This paper presents a hierarchical case representation that uses a context guided retrieval method The performance of this method is compared to that of a simple flat file representation using standard nearest neighbour retrieval. The data presented in this paper is more extensive than that presented in an earlier paper by the same authors. The estimation of the construction costs of light indu...

This document contains a report of our recent work in the area of transmission protocols for large-scale wireless sensor networks. We analyse a sensor network where the nodes do not have any knowledge about the network topology. The nodes are only aware of their own positions and the position of the nearest sink. We propose a MAC protocol that enables each transmitting node to choose its best n...

The current Internet is based on a fundamental assumption of reliability and good intent among actors in the network. Unfortunately, unreliable and malicious behaviour is becoming a major obstacle for Internet communication. In order to improve the trustworthiness and reliability of the network infrastructure, we propose a novel trust model to be incorporated into BGP routing. In our approach, ...

In the indoor space, finding nearest neighbour is of great importance in location-based services. Received Signal Strength Indication (RSSI) has received much attention due to its simplicity and compatibility with existing hardware, which been widely used for localization. Existing search methods are based on real walking distance, need ground survey labor work measure many distances. Crowdsour...

We propose a method for Global Ionospheric Maps of Total Electron Content forecasting using the Nearest Neighbour method. The assumption is that in database global ionosphere maps spanning more than two solar cycles, one can select set past observations have similar geomagnetic conditions to those current map. ionospheric condition be expressed by linear combination seen past. average these lea...

The paper reports a study of nonlinear nature of face image. A novel feature extraction method using state space feature parameter for the recognition of face images is studied. The results of simulation experiments performed on the standard AT & T face database using both Artificial Neural Network and K-Nearest Neighbour recognition algorithms based on Nonlinear Feature Parameter (NLFP) is als...