Hasil Pencarian  ::  Simpan CSV :: Kembali

"An automatic construction of neurons in neural network inspired by immune algorithm is proposed. The new network is combined with the contiguity-constrained method to perform clustering analysis. The applicability of this technique is tested with two widely reference machine-learning cases. The experiment shows that the new technique achieved 99.33% and 100% correctness for Iris plant data and wine recognition data respectively, better than other popular clustering methods."

"To improve the recognition accuracy of a developed artificial odor discrimination system for three mixture fragrance recognition, Fuzzy similarity based Self-Organized Network inspired by Immune Algorithm (F-SONIA) is proposed.Minimum, average, and maximum values of fragrance data acquisition are used to form triangular fuzzy numbers. THen, the fuzzy similarity measure is used to define the relationship between fragrance inputs and connection strengths of hidden units. The fuzzy similarity is defined as the maximum value of the intersection region between triangular fuzzy set of hidden units. In experiments, performances of the proposed method is compared with the conventional self-organized Network inspired by Immune Algorithm (SONIA) and the Fuzzy Learning Vector Quantization (FLVQ). Experiments show that F-SONIA improves recognition accuracy of SONIA by 3-9%. Comparing to the previously developed artificial odor discrimination system that used FLVQ as pattern classifier, the recognition accuracy is increased by 14-15%."

"The demand for a Wireless Sensor Network (WSN) has increased enormously because of its great ability to supervise the outside world as well as due to its vast range of applications. Since these sensor nodes depend greatly on battery power and being deployed in adverse environments, substituting the battery is a tiresome job. Cluster-based routing techniques are prominent methods to extend the lifetime of wireless sensor networks. In this research, the work on energy efficient clustering approach is considered in two phases. During the cluster head selection phase, cluster heads are chosen which can stabilize the power consumption in sensor networks, by considering both the residual energy and distance of node with respect to sink. Later, during the cluster formation phase, a non-cluster head node will choose a cluster head that lies in close proximity with the center point between the sensor nodes and sink. Also, these non-cluster head nodes should be within the transmission range of the cluster head, as selected by the above method. Initially, the Low Energy Adaptive Clustering Hierarchy (LEACH) which is an eminent protocol for sensor networks is investigated. Furthermore, the same LEACH protocol is enhanced by proposing an effective cluster head election scheme as well as a new cluster formation scheme as mentioned above. Simulation results reveal that the proposed algorithm outperforms the traditional LEACH protocol in prolonging network lifetime."