Smart computing & Systems Engineering - (SCSE - 2019)

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/20146

Browse

Author: search.filters.author.Jayalal, S.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Sinhala Handwritten Postal Address Recognition for Postal Sorting
    (IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Ifhaam, M.F.A.; Jayalal, S.
    Sri Lankan post office mail sorting process is done manually, even today. Though employees are well experienced, it takes considerable time and employees need to work overtime in places like Central Mail Exchange (CME). With major issues like unclear handwriting, having trouble to recognize some uncommon or ambiguous names, and carrying these duties twice a day create a negative impact on the efficiency of the postal delivery system. In the prevailing system, forward mails and delivery mails are the two categories of separating mails at the sorting centers. Delivery mails are the posts which can be delivered to its destination directly. Forward mails are the ones which need to be sent to an appropriate post office that can deliver the particular post to its destination. Majority of Sri Lankans use Sinhala language for their day to day activities. The primary objective of the research is to identify the automatic way of forwarding the letter to the next post office from the current post office. Proposed system is focused on the recognition of Sinhala handwriting using Optical Character Recognition (OCR) and image processing technologies. Data collected under different criteria were used for training and testing the solution. Genetic Algorithm (GA) was used to generate more optimized results faster with higher accuracy. Given addresses are written in the default format. This format can be extended to more formats as improvements in future. The algorithm shows accuracy over 92% for addresses which are recognized with 3 misrecognized characters. This algorithm can be used on practice scenario as the AI Recognition has more than 79 % of accuracy.
  • No Thumbnail Available
    Item
    Passion Fruit Disease Detection using Image Processing
    (IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Dharmasiri, S.B.D.H.; Jayalal, S.
    Fruit diseases are a major problem in economic and production losses in the agricultural industry worldwide. In this paper, an image processing approach is proposed for identifying passion fruit diseases. According to the Sri Lankan context, treatment details are taken by the farmers from the field officers. However, it can take a few days. So, this proposed system can be used to identify passion fruit diseases quickly and automatically. This proposed approach is composed of the following main steps; Image Acquisition, Image Preprocessing, Image Segmentation, Feature Extraction, Dataset Preparation, Training & Testing. Healthy and two types of passion fruit diseases, namely passion fruit scab and woodiness images were used for this approach. This approach was tested according to passion fruit disease type and its’ stages, such as mild, moderate and severe. K-Means clustering was used for segmentation. Images were clustered according to k values, such as 2, 4, 6 and 8. Before the segmentation, images were converted to RGB, L*a*b, HSV and Grey colour models, because of find out the most suitable colour model for this approach. Local Binary Pattern was used for feature extraction and Support Vector Machine was used for creating the model. Seventy percent (70%) of each dataset was used to train the SVM and the other thirty percent (30%) was used to test the model. According to this approach, passion fruit diseases can be identified in the average accuracy of 79% and its’ stage can be identified in average accuracy 66%.
  • No Thumbnail Available
    Item
    Prediction of User Intentions Using Web History
    (IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Samarasinghe, K.T.C.S.; Jayalal, S.
    In the present internet has become much more necessary thing to humans and we use it as a way of sharing information and way of communication. If the networks can identify the user’s intentions, it will be affecting to increase productivity and personalization. Predicting user intention(s) is interesting and useful for many applications such as threat identification, imposing restrictions and cashing web details. The aim of this research is to develop a method to predict user intention using supervised machine learning methods with user’s past historical behaviours. Experiments in this study used access log on a local server and focused on creating single user prediction and multiuser generalize prediction models. Experimental models were created based on several multi-classifier algorithms, such as Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbor (KNN). KNN based models outperform other used algorithms. Also results in this study show that there is some sort of behavioural patterns for peoples to use the internet according to the time and the groups they interact