By Topic

Advances in ICT for Emerging Regions (ICTer), 2012 International Conference on

Date 12-15 Dec. 2012

Filter Results

Displaying Results 1 - 25 of 49
  • [Title page]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (220 KB)  
    Freely Available from IEEE
  • Message from the conference chair

    Page(s): ii
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (39 KB)  

    The International Conference on Advances in ICT for Emerging Regions (ICTer) is the successor to the International IT Conference IITC, the major IT Conference in Sri Lanka since 1998. It is a forum for the sharing of knowledge through the presentation of research carried out on various aspects of ICT in the region. This year particular effort was made to establish the conference web site and to include all its past conference papers as well as to index them in Google Scholar. Publicity for the conference was made through many conference promotion sites which led to more site access from over 100 countries. Conference also attracted around 15 international submissions in addition around 60 local papers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Forward by the co-chairs

    Page(s): iii
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (42 KB)  

    We are pleased to welcome you to the 3rd International Conference on Advances in ICT for Emerging Regions (ICTer 2012). ICTer is the successor to the International Information Technology Conference (IITC) held in Sri Lanka since 1998. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Organizing committee

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (32 KB)  
    Freely Available from IEEE
  • Program committee

    Page(s): v - vi
    Save to Project icon | Request Permissions | PDF file iconPDF (38 KB)  
    Freely Available from IEEE
  • Logistics committee

    Page(s): vii
    Save to Project icon | Request Permissions | PDF file iconPDF (31 KB)  
    Freely Available from IEEE
  • Guest speakers

    Page(s): viii
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (44 KB)  

    Provides an abstract for each of the presentations and a brief professional biography of each presenter. The complete presentations were not made available for publication as part of the conference proceedings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Table of contents

    Page(s): ix - xii
    Save to Project icon | Request Permissions | PDF file iconPDF (75 KB)  
    Freely Available from IEEE
  • Agenda

    Page(s): xiii - xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (847 KB)  
    Freely Available from IEEE
  • Keynote speakers [3 abstracts]

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (203 KB)  

    These keynote discusses the following: multicore and extreme scale computing: programming and software challenges; strategies for neutralizing sexually explicit language in cyberspace; and decision analysis in societal planning. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speaker independent Sinhala speech recognition for voice dialling

    Page(s): 3 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (381 KB) |  | HTML iconHTML  

    Speech is the most natural and the most powerful way of communication between humans. Speech recognition for voice dialling applications has already been developed for languages such as English, French and Japanese, etc. However, there is no evidence of existence of such applications for voice dialling in Sinhala language with speaker independent environment. The work described in this paper is based on an attempt to implement a speaker independent Sinhala speech recognizer and a voice dialling application which has been used to communicate with a VoIP application. The underlying concept of building the speech recognizer is Hidden Markov Model (HMM) and the system is developed using the Hidden Markov Model Toolkit (HTK). The first stages of building the speech recognizer involve the preparation of speech samples for training and the creation of the pronunciation dictionary which lists all the speech samples along with their phonetic representations. A noise reduction method has been applied at the front end of the voice dialling application to clean up the speech signal from the beginning. The middle stages comprise of employing a good feature extraction technique to enhance the speech recognition, and building and training the acoustic model to match a spoken digit to the observed input while the latter stages involve the creation of the language model to determine which digit has spoken. The results show that 87.37% of the digits are correctly recognized by the speech recognizer under quiet environment while 82.19% of the digits are correctly recognized in noisy environment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data-driven spell checking: The synergy of two algorithms for spelling error detection and correction

    Page(s): 7 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (540 KB)  

    Sinhala, the majority language of Sri Lanka, is still in its infancy with respect to natural language processing research and applications. Spell checking is an important application which has received inadequate attention. One of the major issues with implementing a Sinhala spell checker is the deficiency of resources such as morphological analyzers, tagged corpora and comprehensive lexica. Due to the richness of Sinhala morphology, using an entirely rule based approach is deficient. An interesting alternative is to use data-driven approaches. This research attempts to improve the quality of Subasa, an existing n-gram based data driven spell checker using minimum edit distance techniques and to make the system freely available online. Our empirical results show that the proposed design improvements succeeded in improving the spell checking coverage. In addition, we also compare the performance of this system with others in the literature. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Translator from Sinhala to English and English to Sinhala (SEES)

    Page(s): 14 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (755 KB)  

    This paper presents a rule based machine translation system which is capable of translating sentences from Sinhala to English and vice versa. This is the first Sinhala to English and English to Sinhala machine translation system which comes with features such as a Sinhalese font translator, which is capable of interpreting Sinhalese words written in English characters (Singlish) to Sinhala characters, and an English grammar and spell checker. An entered sentence to the system will be tokenized and translated according to a rule. When translating Sinhala sentences to English the user input should be in Singlish and when translating English sentences to Sinhala input should be in English. The main objective of this translator is to enable a smooth flow translation of words, sentences and paragraphs to locals as well as foreigners and thereby eliminate the language barrier. A considerable amount of rules, patterns and words of both languages were used to develop this system. With 87% accuracy this pilot machine translation system translated 500 grammatically well-structured Sinhala sentences to English and 150 grammatically well-structured English sentences to Sinhala. The system is capable of translating approximately 70 sentences in one minute. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feeling the motion of object in a dynamic image sequence through haptic interface

    Page(s): 19 - 26
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1606 KB) |  | HTML iconHTML  

    In this paper we discussed how to incorporate haptic signals with a dynamic image sequence or other words a video to feel the motion of objects in it. Haptic technologies are being used in a wide range of application areas. However, the incorporation of haptic interface technology into a video media is still in its infancy. With the invention of digital multimedia and immersive displays, significance of exploring new ways of interacting with video media has grown up. Rather than just seeing and hearing a video, viewers' experience can be further enhanced by letting them feel the movement of the objects in the video through haptic interface, as it is an additional sensation to seeing and hearing. The objective of this research is to use haptic interface technology to interact with a video and enable the viewers to feel the motion of objects in the video beyond passive watching and listening. In this paper, we discuss how to feel the motion, which is computed from frame to frame calculation of velocity using optical flow. For haptic motion rendering, we have proposed a method by experimentally evaluating two methods using a gain controller and using a non-linear function. To interact with the video we used the string based haptic device, SPIDAR, which provides a high definition force feedback sensation to users. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Facial muscle anatomy based approach for forensic facial reconstruction in Sri Lanka

    Page(s): 27 - 35
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2119 KB) |  | HTML iconHTML  

    Forensic facial reconstruction is still at its infancy in Sri Lanka and is yet to utilize the advanced technologies of other countries. Hence introducing a more efficient multimedia based technique to the local forensic officials in order to improve the efficiency and the accuracy of the reconstructions is the aim of this study. In contrast to the other mechanisms used for facial reconstruction by others, this paper adopts a novel approach of muscle based facial reconstruction which goes hand in hand with the manual reconstruction process. The adopted process involved, acquiring a 3D model of the skull and digitally sculpting muscles in a 3D environment, followed by adding different facial features to improve identification. The research also encompassed a tissue thickness analysis that is conducted for the first time on Sri Lankans as well as a facial component analysis, both of which were needed to improve the accuracy of the final output. This procedure was attempted on cases of the age category 20-30 and of medium weight. The outputs and the process were evaluated with different parties such as general public, forensic officials, lawyers and CID all of which are to be benefited from this application. The ultimate goal of conducting the study was to understand and overcome the challenges faced in developing this novel application for the Sri Lankan Forensic officials and to establish the first unit for facial reconstruction in Sri Lanka. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi agent based approach to assist the design process of 3D game environments

    Page(s): 36 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (697 KB) |  | HTML iconHTML  

    Designing complex and reasonable 3D environments for modern 3D games is one of the time consuming challenges faced by present video game industry. We have critically reviewed the existing approaches to automate the design of 3D environments. It was identified that current 3D environment generation techniques being specific to one or few types of environments and the lack of customizable frameworks which are common to many types of environments as the main issues to be addressed. According to literature, surprisingly complex and interesting global behaviours can arise in multi agent systems as a result of simple rules that are followed by number of simple agents operate in an environment. We hypothesize that this emergent behaviour of multi agent systems can be used to design 3D game environments with emergence properties that were not visible in initial constituents. The proposed solution provides a multi agent based approach to develop a framework which is common to design many types of 3D game environments. Each 3D model in a 3D game environment is associated with an agent with simple rules and this system allows users to introduce new 3D models and associate them with agent types. The main input for the proposed system is a parameterized description of an imaginary 3D environment. Output of the system is a 3D game environment with self organized 3D models positioned and oriented in most suitable places. The proposed approach has been evaluated by implementing a prototype and comparing the proposed approach with traditional 3D game environment design approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Single camera based Free Viewpoint Video recording mechanism for premeditated scenarios

    Page(s): 45 - 50
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1254 KB) |  | HTML iconHTML  

    Free Viewpoint Video (FVV) technology is one of the emerging home entertainment mediums. FVVs give viewers the freedom to choose the viewpoint, which they want to watch the video. FVV making technologies mainly follow two approaches, virtual view synthesize and 3D model based video making. Most of the researches are using multiple video streams for 3D reconstruction and texture application on constructed 3D models. This research presents a system that makes a FVV with prebuilt 3D models and one video camera. The proposed system is less process intensive and produces a structurally accurate FVV. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulating narrow channel effect on surge motion of a ship in a virtual environment

    Page(s): 51 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (816 KB) |  | HTML iconHTML  

    Ship navigation behaviors are quite different in narrow and shallow water channels than in an open sea. Pivot point and the resistance to surge motion of a moving ship are changed according to the characteristics of the channel. When enhancing real-time computer based ship simulation in narrow channels which can be used for ship navigational trainings, the resistance force should be considered. This resistance force effect in narrow channels is calculated considering different channel widths and channel depths in a mathematical ship model. This prediction algorithm for narrow channel resistance on surge motion effect is compatible with algorithms and physical models used in a real-time ship simulator which simulates six degrees of freedom ship motions. This paper presents an analysis of observations and findings on the narrow channel resistance on surge motion of a ship that occurs as a result of blockage factor in such a real time ship simulator. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Virtual Eye: A sensor based mobile viewer to aid collaborative decision making in virtual environments

    Page(s): 56 - 61
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (675 KB) |  | HTML iconHTML  

    Current virtual simulation techniques often include multi-user interactivity in virtual environments that can be controlled in real time. Such simulation techniques are mostly employed in virtual military training sessions and in real time gaming experiences, where users have to make more strategic decisions by analyzing the information they receive, in response to the actions of the other users in the same virtual environment. Generally, in the real world, collaborative decision making takes place when a team of people work together to control the behaviour of a single object which cannot be handled alone by an individual. A ship with its crew can be held as an example. When applying this scenario into virtually simulated environments, multiple users have to involve in representing a single object in the virtual world. These users need to obtain sufficient information about the activities in the environment that will contribute to the collaborative decision making process. Out of many sources, visual information is the most reliable source the users tend to depend on. The use of traditional static displays to obtain visual information limits the capability of providing a rich set of information about the 3D environment. Head Mounted Displays address these limitations while introducing several new problems. On the otherhand, our work is focused on exploring how smart devices can be employed by a collaboratively working team of users to obtain visual information to the level beyond which a static display provides, thus aiding the process of decision making. To serve the above purpose, we propose a solution, “Virtual Eye”, which uses a smart mobile device with the ability to view the visual output of the virtual world and the ability to control that view according to user's orientation changes and movements with the use of its inbuilt sensors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensor information fusion architecture for virtual maritime environment

    Page(s): 62 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1257 KB) |  | HTML iconHTML  

    This paper presents a ongoing research on generic sensor fusion architecture and its application to a maritime surveillance system. The importance of information fusion for various sensor types and specialized sensor fusion systems in various domains are discussed. In sensor fusion, centralized versus decentralized refers to where the fusion of the data occurs. In centralized fusion, the clients simply forward all of the data to a central location, and some entity at the central location is responsible for correlating and fusing the data. In this research we intend to correlate multiple maritime sensors such as RADAR, AIS, and other electronic object detection systems. Sri Lanka Navy has myriad of surveillance information sources such as AIS (Automatic Identification System), RADAR (Radio Aid Detection and Ranging), SONAR (Sound Navigation and Ranging), MSTT, HFSWR, AVL (Automatic Vessel Locating), HF Communication, Intelligence Data ect. So it is obvious that an information fusion methodology is needed to harness the effectiveness of multiple sensor information. An object identification pipeline is conceptualized such that an unknown object in the maritime domain is detected reducing the uncertainty of obtained information. The radical new virtual reality application has been developed to visualize the information fused from sensors and discussed in depth in addition to the introduction of the fusion process. The technologies used in developing the virtual world and incorporating the real time information in to the virtual world is presented in simplified modal for the purpose of clarity. Also design aspects and some experimental analysis developed in an applied project at the Sri Lanka Navy intended to demonstrate fusion technologies in this environment through an operative prototype are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A comparative performance evaluation of different application domains on server processor architectures

    Page(s): 67 - 74
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (566 KB) |  | HTML iconHTML  

    In this paper we analyze and describe the impact of processor performance parameters such as: `Resource Stalls, Branch Mis-predictions, Translation Lookaside Buffer (TLB) Misses and Cache Misses' on the performance of different application domains and we analyze how this behavior varies among server processor architectures. We analyze the variant behavior of those processor performance parameters, among different application domains. We carry out this research based on two server microprocessors namely `single processor quad core Intel Xeon E5506' and `dual processor dual core AMD Opteron 2220 SE'. Our findings show that the above parameters makes a major impact in the performance of applications and we find that this behavior varies from application domain to domain and microprocessor to microprocessor. We have evaluated the performance of the two micro-architectures by analyzing the performance statistics obtained from the respective microprocessor hardware performance monitoring counters. In this paper we summarize our results with respect to above discussion made. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TikiriPower - Using TikiriDBabstraction on Smart Home systems

    Page(s): 75 - 81
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1257 KB) |  | HTML iconHTML  

    In the domain of Wireless Sensor Networks, Smart Home applications are becoming the newest trend. Such deployments face challenges of underlying complexity in programming of traditional wireless sensor networks as well as lack of collaboration within hardware components. To address these issues, a platform that considers sensors and actuators in a wireless sensor network as a database framework is presented. Monitoring electrical and environmental parameters and controlling electrical appliances in a Smart Home via SQL queries is suggested. A prototype system consists of monitoring and controlling capabilities was implemented to evaluate the framework. Usage of our platform would makeSmart Home applications more efficient, reliable and maintainable. In return, reduction of domestic energy consumption and cost in monetary terms would be beneficial. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applicability of three complexity metrics

    Page(s): 82 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1467 KB) |  | HTML iconHTML  

    Over the years a number of complexity metrics have been proposed. However, there have been only a few studies conducted to compare those proposed metrics in terms of their practical applicability. The few researches that have been conducted to assess the applicability of a complexity metric have also used the five properties proposed by Briand et al. However determining whether a complexity measure satisfies some theoretical complexity properties is not a reliable method of determining the practical applicability of it. Thus, the main intent of this study was to compare three proposed code complexity metrics: McCabe's cyclomatic complexity, Halstead's software science and Shao and Wangs' cognitive functional size and identify which metric is the most suitable metric that can be used in the current state of the art with the help of thirty programmers. To conduct this empirical study ten freely available java programs were used as the base. From this study it was identified that Shao and Wangs' cognitive functional size is the best complexity metric that can be used in the real world. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analogue driven handling of emergent complexity

    Page(s): 89 - 95
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (745 KB) |  | HTML iconHTML  

    Complexity Science has noted as the next evolution of the science in which the main idea is a global emergent behavior, which is resulting from the interaction between its local, dynamic, complex, interconnected, distributed, and uncertain entities. In Computer Science; modelling of complex systems are not naive and many technologies have been used for this specially due to the advancements in Artificial Intelligence. This paper presents a novel approach to model complex systems through relations on analogy making. Analogy making is considered as a mapping of knowledge between two domains. Multi Agent Technology has been used to facilitate the underneath support for this, while primarily using the power of relating in different domains as the working mechanism for agents. Agents are used to isolate an appropriate domain in which the same problem that happens to be analogically feasible; and for this domain selection, communication and negotiation features of agent technology have been used. The model has been partially scrutinized in the geometric analogy domain for empirical validations and the idea is still in a conceptual level. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An end-to-end caching protocol for web services

    Page(s): 96 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (796 KB) |  | HTML iconHTML  

    Web services have become an extremely popular technology for application integration due to its platform independent nature. However the use of web services has been limited in some areas mainly because of poor performance. Most web service usage scenarios fall into a client server architectural pattern, where a server component serves multiple clients. Caching is considered to be a well-known performance boosting approach in these types of applications. Even though web services have many similarities with the web, it is not easy to apply the same caching strategies used in the web in the context of web services. One key reason for this is that the request XML messages do not reveal enough information about the service semantics. The intention of this research is to implement an end-to-end caching protocol for web services, similar to HTTP caching. The proposed scheme consists of two caches - at the server and at each client. A set of SOAP headers similar to cache control HTTP headers will be used for managing this caching mechanism. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.