Browsing by Author "Jayakody, A"

Now showing 1 - 20 of 59

Open Access
A novel application with explainable machine learning (SHAP and LIME) to predict soil N, P, and K nutrient content in cabbage cultivation
(Elsevier B.V., 2025-03-06) Abekoon, T; Sajindra, H; Rathnayake, N; Ekanayake, I, U; Jayakody, A; Rathnayake, U
Cabbage (Brassica oleracea var. capitata) is commonly cultivated in high altitudes and features dense, tightly packed leaves. The Green Coronet variety is well-known for its robust growth and culinary versatility. Maximizing yield is crucial for food sustainability. It is essential to predict the soil’s major nutrients (nitrogen, phosphorus, and potassium) to maximize the yield. Artificial intelligence is widely used for non-linear predictions with explainability. This research assessed the predictive capabilities of soil nitrogen, phosphorus, and potassium levels with explainable machine learning methods over an 85-day cabbage growth period. Experiments were conducted on cabbage plants grown in central hills of Sri Lanka. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used to clarify the model’s predictions. SHAP analysis showed that high feature values of the number of days and plant average leaf area negatively impacted for nutrient predictions, while high feature values of leaf count and plant height had a positive effect on the nutrient predictions. To validate the results, 15 greenhouse-grown cabbage plants at various growth stages were selected. The nitrogen, phosphorus, and potassium levels were measured and compared with the predicted values. These insights help refine predictive models and optimize agricultural practices. A user-friendly application was developed to improve the accessibility and interpretation of predictions. This tool is a user-friendly platform for end-users, enabling effective use of the model’s predictive capabilities.
Open Access
“AccessBIM” - A Model of Environmental Characteristics for Vision Impaired Indoor Navigation and Way Finding
(Curtin University, 2018-06) Jayakody, A
The navigation of indoor and outdoor environments play a pivotal role in the daily routine of humans. Navigation systems that provide path planning and exploration services for outdoor environments are readily available while navigation within a building is still a challenge due to limited information availability and the poor quality of GPS signals, which makes it difficult to capture characteristics within the indoor environment. Consequently, the use of GPS tracking devices for real-time map generation is not feasible. Indoor navigation is particularly difficult for people with vision impairment. According to the factsheet of the World Health Organization (WHO) as of October 2017, over 253 million people are estimated to be vision impaired: 36 million to be blind, and 217 to have poor vision. Currently, most blind and vision-impaired individuals use the white cane as an assistive tool and are often accompanied by care takers or voluntary helpers. Most modern indoor environments consist of complex architectural structures with varying arrangement of physical objects. Since retrieving indoor location information has been challenging for the vision impaired, it would be helpful if spatial information of doors, walls and staircases were made available. To address the above-mentioned problem, this thesis presents an improved schema design, an Accessible Building Information Model (AccessBIM) which could be used for generating an indoor map that could instruct vision impaired individuals in navigation, by the classification of real world objects and their locations. AccessBIM is a real-time relational database, which acts as the main component of the central system implemented to manipulate crowdsourced data such as the floor plan and architectural data along with semantic information within the built environment. The AccessBIM database stores information on the indoor arrangement of objects within buildings to facilitate the exchange and interoperability of real-time information. The database is equipped with an optimization algorithm that reduces the query execution time with the support of indexing, query re-writing, schema redesigning and a memory optimization technique introduced as “BIMcache”. vi In order to create a real-time map, the AccessBIM manipulates crowdsourced data from “smart devices” or AccessBIM users. The collection and storage of crowdsourced data, database optimization, API functions and the map construction algorithms were tested using a simulated test engine. The AccessBIM framework has the potential to play an integral role in assistive technologies related to localization and mapping, thus significantly improving the independence and quality of life for people with vision impairment whilst also decreasing the cost to the community related to support workers
Embargo
Agro-Mate: A Virtual Assister to Maximize Crop Yield in Agriculture Sector
(IEEE, 2021-12-09) Dayalini, S; Sathana, M; Navodya, P. R. N; Weerakkodi, R. W. A. I. M. N; Jayakody, A; Gamage, N
Information Technology plays a vital role in the agriculture industry. The main goal of the project is to develop a mobile application to support farmers to take accurate decisions and help them with activities such as soil quality determination, best crop selection, rice disease prediction, and disaster prediction for the wet zone of Sri Lanka. To achieve the main goal the project has incorporated advanced technologies such as Deep Learning, Image Processing (IP), Internet of Things (IoT), and Machine Learning that can support farmers or investors in a way to maximize yield. ‘Agro-Mate’ application is developed in a way to facilitate the agriculture industry. ‘Agro-Mate’ consists of four components such as soil quality determination and fertilizer recommendation, best crop selection, rice disease prediction and recommendation, and natural disaster prediction and providing the recommendation. Also, the application suggests fertilizer when soil is lacking quality and provides recommendations whenever rice diseases or natural disasters are identified. The usage of android mobile devices in agriculture is one of the key components of the sector's growth, which facilitates the farmer's inaccurate decision-making to gain more quality and quantity of crops. Agro-mate’ is more likely to increase the productivity of crops and indirectly increase the GDP of Sri Lanka.
Embargo
Agro-Mate: A Virtual Assister to Maximize Crop Yield in Agriculture Sector
(IEEE, 2021-12-09) Dayalini, S; Sathana, M; Navodya, P. R. N; Weerakkodi, R. W. A. I. M. N; Jayakody, A; Gamage, N
Information Technology plays a vital role in the agriculture industry. The main goal of the project is to develop a mobile application to support farmers to take accurate decisions and help them with activities such as soil quality determination, best crop selection, rice disease prediction, and disaster prediction for the wet zone of Sri Lanka. To achieve the main goal the project has incorporated advanced technologies such as Deep Learning, Image Processing (IP), Internet of Things (IoT), and Machine Learning that can support farmers or investors in a way to maximize yield. ‘Agro-Mate’ application is developed in a way to facilitate the agriculture industry. ‘Agro-Mate’ consists of four components such as soil quality determination and fertilizer recommendation, best crop selection, rice disease prediction and recommendation, and natural disaster prediction and providing the recommendation. Also, the application suggests fertilizer when soil is lacking quality and provides recommendations whenever rice diseases or natural disasters are identified. The usage of android mobile devices in agriculture is one of the key components of the sector's growth, which facilitates the farmer's inaccurate decision-making to gain more quality and quantity of crops. Agro-mate’ is more likely to increase the productivity of crops and indirectly increase the GDP of Sri Lanka.
Embargo
AI Based Cyber Threats and Vulnerability Detection, Prevention and Prediction System
(IEEE, 2019-12-05) Amarasinghe, A. M. S. N; Wijesinghe, W. A. C. H; Nirmana, D. L. A; Jayakody, A; Priyankara, A. M. S
Security of the computer systems is the most important factor for single users and businesses, because an attack on a system can cause data loss and considerable harm to the businesses. Due to the increment of the range of the cyber-attacks, anti-virus scanners cannot fulfil the need for protection. Hence, the increment of the skill level that required for the development of cyber threats and the availability of the attacking tools on the internet, the need for Artificial Intelligence-based systems, is a must to the users. The proposed approach is an automated system that consists of a mechanism to deploy vulnerabilities and a rich database with known vulnerabilities. The Convolutional Neural Networks detects the vulnerabilities and the artificial intelligence-based generative models do the prevention process and improves reliability. The prediction procedure implemented using the algorithm called “Time Series” and the model called “SARIMA”. These implementations give an output with considerable accuracy.
Embargo
An algorithm for labeling topological maps to represent point of interest for vision impaired navigation
(IEEE, 2015-10-13) Jayakody, A; Murray, I; Herrmann, J
Navigation in indoor environments is highly challenging for both vision impaired and sighted people, particularly in unknown environments visited for the first time. Several solutions have been implemented and proposed to deal with this challenge. Although some of them have shown to be useful in real scenarios, each solution involves a significant deployment effort or describes objects in a manner that is unfamiliar or incomprehensible to an individual with severe blindness. This paper presents a model of adding informational point of interest to the typical indoor topological map; with particular attention to the semantic labels of the different type of indoor places and proposes a simple way to include the tags to build the topological map. Using this POI and the semantic information, the system determines the user's path, locates possible obstacles on that route, and offers navigation information to assist vision impaired navigation.
Embargo
Assistive Learning Platform for Children with Down Syndrome
(IEEE, 2020-11-04) Wellala, S; Thathsarani, S. A; Senaratne, D; Samaranayake, P; Jayakody, A
Down Syndrome (DS) is a genetic disorder. Researchers believe that persons with DS generally have poor logical knowledge, communication, motor skills, and skills needed for everyday life. The proposed system is a web-based assistive learning platform for children with DS to address those problems. It provides an excellent opportunity for learning educational subjects, including math and language. The authors also created interactive modules improving their health habits, social skills, and motor skills. Since the authors deeply consider their requirements, the system was developed by providing excellent features with those modules. Users' faces can be recognized to keep their attention with the system, thereby suggesting and referring their most interesting content according to their emotions while using the system. Also, the dashboard can analyze user data. Most importantly, it capable of assessing the users through the system. Here the research team has assessed 50 children with DS, and 31 showed improvement after using the system. Therefore, the proposed system with all these modules and features can be introduced as a very productive assistive learning platform in Sri Lanka.
Embargo
AVII [assist vision impaired individual]: an intelligent indoor navigation system for the vision impaired individuals with vlc
(IEEE, 2016-12-16) Jayakody, A; Meegama, C. I; Pinnawalage, H. U; Muwenwella, R. M. H. N; Dalpathado, S. C
Vision impaired individuals confront unique challenges every day in their day-to-day life when navigating in unfamiliar public locations. The proposed system focuses on designing a device for vision impaired people that is comfortable, user friendly and can help with travelling independently. The solution is an audio guidance system that provides guidance through voice commands and beep sounds. In this study, authors propose an indoor navigation system that utilizes visible light communication (VLC) technology, which employs LED lights, geomagnetism technology, best path detection algorithms and obstacle detection aimed at supporting visually impaired people to overcome the positioning and navigating problems. System uses a MCU based mechanism to transmit positional information by leveraging the existing LED lights of the indoor environment. The study looks at an improved version of Dijkstra's algorithm to estimate search time and distance to find the best path for the navigation purposes. Geomagnetic sensor is used to obtain the travelling direction of the visually impaired individual to provide an extreme accurate system to take the turns accurately according to the best path and to correct the individual while traveling. Sonar sensors are used for obstacle detection which aids the individual to prevent any collisions or injury. Database optimization involves in increasing the speed and efficiency of the retrieved data and reduces the system response time.
Embargo
Awareness of Sri Lankan internet users on web browsing related threats and vulnerabilities
(IEEE, 2016-12-16) Ilangakoon, S. D; Jayakody, A
This research work presents new trends in cyber threats, and it also quantifies user awareness of web threats and attacks. Using an online questionnaire information for the analysis of whether individuals had adequate knowledge of internet threats and attacks in order to safeguard themselves was obtained. The survey showed that many users lack an adequate understanding of what to do and what not to do in order to remain safe on the internet. Therefore, it is crucial that training and awareness be given to all individuals, especially at a young age.
Embargo
Cloud Native Efficient Solution for API Migration Across Environments For Agile Integration Enterprises
(IEEE, 2019-12-05) Jayakody, A; Perera, A. K. A; Perera, G. L. A. K. N
This paper describes an approach to minimize the effort and time in recreating Application programming interface artifacts and facilitate cross-collaboration and efficient migration across heterogeneous platforms environments without any significant post-migration changes and additional effort. The current software development evolution came up with the Agile concept of developing and delivering products in milestones based approach software development organizations are now maintaining separate environments for development, quality assurance, and production. These environments execute independently and have their deployments and own methods of traffic control. When moving Application programming interface artifacts from one environment to another, all the created APIs need to migrate across different environments to test the exact functionality and behavior of the application. Our motivation is to minimize the effort and time in recreating APIs and facilitate accurate and efficient migration across different environments without any significant post-migration changes and additional effort.
Embargo
Common Object Request Broker-based Publisher-Subscriber Middleware for Internet of Things - Edge Computing
(IEEE, 2022-10-04) Perera, H; Jayakody, A
The edge computing layer in IoT reduces the flow of a massive amount of data directly to the cloud by processing some data in the local network. The middleware in the layer enables this processing of data and the communication between heterogeneous devices and services in the nearby layers. CORBA, which uses as a powerful middleware technology in developing middleware solutions in enterprise-level distributed applications, has been abandoned in the current generation. The paper presents the design, and the performance evaluation of a publisher-subscriber middleware implemented using CORBA that was studied when exploring the applicability of CORBA as an IoT edge computing middleware. The evaluation was continued in two steps to analyse several parallel connections (Load test) and handle requests in a unit time (burst test) via simulating an IoT environment in a cloud environment.
Embargo
Compromising AODV for better performance: Improve energy efficiency in AODV
(IEEE, 2017-01-27) Paranavithana, P; Jayakody, A
MANETs became a principal research area as a promising routing protocol for a large scale of applications, due to its' behavior of self-configuring ability according to the infrastructure. Energy efficient in MANETs is a significant area in MANETs related researchers. Nodes in a MANET networks are basically battery operated, and thus have access to a limited amount of energy. The lack of energy can lead to a link failure during an active communication session, which affects the throughput and energy wastage due to a re-run of the algorithm. These papers presents a modified AODV algorithm, where a node calculates its residual energy and select the best path based on the existing matrices and total energy of the path. During the RREQ packet exchange, each node adds its residual energy to the packet and forwards it until it reaches the destination. At the destination, the total energy value is copied to the RREP packet from RREQ packet and sent to the source node through the reverse path. During the process of route selection, the path with the highest energy value gets the priority.
Embargo
The construction of an indoor floor plan using a smartphone for future usage of blind indoor navigation
(IEEE, 2014-11-27) Jayakody, A; Murray, I
Most blind people require assistance to navigate within unfamiliar environments as there is often insufficient information about the buildings available to them. To address aspects of this problem, this paper describes the “AccessBIM” model as an approach to facility management in which a digital representation of the indoor building features is used to facilitate the exchange and interoperability of real-time information in digital format which can assist blind people to independently access unfamiliar building indoor environments. The model driven architecture that can be implemented for way finding and data synchronization, generating, in real-time topological map, to assist vision impaired individuals to navigate known and unknown indoor environment.
Embargo
Context Rich Hybrid Navigation Using WiFi and Geomagnetic Sensors in Smartphones and Map Generation Using Lidar
(IEEE, 2019-10-08) Jayakody, A; Lokuliyana, S; Weerawardene, V. N. N; Somathilake, K. D. P. S; Ishara, A. M. D. D. U
Navigation systems perform a huge role in traveling component of life. Most importantly it helps people to get to places even in foreign or unfamiliar environments. This research introduces a way of mapping environments with less effort, which shows that mapping an indoor environment is an easy task that could be performed by any tech savvy individual. This has been done by examining several projects and researches conducted by various personnel and organizations including NASA. It has become clear that the technology `LIDAR,' is clearly feasible for the requirement of indoor map generation. A software was later built to accommodate the device which is built using LIDAR and to give the user a better experience in map generation. The software helps to overcome the limitations that are imposed by the device. The overall product with the device and software integrated provides an ideal low-budget solution for the users. The proposed system service features three highly desirable properties, namely accuracy, scalability, and crowdsourcing. IPS is implemented with a set of crowdsourcing-supportive mechanisms to handle the collective amount of raw data, filter incorrect user contributions and exploit Wi-Fi data from diverse mobile devices. Furthermore, it uses a big-data architecture for efficient storage and retrieval of localization and mapping data. In this research, the service relies on the sensitive data collected by smartphones (Wi-Fi signal strength and geomagnetic measurements) to deliver reliable indoor geolocation information.
Embargo
Converting high resolution multi-lingual printed document images in to editable text using image processing and artificial intelligence
(IEEE, 2022-06-21) Jayakody, A; Premachandra, H. W. H; Kawanaka, H
The optical character recognition technique is used to convert information, mainly printed or handwritten text in paper materials, into an electronic format that the computers can edit. According to the literature, there are few competent OCR systems for recognizing multilingual characters in the form of Sinhala and English characters together. The lack of an appropriate technology to recognize multilingual text still remains as a problem that the current research community must address, and it has been designated as the key problem for this study. The main goal of this research is to develop a multilingual character recognition system that uses character image geometry features and Artificial Neural Networks to recognize printed Sinhala and English scripts together. It is intended that the solution would be improved to cover three Sri Lanka’s most commonly spoken languages, with the addition of Tamil as a later upgrade. The primary technologies for this study were character geometry features and Artificial Neural Networks. At the moment almost an 85% of success rate has been achieved with a database containing around 800 images, which are divided into 46 characters (20 Sinhala and 26 English), and each character is represented in 20 different forms of character images. Recognition of text from printed bi-lingual documents is experimented by extracting individual character data from such printed text documents and feeding them to the system.
Embargo
Database modelling for vision impaired indoor navigation systems
(IEEE, 2015-08-24) Jayakody, A; Murray, I; Herrmann, J
Cooperative research has been conducted to improve navigation services for vision impaired when they are moving through an indoor environment. Hence, to facilitate vision impaired individual in indoor environment requires a formal modelling approach for map generation and decision making about navigation pathways avoiding obstacles. The proposed data model consists "AccessBIM" database (DB) and API functions. The "AccessBIM" features such as, database connection initiation, function call, function return and database connection termination are organized as a series of function objects that meet the various needs of the database to maintain the relational schema. The proposed API primarily consists of two components, namely; DB connector and the API functions. Proposed "AccessBIM" DB will be implemented using real-time database such as "PostgreSQL". The weighted focus will be given to the areas such as Queries, Indexes and Transactions in relation to tuning the DB and the queries. The performance of the proposed API will be evaluated based on the time required to parse and Data insert rate and retrieval rates.
Embargo
A database optimization model with quantitative benchmark
(IEEE, 2016-03-11) Murray, I; Jayakody, A; Herrmann, J; Lokuliyana, S; Kandawala, D. S. A; Nanayakkara, S. E. C
Query optimization and indexing have an immense impact on database optimization. This has been considered in many different perspectives which provide several different solutions in each case. The purpose of this paper is to primarily provide a comprehensive review and discussion of the core problems through the research on query optimization technology and indexing, based on a number of optimization techniques commonly used in the general approach of a query. A new database optimization model is designed and experiments show that this model can significantly reduce the amount of query execution time to improve the optimization efficiency. Regardless of research on the database optimization model, significant work has been done to comparatively evaluate three scenarios; non-optimized query, optimized query without following any optimization standard, and optimized query via proposed optimization model using the same experimental methodology. Further, this paper describes a benchmark that was developed specifically for the purpose of measuring the quantitative evaluations of the proposed database optimization model.
Open Access
Digital Talking Book
(https://www.researchgate.net/publication/280314319, 2015-07) Thirasi, W. A. P. B; Illangasinghe, I. M. B. S. C; Dickwella, U. P; Jayakody, A; Peiris, G. C; Lokuliyana, S
This paper, presents user friendly ways to read books for print disable individuals. "Reading" is the process of looking at a series of written symbols and making meaning from them. However, there, the print disabled who are, the blind, partially sighted, dyslexics, those with visual impairments, physically disabled, and learning-disabled who have difficulty in accessing print media information. Digital talking books are the significant technology for the print disabled community to access printed media information. The Digital Accessible Information System (DAISY) technology; it is an open international standard for accessible multimedia developed by libraries serving persons with print disabilities in collaboration with the target users around the globe. The proposed “Talking Book" improves the blind users' ability to read digital daisy books. The main function of the talking book player; computer memory and retrieves bookmarks, automatically unzip downloaded zip files and convert them into readable manner. Additionally, it consists predefined gestures and voice commands to navigate through the pages in the diligence. This paper presents a user interface with an easy-to-distinguish layout, auditory output and gestural input that enables visually impaired people to interact with an Android smartphone device.
Embargo
Document Reader for Vision Impaired Elementary School Children to Identify Printed Images
(IEEE, 2019-12-05) Gamage, N. D. U; Jayadewa, K. W. C; Jayakody, A
Vision Impairment is a severe reduction of one or more functions of the eye. The print disability prevents a person from gaining information from printed material in the standard way and requires them to utilize alternative methods to access the information. World Health Organization estimated that nineteen (19) million children are visually impaired worldwide. As they are the future of the world it is necessary to eradicate barriers to the journey of gaining knowledge. Hence, this paper presents a mobile-based application targeting elementary school students to read textual documents, which contains a graphical image. The mobile application provides audio assistance to navigate through a mobile application, autofocused image capturing of printed papers, store captured images, classify selected text, images, and read-aloud generated digitized text. Therefore, “Schmoozer” would allow visually impaired individuals to read unbraided documents without others' interaction. Furthermore, this paper discusses the test results and evaluations to justify the feasibility of the proposed solution.
Unknown
Efficient Agricultural Sensor Network with Disease Detection
(IEEE, 2019-12-05) Gunathilaka, M. D. N; Lokuliyana, S; Udurawana, A. W. G. C; Dissanayaka, D. M. A. S; Jayakody, A
The smart Agriculture concept is a new trending topic in making traditional agriculture task automation to make them more effective and efficient to suit current human requirements. With machine learning and image processing technologies those tasks are made more robust and accurate while maintaining the low cost made this research inspired to adopt Sri Lankan farmers to develop a real-time disease detection monitoring system with wireless sensor node for crops, so that would be able to harvest and store energy for battery-free operation using supercapacitors and technologies such as Maximum Power Point Tracking. The main outcomes of this nodes are to monitor the growth environment and also the crop for diseases by using image processing and machine learning techniques in order to cultivate a better fruit overall. The wireless sensor node can be adapted to be used on multiple types of remote farms. Pineapple (Ananas comosus) was selected as the test crop for the research which is a fruit grown widely in tropical countries in large fields. The texture, shape of the fruit and the taste of pineapple changes due to various conditions. The final system makes monitoring the crop for diseases a lot effective while making monitoring the growth conditions more efficient compared with what's available on the market.