ICITR - 2017

Permanent URI for this collectionhttp://192.248.9.226/handle/123/14729

Browse

Now showing 1 - 15 of 15

item: Conference-Full-text
2nd International Conference on Information Technology Research 2017 (Pre Text)
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Sudantha, BH
item: Conference-Full-text
Generate bioinformatics data using generative adversaria l network: a review
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Sharmilan, S; Chaminda, HT; Sudantha, BH
Data is the most important part in machine learning. In bioinformatics field the sensitivity of the data is high and due to that the accessibility of the data for a secondary purpose (e.g.: research) is consist with many legal and ethical issues. Due to that in many bioinformatics researches collecting the data consume more time than the development phase. There are some researches done to solve the legal and ethical issues by anonymising the data using encryption, de-identification and perturbation of potentially identifiable attributes. For some extend those solutions restricted the data breach but in other hand anonymized data not performed well during the analysis and mining tasks. Recently Generative adversarial networks (GANs) have become a research focus of artificial intelligence. The goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that distribution. Here, researcher review GAN in bioinformatics to generate data sets, presenting examples of current research. To provide a useful and comprehensive perspective, Researcher categorize research both by the bioinformatics data and GAN architecture and flow. Additionally, discussed about the issues of GAN in bioinformatics to generate data sets and suggest future research directions. Researcher believes that this review will provide valuable insights for researchers to apply GAN to generate bioinformatics data sets.
item: Conference-Full-text
A Scheme for Tamper Detection by Image Watermarking
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Rajeenthini, R; Ranathunga, L; Amalraj, CRJ; Sudantha, BH
This study proposes inattentive image watermarking scheme for tamper detection. By comparing pixel channel values of the image, the scheme endows to distinguish tamper attacks such as blurring, replacing, adding features from non - tamper regions out coming from general image processing operations. This technique can be implemented with small memory and computational requirements, which makes it potentially useful for hardware implementation in digital cameras. The scheme works by increasing the pixel value of odd number of an each pixel channel by one and embedding the hidden data value into the base image, robust watermark that sensitively depends on a secret key. The technique of watermarking method is designed based on Least Significant Bit algorithm. To achieve of finding the tamper region on the tampered image, this study proposed the inverse extraction procedure that extracts the watermark region and tampered region on the testing image.
item: Conference-Full-text
Conversational agent acting as a shopping assistant for e-commerce sites
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Walgama, MS; Sirisuriya, SCM de S; Sudantha, BH
E-commerce has been gaining momentum drastically over past few years with new trends in technology. The key entity of any e-commerce business is to provide the customer with maximum benefits. Due to this reason using sophisticated technology in ecommerce aspects were seen vividly. With the rapid improvement and usage of messaging apps 2015 most of the business entities where interested in shifting their business deals through most of the messaging apps. The concept of messaging apps where further developed in to a phase of using an embedded conversational interface which allows the customer and the business to deal peacefully. E commerce sites provide a key word search along with a menu driven navigation. Users have come across issues in choosing the exact item needed with the prevailing system. It is reported that about 80% of web shoppers have left the e-commerce sites due to not finding what they needed. To address this problem, the concept of Natural Language interface acting as a shopping assistant was developed. This will build a conversation with the user forwarding a series of questions regarding the goods the user wishes to purchase. This system is mainly developed using AIML scripting, java and prolog.
item: Conference-Full-text
Approach for general lossless visible watermarking
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Mahenthirarasa, T; Ranathunga, L; Amalraj, CRJ; Sudantha, BH
the impact of the Internet has influenced in many new circumstances for the creation and delivery of content in digital form. An important issue that arises in these applications is the protection of the rights of all participants. It has been recognized for quite some time that current copyright laws are inadequate for dealing with digital image. This has led to an interest towards developing new copy deterrence and protection mechanisms. One such effort that has been attracting increasing interest is based on digital image watermarking techniques. Digital image watermarking is the process of embedding information into digital image content such that the information can later be extracted or detected for a variety of purposes including copy right protection and control. A visible watermark typically consists of a conspicuously visible message or a company logo indicating the ownership of the image. The system is designed for choosing best watermark for the cover image and three new algorithms for the visible watermarking process. Comparing and testing the three proposed algorithms is done in the evaluation process and highlight the best things of the algorithms proposed by using PSNR values.
item: Conference-Full-text
Multi-language search for strengthening the outcome of systematic review
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Adikaram, KKLB; Nawarathna, CM; Sudantha, BH
Web based searching plays a vital role in systematic review which is a literature review method designed to locate the best available evidence relating to a specific topic. In addition to English language, languages such as German, French, Japanese, Spanish, and Chinese (Mandarin) considerably contribute in web based information propagation. On the other hand, publications related to some regional specific scientific research areas (e.g.: earthquake and tsunami) and especially some art and literature related research areas fully or partially in a language other than English. Thus, searching based on single language definitely not provide complete appraise and synthesize of a research question. Therefore, in this paper we propose searching in multiple languages to gain much better evidence about the intended topic. Initial findings showed that the number of search results in Japanese language gave 89 times more results than search results in English when searching topics that has regional importance (e.g.: “"Earthquake resistant buildings"”). However, this is an exhausting and time consuming task; because the researcher has to do the same search several times in different languages. This drawback is because none of the popular search engines is capable of providing results in different languages simultaneously (e.g.: English, German, etc.) to a search topic in one language (e.g.: English). Therefore, to have better systematic review, we propose a search engine that is capable of taking search topic in one language and providing ordered results in multiple languages simultaneously, including a brief translation in intended language.
item:
An ad-hoc network based on low cost wi-fi device for iot device communication
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Elvitigala, CS; Sudantha, BH; Sudantha, BH
This paper provides an implementation which solves some of the problems in establishing and operation of ad Hoc networks for embedded system based IoT devices. For the implementation of the system, it used the currently famous module of ESP8266 ESP07 version and the module provides all the necessary features and facilities expected to be in such framework. The system also can work independently and it provides most of the operations that is not available in the current systems. This paper also shows one of the applications tested in this research as an implementation of the system. This solves most of the communication issues faced in ad hoc networks of various embedded systems.
item: Conference-Full-text
A review of augmented reality applications for tourism industry
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Peiris, HRR; Kulawansa, KADT; Sudantha, BH
Augmented reality has been popular among people because its ability to enhance collaboration between real world and virtual environment.AR has been used in many fields such as medical, education and automobile. Tourism is also one of those sectors. Lot of the cultural heritages of a country are centered on ruins. Most of the ruins have had complex structures and elaborate architectures, most of which have been reduced to a small percentage of what they originally were. Tourists cannot get clear understanding by just seeing ruins left present. This paper provides an overview of tourism applications that have been developed to get attraction of tourists and to enhance tourist experience while travelling Sri Lanka.
item: Conference-Full-text
A review of medical holographic technology
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Udeshika, MMAM; Kulawansa, KADT; Sudantha, BH
2D image is worth thousands, then 3D image is worth millions, with holography. New technologies invented with huge price tag. It’s same always. But, this revolutionary concept of Hologram for Medical Application is a gift of Science. No one can valuate Hologram Technology. This is so real and very reliable technology. In addition it has Artificial Intelligent features to collect information, process and generate 3D models of any organ in human body and also real time information can be acquired. System which controls future Medical Field. This paper explores the 3D image processing concepts and usage of Holographic Technology in Medical Field and new trends of Hologram Applications for generate real time 3D images.
item: Conference-Full-text
Rise of the smart cities in Sri Lanka
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Wijesinghe, WAN; Ganegoda, GU; Sudantha, BH
Today nations are presently concentrating on getting to be noticeably smart with a specific end goal to defeat the difficulties of expanding urban populace and practical improvement. Therefore, cities are heavily address their studies into energy management, telecommunication, transport, health, agriculture, surveillance, water resource systems, sewerage systems that anchor around reduce costs of living, improve efficiency and effectiveness of work, and deliver the quality as well as satisfaction of life. In other word it’s about productive thinking, innovation of latest technologies and devices which make life easy, ecologically sustainable transformation and entrepreneurial spirit counting investigation of financial advancement. As well as “Smart Technology” is obligatory which specifically, implies enhancement of mobility, transport, effectiveness of power generation process as well as optimum utilization of energy, entrepreneurial dynamics, systems based on information technolgy along with other essential services. As other nations in the world, today Sri Lanka also mainly focusing on becoming smart in near future. Therefore this paper first explain smart city concept with IoT technologies, secondly discusses recent smart projects, challenges and issues related with smart implementations in Sri Lankan context.
item: Conference-Full-text
Software solution effectiveness for image identification and artistic skills for visually impaired people through braille
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Fonseka, ODS; Wedasinghe, N; Sudantha, BH
At present the visually impaired individuals do not perform or engage much in art. They do not draw paintings because they don’t have the capability to draw a world unknown and unseen before. New immerging softwares are developed within the world but the success of it is enjoyed only by the visual impaired who can afford it. It’s mainly due to the low income status and high costs of such softwares or hardware equipment. Developing a baseline software in order to make all visually impaired individuals to get the ability to identify images within their mind and giving them the ability to draw them is referred within this paper. This paper also presents the pros and cons of previously developed systems in order to develop a better system in order for visually impaired individuals to perform art and identify the world beyond their sight. The results of the survey conducted for the research problem is also presented in this paper reflecting the ideas of the society on the Software solution effectiveness for Image Identification and Artistic skills for visually impaired people through Braille.
item: Conference-Full-text
4onse – 4 times open and non-conventional technology for sensing the environment: an integrated low-cost environmental monitoring system (ems) for developing countries
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Ratnayake, GR; Mahanama, PKS; Warusavitharana, EJ; Weerasinghe, SN; Warnakulasooriya, KMHK; Sudantha, BH; Jayasuriya, YP; Sudantha, BH
4 times Open & Non-conventional technologies for Sensing the Environment (4ONSE) is an ongoing joint research project between University of Moratuwa, Sri Lanka and University of Applied Sciences and Arts of Southern Switzerland. This project was initiated in a time where the necessity of a low-cost, non-conventional, and precise hydrometeorological monitoring system has been of great demand due to the increased number of weather-related environmental hazards and disasters in Sri Lanka. This work comprises an integrated approach to setting-up an experimental nonconventional Environment Monitoring System (EMS) based on open hardware, open software, open standards and open data which could measure the rainfall, wind speed, wind direction, relative humidity, air temperature, barometric pressure, soil moisture, light intensity, and the water level. With comparison to other available weather stations, this research argues the cost effectiveness of the 4ONSE system, in terms of its technology, hardware and software. Such a fully accessible, royalty-free and low cost system could provide developing countries with accessible technology for the so called ‘Internet of Things’ economy. Even though the use of technologically sound and low system is necessary to monitor the environmental data, less is known about use, validity, accuracy and cost effectiveness of such systems. This research explores the accuracy of 4ONSE’s measurements against those of a reference station and further explores and proves its effectiveness and suitability in terms of environmental monitoring in the context of developing countries.
item: Conference-Full-text
Intelligent personal assistant using multi-agent technology
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Rosa, SN; Hettige, B; Sudantha, BH
At present, most of the people not literate to carry out complex activities using computers. Hence to overcome this situation an intelligent personal assistant was introduced which has the capability of performing complex tasks on behalf of the user through the voice or text-based communication. These assistants make use of Artificial Intelligence techniques which are trending and evolving area in the aspect of Information Technology to address the difficulties that individuals face when using high tech devices with the aim of helping the growth of the use of new technology with no discrimination. Many such assistants have been developed so far using different technologies. We present such an assistant developed using multi-agent technology which can be considered as a promising technology when considering using on smart devices due to its robust and scalable nature. Thus, the developed system uses multi-agent technology for interprocess communication, Sphinx for voice recognition and the entire multi-agent system is developed with MaSMT framework including Manager agent and seven ordinary agents.
item: Conference-Full-text
Review of visual programming environments for conversational interfaces
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Dias, S; Chaminda, HT; Sudantha, BH
Conversational interfaces are a rapidly growing trend among organizations and consumers around the word. It is our belief that the process of production of conversational interfaces is more efficient when developed visually. From Virtual Assistants, to chatbots, everything interacts with users through conversation, instead of relying on traditional Graphical User Interfaces. Our goal is to develop a programming language, and a corresponding tool for developers to visually design the flow of conversations for any application in the field of dialogue management, while being able to perform various operations such as mathematical computations, programming functions (logics, conditions, loops, etc.), database queries, and external API calls. The proposed tool could be used to develop applications for existing VA and chatbot platforms such as Amazon Alexa or Facebook Messenger, or novel applications for custom systems interacting with users through conversation. In this paper, we propose an architecture for such a system and review existing implementations for each of its components.
item: Conference-Full-text
Low cost lab-scale bioreactor for optimization of microbial fermentation processes
(Proceedings of the 3rdth International Conference in Information Technology Research 2018, 2017-12) Warnakulassooriya, KMHK; Bandara, JDSACS; Sudantha, BH; Priyadarshana, KHH; Sudantha, BH
Due to the current environmental pollution crisis a food packaging industry always looking for environmental friendly methods for their use. The process of making poly lactic acid from lactic acid is achieved more and more attraction because it is considered to be the most demanded bio-degradable food packaging film rather than petroleum based polymer like polythene. This research is focused to make an instrumentation to enhance this process while reducing the instrumentation cost also. The device has been developed using Atmel general purpose microcontroller and few semiconductor sensors. The controlling of the device would be carried out automatically and date will be sent to a PC for further analysis.

Browse

Recent Submissions