Using Hopfield to Solve Resource-Leveling Problem

Although the traditional permute matrix coming along with Hopfield is able to describe many common problems, it seems to have limitation in solving more complicated problem with more constrains, like resource leveling which is actually a NP problem. This paper tries to find a better solution for it by using neural network. In order to give the neural network description of resource leveling problem, a new description method called Augmented permute matrix is proposed by expending the ability of the traditional one. An Embedded Hybrid Model combining Hopfield model and SA are put forward to improve the optimization in essence in which Hopfield servers as State Generator for the SA. The experiment results show that Augmented permute matrix is able to completely and appropriately describe the application. The energy function and hybrid model given in this study are also highly efficient in solving resource leveling problem.

Scale-Invariant Local Descriptor for Event Recognition in 1D Sensor Signals

In this paper, we introduce a shape-based, time-scale invariant feature descriptor for 1-D sensor signals. The time-scale invariance of the feature allows us to use feature from one training event to describe events of the same semantic class which may take place over varying time scales such as walking slow and walking fast. Therefore it requires less training set. The descriptor takes advantage of the invariant location detection in the scale space theory and employs a high level shape encoding scheme to capture invariant local features of events. Based on this descriptor, a scale-invariant classifier with "R" metric (SIC-R) is designed to recognize multi-scale events of human activities. The R metric combines the number of matches of keypoint in scale space with the Dynamic Time Warping score. SICR is tested on various types of 1-D sensors data from passive infrared, accelerometer and seismic sensors with more than 90% classification accuracy.