines for stream processing and presents a performance study that exhibits that Siddhi CEP Engine has significantly improved performance. Primary contributions of this paper are, a critical analysis of the CEP and Event Stream Processing engine architecture and identifying areas for improvements, implementing those improvements through Siddhi, and demonstrating the soundness of those suggestions through empirical evidence.
item: Conference-Full-text
Gpu acceleration of logistic regression with cuda
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Madhawa, PKK; Jeevananda, MS; Malmi, PMBC; Sandaruwan, URV; Wimalawarne, K; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Logistic regression (LR) is a widely used machine learning algorithm. It is regarded unsuitably slow for high dimensional problems compared to other machine learning algorithms such as SVM, decision trees and Bayes classifier. In this paper we utilize the data parallel nature of the algorithm to implement it on NVidia GPUs. We have implemented this GPU-based LR on the newest generation GPU with Compute Unified Device Architecture (CUDA). Our GPU implementation is based on BFGS optimization method. This implementation was extended to multiple GPU and cluster environment. This paper describes the performance gain while using GPU environment.
item: Conference-Full-text
Maharawana
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Katugampala, N; Ambegoda, P; Gunarathna, A; Bandara, D; Dias, G; Jayasena, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
Sihnhala is the main language used in Sri Lanka. With the increased use of Infomation Technology, typical Sri LAnkana tend to use software up to a significant extent in their day to day operations. A major problem that has occurred was lack of software support for sinhala language.
item: Conference-Full-text
Plagiabust- a plagiarism detection framework using text mining
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Costa, WUC; Jayasinghe, KPCK; Seneviratne, GGADND; Wijesinghe, IA; Walpola, M; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
With the rapid growth of online resources and data processing tools, today plagiarism is considered as a serious issue in the academic field. Plagiarism can be considered as a theft of intellectual property and many academic institutions are keen to take action against plagiarism. In this paper we discuss about a plagiarism detection framework which enables detecting plagiarism in textual documents. Here we address both the common plagiarism scenarios, namely peer plagiarism detection and Internet plagiarism detection. In our plagiarism detection algorithm, we consider not only copy-paste plagiarism but also paraphrase plagiarism because we consider both methods to be equally important. Also we present the implementation details of our plagiarism detection framework and the core components of our system.
item: Conference-Full-text
Automated Teleprompter
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Paris, MMSA; Udayanga, GWGKN; Weerakoon, WMTCB; Mihiran, KWC; Silva, CRD; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
This project is focused on automating the current manual teleprompting system. Teleprompting is one of the most widely used techniques in many broadcasting systems. Nowadays, the teleprompting process is handled manually. Our purpose is to automate the teleprompting scenario, so that no manual intervention is needed to operate the process.This project mainly consists of two sections; Teleprompter Automation and Graphical implementation for sign language to illustrate the speeches or conversion for the handicaps.
item: Conference-Full-text
Interact: a framework to generate device specific smart user interfaces
(Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011-11) Nawarathna, H; De Alwis, P; Liyanage, S; Weerawarana, S; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
InterAct is a form based User Interfaces (UI) designing framework for non-technical users. It can be used to design UIs for multiple device platforms. The framework consists of two parts, an Integrated Development Environment (IDE) and a conversion library. The designed UIs are saved in an XML format type, called IXML. These user sketches are then converted into HTML pages, which can be displayed in various devices using the conversion library. Data is bound to the UI elements at runtime. Usability is the major concern of the InterAct Framework. This aspect is addressed by applying the best practices of Human Computer Interaction (HCI) in order to provide the user a better experience.