Abstract: Most of self-tuning fuzzy systems, which are
automatically constructed from learning data, are based on the
steepest descent method (SDM). However, this approach often
requires a large convergence time and gets stuck into a shallow
local minimum. One of its solutions is to use fuzzy rule modules
with a small number of inputs such as DIRMs (Double-Input Rule
Modules) and SIRMs (Single-Input Rule Modules). In this paper,
we consider a (generalized) DIRMs model composed of double
and single-input rule modules. Further, in order to reduce the
redundant modules for the (generalized) DIRMs model, pruning and
generative learning algorithms for the model are suggested. In order
to show the effectiveness of them, numerical simulations for function
approximation, Box-Jenkins and obstacle avoidance problems are
performed.
Abstract: Although Mobile Wireless Sensor Networks (MWSNs),
which consist of mobile sensor nodes (MSNs), can cover a wide range
of observation region by using a small number of sensor nodes, they
need to construct a network to collect the sensing data on the base
station by moving the MSNs. As an effective method, the network
construction method based on Virtual Rails (VRs), which is referred
to as VR method, has been proposed. In this paper, we propose two
types of effective techniques for the VR method. They can prolong
the operation time of the network, which is limited by the battery
capabilities of MSNs and the energy consumption of MSNs. The
first technique, an effective arrangement of VRs, almost equalizes
the number of MSNs belonging to each VR. The second technique,
an adaptive movement method of MSNs, takes into account the
residual energy of battery. In the simulation, we demonstrate that each
technique can improve the network lifetime and the combination of
both techniques is the most effective.