Science

Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/1

Browse

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Interpretation of Sri Lankan Sign Language: A Wearable Sensor-based Approach
    (Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Kusalanga, M.N.; Jayalal, S.; Wijayasiriwardhane, T. K.
    Hearing-impaired and speech-impaired people communicate not only with themselves but also with ordinary people using visual languages. Sri Lankan Sign Language (SSL) is the standard visual language used in Sri Lanka. Like other sign languages, the SSL relies on a distinct combination of hand gestures, body movements, and facial expressions for communication. As a result, SSL is more challenging for individuals without knowledge of SSL to understand. On the other hand, the steep learning curve associated with SSL makes it even more difficult to acquire. Thus, the interpretation of SSL has become a need. However, Sri Lanka is suffering from a severe dearth in the availability of SSL interpreters. This justifies the need to use either vision- based or sensor-based technological approaches to help the interpretation of SSL. However, vision-based approaches are susceptible to conditions such as skin tone, background color, ambient light intensity, and real-time constraints, whilst the sensor-based solutions are generally better in gesture recognition. Further, there is no attempt has been made on developing a cost-effective, portable, and real-time solution to accurately interpret the hand gestures of SSL. In this paper, we, therefore, present a novel, wearable, sensor-based, real-time gesture recognition glove, and a machine-learning Long Short-Term Memory (LSTM) model to recognize the hand and finger positions in three-dimensional space for classification and interpretation of SSL. The proposed approach has achieved 320ms of lowest inference time while showing a promising result of 83% for categorical accuracy. Our aim is to help the interpretation of SSL with an affordable, portable as well as a real-time solution.
  • Thumbnail Image
    Item
    A method to determine user location distribution pattern in a Wi-Fi network through SNMP protocol
    (Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Abeysekara, A. M. R. B.; Jayawardena, B.; Wijayasiriwardhane, T. K.
    In today’s connected world, the biggest challenge that a network manager encounters is the allocation of the bandwidth within the network in response to the user requests to increase it in different areas of the network. However, due to the limited bandwidth provided by the service provider, in most of the situations, the network manager would not be in a position to increase the bandwidth as much as the users’ request. This is because to increase the bandwidth in a particular area, it requires to decrease the bandwidth in some other area in the network in order to maintain a maximum utilization of the provided bandwidth in the entire network. On the other hand, in every network there is a pattern of user location distribution. As a result, some areas in the network require more bandwidth during a certain period of time due to the more users located in that area during that period of time whilst the other areas may not need that much of bandwidth due to the lesser number of users located. Therefore, if the pattern of user location distribution of a network can be determined, the network manager can dynamically allocate a different amount of bandwidth to the different areas of the network accordingly. In this research, we propose a novel method to determine the user location distribution data in a Wi-Fi network using Simple Network Management Protocol (SNMP protocol) and thereby to identify any pattern of user location distribution against the time. In our method is, first we get the information such as MAC addresses, IP Addresses using SNMP protocol from the routers in the network. From that information, we then get the location distribution of the users based on the router’s location. We use that information to do pattern analysis and the location distribution pattern against the time is then determined. Our aim is to provide a more rational approach for network managers to allocate different amounts of bandwidth to different areas in their network while maintaining a maximum utilization of the provided bandwidth in the entire network.
  • Thumbnail Image
    Item
    A haptic feeding GPS navigation solution for the visually impaired.
    (International Research Symposium on Pure and Applied Sciences, 2017 Faculty of Science, University of Kelaniya, Sri Lanka., 2017) Rajatheja, M. K. B. C.; Wijayasiriwardhane, T. K.
    According to a fact sheet published by the World Health Organization (WHO) in 2014, it is estimated that 285 million people are visually impaired worldwide and out of which 39 million of people are blind. Further, about 90 percent of the visually impaired people in the world live in low-income settings. Among many difficulties that they encounter in their day-to-day activities, the visually impaired people are often disadvantaged particularly when travelling due their inability to see the obstacles and visual signs of directions that are essential to navigate not only through the unfamiliar terrains but also in the familiar environments. Therefore, the visually impaired people usually use a white cane to detect obstacles on their path and also get the assistance of the trained guide dogs. However, when they roam in an unfamiliar environment, they always have to rely on a third party for finding their directions. With the advancement of the Global Positioning System (GPS) technology, development of GPS navigation solutions for the visually impaired people have become an active domain of research in the recent years. They include the Brunel Navigation System for the Blind, BrailleNote GPS, Trekker Breeze and BlindSquare to name a few. However, the most of the present GPS navigation solutions for the visually impaired people are based on the auditory perception of visual information. These navigation systems capture data from various sensors and information services, process them and convert the navigational instructions into sounds. As the visually impaired people see the world through their ears due to their lack of vision, these sonification systems not only pose a high risk of interference to a visually impaired traveler’s perception of environmental sounds, but also attract an unnecessary attention. In this paper, we propose a novel GPS navigation solution for the visually impaired, with a haptic feeding system as an alternative to the sonification systems. The objective is to develop an economically viable haptic feeding GPS navigation system that could be used, to assist them in their everyday activities without having to depend on care providers. The proposed solution contains two interconnected main components, a wearable device and a navigational directions providing server. The wearable device consists of a haptic feeding system, a GPS locator, a GSM module, an electronic compass and an embedded processor. The navigational directions providing server, obtains real-time navigational directions from the free Google Map Direction API using the GPS location of the wearable device and intended destination to be reached. The obtained navigational directions are then narrowed-down into simple navigational directions in order to meet the requirements of the haptic feeding system. These simple navigational directions are transferred into the wearable device via a GSM link. Based on the simple navigational directions, the visually impaired user is then guided with simple and easily understandable haptic instructions until the destination is reached.