A New Classification Method for Stored Grain Insect Infestation Using KIII and SVM Based Electronic Nose

Insect infestation is a common problem for stored grain. In this paper, a novel pattern recognition approach combining an olfactory neural network entitled KIII with support vector machine (SVM) is proposed and used in conjunction with an electronic nose to generate recognition models. Using this approach, feature vectors are firstly processed by KIII model which stimulates information processing function of olfactory bulb, and then classified by SVM. Through optimization of SVM model parameters, the data are mapped into high dimension space and the stored wheat samples with different degrees of insect damage are distinguished successfully. The experimental results demonstrate that the proposed method can achieve up to 100% classification rate and significantly outperforms the conventional KIII-Minimum Euclidean Distance Classifier.

Odor-Driven Activity in the Olfactory Cortex of an In Vitro Isolated Guinea Pig Whole Brain With Olfactory Epithelium

We developed a new technique to isolate a whole guinea pig brain with an intact olfactory epithelium (OE) that enables us to access the ventral surface of the brain including olfactory areas with ease during natural odor stimulation. We applied odorants to OE and confirmed that odor-induced local field potentials (LFPs) could be induced in olfactory areas. In the olfactory bulb (OB) and the piriform cortex (PC), odor-induced LFPs consisted of a phasic initial component followed by a fast activity oscillation in the beta range (20 Hz). To understand the neural mechanisms of odor-induced responses especially in the anterior PC, we analyzed odor-induced LFPs, together with unit activity data. We confirmed that the initial component of odor-induced response has a characteristic temporal pattern, generated by a relatively weak direct afferent input, followed by an intra-cortical associative response, which was associated with a phasic inhibition. The beta oscillation might be formed by the repetition of these network activities. These electrophysiological data were consistent with the results of previous studies that used slice or in vivo preparations, suggesting that the olfactory neural network and activities of the brain are preserved in our new in vitro preparation. This study provides the basis for clarifying the sequence of neural activities underlying odor information processing in the brain in vitro following natural olfactory stimulation.