Browsing by Author "Laksiri, P.H.P.N."

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Analyzing Infant Crying Patterns: Classification of Hunger and Discomfort
    (Uva Wellassa University of Sri Lanka, 2021) Fernando, M.M.T.; Laksiri, P.H.P.N.
    Infant crying is the crying of infants as a response to an internal or external stimulus. Infants cry as a form of basic instinctive communication. An infant's cry contains a lot of information about the baby such as hunger, pain, discomfort, sleepiness, burp, anger, etc. Parents‟ or guardian's inability to recognize and timely address the reason for the infant's cry prompts dissatisfaction for the infant and a feeling of helplessness for the parents. Therefore, an accurate, efficient automatic method for analyzing infant cry patterns and notifying the cause of cry is a very useful tool for parents. This study aims at the detection of baby cry patterns and identification of uniqueness of the hunger and discomfort crying patterns of the infants. This is achieved through analyzing the different patterns of the sound waves of the infants crying by converting the crying signal to an equivalent frequency waveform. This novel model can fill the gaps in the current models by achieving higher accuracy. Thus, this research is beneficial in various ways such as reducing parental dissatisfaction and helplessness when infant crying, minimizing child abuse and helping parents to better understand their child‟s needs and psychosis by analyzing crying patterns. The proposed model detects sound frequency, draws the waveform of the signal, and uses a Convolutional Neural Networks methodology to identify and distinguish the crying patterns of the infants. The dataset was collected, and the crying patterns were labeled by getting assistance from the domain experts. The model was trained and tested against the labeled data and it gained an accuracy of 91%. The proposed model will be further enhanced to identify more feelings of the infants and will be further developed to assists to recognize selected medical conditions by analyzing the crying patterns of the infants. Keywords: Cry signal; Discomfort; Hunger; Infant crying patterns
  • No Thumbnail Available
    Item
    Early Identification of Major Pest attacks Caused to Crop Loss in Paddy Fields: A Case Study
    (Uva Wellassa University of Sri Lanka, 2021) Lakshan, W.D.T.; Laksiri, P.H.P.N.
    Unrecognized or late recognized pest attacks are one of the major problems which lead to crop loss in paddy cultivation. According to the most recent season harvest Data of Rice research institute, it was recorded 40% of crop loss in the paddy cultivation in the Hambanthota district. Under a preliminary survey, it was identified Aphids, Brown-planthoppers, and Thrips were the major pests that caused the crop loss in paddy in the selected area. Due to the lack of proper knowledge in identification and lack of timely and accurate information, farmers are struggling to identify and control these pest attacks in their paddy fields. Due to crop loss, most of them are losing their money, interest, time, and confidence in paddy cultivation. During the study, domain experts revealed that early identification and early-stage of controlling these pests can save the majority of the crop loss and save lots of money which were spent on pesticides in paddy cultivation. This Case study was conducted to address the issues identified above, in the selected paddy fields in the Gonnoruwa area in the Hambanthota district. The proposed model use image processing techniques in combination with Convolutional Neural Networks to detect the pest's attacks in paddy cultivation by analyzing the symptoms. A set of self-captured images which were labeled with the help of domain experts were used to build and train the proposed model. The model has achieved 95% of accuracy while testing. The proposed model will be further improved to identify more pests and disease attacks in the future while delivering it as a handheld portable device where farmers can use it in real-time in their paddy fields which will lead to saving their time and money while increasing the paddy yield. Keywords: Crop loss; Paddy; Pest and diseases; Pest identification model
  • No Thumbnail Available
    Item
    Identification of Diseases of Rose Flowers using Image Processing Techniques
    (Uva Wellassa University of Sri Lanka, 2021) Madhupriya, M.T.M.; Laksiri, P.H.P.N.
    Exporting rose flowers are one of the major business for farmers in upcountry. When exporting roses, there are several quality factors to be considered like size and color. Due to the high sensitivity to its growing environment roses are vulnerable to several diseases. Due to the diseases, the quality factors are heavily affected and sometimes entire fields of cultivations are getting wasted before plucking a single flower. The lack of knowledge in symptom identification by farmers and the limited no of domain expertise in the area are the major problems in identifying and controlling the diseases which are affected the rose flowers. Through a field survey and by consulting domain experts, it has been identified that gray mold, black spots, and anthracnose are the major diseases that are heavily affected to bud, flower, and lifetime of flower and the rose plant. Further, the survey revealed that early identification of these diseases can save flowers, plants, money, and the confidence of the farmers while improving the export quality and volume of flowers. To address the findings of the survey, this study was conducted in selected rose fields in Bandarawela, Badulla district. A set of self-captured images which were labeled with the help of domain experts were used to build and train the proposed model. The proposed model will identify the diseases by identifying and categorizing the symptoms. The model was built in combination with the image processing techniques and Convolutional Neural Networks and used the guided data processing technique for training the data set. The developed model achieved over 94% of accuracy with the test set. The model will further be improved to identify the severity and the stage of the diseases and it will assist farmers in their rose cultivation by providing context-specific, updated information to identify, control and prevent the spreading of the identified diseases by improving the quality of the export rose flowers. Keywords: Anthracnose; Black spots; Gray mold; Disease identification model; Rose