Statistical Extraction Method for Revealing Key Factors from Posture before Initiating Successful Throwing Technique in Judo

Many methods such as biomechanics and coaching have been proposed to help people learn a certain movement. There have been proposals for methods to discover characteristics of movement based on information obtained from videos and sensors. Especially in sports, it is expected that these methods can provide hints to improve movement skills. However, conventional methods focus on individual movements, and do not consider cases where external factors influence the movement, such as combat sports. In this paper, we propose a novel method called the Extraction for Successful Movement method (XSM method). Applying the method, this paper focuses on throwing techniques in judo to discover key factors that induce successful throwing from the postures right before initiating the throwing techniques. We define candidate factors by observing the video scenes where the throwing techniques are successfully performed. The method demonstrates the significance of the key factors according to the predominance of factors by χ2 test and residual analysis. Applying the XSM method to the dataset obtained from the videos of the Judo World Championships, we demonstrate the validity of the method with discussing the key factors related to the successful throwing techniques.

Chaotic time series forecasting with residual analysis using synergy of ensemble neural networks and Taguchi's design of experiments

This dissertation aims to develop an effective and practical method to forecast chaotic time series. Chaotic behaviour has been observed in the areas of marketing, stock markets, supply chain management, foreign exchange rates, weather forecasting and many others. An effective forecasting model can reduce the potential risks and uncertainty and facilitate planning and decision making in chaotic systems. In this study, residual analysis using a combination of the embedding theorem and ensemble artificial neural networks is adopted to forecast chaotic time series. Based on the embedding theorem, the embedding parameters are determined and the time series is reconstructed into proper phase space points. The embedded phase space points are fed into the first neural network and trained. The weights and biases are kept to predict the future values of phase space points and accordingly to obtain future values of chaotic time series. The residual of the predicted time series is further analyzed; and, if a chaotic behaviour is observed, then the residuals are processed as a new chaotic time series and predicted. This iterative residual analysis can be repeated several times depending on the desired accuracy level and computational efficiency. Finally, the last neural network is trained using neural networks' result values of the time series and the residuals as input and the original time series as output. The initial weights and biases of the neural networks are improved using genetic algorithms. Taguchi's design of experiments is adopted to identify appropriate factor-level combinations to improve the result of the proposed forecasting method. A systematic approach is proposed to improve the combination of ensemble artificial neural networks and their parameters. The proposed methodology is applied to a number of benchmark and some real life chaotic time series. In addition, the proposed forecasting method has been applied to financial sector time series, namely, the stock markets and foreign exchange rates. The experimental results confirm that the proposed method can predict the chaotic time series more effectively in terms of error indices when compared with other forecasting methods in the literature.

Chaotic time series forecasting with residual analysis using synergy of ensemble neural networks and Taguchi's design of experiments

This dissertation aims to develop an effective and practical method to forecast chaotic time series. Chaotic behaviour has been observed in the areas of marketing, stock markets, supply chain management, foreign exchange rates, weather forecasting and many others. An effective forecasting model can reduce the potential risks and uncertainty and facilitate planning and decision making in chaotic systems. In this study, residual analysis using a combination of the embedding theorem and ensemble artificial neural networks is adopted to forecast chaotic time series. Based on the embedding theorem, the embedding parameters are determined and the time series is reconstructed into proper phase space points. The embedded phase space points are fed into the first neural network and trained. The weights and biases are kept to predict the future values of phase space points and accordingly to obtain future values of chaotic time series. The residual of the predicted time series is further analyzed; and, if a chaotic behaviour is observed, then the residuals are processed as a new chaotic time series and predicted. This iterative residual analysis can be repeated several times depending on the desired accuracy level and computational efficiency. Finally, the last neural network is trained using neural networks' result values of the time series and the residuals as input and the original time series as output. The initial weights and biases of the neural networks are improved using genetic algorithms. Taguchi's design of experiments is adopted to identify appropriate factor-level combinations to improve the result of the proposed forecasting method. A systematic approach is proposed to improve the combination of ensemble artificial neural networks and their parameters. The proposed methodology is applied to a number of benchmark and some real life chaotic time series. In addition, the proposed forecasting method has been applied to financial sector time series, namely, the stock markets and foreign exchange rates. The experimental results confirm that the proposed method can predict the chaotic time series more effectively in terms of error indices when compared with other forecasting methods in the literature.

Application of LC-MS and Methyl Orange Methods for Improved Residual Surfactant Detection in Liquids-Rich Shale Plays

Successful field trials of surfactant-based Production Enhancement (PROE) technology in different shale plays including Permian Basin, Bakken and Eagle Ford indicate that specially tailored surfactant formulations can improve the unconventional well productivity during flowback and production. One major challenge for the operator is to further optimize the surfactant dosage to maximize the economic return. Analysis of the residual surfactant concentration in the produced water (PW) might provide a new path to optimize the surfactant application in the field. Such quantitative measurements can help understand how much surfactant is consumed in the downhole and how much surfactant is in the flowback, and possibly correlate back to the well performance. Additionally, surfactant partitioning and adsorption behaviors can be studied through residual analysis, which will further provide guidance to develop next generation of surfactant formulations. In this study, a liquid chromatography-mass spectrometry (LC-MS) method was developed to accurately measure the residual surfactant concentration in the produced water. The liquid chromatograph (LC) separates the surfactant from sample matrix and avoids the possible interference, and then the mass spectrometer (MS) detects the separated surfactant, signal correlating to the residual concentration. This analytical method provides unrivalled selectivity and specificity compared to other methods reported in the literature. In addition, a Methyl Orange method was developed and can potentially be used in the field for quicker measurements. Produced water samples collected from a Huff-and-Puff treatment in the Permian Basin were evaluated using both methods. Our results indicate that both methods can successfully capture the trend of residual concentration vs. production time. The deviation between LC-MS and Methyl Orange measurements was due to the presence of ADBAC (alkyldimethylbenzylammonium chloride) in the produced water, which is a cationic amine surfactant typically used as biocide in the well stimulation. It produces positive interference and thus leads to a higher residual detection in the Methyl Orange test. Notably, the residual concentration of surfactant in produced water decreased with time after the well was placed back to production, which is consistent with the concept that more surfactant will adsorb to the rock surface or partition into the oil phase over production time. In summary, we believe the LC-MS and Methyl Orange methods can potentially be used to detect residual concentration for any type of surfactant-based applications in unconventional reservoirs including Huff-and-Puff, completion, frac protect, surfactant flooding and re-frac. The field application of surfactant-based chemistry followed by this type of residual analysis can help understand the underlying mechanisms of the surfactant and provide further guidance for production optimization of shales.