Browsing by Author "Dogo, E."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Comparison of Strategies for Missing Values in Data on Machine Learning Classification Algorithms
    (IEEE, 2019) Makaba, T.; Dogo, E.
    Dealing with missing values in data is an important feature engineering task in data science to prevent negative impacts on machine learning classification models in terms of accurate prediction. However, it is often unclear what the underlying cause of the missing values in real-life data is or rather the missing data mechanism that is causing the missingness. Thus, it becomes necessary to evaluate several missing data approaches for a given dataset. In this paper, we perform a comparative study of several approaches for handling missing values in data, namely listwise deletion, mean, mode, k-nearest neighbors, expectation-maximization, and multiple imputations by chained equations. The comparison is performed on two real-world datasets, using the following evaluation metrics: Accuracy, root mean squared error, receiver operating characteristics, and the F1 score. Most classifiers performed well across the missing data strategies. However, based on the result obtained, the support vector classifier method overall performed marginally better for the numerical data and naïve Bayes classifier for the categorical data when compared to the other evaluated missing value methods.
  • No Thumbnail Available
    Item
    Development of a solar-powered greenhouse integrated with SMS and web notification systems
    (IGI Global, 2021) Jafta, L.; Nwulu, N.; Dogo, E.
    Energy for heating and cooling is among the biggest costs in greenhouse crop production. This has led to a rethink on energy-saving strategies, including the demand for solar energy as a viable renewable and sustainable choice for greenhouse farming. This chapter presents the development of a solar-powered system leveraging on internet of things and GSM technologies for sensing, controlling, and maintaining optimal climatic parameters inside a greenhouse. The proposed system is designed to automatically measure and monitor changes in temperature, humidity, soil moisture, and the light intensity. The strategy utilized in the design framework provides the user with the information of the measured parameters online and via SMS regardless of their geographical location. The chapter also incorporates a mechanism to self-regulate the climatic condition inside the greenhouse, suitable for the plant growth. Such a system can help improve the quantity and quality of crops grown in a greenhouse. Tests carried out on the system prove its effectiveness according to the design considerations.