Fengchun Tian

Performance Study of Multilayer Perceptrons in a Low-Cost Electronic Nose

Nonselective gas sensor array has different sensitivities to different chemicals in which each gas sensor will also produce different voltage signals when exposed to an analyte with different concentrations. Therefore, the characteristics of cross sensitivities and broad spectrum of nonselective chemical sensors promote the fast development of portable and low-cost electronic nose (E-nose). Simultaneous concentration estimation of multiple kinds of chemicals is always a challengeable task in E-nose. Multilayer perceptron (MLP) neural network, as one of the most popular pattern recognition algorithms in E-nose, has been studied further in this paper. Two structures of single multiple inputs multiple outputs (SMIMO) and multiple multiple inputs single output (MMISO)-based MLP with parameters optimization in neural network learning processing using eight computational intelligence optimization algorithms are presented in this paper for detection of six kinds of indoor air contaminants. Experiments prove that the performance in accuracy and convergence of MMISO structure-based MLP are much better than SMIMO structure in concentration estimation for more general use of E-nose.

An adaptive QoS and energy-aware routing algorithm for wireless sensor networks

As wireless sensor networks (WSNs) increasingly attract more attention, new ideas for specific applications are continually being developed, many of which involve the energy consumption of nodes. However, not much has been done to optimize the quality of services (QoS) of WSNs. Many applications like target tracking require some QoS guarantees. Besides, certain factors limit the ability of multi-hop sensor networks to achieve desired goals such as the delay caused by network congestion, limited energy and computation of sensor nodes, packet loss due to interferences and mobility. In this paper, an adaptive QoS and energy-aware routing approach is proposed using an improved ant colony algorithm for WSNs to not only meet QoS requirements in an energy-aware fashion, but also balance the node energy utilization to maximize the network lifetime. Extensive simulation results under various experimental settings demonstrated the effectiveness of the proposed algorithm in terms of packet delivery rate, load balance, and the delay in comparison to the existing state-of-the-art directed diffusion routing algorithm.

A new kernel discriminant analysis framework for electronic nose recognition

Electronic nose (e-Nose) technology based on metal oxide semiconductor gas sensor array is widely studied for detection of gas components. This paper proposes a new discriminant analysis framework (NDA) for dimension reduction and e-Nose recognition. In a NDA, the between-class and the within-class Laplacian scatter matrix are designed from sample to sample, respectively, to characterize the between-class separability and the within-class compactness by seeking for discriminant matrix to simultaneously maximize the between-class Laplacian scatter and minimize the within-class Laplacian scatter. In terms of the linear separability in high dimensional kernel mapping space and the dimension reduction of principal component analysis (PCA), an effective kernel PCA plus NDA method (KNDA) is proposed for rapid detection of gas mixture components by an e-Nose. The NDA framework is derived in this paper as well as the specific implementations of the proposed KNDA method in training and recognition process. The KNDA is examined on the e-Nose datasets of six kinds of gas components, and compared with state of the art e-Nose classification methods. Experimental results demonstrate that the proposed KNDA method shows the best performance with average recognition rate and total recognition rate as 94.14% and 95.06% which leads to a promising feature extraction and multi-class recognition in e-Nose.

Classification of Electronic Nose Data in Wound Infection Detection Based on PSO-SVM Combined with Wavelet Transform

Abstract In this paper, a new method for classifying electronic nose data in rats wound infection detection based on support vector machine (SVM) and wavelet analysis was developed. Signals of the sensors were decomposed using wavelet analysis for feature extraction and a PSO-SVM classifier was developed for pattern recognition. The sensor array was optimized and model parameters were selected to achieve the maximum classification accuracy of SVM. Particle swarm optimization (PSO) was used to achieve optimization of the sensor array and the SVM model parameters. A classification rate of 97.5% was achieved by the proposed method for data discrimination. Compared with the methods of radial basis function (RBF) neural network classifier with maximum or wavelet coefficients feature and SVM without sensor array optimization, this method gave better performance on classification rate and time consumption in rats wound infection data recognition.

Improving the performance of electronic nose for wound infection detection using orthogonal signal correction and particle swarm optimization

Purpose – The purpose of this paper is to detect wound infection by electronic nose (Enose) and to improve the performance of Enose. Design/methodology/approach – Mice are used as experimental subjects. Orthogonal signal correction (OSC) is applied to preprocess the response of Enose. Radical basis function (RBF) network is used for discrimination, and the parameters in RBF are optimized by particle swarm optimization. Findings – OSC is very suitable for eliminating interference and improving the performance of Enose in wound infection detection. Research limitations/implications – Further research is required to sample wound infection dataset of human beings and to demonstrate that the Enose with proper algorithms can be used to detect wound infection. Practical implications – In this paper, Enose is used to detect wound infection, and OSC is used to improve the performance of the Enose. This widens the application area of Enose and OSC. Originality/value – The innovative concept paves the way for the ap...

A Solid Trap and Thermal Desorption System with Application to a Medical Electronic Nose

In this paper, a solid trap/thermal desorption-based odorant gas condensation system has been designed and implemented for measuring low concentration odorant gas. The technique was successfully applied to a medical electronic nose system. The developed system consists of a flow control unit, a temperature control unit and a sorbent tube. The theoretical analysis and experimental results indicate that gas condensation, together with the medical electronic nose system can significantly reduce the detection limit of the nose system and increase the systems ability to distinguish low concentration gas samples. In addition, the integrated system can remove the influence of background components and fluctuation of operational environment. Even with strong disturbances such as water vapour and ethanol gas, the developed system can classify the test samples accurately.

A novel sensor array and classifier optimization method of electronic nose based on enhanced quantum-behaved particle swarm optimization

Purpose – The purpose of the paper is to propose a new optimization algorithm to realize a synchronous optimization of sensor array and classifier, to improve the performance of E-nose in the detection of wound infection. When an electronic nose (E-nose) is used to detect the wound infection, sensor array’s optimization and parameters’ setting of classifier have a strong impact on the classification accuracy. Design/methodology/approach – An enhanced quantum-behaved particle swarm optimization based on genetic algorithm, genetic quantum-behaved particle swarm optimization (G-QPSO), is proposed to realize a synchronous optimization of sensor array and classifier. The importance-factor (I-F) method is used to weight the sensors of E-nose by its degree of importance in classification. Both radical basis function network and support vector machine are used for classification. Findings – The classification accuracy of E-nose is the highest when the weighting coefficients of the I-F method and classifier’s para...

Hole-filling Based on Disparity Map for DIBR

Due to sharp depth transition, big holes may be found in the novel view that is synthesized by depth-image-based rendering (DIBR). A hole-filling method based on disparity map is proposed. One important aspect of the method is that the disparity map of destination image is used for hole-filling, instead of the depth image of reference image. Firstly, the big hole detection based on disparity map is conducted, and the start point and the end point of the hole are recorded. Then foreground pixels and background pixels are distinguished for hole-dilating according to disparity map, so that areas with matching errors can be determined and eliminated. In addition, parallaxes of pixels in the area with holes and matching errors are changed to new values. Finally, holes are filled with background pixels from reference image according to these new parallaxes. Experimental results show that the quality of the new view after hole-filling is quite well; and geometric distortions are avoided in destination image, in contrast to the virtual view generated by depth-smoothing methods and image inpainting methods. Moreover, this method is easy for hardware implementation.

Bilateral similarity function: A novel and universal method for similarity analysis of biological sequences

Bilateral similarity function is designed for analyzing the similarities of biological sequences such as DNA, RNA secondary structure or protein in this paper. The defined function can perform comprehensive comparison between sequences remarkably well, both in terms of the Hamming distance of two compared sequences and the corresponding location difference. Compared with the existing methods for similarity analysis, the examination of similarities/dissimilarities illustrates that the proposed method with the computational complexity of O(N) is effective for these three kinds of biological sequences, and bears the universality for them.

A Novel Representation Approach to DNA Sequence and Its Application

The representation of a DNA sequence is the first stage of genome analysis. A wide variety of approaches has been proposed for different applications in bioinformatics. In this letter, based on the principle of symbolic dynamics, a novel representation approach is proposed, which maps DNA sequence into 3-D chaotic sequences of sawtooth function and completely conserve its biological information. With the application of the new representation approach to DNA sequence, three extended Kalman filters are used to implement gene prediction. Simulation results are presented to illustrate the validity and feasibility of the proposed representation approach to DNA sequence.