This paper investigates algorithms for constructing velocity approximations from discrete position versus time data. The study is limited to algorithms suitable to provide velocity information in discrete-time feedback control systems such as microprocessor-based systems with a discrete position encoder. Velocity estimator based on lines per period reciprocal-time Taylor erie expansions, backward difference expansions, and least-square curve fits are presented. Based on computer simulation comparisons of relative accuracies of the different algo-rith~s are made. Tbe lea t-sqoares velocity estimator • tillered the effect of imperfect measurements (" noise") best, whereas the Taylor series expansions and backward difference equation estimators respond better to velocity transients.

The problems associated with training feedforward artificial neural networks (ANNs) such as the multilayer perceptron (MLP) network and radial basis function (RBF) network have been well documented. The solutions to these problems have inspired a considerable amount of research, one particular area being the application of evolutionary search algorithms such as the genetic algorithm (GA). To date, the vast majority of GA solutions have been aimed at the MLP network. This paper begins with a brief overview of feedforward ANNs and GAs followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.

Deep neural networks are proposed for short-term natural gas load forecasting. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields such as image recognition and speech processing. We provide an overview of natural gas forecasting. Next, the deep learning method, contrastive divergence is explained. We compare our proposed deep neural network method to a linear regression model and a traditional artificial neural network on 62 operating areas, each of which has at least 10 years of data. The proposed deep network outperforms traditional artificial neural networks by 9.83% weighted mean absolute percent error (WMAPE).

This study examined parotid salivary flow rate and composition in three groups of differently treated diabetics and a control group of non-diabetics. The study population was composed of edentulous African-Americans at least 65 years of age. Group A was the control, Group B insulin-dependent (Regular Iletin, U-100 qd.), Group C controlled by oral medication (Tolbutamide, 500 mg qd.), and Group D was diet controlled. All diabetic patients had serum glucose values under 250 mg/dl. Salivary flow rates, secretory IgA, electrolytes (Na+, Cl-, K+, Ca++) and total protein concentrations were evaluated. The results showed no significant differences between groups with respect to salivary flow rates, electrolytes and IgA concentrations. Additionally, all diabetic groups demonstrated a significantly lower salivary total protein concentration when compared to the controls. There appears to be no evident decrease in salivary flow rate in these three differently controlled diabetic groups compared with healthy non-diabetics.

-This paper develops the foundations of a technique for detection and categorization of dynamic/static eccentricities and bar/end-ring connector breakages in squirrelcage induction motors that is not based on the traditional Fourier transform frequency domain spectral analysis concepts. Hence, this approach can distinguish between the "fault signatures" of each of the following faults: eccentricities, broken bars, and broken end-ring connectors in such induction motors. Furthermore, the techniques presented here can extensively and economically predict and characterize faults from the induction machine adjustable speed drive design data without the need to have had actual fault data from field experience. This is done through the development of dual-track studies of fault simulations and hence simulated fault signature data. These studies are performed using our proven Time Stepping Coupled Finite Element-State Space method to generate fault case performance data, which contain phase current waveforms and time-domain torque profiles. Then from this data, the fault cases are classified by their inherent characteristics, so called "signatures" or "fingerprints". These fault signatures are extracted or "mined" here from the fault case data using our novel Time Series Data Mining technique. The dual-track of generating fault data and mining fault signatures was tested here on dynamic and static eccentricities of 10% and 30% percent of airgap height as well as cases of 1, 3, 6, and 9 broken bars and 3, 6, and 9 broken end-ring connectors. These cases were studied for proof-of-principle in a 208-volt, 60-Hz, 4-pole, 1.2-hp, squirrel cage 3-phase induction motor. The paper presents faulty and healthy performance characteristics and their corresponding so-called phase space diagnoses that show distinct fault signatures of each of the above mentioned motor faults.