Browsing by Subject "Artificial intelligence"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Open Access
    Fully moral artificial agents: future or fiction
    (2025) Moore, Jaimee; Nefdt, Ryan
    The rapid technological progress has resulted advancements in technology that includes the development of Artificially Intelligent agents (AI) for various purposes. The extensive progress in AI has reached a point where the introduction of AI agents as android robots or humanoids into society is plausible. This highlights the evolving relationship between humans and technology. This thesis explores the multidimensional aspects of artificial intelligence (AI) by examining the intersection of machine ethics, ethical theories, and deep learning. The central focus is on assessing the compatibility of ethical theories with the rapid advancements in technology, particularly the potential development of fully moral artificial agents. The aim of this thesis is to address the ethical concerns associated with the evolution of AI, particularly the introduction of artificially intelligent agents into various societal roles, such as care robots in healthcare. The need for an impartial approach to address these concerns is identified, leading to the proposal of machine ethics as a framework. Machine ethics, defined as ensuring moral behaviours in AI, provides a basis for evaluating the ethical capabilities of artificially intelligent agents. As technology continues to progress, the demand for a comprehensive ethical framework for AI decision-making becomes increasingly apparent. Machine ethics offers insights into the ethical processes involved in AI decision-making, allowing a closer examination of computational abilities and ethical capacities. The primary inquiry revolves around whether AI agents can achieve full morality and if existing ethical theories can govern their behaviour effectively. To explore these questions, the thesis draws upon three ethical theories—Utilitarianism, Deontology, and African Ubuntu Ethics—and their applicability to the development of fully moral artificial agents. It employs deep learning as a critical component in understanding moral agency within the context of AI. The analysis unfolds in four parts: first, providing a background on AI concepts; second, examining recent AI progress and the potential for ethical AI agents; third, exploring the future of AI in relation to morality through ethical theories; and fourth, establishing criteria for considering AI agents as moral agents. In conclusion, the thesis argues that, with the advancements in technology and the insights provided by machine ethics and ethical theories, the development of fully moral artificial intelligent agents is possible.
  • Thumbnail Image
    Item
    Open Access
    Short-term wind power forecasting using artificial neural networks-based ensemble model
    (2020) Chen,Qin; Folly, Komla
    Short-term wind power forecasting is crucial for the efficient operation of power systems with high wind power penetration. Many forecasting approaches have been developed in the past to forecast short-term wind power. In recent years, artificial neural network-based approaches (ANNs) have been one of the most effective and popular approaches for short-term wind power forecasting because of the availability of large amounts of historical data and strong computational power. Although ANNs usually perform well for short-term wind power forecasting, further improvement can be obtained by selecting suitable input features, model parameters, and using forecasting techniques like spatial correlation and ensemble for ANNs. In this research, the effect of input features, model parameters, spatial correlation and ensemble techniques on short-term wind power forecasting performance of the ANNs models was evaluated. Pearson correlation coefficients between wind speed and other meteorological variables, together with a basic ANN model, were used to determine the impact of different input features on the forecasting performance of the ANNs. The effect of training sample resolution and training sample size on the forecasting performance was also investigated. To separately investigate the impact of the number of hidden layers and the number of hidden neurons on short-term wind power forecasting and to keep a single variable for each experiment, the same number of hidden neurons was used in each hidden layer. The ANNs with a total of 20 hidden neurons are shown to be sufficient for the nonlinear multivariate wind power forecasting problems faced in this dissertation. The ANNs with two hidden layers performed better than the one with a single hidden layer because additional hidden layer adds nonlinearity to the model. However, the ANNs with more than two hidden layers have the same or worse forecasting performance than the one with two hidden layers. ANNs with too many hidden layers and hidden neurons can overfit the training data. Spatial correlation technique was used to include meteorological variables from highly correlated neighbouring stations as input features to provide more surrounding information to the ANNs. The advantages of input features, model parameters, and spatial correlation and ensemble techniques were combined to form an ANN-based ensemble model to further enhance the forecasting performance from an individual ANN model. The simulation results show that all the available meteorological variables have different levels of impact on forecasting performance. Wind speed has the most significant impact on both short-term wind speed and wind power forecasting, whereas air temperature, barometric pressure, and air density have the smallest effects. The ANNs perform better with a higher data resolution and a significantly larger training sample size. However, one requires more computational power and a longer training time to train the model with a higher data resolution and a larger training sample size. Using the meteorological variables from highly related neighbouring stations do significantly improve the forecasting accuracy of target stations. It is shown that an ANNs-based ensemble model can further enhance the forecasting performance of an individual ANN by obtaining a large amount of surrounding meteorological information in parallel without encountering the overfitting issue faced by a single ANN model.