Rough Sets theory is widely used as a method for estimating and/or inducing knowledge structure of if-then rules from various decision tables. This paper presents results of a retest of rough set rule induction ability by the use of simulation data sets. The conventional method has two main problems: the first is the accuracy of the estimated rules, and the second is the strong dependence of the estimated rules on the data set sampling from the population. We here propose a new rule induction method based on the view that the rules existing in their population cause partiality of the distribution of the decision attribute values. This partiality can be utilized to detect the rules using a statistical test. The proposed new method is applied to the simulation data sets. The results show the method is valid and has clear advantages, as it overcomes the above problems inherent in the conventional method.
The hidden terminal problem is a big problem when we use a wireless LAN. To solve that problem, IEEE 802.11 employs the RTS/CTS scheme which informs, before packet transmission, existence of a sending terminal to the neighbors of the sender and the receiver. However, when offered load increases, collisions of RTS frames also increase and they cause performance degradation. In this paper, we replace an RTS frame with a random length jam signal which does not have any information. The proposed scheme gives a transmission privilege to the terminal which lastly completes the jam signal. Thus the terminal can proceed to the next stage, packet transmission, even if its jam signal is collided. The simulation results show that our scheme improves throughput in comparison with the RTS/CTS scheme.
In this paper, we propose a new template matching method using principal component analysis and image edge information. First, we introduce the previous eigen template method and the edge based eigen template method. Secondly, we proposed a new edge based image similarity suitable to the eigen template method and the proposed method is robust to the local illumination changes such as the image shading. The experimental results show that the proposed method can detect the target correctly and its computation time is almost same as the previous method.