Abstract: An adaptive dynamic cerebellar model articulation
controller (DCMAC) neural network used for solving the prediction
and identification problem is proposed in this paper. The proposed
DCMAC has superior capability to the conventional cerebellar model
articulation controller (CMAC) neural network in efficient learning
mechanism, guaranteed system stability and dynamic response. The
recurrent network is embedded in the DCMAC by adding feedback
connections in the association memory space so that the DCMAC
captures the dynamic response, where the feedback units act as
memory elements. The dynamic gradient descent method is adopted to
adjust DCMAC parameters on-line. Moreover, the analytical method
based on a Lyapunov function is proposed to determine the
learning-rates of DCMAC so that the variable optimal learning-rates
are derived to achieve most rapid convergence of identifying error.
Finally, the adaptive DCMAC is applied in two computer simulations.
Simulation results show that accurate identifying response and
superior dynamic performance can be obtained because of the
powerful on-line learning capability of the proposed DCMAC.
Abstract: Due to the fast development of technology, the
competition of technological products is turbulent; therefore, it is
important to understand the market trend, consumers- demand and
preferences. As the smartphones are prevalent, the main purpose of
this paper is to utilize Analytic Hierarchy Process (AHP) to analyze
consumer-s purchase evaluation factors of smartphones. Through the
AHP expert questionnaire, the smartphones- main functions are
classified as “user interface", “mobile commerce functions",
“hardware and software specifications", “entertainment functions" and
“appearance and design", five aspects to analyze the weights. Then
four evaluation criteria are evaluated under each aspect to rank the
weights. Based on an analysis of data shows that consumers consider
when purchase factors are “hardware and software specifications",
“user interface", “appearance and design", “mobile commerce
functions" and “entertainment functions" in sequence. The “hardware
and software specifications" aspect obtains the weight of 33.18%; it is
the most important factor that consumers are taken into account. In
addition, the most important evaluation criteria are central processing
unit, operating system, touch screen, and battery function in sequence.
The results of the study can be adopted as reference data for mobile
phone manufacturers in the future on the design and marketing
strategy to satisfy the voice of customer.