SLIIT International Conference On Engineering and Technology Vol. 01 [SICET] 2022

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/2988

Browse

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Low Cost – Remote Passive Sensory Based Weather Prediction System with Internet of Things
    (SLIIT, 2022-02-11) Tennekoon, S; Chandrasekara, S; Abhayasinghe, N
    Climate effects many major daily aspects of the society, from the food sources and transport infrastructure to the choice of fashion and certain daily routines. Due to these reasons, the demand for means to accurately foresee climatic changes have increased. Weather forecasting, especially in Sri Lanka, has been hampered due to numerous reasons and this has resulted in erroneous predictions that has adversely affected many areas of development ranging from agriculture, irrigation, and the tourism industry to certain branches of engineering. Many researchers have analyzed and proposed solutions to these problems. However, the need for accurate predictions prevails due to the hardship of accurate data acquisition, processing, and transmission. To address these problems, in this paper, a system that adheres to the rules and regulations set forth by the World Meteorological Organization (WMO) to carry out well informed and reliably accurate weather predictions based on the data attained from a wireless passive remote sensory medium has been implemented. This task was carried out by means of feeding the relevant climatic parameter readings measured via multiple wireless passive remote sensory nodes placed within the proximity of a considered area to a selected computational model, which in turn was implemented to yield considerably accurate predictions compared to the weather prediction systems currently available in the market. The paper comprises of the implementation of the category, Low-Cost Automatic Weather Station (LC-AWS) specified by the WMO and Internet of Things (IoT), one of the latest technologies, for the transmission of attained data even in the absence of Wi-Fi. The research was further conducted to perform an analytical comparison between highly accurate weather stations and the implemented low-cost weather station when compromising accuracy due to low cost. The hardware and related software implementation yielded an acceptable success rate and was concluded successfully.
  • Thumbnail Image
    PublicationOpen Access
    Support Vector Machine Based an Efficient and Accurate Seasonal Weather Forecasting Approach with Minimal Data Quantities
    (SLIIT, 2022-02-11) Chandrasekara, S; Tennekoon, S; Abhayasinghe, N; Seneviratne, L
    Climate change makes a big impact in our daily activities. Therefore, forecasting climate changes prior to its actual occurrences is important. Even though highly accurate weather prediction systems throughout the world are available, they require mass amounts of data exceeding thousands of data points to obtain a significant accuracy. This study was aimed at proposing a Support Vector Machine based approach to carryout seasonal weather predictions up to thirty-minute intervals, the results of which would be considerably effective with respect to predictions carried out with models trained with annual datasets. The model was trained utilizing a dataset corresponding to the district of Kandy which consisted of 136 samples, 20 features, and 5 labels. By means of carrying out numerous data preprocessing steps, the model was trained, and the relevant hyperparameters were optimized considering the grid search algorithm to yield a maximum accuracy of 86%, once tested via the k-fold cross validation. The performance of the Support Vector Machine was also then compared for the same dataset with that of the K-Nearest Neighbor algorithm which consumed relatively fewer computing resources. An optimal accuracy of 61% was observed for this model for a K-value of 27. This approach supported the concept of a Support Vector Machine’s ability to perceive time series forecasts to a relatively higher degree and its ability to perform effectively in higher dimensional datasets with smaller number of samples. As per the future work, the Receiver Operating Characteristic analysis is proposed to be carried out to evaluate the performance of the model and the dataset size is proposed to be further enhanced to a maximum of a thousand samples to yield the best performance results.