Faculty of Engineering

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4203

Browse

Filters

2019 - 201932020 - 20223

Advanced Search

Filter by

Settings

Start date: 2010Subject: search.filters.subject.Comparison

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    PublicationEmbargo
    Performance Comparison of Sea Fish Species Classification using Hybrid and Supervised Machine Learning Algorithms
    (IEEE, 2022-10-04) Nalmi, R; Rathnayake, N; Mampitiya, L.I
    In the domain of autonomous underwater vehicles, the classification of objects underwater is critical. The hazy effect of the medium causes this obstacle, and these effects are directed by the dissolved particles that lead to the reflecting and scattering of light during the formation process of the image. This paper mainly focuses on exploring the best possible image classifier for the underwater images of the different fish species. The classifications were carried out by different hybrid and supervised machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Neural Networks (NN), Logistic Regression (LR), Decision Tree (DT), and Naive Bayes (NB). This study compares the algorithms’ accuracy and time and analyzes crucial features to decide the most optimal algorithm. Furthermore, the results of this paper depict that using dimension reduction methods such as PCA and LDA increases the accuracy of some algorithms. Random Forest was able to outperforms with a higher accuracy of 99.89% with the proposed feature extraction methods.
  • Thumbnail Image
    PublicationEmbargo
    A Comparison of Fuzzy Logic Controller and PID Controller for Differential Drive Wall-Following Mobile Robot
    (IEEE, 2019-12-18) Ratnayake, R. M. N. B; De Silva, S; Rodrigo, C. J
    This paper presents a comparison between PID controller and Fuzzy rule based controller of a differentially steered wall following mobile robot. Four different maps, generated using Mapper3 software are used to simulate the robot in MobileSim platform. The code was implemented using C++ language in ARIA development package. The robot simulation is performed with Pioneer P3-DX robot. In this study, the data was collected for each cases such as: left wall following and right wall following. In order to validate the results, maximum of 40 runs were conducted for each map and the results were compared with the illustrated methods.
  • Thumbnail Image
    PublicationEmbargo
    A comparison of fuzzy logic controller and pid controller for differential drive wall-following mobile robot
    (IEEE, 2019-12-18) Ratnayake, R. M. N. B; De Silva, T. S; Rodrigo, C. J
    This paper presents a comparison between PID controller and Fuzzy rule based controller of a differentially steered wall following mobile robot. Four different maps, generated using Mapper3 software are used to simulate the robot in MobileSim platform. The code was implemented using C++ language in ARIA development package. The robot simulation is performed with Pioneer P3-DX robot. In this study, the data was collected for each cases such as: left wall following and right wall following. In order to validate the results, maximum of 40 runs were conducted for each map and the results were compared with the illustrated methods.
  • Thumbnail Image
    PublicationOpen Access
    Comparison of different analyzing techniques in identifying rainfall trends for Colombo, Sri Lanka
    (Hindawi, 2020-08) Perera, A; Ranasinghe, T; Gunathilake, M. B; Rathnayake, U. S
    Identifying rainfall trends in highly urbanized area is extremely important for various planning and implementation activities, including designing, maintaining and controlling of water distribution networks and sewer networks and mitigating flood damages. However, different available methods in trend analysis may produce comparable and contrasting results. Therefore, this paper presents an attempt in comparing some of the trend analysis methods using one of the highly urbanized areas in Sri Lanka, Colombo. Recorded rainfall data for 10 gauging stations for 30 years were tested using the MannKendall test, Sen’s slope estimator, Spearman’s rho test, and innovative graphical method. Results showcased comparable findings among three trend identification methods. Even though the graphical method is easier, it is advised to use it with a proper statistical method due to its identification difficulties when the data scatter has some outliers. Nevertheless, it was found herein that Colombo is under a downward rainfall trend in the month of July where the area receives its major rainfall events. In addition, the area has several upward rainfall trends over the minor seasons and in the annual scale. Therefore, the water management activities in the area have to be revisited for a sustainable use of water resources.
  • Thumbnail Image
    PublicationOpen Access
    Comparison of statistical, graphical and wavelet transform analyses for rainfall trends and patterns in Badulu Oya catchment Sri Lanka
    (Hindawi, 2020-09) Ruwangika, A. M; Perera, A; Rathnayake, U. S
    Climate change has adversely influenced many activities. It has increased the intensified precipitation events in some places and decreased the precipitation in some other places. In addition, some research studies revealed that the climate change has moved seasons in the temporal scale. Therefore, the changes can be seen in both spatial and temporal scales. Thus, analyzing climate change in the localized environments is highly essential. Rainfall trend analysis in a localized catchment can improve many aspects of water resource management not only to the catchment itself but also to some of the related other catchments. This research is carried to identify the rainfall trends in Badulu Oya catchment, Sri Lanka. The catchment is important as it is in the intermediate climate zone and rich in agricultural productions. Four rain gauges (namely, Badulla, Kandekatiya, Lower Spring Valley, and Ledgerwatte Estate) were used to analyze the rainfalls in the resolutions of monthly, seasonally, and annually. 30-year monthly cumulative rainfall data for the above four gauging stations are analyzed using various standard tests. Nonparametric tests including Mann–Kendall test and sequential Mann–Kendall test and innovative trend analysis methods are used to identify the potential rainfall trends in Badulu Oya catchment. In addition, continuous wavelet transforms and discrete wavelet transforms tests are carried out to check the patterns on rainfall to the catchment. The trend analysis methods are compared against each other to identify the better technique. The results reveal that the nonparametric Mann–Kendall test is powerful to produce the statistically significant rainfall trends in qualitative and quantitative manner. Mann–Kendall analysis shows a positive trend to Ledgerwatte Estate in monthly (3.7 mm in February and 7.4 mm in October), seasonal (6.9 mm in the 2ndintermonsoon), and annual (3 mm annually) scales. However, the analysis records one decreasing rainfall trend to Kandekatiya (8.1 mm in December) only in monthly scale. Nevertheless, it was found that the graphical method can be easily used in qualitative analysis, while discrete wavelet transformations are efficient in identifying the rainfall patterns effectively.
  • Thumbnail Image
    PublicationOpen Access
    Comparison of statistical methods to graphical methods in rainfall trend analysis – case studies from tropical catchments
    (https://www.hindawi.com/journals/amete/2019/8603586/, 2019-09-02) Rathnayake, U. S
    Time series analyses for climatic factors are important in climate predictions. Rainfall is being one of the most important climatic factors in today’s concern for future predictions; thus, many researchers analyze the data series for identifying potential rainfall trends. The literature shows several methods in identifying rainfall trends. However, statistical trend analysis using Mann–Kendall equation and graphical trend analysis are the two widely used and simplest tests in trend analysis. Nevertheless, there are few studies in comparing various methods in the trend analysis to suggest the simplest methods in analyzing rainfall trends. Therefore, this paper presents a comparison analysis of statistical and graphical trend analysis techniques for two tropical catchments in Sri Lanka. Results reveal that, in general, both trend analysis techniques produce comparable results in identifying rainfall trends for different time steps including annual, seasonal, and monthly rainfalls.