Browsing by Author "Wilson, R.S.I."

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Application of Image Processing and Neural Network Technique for Rice Grading
    (Uva Wellassa University of Sri Lanka, 2019-02) Wasana, P.L.D.; Fernando, P.S.R.; Lakmal, M.K.A.; Illoshini, P.A.A.; Wilson, R.S.I.; Ekanayake, E.M.U.W.J.B.
    When considering the agricultural industry, Rice is a principal food source in Asian countries. It is the most commonly and widely used grain in the local consumer market. Thus, analyzing the quality of rice is important. The quality of Rice will depend on the milling. Most mill owners do not have a proper method of measuring the quality of rice. Calculations are currently carried out using the Vernier Caliper in research centers, but it is a time-consuming task. Though there are some machines for automating this process, its usage is very low because of the high cost. Rice can primarily be classified based on colour and shape. Here we analyzed the two genres, Red Kekulu rice and Samba rice produced by Bombuwala rice research center. This paper introduces the rice classification method according to image processing approaches and neural network. Physical characteristics of the grain such as major and minor axis length, perimeter, area, colour and chalkiness are used to classify the rice grains. Identifying broken rice and wastages are the major objectives of the grading system. We have compared the proposed system results with manual measurements and visual observations. Matlab tool is used for image acquisition, preprocessing, segmentation, feature extraction and training the data set. This proposed grading system has scales such as premium, grade A, grade B and it was defined under supervision of rice researchers using broken rice and wastage content. The proposed image processing methods can reduce the time of operation and increase the accuracy. Finally, with the proposed grading system consumers will be able to receive information regarding the quality of the rice.
  • Thumbnail Image
    Item
    Distinguish Garnet Mineral from Pulmuddai Beach Sand Using Image Processing Techniques
    (Uva Wellassa University of Sri Lanka, 2019-02) Hirosh, D.M.H.; Darshana, J.V.A.; Doratiyawa, H.M.M.S.; Wilson, R.S.I.; Mehendran, Y.; Jaliya, R.G.C.
    Beach sand is one of the major minerals producing source in Sri Lanka. Pulmuddai Beach, rich in Ilmenite, Rutile and Zircon and Garnet and it is the largest mineral processing plant in Sri Lanka. It's a great necessity to explore high mineral localities for production. In the industrial level, the percentage of a specific mineral is calculated using a visual inspection through a microscope which is manual and time-consuming. The research introduces an innovative method to distinguish Garnet mineral from sand using image processing techniques. In this study, 1125 visible light RGB (Red, Green, Blue) images and 1125 Infrared (IR) images of beach sand were captured in a controlled light environment. RGB color composite images and IR images were analyzed separately to identify Garnet mineral from the gang and to calculate Garnet percentage. For the machine learning classification purpose, contrast, variance, mean, median, min, max, range, kurtosis, skewness, standard deviation and correlation were extracted from sand grains images. Then RGB, HSV (Hue, Saturation, Value) and RGBIR (Red, Green, Blue and Infrared) color models were used through a machine learning model. The highest accuracy of 63% of separation accuracy was given by the HSV color model. The accuracy could be increased by introducing more images to the machine learning process. The final model was built based on the HSV color model since it has the high accuracy of separation. Then the HSV model subjected to object counting model, area-based counting model and volume based counting model to identify the most suitable method for the percentage calculations. Among these three methods, an object counting model produced the more accuracy results with 57%. Thus, the HSV color model incorporates with object counting model produces the best combination to identify Garnet and calculate its percentage.
  • No Thumbnail Available
    Item
    Embedded System for Identifying the Quality of Grass Using Colour Patterns for the Sri Lankan Dairy Industry
    (Uva Wellassa University of Sri Lanka, 2020) Jayaweera, S.M.D.B.; Rupasinghe, P.M.S.; Eranda, S.A.L.; Ratnayake, A.M.B.; Jayasinghe, J.M.P.; Wilson, R.S.I.
    Sri Lankan dairy sector operates at its suboptimal level. Efficient and reliable technologies are needed to increase productivity enabling farmers to make farm management decisions based on accurate and current information. Precision farming technologies could be successfully integrated to monitor farm-grown pasture and make real-time decisions to optimize utilization. The present study is aimed to develop an embedded system-based method to efficiently monitor and utilize available pasture in dairy farming. A custom-made drone with F450 frame and Ardu pilot mega 2.6 was used in the study. The drone was tested at Uva Wellassa University and NLDB farm, Melsiripura. Flight controller was automated using the mission planner tool to fly at an automated waypoint flight of a Grid pattern. Drone mounted go-pro camera was used to acquire pre-processed images contained GPS metadata and webODM tool merged images with GPS data to produce a georeferenced output (Orthomosaic image). Developed shadow removal algorithm converted BGR to YCbCr color space and computed average Y channel and intensities. Subsequent process detected shadow regions and saved binary shadow images. Then the algorithm computed average pixel intensities of shadow and non-shadow areas adding difference with Y channel. Furthermore, the color identification algorithm obtained shadow processed image and applied the median filter (blur/Sharpened image) to convert color mode from RGB to HSV format. The image was color filtered based on identified color ranges of high yield grass. To identify overall color identification, an aerial map was marked by an expert in the field, subsequently algorithm processed image and marked image compared. Images were measured by pixels coverage of marked area and results provided a 90% identification rate through the algorithm. Results revealed, developed an embedded system-based method successfully measured field grass coverage compared with a manual method. Keywords: Embedded system, Pasture, Precision agriculture, Colour identification
  • No Thumbnail Available
    Item
    An Image Processing Application for Diagnosing Acute Lymphoblastic Leukaemia (ALL)
    (Uva Wellassa University of Sri Lanka, 2021) Rathnayake, R.M.S.K.K.; Piyumali, R.W.S.U.; Withanage, W.S.U.; Pathirana, K.P.P.S.; Wilson, R.S.I.
    Acute Lymphoblastic Leukaemia is a fatal disease that affects white blood cells and bone marrow in the human body. Every year, considerably a large number of adolescents and children become victims of this type of leukaemia. The early detection of this disease directly affects the recovery rate of the patients. In the manual process, pathologists can identify Acute Lymphoblastic Leukaemia and the accuracy of the prediction may rely upon their experience. Hence this research has proposed an image processing approach for early detection of Acute Lymphoblastic Leukaemia cells to prevent the spreading of cancer, enabling the medical experts to initiate the treatment without any delay and increase the recovery rate of such patients. For that, microscopic blood sample images were analyzed considering the features such as color, shape, presence of nucleoli, and nucleon to a cytoplasmic ratio of the cells separately using three Conventional Neural Networks (CNNs). Based on that, the Acute Lymphoblastic Leukaemia cells were identified and classified as either Acute Lymphoblastic Leukaemia or healthy. Compared to the laboratory testing methods, this approach obviously leads to early detection of Acute Lymphoblastic Leukaemia with an accuracy of 94.57% that has been confirmed by the domain experts. The proposed approach is an effective and less expensive method that would assist doctors to get fast and accurate results. Hence the originality of this research was to identify the presence of Acute Lymphoblastic Leukaemia cells in the microscopic blood sample images and classify them as either Acute Lymphoblastic Leukaemia or healthy by identifying the features of the Acute Lymphoblastic Leukaemia cells separately. Moreover, this research has found that Conventional Neural Networks (CNN) is the most suitable Neural Network to identify Acute Lymphoblastic Leukaemia using image processing technique. Keywords: Acute Lymphoblastic Leukaemia; white blood cells; conventional neural networks; Image Processing; Machine Learning
  • No Thumbnail Available
    Item
    A Nutrient Based Diet Plan Recommendation System using Machine Learning
    (Uva Wellassa University of Sri Lanka, 2021) Baskaran, K.; Yokarasa, K.; Paraloganathan, V.; Ekanayake, E.M.U.W.J.B.; Wilson, R.S.I.
    At present obesity is a key health issue as everyone is busy with their day-to-day lives. Existing diet recommendation systems suggest a common diet plan instead of considering the person‟s lifestyle and diseases and hence it leads to health issues. This research develops a system to recommend an appropriate diet plan for each person based on their personal profiles. The proposed system collects the personal information from users such as age, height, weight, gender, chronic diseases, and physical activities, and then it recommends the diet plans for the breakfast, lunch, tea time and dinner with appropriate calorie levels (carbohydrate, protein, lipid, calcium, phosphorous, fiber and iron) that helps to maintain the healthy weight of the body. The data was collected from the hospitals using a questionnaire. A Linear Regression models and a Neural Network model are trained to predict the required amount of calories per day based on the users‟ profile. Based on the error rate comparison of both model, the Neural Network model is the best fit for calorie prediction. The diet plan is defined by a rule-based system based on the predicted calorie level. The predicted diet plan for a given user is compared with the diet plan recommended by a nutritionist to measure the accuracy of the proposed system. Accordingly, the prediction accuracy of the system is 95%, which is decent enough when compared to the existing models in the literature. A limited number of parameters of users are considered to predict the calorie level and the diet food combinations. However, considering more parameters would further enhance the diet plan suggestions. Keywords: Machine Learning; Obesity; Linear Regression; Neural Network; Diet Plan
  • No Thumbnail Available
    Item
    Preliminary Study on ICT Applications in Agriculture to Enhance Information System using Mobile Crowdsensing
    (Uva Wellassa University of Sri Lanka, 2018) Wilson, R.S.I.; Goonetillake, M.D.J.S.; Walisadeera, A.I.
    This study analyzed the existing Information and Communication Technology (ICT) applications in the agriculture information system and proposed a method to enhance a mobile-based information system using mobile crowdsensing. The proposed system enables farmers in Sri Lanka to report events such as diseases, about their crops and get advices for making farming decisions. The lack of realtime information environment makes issues in the farming life cycle and that will affect the national economy and employment. Existing studies were analyzed for identifying the capability to establish a mobile-based information environment in the farmer-community in Sri Lanka. The applications introduced in the studies are covering several aspects such as market price, vendors, crop details, pest and disease information, etc. In order to create a real-time information environment, the real-time data related to farms need to be collected. Mobile sensing is a technique to obtain real-time data from a large group of individuals. Thus, the mobile sensing technique introduces for the farmer-community that allows farmers to participate the system by sharing mobile sensing data like images, text, voice, location, date and time. The knowledge-base of the system contains knowledge about crops, diseases, pests, fertilizer requirements and control methods for growing problems. Thus, the agriculture information in the knowledge-base can be accessed by the farmers according to the shared sensory data. Over the time period, agriculture information can be updated as the technology advancement, seasonal changes or unexpected weather changes. Thus, new knowledge needs to be stored in the agriculture knowledge-base with the help of domain experts. Moreover, by reasoning the collective data shared by farmers and experts, interesting aspects like the suitable crops to grow in a particular area, the crops badly affected by a specified disease in a particular area or treats rapidly spread in a particular period, etc. can be obtained for decision making. Further analysis can be done for future predictions from the large collection of data.
  • No Thumbnail Available
    Item
    Real-Time Bus Tracking System for Minimizing Passenger Time Wastage in Sri Lanka
    (Uva Wellassa University of Sri Lanka, 2020) Jayasekara, A.V.; Jayasekara, L.B.R; Wilson, R.S.I.
    Bus transportation has become the major transportation mode in Sri Lanka due to ease of access and cost-effectiveness. However, the passengers, mainly those who are in the middle stations, face the difficulties of getting a bus because of the unavailability of a solid mechanism to get the real-time bus location. After several field visits and interviews with the respective bodies, the study has introduced a solution for the passenger time wastage by developing an Arduino based device and a simplified user environment. This device consists of UNO microcontroller, SIM800c GSM module, and NEO 6m GPS which is capable of achieving the highest sensitivity of the industry by tracking up to twenty-two satellites on fifty channels. The Tiny GPS++ library was included and some conducive core sub-objects like the latest position fix, latest altitude fix, the number of visible participating satellites, and horizontal diminution of precision adapted to succeed in the process. After setting up the configuration of the GSM, checks the availability of AT commands. AT commands are used for receiving an SMS sent by the user requesting the current location. As the user environment, a Cross-Platform web application is developed, including bus information in which the user can get bus journey/fare details, bus ID which is provided by the system to uniquely identify a particular bus, and its realtime location. The user can receive the location just via an SMS as a google maps link, using that bus ID. Moreover, to assess the functionalities and usability, the Arduino based tracking device was placed in a bus and a potential user was provided with the web application. The user could manage simple operations and get information about the desired bus. Further, the study recommends the use of this web application to trivialize the time wastage and irregularity of bus service and make people more attracted to public bus transportation. Keywords: Arduino-based device, GSM Module, GPS, Real-time bus tracking