Logistic Regression Analysis of Customer Satisfaction Data

Variation exists in all processes. Significant work has been done to identify and remove sources of variation in manufacturing processes resulting in large returns for companies. However, business process optimization is an area that has a large potential return for a company. Business processes can be difficult to optimize due to the nature of the output variables associated with them. Business processes tend to have output variables that are binary, nominal or ordinal. Examples of these types of output include whether a particular event occurred, a customer's color preference for a new product and survey questions that assess the extent of the survey respondent's agreement with a particular statement. Output variables that are binary, nominal or ordinal cannot be modeled using ordinary least‐squares regression. Logistic regression is a method used to model data where the output is binary, nominal or ordinal. This article provides a review of logistic regression and demonstrates its use in modeling data from a business process involving customer feedback. Copyright © 2006 John Wiley & Sons, Ltd.     

Highly oriented star-like patterns observed on GaSe epilayers grown on Si(111)

Epitaxial lamellar gallium selenide (GaSe) semiconductors have been grown on trench-patterned silicon (Si) substrates by molecular beam epitaxy. An intriguing star-like patterned morphology was identified by atomic force microscopy on these epilayers. This non-trivial feature can be correlated with the accumulation of stacking faults of two concurrent epitaxial domains around self-oriented triangular pits developed earlier on the Si(111) surface by the chemical etching. Crystallographic considerations show how the stars can be formed.     

化学事故危害评估

根据化学事故危害的主要影响因素对化学事故进行危害评估,考查了危害纵深、人员杀伤率、危害地域估算、爆炸燃烧事故危害等内容。     

A Low-Power CMOS Linear-in-Decibel Variable Gain Amplifier With Programmable Bandwidth and Stable Group Delay

This brief presents a new circuit architecture for linear-in-decibel, constant-bandwidth variable gain amplifier (VGA). To obtain high linearity under low-voltage operation, this VGA is a closed-loop structure. In loop amplifier design, two techniques are applied: first, the loop amplifier is given finite input impedance. This arrangement keeps the VGA bandwidth constant under different gain setting. Second, a current-buffered compensation is applied for loop stability. Compared to the Miller compensation, this method achieves wider bandwidth. The prototype chip using 0.18-mum CMOS technology demonstrates that -10- to 20-dB gain and 0.5- to 30-MHz bandwidth can be programmed independently. The group delay difference within 30-dB gain control range is smaller than 1%. The total circuit dissipates 1.35 mA from a 1.8-V supply     

Lifting-based wavelet domain adaptive Wiener filter for image enhancement

A method of applying lifting-based wavelet domain Wiener filter (LBWDMF) in image enhancement is proposed. Lifting schemes have emerged as a powerful method for implementing biorthogonal wavelet filters. They exploit the similarity of the filter coefficients between the low-pass and high-pass filters to provide a higher speed of execution, compared to classical wavelet transforms. LBWDMF not only helps in reducing the number of computations but also achieves lossy to lossless performance with finite precision. The proposed method utilises the multi-scale characteristics of the wavelet transform and the local statistics of each subband. The proposed method transforms an image into the wavelet domain using lifting-based wavelet filters and then applies a Wiener filter in the wavelet domain and finally transforms the result into the spatial domain. When the peak signal-to-noise ratio (PSNR) is low, transforming an image to the lifting-based wavelet domain and applying the Wiener filter in the wavelet domain produces better results than directly applying Wiener filter in spatial domain. In other words each subband is processed independently in the wavelet domain by a Wiener filter. Moreover, in order to validate the effectiveness of the proposed method the result obtained using the proposed method is compared to those using the spatial domain Wiener filter (SDWF) and classical wavelet domain Wiener filter (CWDWF). Experimental results show that the proposed method has better performance over SDWF and CWDWF both visually and in terms of PSNR.     

Novel tiO2 nanocatalysts for wastewater purification: tapping energy from the sun.

Water treatment using TiO2 semiconductor as a durable heterogeneous photocatalyst has been the focus of environmentalists in recent years. Currently, we developed an inexpensive and highly efficient approach for synthesizing nitrogen-doped TiO2 with lower band-gap energy that can respond to visible light. Doping on the molecular scale led to an enhanced nitrogen concentration of up to 21.8%. Reflectance measurements showed the synthesized N-doped TiO2 nanoparticles are catalytically active with the absorbance that extends into the visible region up to 600 nm. The water purification potential of this new class of compound was evaluated by studying the photodegradation of Acid Orange 7 (AO7) and E. coli. Experiments were conducted to compare the photocatalytic activities of N-doped TiO2 nanocatalysts and commercially available Degussa P25 power under identical solar light exposure. N-doped TiO2 demonstrated superior photocatalytic activities in both chemical compound degradation and bactericidal reactions. The result of this study shows the potential of applying new generations of catalyst for wastewater purification and disinfection.     

Entropy of multidimensional cellular automata

Since the topological entropy of a vast class of two-dimensional cellular automata (CA) is infinite, of interest is the possibility to renormalize it so that to obtain a positive finite value. We find the asymptotics of the information function of a multidimensional CA and, accordingly, introduce the renormalized topological entropy as a coefficient of this asymptotics. We describe some properties of the introduced quantity, in particular, its positivity for CA of the type of “The Game of Life.” Also, we give an example of an explicit evaluation of this parameter for a particular cellular automaton.     

Methods for controlling pulsed stochastic operating regimes of nuclear reactors

Methods are proposed for controlling temporal and space-time pulsed chaos in nuclear reactors where the control actions are implemented as a result of external changes in the neutron multiplication coefficient or introducing external neutron sources. Cases of periodically varying controlling actions and cases where the controlling actions are introduced at the moment the neutron pulses start are examined. The cases of a singly connected regulation system, introducing control at each point of a reactor, and multiconnected systems consisting of several regulators, introducing controlling actions in local regions of the core, are examined. The case where control is introduced in the regions where neutrons bursts start is examined. The proposed methods of control make it possible to excite or suppress pulsed stochastic regimes in reactors and change the regime characteristics purposefully. __________ Translated from Atomnaya énergiya, Vol. 101, No. 2, pp. 103–112, August, 2006.     

Learning with belief levels

We study learning of predicate logics formulas from “elementary facts,” i.e. from the values of the predicates in the given model. Several models of learning are considered, but most of our attention is paid to learning with belief levels. We propose an axiom system which describes what we consider to be a human scientist's natural behavior when trying to explore these elementary facts. It is proved that no such system can be complete. However we believe that our axiom system is “practically” complete. Theorems presented in the paper in some sense confirm our hypothesis.     

Factors influencing feature usage in work-related communication

Two studies are presented. The first aimed to identify possible barriers to the uptake and use of commonly available telephony features and to determine whether greater knowledge of features/access codes and availability of user manuals could increase feature usage under certain conditions. Results showed that feature-usage patterns were not affected by any of the manipulations, but that they were determined by specific job demands. Using Constantine and Lockwood's (1999) conceptualization of user roles, a method to support feature bundling decisions for specific target markets was developed and tested in the second study. The method - Strategic User Needs Analysis (SUNA) - was shown to yield a useful balance between high- and low-level information about selected roles. SUNA provided sufficient information to distinguish between PDA feature usage patterns of two similar target user groups as well as to suggest additional features each of the two target groups would find useful. The development of SUNA and observational findings of actual PDA usage are reported.