Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k-nearest neighbor (k-NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms.

This paper proposes a MAC protocol for ad hoc networks using In-band Full-duplex (IBFD) wireless communications, which are named as AdHoc-FDMAC. To utilize IBFD communications in ad hoc networks, this protocol modifies a number of control frames in the IEEE 802.11 Distributed Coordination Function (DCF) MAC standard. Here, the detailed time sequences for all types of IBFD communications are shown for the data transmission and routing. In this paper, the probability and throughput equations for IBFD communications in different situations have been derived. The performance of the proposed AdHoc-FDMAC has been analysed in terms of probability, throughput, and routing time. The Maximum throughput of AdHoc-FDMAC has been found to be 48.34 Mbps, and it is compared with a recently published ad hoc MAC as well as with the conventional HD MAC. The AdHoc-FDMAC outperforms the recently published ad hoc MAC and conventional HD MAC by 16.80% and 66.50% throughput gain, respectively. AdHoc-FDMAC incorporates the existing Ad hoc On-demand Distance Vector (AODV) routing protocol, but this AODV routing is utilized here using IBFD communications. This paper also compares the routing time of the IBFD-based AODV with the conventional AODV. The result shows that the IBFD-based AODV requires 33.33% less routing time than that of the conventional AODV for 3-hop distance between the transmitter and receiver. This paper suggests that the AdHoc-FDMAC protocol provides much more throughput in ad hoc networks by utilizing IBFD communications.