The dissertation examines advancements in the methods and techniques used in the field of econometrics. These advancements include: (i) a re-examination of the underlying statistical foundations of statistical models with binary dependent variables. (ii) using feed-forward backpropagation artificial neural networks for modeling dichotomous choice processes, and (iii) the estimation of unconditional demand elasticities using the flexible multistage demand system with asymmetric partitions and fixed effects across time. The first paper re-examines the underlying statistical foundations of statistical models with binary dependent variables using the probabilistic reduction approach. This re-examination leads to the development of the Bernoulli Regression Model, a family of statistical models arising from conditional Bernoulli distributions. The paper provides guidelines for specifying and estimating a Bernoulli Regression Model, as well as, methods for generating and simulating conditional binary choice processes. Finally, the Multinomial Regression Model is presented as a direct extension. The second paper empirically compares the out-of-sample predictive capabilities of artificial neural networks to binary logit and probit models. To facilitate this comparison, the statistical foundations of dichotomous choice models and feed-forward backpropagation artificial neural networks (FFBANNs) are re-evaluated. Using contingent valuation survey data, the paper shows that FFBANNs provide an alternative to the binary logit and probit models with linear index functions. Direct comparisons between the models showed that the FFBANNs performed marginally better than the logit and probit models for a number of within-sample and out-of-sample performance measures, but in the majority of cases these differences were not statistically significant. In addition, guidelines for modeling contingent valuation survey data and techniques for estimating median WTP measures using FFBANNs are examined. The third paper estimates a set of unconditional price and expenditure elasticities for 49 different processed food categories using scanner data and the flexible and symmetric translog (FAST) multistage demand system. Due to the use of panel data and the presence of heterogeneity across time, temporal fixed effects were incorporated into the model. Overall, estimated price elasticities are larger, in absolute terms, than previous estimates. The use of disaggregated product groupings, scanner data, and the estimation of unconditional elasticities likely accounts for these differences. / Ph. D.

Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%. / Ph. D.

Human beings have a touch and force estimation mechanism beneath their feet. They use this feeling of touch and force to maintain balance, walk, run and perform various agile motions. This paper presents a new sensor platform beneath the humanoid feet, enabled by a pragmatic model based compliant foot design and sensor configuration that mimics the human tactile sensory system for contact force measurement in humanoid robots. Unlike previous force sensor based approaches, the system is defined as a total and sufficient method of Ground Reaction Force (GRF) and Zero Moment Point (ZMP) measurement for balancing and walking using contact force feedback in mid to full sized humanoids. The conventional systems for the GRF and ZMP measurement are made of heavy metallic parts that tend to be bulky and vulnerable to inertial noises upon high acceleration. In addition to low cost and reliable operation, the proposed system can withstand shock and enable agile motion much like humans do with their footpad. The proposed foot is manufactured using state-of-the-art technique with elastomer padding which not only protects the sensors but also acts as a compliance beneath the foot giving integrity in structural design. This composite layer provides compliance and traction for foot collision while the contact surfaces are sampled for pressure distribution which can be mapped into three axis force and ZMP. A single step training process is required to relate the sensor readings to force measurement. The system’s capability of contact force measurement, subsequent ZMP estimation is experimentally verified with the application of appropriate software. Moreover, a simulation study has been conducted via Finite Element Analysis (FEA) of the footpad structure to analyze the proposed footpad structure. The experimental results demonstrate why this can be a major step toward a biomimetic, affordable yet robust contact force and ZMP measurement method for humanoid robots. This work was supported by the Office of Naval Research, Grant N00014-15-1-2128 as part of development of Project SAFFiR (Shipboard Autonomous Firefighting Robot). / Master of Science / How we interact with the surfaces in contact with us has a crucial role for balancing and walking with agility. The biological touch and force measurement systems in human is currently unmatched, not even mimicked in a significant way in the state-of-the-art humanoid robots’ systems. Human beings use this feeling of touch and force beneath the feet to maintain balance, walk, run and perform various agile motions. This research aims to find a holistic system in humanoid robot’s feet design that can mimic this human characteristics of force estimation beneath the feet and using that estimation for balancing and walking. A practical model based sensor configuration is derived from the rigorous study of human and humanoid robot’s feet contact with the ground. The sensors are tactile in nature, and unlike previous below feet based approaches, the system is defined as a total and sufficient system of Ground Reaction Force (GRF) and Center of Pressure (CoP) measurement. The conventional systems for this purpose are not only highly expensive but also having error in quantification during accelerated movement. The proposed foot is designed following the practical model derived and manufactured using the state-of-the-art mechanism for having a soft cushion between the sensors and the contact surfaces. In addition to low cost and reliable operation, the proposed system can withstand shock and enable agile motion much like humans do with their footpad. The quantification of the forces and pressure from the sensor readings and developed using appropriate software and algorithms. The system’s capability of contact force measurement, subsequent Center of Pressure measurement is experimentally verified with the application of appropriate software. Moreover, a simulation study has been conducted of the footpad structure to analyze the proposed footpad structure. The experimental results demonstrate why this can be a major step toward a biomimetic, affordable yet robust contact force and Center of Pressure measurement method for human-like robots.

This thesis presents a generic passive non-contact based acoustic health monitoring approach using ultrasonic acoustic emissions (UAE) to facilitate classification of bearing health via neural networks. This generic approach is applied to classifying the operating condition of conventional ball bearings. The acoustic emission signals used in this study are in the ultrasonic range (20-120 kHz), which is significantly higher than the majority of the research in this area thus far. A direct benefit of working in this frequency range is the inherent directionality of the microphones capable of measurement in this range, which becomes particularly useful when operating in environments with low signal-to-noise ratios. Using the UAE power spectrum signature, it is possible to pose the health monitoring problem as a multi-class classification problem, and make use of a multi-layer artificial neural network (ANN) to classify the UAE signature. One major problem limiting the usefulness of ANN's for failure classification is the need for large quantities of training data. Artificial training data, based on statistical properties of a significantly smaller experimental data set is created using the combination of a normal distribution and a coordinate transformation. The artificial training data provides a sufficient sized data set to train the neural network, as well as overcome the curse of dimensionality. The combination of the artificial training methods and ultrasonic frequency range being used results in an approach generic enough to suggest that this particular method is applicable to a variety of systems and components where persistent UAE exist. / Master of Science

Yes / For meeting the external requirements of the Paris Agreement and reducing energy consumption per gross domestic product, China needs to improve its energy efficiency. Although the existing studies have attempted to investigate energy efficiency from different perspectives, little effort has yet been made to consider the collaboration among different stages in the production chain to produce energy outputs. In addition, various studies have also examined the determinants of energy efficiency, however, they mainly focused on technology and economic factors, no study has yet proposed and considered the influence of geographical factors on energy efficiency. In this article, we fill in the gap and make theoretical and empirical contributions to the literature. In this study, a two-stage analysis method is used to analyse energy efficiency and the influencing factors in China between 2009 and 2021. More specifically, from the theoretical/methodological perspective, a multi-activity network data envelopment analysis model is used to measure energy efficiency of different processes in the energy production chain. From the empirical perspective, we attempt to investigate the influence of geographical factors on energy efficiency through a neural network analysis. Meanwhile, the comparisons among different provinces are made. The result shows that the overall energy efficiency is low in China, and China relies more on the traditional energy industry than the clean energy industry. The efficiency level experiences a level of volatility over the examined period. Finally, we find that raw fuel pre-process and industry have a significant and positive impact on energy efficiency in China.

No / This study has investigated an artificial intelligence technology ¿ model trees ¿ as a modelling tool applied to an immediate release tablet formulation database. The modelling performance was compared with artificial neural networks that have been well established and widely applied in the pharmaceutical product formulation fields. The predictability of generated models was validated on unseen data and judged by correlation coefficient R2. Output from the model tree analyses produced multivariate linear equations which predicted tablet tensile strength, disintegration time, and drug dissolution profiles of similar quality to neural network models. However, additional and valuable knowledge hidden in the formulation database was extracted from these equations. It is concluded that, as a transparent technology, model trees are useful tools to formulators

Este trabalho apresenta um método utilizando redes neurais artificiais para a determinação das amplitudes e fases dos componentes harmônicos presentes na corrente de carga monofásica. O número de harmônicos identificados é previamente selecionado. Os hamônicos identificados estão presentes na corrente de cargas não-lineares de um sistema de iluminação onde é considerada a variação no tempo das características da forma de onda desta corrente. Os harmônicos presentes no sistema degradam a qualidade de energia, sendo assim é apresentado um breve estudo sobre este tema e métodos para atenuar a distorção harmônica no sistema. Dentre estes métodos é dado ênfase na aplicação de filtros ativos de potência em paralelo com carga não-linear. O trabalho também apresenta um estudo sobre os mais comumente métodos utilizados na identificação harmônica. Dentre eles está o método baseado em redes neurais artificiais. Este método é validado com base nos dados levantados por meio de simulação e de forma experimental. / In this thesis artificial neural networks are employed in a novel approach to identifying harmonic components of the single-phase nonlinear load current, whose amplitudes and phase angles are subject to unpredictable changes in steady-state. An identified harmonics number is previously selected. These harmonics are present in the non-linear loads current of electrical illumination system. The harmonics in the power system degrade the power quality, then is exhibited a concise study dealing with power quality problems and methods to mitigate the harmonic distortion in the power system. Among these methods emphasis is given in the application of pure active power filters in parallel with the non-linear load. The thesis also shows a study about the more commonly methods used in the harmonic detection. Among them is the method based on artificial neural networks. Simulation and experimental results are presented to validate the proposed approach.

The automatic synthesis of embodied creatures through artificial evolution has become a key area of research in robotics, artificial life and the cognitive sciences. However, the research has mainly focused on genetic encodings and fitness functions. Considerably less has been said about the role of controllers and how they affect the evolution of morphologies and behaviors in artificial creatures. Furthermore, the evolutionary algorithms used to evolve the controllers and morphologies are pre-dominantly based on a single objective or a weighted combination of multiple objectives, and a large majority of the behaviors evolved are for wheeled or abstract artifacts. In this thesis, we present a systematic study of evolving artificial neural network (ANN) controllers for the legged locomotion of embodied organisms. A virtual but physically accurate world is used to simulate the evolution of locomotion behavior in a quadruped creature. An algorithm using a self-adaptive Pareto multi-objective evolutionary optimization approach is developed. The experiments are designed to address five research aims investigating: (1) the search space characteristics associated with four classes of ANNs with different connectivity types, (2) the effect of selection pressure from a self-adaptive Pareto approach on the nature of the locomotion behavior and capacity (VC-dimension) of the ANN controller generated, (3) the effciency of the proposed approach against more conventional methods of evolutionary optimization in terms of computational cost and quality of solutions, (4) a multi-objective approach towards the comparison of evolved creature complexities, (5) the impact of relaxing certain morphological constraints on evolving locomotion controllers. The results showed that: (1) the search space is highly heterogeneous with both rugged and smooth landscape regions, (2) pure reactive controllers not requiring any hidden layer transformations were able to produce sufficiently good legged locomotion, (3) the proposed approach yielded competitive locomotion controllers while requiring significantly less computational cost, (4) multi-objectivity provided a practical and mathematically-founded methodology for comparing the complexities of evolved creatures, (5) co-evolution of morphology and mind produced significantly different creature designs that were able to generate similarly good locomotion behaviors. These findings attest that a Pareto multi-objective paradigm can spawn highly beneficial robotics and virtual reality applications.

Visualization is the process of constructing methods, which are able to synthesize interesting and informative images from data sets, to simplify the process of interpreting the data. In this thesis a new approach to construct meteorological visualization methods using neural network technology is described. The methods are trained with examples instead of explicitely designing the appearance of the visualization. This approach is exemplified using two applications. In the fist the problem to compute an image of the sky for dynamic weather, that is taking account of the current weather state, is addressed. It is a complicated problem to tie the appearance of the sky to a weather state. The method is trained with weather data sets and images of the sky to be able to synthesize a sky image for arbitrary weather conditions. The method has been trained with various kinds of weather and images data. The results show that this is a possible method to construct weather visaualizations, but more work remains in characterizing the weather state and further refinement is required before the full potential of the method can be explored. This approach would make it possible to synthesize sky images of dynamic weather using a fast and efficient empirical method. In the second application the problem of computing synthetic satellite images form numerical forecast data sets is addressed. In this case a mode is trained with preclassified satellite images and forecast data sets to be able to synthesize a satellite image representing arbitrary conditions. The resulting method makes it possible to visualize data sets from numerical weather simulations using synthetic satellite images, but could also be the basis for algorithms based on a preliminary cloud classification. / Report code: LiU-Tek-Lic-2004:66.

Introduction: Tropical Cyclones (TCs) inflict considerable damage to life and property every year. A major problem is that residents often hesitate to follow evacuation orders when the early warning messages are perceived as inaccurate or uninformative. The root problem is that providing accurate early forecasts can be difficult, especially in countries with less economic and technical means. Aim: The aim of the thesis is to investigate how cyclone early warning systems can be technically improved. This means, first, identifying problems associated with the current cyclone early warning systems, and second, investigating if biologically based Artificial Neural Networks (ANNs) are feasible to solve some of the identified problems. Method: First, for evaluating the efficiency of cyclone early warning systems, Bangladesh was selected as study area, where a questionnaire survey and an in-depth interview were administered. Second, a review of currently operational TC track forecasting techniques was conducted to gain a better understanding of various techniques’ prediction performance, data requirements, and computational resource requirements. Third, a technique using biologically based ANNs was developed to produce TC track and intensity forecasts. Systematic testing was used to find optimal values for simulation parameters, such as feature-detector receptive field size, the mixture of unsupervised and supervised learning, and learning rate schedule. Five types of 2D data were used for training. The networks were tested on two types of novel data, to assess their generalization performance. Results: A major problem that is identified in the thesis is that the meteorologists at the Bangladesh Meteorological Department are currently not capable of providing accurate TC forecasts. This is an important contributing factor to residents’ reluctance to evacuate. To address this issue, an ANN-based TC track and intensity forecasting technique was developed that can produce early and accurate forecasts, uses freely available satellite images, and does not require extensive computational resources to run. Bidirectional connections, combined supervised and unsupervised learning, and a deep hierarchical structure assists the parallel extraction of useful features from five types of 2D data. The trained networks were tested on two types of novel data: First, tests were performed with novel data covering the end of the lifecycle of trained cyclones; for these test data, the forecasts produced by the networks were correct in 91-100% of the cases. Second, the networks were tested with data of a novel TC; in this case, the networks performed with between 30% and 45% accuracy (for intensity forecasts). Conclusions: The ANN technique developed in this thesis could, with further extensions and up-scaling, using additional types of input images of a greater number of TCs, improve the efficiency of cyclone early warning systems in countries with less economic and technical means. The thesis work also creates opportunities for further research, where biologically based ANNs can be employed for general-purpose weather forecasting, as well as for forecasting other severe weather phenomena, such as thunderstorms.