The multi-weight neuron with geometry algorithm and its application

A novel approach for multi-dimension signals processing, that is multi-weight neural network based on high dimensional geometry theory, is proposed. With this theory, the geometry algorithm for building the multi-weight neuron is mentioned. To illustrate the advantage of the novel approach, a Chinese speech emotion recognition experiment has been done. From this experiment, the human emotions are classified into 6 archetypal classes: fear, anger, happiness, sadness, surprise and disgust. And the amplitude, pitch frequency and formant are used as the feature parameters for speech emotion recognition. Compared with traditional GSVM model, the new method has its superiority. It is noted that this method has significant values for researches and applications henceforth.

Iris recognition algorithm based on point covering of high-dimensional space and neural network

In this paper, we constructed a Iris recognition algorithm based on point covering of high-dimensional space and Multi-weighted neuron of point covering of high-dimensional space, and proposed a new method for iris recognition based on point covering theory of high-dimensional space. In this method, irises are trained as "cognition" one class by one class, and it doesn't influence the original recognition knowledge for samples of the new added class. The results of experiments show the rejection rate is 98.9%, the correct cognition rate and the error rate are 95.71% and 3.5% respectively. The experimental results demonstrate that the rejection rate of test samples excluded in the training samples class is very high. It proves the proposed method for iris recognition is effective.

Determining of the delay time for a heating ventilating and air-conditioning plant using multi-weights neurons approach

This paper presents an multi weights neurons approach to determine the delay time for a Heating ventilating and air-conditioning (HVAC) plan to respond to control actions. The multi weights neurons is a fully connected four-layer network. An acceleration technique was used to improve the general delta rule for the learning process. Experimental data for heating and cooling modes were used with both the multi weights neurons and a traditional mathematical method to determine the delay time. The results show that multi weights neurons can be used effectively determining the delay time for HVAC systems.

A speaker-independent continuous speech recognition system using biomimetic pattern recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology (HMMs, or Hidden Markov models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic pattern recognition (BPR) in recognizing some mandarin continuous speech in a speaker-independent manner. A speech database was developed for the course of study. The vocabulary of the database consists of 15 Chinese dish's names, the length of each name is 4 Chinese words. Neural networks (NNs) based on Multi-weight neuron (MWN) model are used to train and recognize the speech sounds. The number of MWN was investigated to achieve the optimal performance of the NNs-based BPR. This system, which is based on BPR and can carry out real time recognition reaches a recognition rate of 98.14% for the first option and 99.81% for the first two options to the persons from different provinces of China speaking common Chinese speech. Experiments were also carried on to evaluate Continuous density hidden Markov models (CDHMM), Dynamic time warping (DTW) and BPR for speech recognition. The Experiment results show that BPR outperforms CDHMM and DTW especially in the cases of samples of a finite size.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Research on multi-degree-of-freedom neurons with weighted graphs

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

Electro-mass olfactory multi-sensor (EMMS)

For an olfactory sensor or electronic nose, the task is not only to detect the object concentration, but also to recognize it. It is well known that all the elements can be identified by their charge to mass ratio e(+)/m. We tried to imitate this principle for molecular recognition. Two kinds of sensors are used simultaneously in testing. One is quartz crystal microbalance (QCM) for detecting the change in mass, the other is interdigital electrode (IE) for detecting the change in conduction, as an electro-mass multi-sensor (EMMS). in this paper, the principle and the feasibility of this method are discussed. The preliminary results on the recognition of alcohol by EMMS coated with lipids are presented. Meanwhile, the multi-sensor can also be used as an instrument for research on some physico-chemistry problems. The change in conduction of coated membrane caused by one absorbed molecule is reported. It is found that when a QCM is coated with membrane, it still obeys the relationship Delta F (frequency change of QCM) = K Delta m (mass change of absorbed substance) and the proportional coefficient, K, depends not only on quartz properties but also on membrane characteristics as well. (C) 2000 Elsevier Science S.A. All rights reserved.

Biomimetic pattern recognition for speaker-independent speech recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology ( Hidden Markov Models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic Pattern Recognition (BPR) in recognizing some Mandarin Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Research on multi-degree-of-freedom neurons with weighted graphs

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

A method of Biomimetic Pattern Recognition for face recognition

A new method of face recognition, based on Biomimetic Pattern Recognition and Multi-Weights Neuron Network, had been proposed. A model for face recognition that is based on Biomimetic Pattern Recognition had been discussed, and a new method of facial feature extraction also had been introduced. The results of experiments with BPR and K-Nearest Neighbor Rules showed that the method based on BPR can eliminate the error recognition of the samples of the types that not be trained, the correct rate is also enhanced.

Electro-mass multi odor sensor

For an olfactory sensor or electronic nose the task is not only to detect the object concentration, but also to recognize it. It is well known that all the elements can be identified by their charge to mass ratio e+/m. We tried to use this principle for molecular recognition. Two kinds of sensors are used simultaneously in testing. One is Quartz Crystal Microbalance (QCM) for detecting the change in mass, the other is Interdigital Electrode (IE) for detecting the change in conduction. In this paper the principle and the feasibility of this method are reported. The preliminary results on the recognition of alcohols are presented. The multisensor can be used as an instrument for research on material properties and kinetic process as well.

Electro-mass olfactory multi-sensor (EMMS)

For an olfactory sensor or electronic nose, the task is not only to detect the object concentration, but also to recognize it. It is well known that all the elements can be identified by their charge to mass ratio e(+)/m. We tried to imitate this principle for molecular recognition. Two kinds of sensors are used simultaneously in testing. One is quartz crystal microbalance (QCM) for detecting the change in mass, the other is interdigital electrode (IE) for detecting the change in conduction, as an electro-mass multi-sensor (EMMS). in this paper, the principle and the feasibility of this method are discussed. The preliminary results on the recognition of alcohol by EMMS coated with lipids are presented. Meanwhile, the multi-sensor can also be used as an instrument for research on some physico-chemistry problems. The change in conduction of coated membrane caused by one absorbed molecule is reported. It is found that when a QCM is coated with membrane, it still obeys the relationship Delta F (frequency change of QCM) = K Delta m (mass change of absorbed substance) and the proportional coefficient, K, depends not only on quartz properties but also on membrane characteristics as well. (C) 2000 Elsevier Science S.A. All rights reserved.

Reducing H2S production by O-2 feedback control during large-scale sewage sludge composting

Hydrogen sulfide (H2S) production patterns and the influence of oxygen (O-2) concentration were studied based on a well operated composting plant. A real-time, online multi-gas detection system was applied to monitor the concentrations of H2S and O-2 in the pile during composting. The results indicate that H2S was mainly produced during the early stage of composting, especially during the first 40 h. Lack of available O-2 was the main reason for H2S production. Maintaining the O-2 concentration higher than 14% in the pile could reduce H2S production. This study suggests that shortening the interval between aeration or aerating continuously to maintain a high O-2 concentration in the pile was an effective strategy for restraining H2S production in sewage sludge composting. (C) 2010 Elsevier Ltd. All rights reserved.

Polypropylene as a carbon source for the synthesis of multi-walled carbon nanotubes via catalytic combustion

Multi-walled carbon nanotubes (MWCNTs) were efficiently synthesized by catalytic combustion of polypropylene (PP) using nickel compounds (such as Ni2O3, NiO, Ni(OH)(2) and NiCO3 (.) 2Ni(OH)(2)) as catalysts in the presence of organic-modified montmorillonite (OMMT) at 630-830 degrees C. Morphologies of the sample undergoing different combustion times were observed to investigate actual process producing MWCNTs by this method. The obtained MWCNTs were characterized by X-ray diffraction (XRD), transmission electron microscope and Raman spectroscopy. The yield of MWCNTs was affected by the composition of PP mixtures with OMMT and nickel compounds and the combustion temperature. The proton acidic sites from the degraded OMMT layers due to the Hoffman reaction of the modifiers at high temperature played an important role in the catalytic degradation of PP to supply carbon sources that are easy to be catalyzed by nickel catalyst for the growth of MWCNTs. The XRD measurements demonstrated that the nickel compounds were in situ reduced into the Ni(0) state with the aid of hydrogen gas and/or hydrocarbons in the degradation products of PP, and the Ni(O) was really the active site for the growth of MWCNTs. The combination of nickel compounds with OMMT was a key factor to efficiently synthesize MWCNTs via catalytic combustion of PP.