Linear Discriminant Analysis Method Research Articles

Modeling the diagnosis of coronary artery disease by discriminant analysis and logistic regression: a cross-sectional study

PurposeCoronary artery disease (CAD) is one of the most significant cardiovascular diseases that requires accurate angiography to diagnose. Angiography is an invasive approach involving risks like death, heart attack, and stroke. An appropriate alternative for diagnosis of the disease is to use statistical or data mining methods. The purpose of the study was to predict CAD by using discriminant analysis and compared with the logistic regression.Materials and methodsThis cross-sectional study included 758 cases admitted to Fatemeh Zahra Teaching Hospital (Sari, Iran) for examination and coronary angiography for evaluation of CAD in 2019. A logistics discriminant, Quadratic Discriminant Analysis (QDA) and Linear Discriminant Analysis (LDA) model and K-Nearest Neighbor (KNN) were fitted for prognosis of CAD with the help of clinical and laboratory information of patients.ResultsOut of the 758 examined cases, 250 (32.98%) cases were non-CAD and 508 (67.22%) were diagnosed with CAD disease. The results indicated that the indices of accuracy, sensitivity, specificity and area under the ROC curve (AUC) in the linear discriminant analysis (LDA) were 78.6, 81.3, 71.3, and 81.9%, respectively. The results obtained by the quadratic discriminant analysis were respectively 64.6, 88.2, 47.9, and 81%. The values of the metrics in K-nearest neighbor method were 74, 77.5, 63.7, and 82%, respectively. Finally, the logistic regression reached 77, 87.6, 55.6, and 82%, respectively for the evaluation metrics.ConclusionsThe LDA method is superior to the Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor (KNN) and Logistic Regression (LR) methods in differentiating CAD patients. Therefore, in addition to common non-invasive diagnostic methods, LDA technique is recommended as a predictive model with acceptable accuracy, sensitivity, and specificity for the diagnosis of CAD. However, given that the differences between the models are small, it is recommended to use each model to predict CAD disease.

Vegetable and Fruit Image Classification with SqueezeNet based Deep Feature Generator

Automatic classification of food products according to their types is one of the most common problems in computer vision. In this paper, 15 different types of vegetables were automatically classified through transfer learning in deep learning. The dataset used in the study is large and consists of 21,000 vegetable images. These images in the dataset are divided into 3 groups as training, testing and validation. Within the scope of the study, all of these groups were combined and a large dataset was obtained. SqueezeNet architecture is used for feature extraction in the developed deep learning-based machine learning model. In addition, the ReliefF method was used for feature selection and the most significant features were determined by eliminating negative features. In the classification phase of the developed application, Linear Discriminant Analysis (LDA) method was preferred. In this study, Hold-Out and 10-fold cross-validation techniques were used. Approximately 99% accuracy value was obtained in both validation techniques. The obtained results of the study show that the proposed method can be used successfully in automatic vegetable classification.

Study on Sensor Array Optimization of Medical Electronic Nose for Wound Infection Detection

In order to improve the detection effect and simplify the number of sensors of electronic nose system for wound infection detection, the sensor arrays are optimized based on Hilbert-Schmidt independence criterion (HSIC) in this brief. Specifically, the HSIC optimization algorithm of Gaussian kernel function is exploited. The criterion of Hilbert-Schmidt independence is obtained by empirical estimation of norm of Hilbert-Schmidt cross-covariance operator. The main idea of its application in sensor array optimization is that the larger the empirical norm estimates of Hilbert-Schmidt cross-covariance operator, the stronger the correlation between sensor features and labels, the greater the role of sensor features in classification and recognition. The experimental results show that the HSIC optimization method (Gaussian kernel function) performs better than the linear discriminant analysis (LDA) method and the principal component analysis (PCA).

HUMAN IDENTIFICATION SYSTEM BASED ON BRAINPRINT USING MACHINE LEARNING ALGORITHMS

In the medical field, due to the development of neuroimaging, several new methods of the biometric field have been attending and favorable candidates for the identification of people. These methods are part of "covert biometrics" that involve the use of measures of clinical and medical images to identify them. The prime motivation to use an invisible (Hidden biometric) is the fact that attacks of a system can be very hard to deal with. This privacy strongly contributes to the increased strongest in the topic of person's verification and identification. In this article, he extracted a brain signature, called a "brain fingerprint" from brain (MRI) Magnetic Resonance Image, obtained from 30 healthy subjects as images (1739), these real data sets from Yarmok Medical Hospital. These brainprint in this work are considered to be a hallmark of the brain. The objective of this proposed work which is design a robust, accurate human identification using human brain print, the brain classification based on several phases, included Data acquisition, Feature extraction processing depend on linear discrimination analysis (LDA) to gain important and interesting features of every image calculated by (number of features in the class). The proposed system shows rise detection precision with the features extracted based on LDA with automatical classifier learning by K nearest neighbor (K-NN) and logistic regression (LR) from the LDA method gained with the LR algorithm of (93%) while LDA method gained (91%) with K-NN.

Audio Classification Algorithm for Hearing Aids Based on Robust Band Entropy Information

Audio classification algorithms for hearing aids require excellent classification accuracy. To achieve effective performance, we first present a novel supervised method, involving a spectral entropy-based magnitude feature with a random forest classifier (SEM-RF). A novel-feature SEM based on the similarity and stability of band signals is introduced to improve the classification accuracy of each audio environment. The random forest (RF) model is applied to perform the classification process. Subsequently, to resolve the problem of decreasing classification accuracy of the SEM-RF algorithm in mixed speech environments, an improved algorithm, ImSEM-RF, is proposed. The SEM features and corresponding phase features are fused on multiple time resolutions to form a robust multi-time resolution magnitude and phase (multi-MP) feature, which improves the stability of the feature with which the speech signal interferes. The RF model is improved using the linear discriminant analysis (LDA) method to form a linear discriminant analysis-random forest (LDA-RF) joint classification model, which performs model acceleration. Through experiments on hearing aid research data sets for acoustic environment recognition, the effectiveness of the SEM-RF algorithm was confirmed on a background audio signal dataset. The classification accuracy increased by approximately 7% compared with the background noise classification algorithm using an RF tree classifier. The validity of the ImSEM-RF algorithm in speech-interference environments was confirmed using the speech in the background audio signal dataset. Compared with the SEM-RF algorithm, the classification accuracy was improved by approximately 2%. The LDA-RF reduced the program’s running time by >80% with multi-MP features compared with RF.

Classification of cloud images by using super resolution, semantic segmentation approaches and binary sailfish optimization method with deep learning model

• In this study, the classification of cloud types was performed. • Super Resolution and Semantic Segmentation were used for image enhancement and efficient feature extraction. • ShuffleNet was used for feature extraction and Binary Sailfish Optimization for feature selection. • The efficiency ranking of the features was achieved with the optimization method. • Successful results were obtained with the proposed approach in the CCSN and SWIMCAT-Ext datasets. Clouds are structures formed by ice crystals, water grains, or both that come together in the atmosphere for various reasons. Clouds have a direct impact on areas such as climate, ecological balance, and air traffic. It is now inevitable to knead the devices used to detect cloud types with artificial intelligence technologies. In this process, deep learning models have begun to be used in the detection of cloud types that are the result of meteorological events. In this study, two publicly available datasets of cloud types were used. In the proposed approach, super-resolution and semantic segmentation were applied as pre-processing steps. Then, feature sets were created using the ShuffleNet model. The binary sailfish optimization method was used for efficient feature selection and classification was performed using the linear discriminant analysis method. Overall accuracy successes of 98.56% and 100% were obtained for the two datasets used for cloud type classification. It was concluded that the approach proposed in this study is successful in cloud type detection.

QSAR modelling of organic dyes for their acute toxicity in Daphnia magna using 2D-descriptors

ABSTRACT The present study reports quantitative structure-activity relationship (QSAR) models for 22 organic dyes spanning a broad chemical domain to predict their toxicity in Daphnia magna [log (1/EC50)]. Only two-dimensional descriptors with clear physicochemical meaning were used to construct the QSAR models. The process of development, validation, and interpretation of models adheres to the stringent recommendations of the Organization for Economic Cooperation and Development (OECD) guidelines. In this study, the multi-layered stepwise regression method and linear discriminant analysis (LDA) method were employed for the deployment of regression – and classification-based models respectively; however, the final regression-based QSAR models were obtained through the partial least squares (PLS) regression. Additionally, the applicability domain of the developed models was verified. The constructed models should be applicable in the absence of toxicity data of new or untested dye structures, particularly when the compounds fall within the developed models’ scope, and also implementable to develop more environmentally friendly alternatives.

Harvesting Brain Signal Using Machine Learning Methods

Abstract Brain computer interface (BCI) systems are developed in the biomedical engineering fields to increase the quality of life among patients with paralysis and neurological conditions. The development of a six class BCI controller to operate a semi-autonomous mobile robotic arm is presented. The controller uses the following mental tasks: imagined left/right hand squeeze, imagined left/right foot tap, rest, and a physical jaw clench. To design a controller, the locations of active electrodes are verified, and an appropriate machine learning algorithm is determined. Three subjects, ages ranging between 22 and 27, participated in five sessions of motor imagery experiments to record their brainwaves. These recordings were analyzed using event related potential (ERP) plots and topographical maps to determine active electrodes. bcilab was used to train two, three, five, and six class BCI controllers using linear discriminant analysis (LDA) and relevance vector machine (RVM) machine learning methods. The subjects' data were used to compare the two-method's performance in terms of error rate percentage. While a two class BCI controller showed the same accuracy for both methods, the three and five class BCI controllers showed the RVM approach having a higher accuracy than the LDA approach. For the five-class controller, error rate percentage was 33.3% for LDA and 29.2% for RVM. The six class BCI controller error rate percentage for both LDA and RVM was 34.5%. While the percentage values are the same, RVM was chosen as the desired machine learning algorithm based on the trend seen in the three and five class controller performances.

Brain tumor segmentation using extended Weiner and Laplacian lion optimization algorithm with fuzzy weighted k-mean embedding linear discriminant analysis

This paper presents an efficient skull stripping method to improve the decision-making process. Extended Weiner filtering (EWF) is used for removing the noise and enhancing the quality of images. Further, laplacian lion optimization algorithm (LXLOA) is implemented. LXLOA utilizes the Otsu’s and Tsallis entropy fitness function to determine an optimal solution. The implemented LXLOA provides a threshold value required for performing the segmentation on the brain MRI images. The extracted features are selected using fuzzy weighted k-means embedding LDA (linear discriminant analysis) method for improving training of the classification model. The proposed LXLOA is extensively tested on standard benchmark functions CEC 2017 and outperforms the existing state-of-the-art algorithm. Rigorous statistical analysis is conducted to determine the statistical significance. Three-fold performance comparison is performed by considering (a) the quality of the segmented image; (b) accuracy, sensitivity, and specificity; and (c) computational cost of convergence for finding an optimal solution. Result reveals that LXLOA gives promising results and demonstrate effective outcomes on the standard quality measures (a) accuracy (97.37%); (b) sensitivity (85.8%); (c) specificity (90%); and (d) precision (91.92%).

The intelligent design of reflow soldering based on an improved high-dimensional surrogate assisted optimization method

The Efficient Global Optimization (EGO) optimizes the temperature curve of the reflow soldering process by constructing the Kriging model. Compared with the traditional Surrogate Assisted Optimization (SAO), it can meet two different requirements: exploitation of optima and exploration of uncertain areas. However, due to the inversion of the covariance correlation matrix and the solving of Kriging-related parameters, the Kriging approximation process for high-dimensional problems is time consuming and even impossible to construct. For this reason, a High-Dimensional Kriging Modeling method through Linear Discriminant Analysis (HDKRG-LDA) method is proposed by considering the correlation parameters and the design variables of a Kriging model. It uses LDA to transform a high-dimensional correlation parameter vector in Kriging into low-dimensional one, which is used to reconstruct a new correlation function. In this study, the HDKRG-LDA method assisted EGO algorithm is applied to optimize the temperature curve of the reflow soldering process. In the optimization results of the reflow soldering, the method can effectively predict the temperature curve, and provide guidance for the production process of the reflow soldering.

Estimation of Sex from the Osteometric Measurements of the Femur in a Contemporary Sri Lankan Population

Sex estimation from human skeletal remains is of vital importance in the buildup of a biological profile of an individual in medico-legal and bioarchaeological studies. The present study is focused on the estimation of sex from osteometric measurements of the complete femur and its fragmentary parts, and the development of a web based application related to this. Fifteen osteometric measurements were taken from 78 dry cadaveric femurs from the Faculty of Medicine, University of Kelaniya. Using R software, linear discriminant analysis and logistic regression methods were applied to build classification models with the help of the application of a stepwise procedure, to identify the best combination of measurements to estimate the sex of the femur. A cross-validation method was applied to estimate the predictive accuracy of each model. Since the linear discriminant analysis model gave more predictive accuracy than the regression model, we suggest using linear discriminant analysis to estimate the sex using osteometric measurements of the femur. From the whole femur measurements, a formula to determine sex was developed with highest total accuracy of 83 % using four parameters; epicondylar breadth, anteroposterior mid-shaft diameter, bi-trochanter length, and maximum shaft diameter. Similarly, measurements of transverse head diameter and bi-trochanter length with a total accuracy of 76 % for the proximal part of the femur, measurements of anteroposterior mid-shaft diameter with a total accuracy of 77 % for the mid-shaft, and measurements of epicondylar breadth and maximum length of the lateral condyle with a total accuracy of 70 % for the distal part of the femur were identified as significant discriminants to determine sex, and formulae were written accordingly. Average accuracy ranged from 83 % to 70 %, with male accuracy slightly higher than that of females. A web application to estimate the sex of femur using these formulae was developed and this will be of great importance for forensic medicine and bio-archaeological research in Sri Lanka.

Application of the linear method of discriminant analysis of reflectance spectra in the near infrared region for the species identification of fish of the Salmonidae family

It is well known that fish belonging to the Salmonidae family differ in their nutritional value. Anatomical and morphological features of different salmon species have a certain similarity; therefore, representatives of this family are most often falsified. Assortment falsification of products from fish of this family is usually carried out by replacing more valuable species with cheaper ones with a reduced nutritional value. Most often, counterfeiting of Atlantic salmon (salmon) by Far Eastern ones (chum salmon, pink salmon, chinook salmon, coho salmon) is found. Near infrared spectroscopy (NIR) is now increasingly used for identification and authentication of closely related organisms, in some cases being a rapid method replacing genetic analysis. We have obtained diffusion reflectance spectra of NIR radiation for three species of fish from the Northern Basin belonging to the salmon family. The best classification by fish species has been obtained by analyzing the NIR spectra of pre-dried fat-free muscle tissue samples. In case of wet samples, the observed differences are less significant, up to insignificant differences in individual values from neighboring clusters. The possibility of using the method of linear discriminant analysis of the NIR reflection spectra of muscle proteins for the species identification of fish has been shown.

Electroencephalography-Based Brain-Computer Interface Motor Imagery Classification.

Background:Advances in the medical applications of brain–computer interface, like the motor imagery systems, are highly contributed to making the disabled live better. One of the challenges with such systems is to achieve high classification accuracy.Methods:A highly accurate classification algorithm with low computational complexity is proposed here to classify different motor imageries and execution tasks. An experimental study is performed on two electroencephalography datasets (Iranian Brain–Computer Interface competition [iBCIC] dataset and the world BCI Competition IV dataset 2a) to validate the effectiveness of the proposed method. For lower complexity, the common spatial pattern is applied to decrease the 64 channel signal to four components, in addition to increase the class separability. From these components, first, some features are extracted in the time and time–frequency domains, and next, the best linear combination of these is selected by adopting the stepwise linear discriminant analysis (LDA) method, which are then applied in training and testing the classifiers including LDA, random forest, support vector machine, and K nearest neighbors. The classification strategy is of majority voting among the results of the binary classifiers.Results:The experimental results indicate that the proposed algorithm accuracy is much higher than that of the winner of the first iBCIC. As to dataset 2a of the world BCI competition IV, the obtained results for subjects 6 and 9 outperform their counterparts. Moreover, this algorithm yields a mean kappa value of 0.53, which is higher than that of the second winner of the competition.Conclusion:The results indicate that this method is able to classify motor imagery and execution tasks in both effective and automatic manners.

Rapid Identification of Peucedanum praeruptorum Dunn and Its Adulterants by Hand-Held Near-Infrared Spectroscopy.

Peucedanum praeruptorum Dunn (PPD) is a traditional Chinese medical herb of high medical and economic value. However, PPD is often adulterated by inexpensive plants. In order to establish an integrated and straightforward methodology to identify adulterated PPD products, hand-held near-infrared spectroscopy (NIRS) combined with chemical pattern recognition techniques was employed. The standard normal variate (SNV) was used to preprocess the original near-infrared spectra. Principal component analysis (PCA), linear discriminant analysis (LDA), and partial least-squares regression analysis (PLSDA) were used to construct the recognition models. PCA analysis could not correctly distinguish PPD from non-PPD. However, based on absorbance in the spectral region of 1405-2442 nm and SNV pretreatment, the accuracy of the LDA model was above 90% at identifying genuine PPD. Compared with the LDA method, the PLSDA model is more stable and reliable, and its model prediction accuracy was 93.4%. The combination of NIRS and chemometric methods based on a hand-held near-infrared spectrometer is an efficient, nondestructive, and reliable method for validating traditional Chinese medicine PPD. The advanced method based on a hand-held near-infrared spectrometer can be used for rapid identification and quality evaluation of PPD in the field, medicinal material markets, and points of sale.

Quantitative computed tomography imaging-based classification of cement dust-exposed subjects with an artificial neural network technique

Background and objectiveCement dust exposure is likely to affect the structural and functional alterations in segmental airways and parenchymal lungs. This study develops an artificial neural network (ANN) model for identifying cement dust-exposed (CDE) subjects using quantitative computed tomography-based airway structural and functional features. MethodsWe obtained the airway features in five central and five sub-grouped segmental regions and the lung features in five lobar regions and one total lung region from 311 CDE and 298 non-CDE (NCDE) subjects. The five-fold cross-validation method was adopted to train the following classification models:ANN, support vector machine (SVM), logistic regression (LR), and decision tree (DT). For all the classification models, linear discriminant analysis (LDA) and genetic algorithm (GA) were applied for dimensional reduction and hyperparameterization, respectively. The ANN model without LDA was also optimized by the GA method to observe the effect of the dimensional reduction. ResultsThe genetically optimized ANN model without the LDA method was the best in terms of the classification accuracy. The accuracy, sensitivity, and specificity of the GA–ANN model with four layers were greater than those of the other classification models (i.e., ANN, SVM, LR, and DT using LDA and GA methods) in the five-fold cross-validation. The average values of accuracy, sensitivity, and specificity for the five-fold cross-validation were 97.0%, 98.7%, and 98.6%, respectively. ConclusionsWe demonstrated herein that a quantitative computed tomography-based ANN model could more effectively detect CDE subjects when compared to their counterpart models. By employing the model, the CDE subjects may be identified early for therapeutic intervention.

Impact of temperature and sunlight exposition on locally brewed beers composition revealed by fluorescence spectroscopy coupled with chemometric methods.

Fluorescence excitation-emission matrix (EEM) and synchronous scanning fluorescence (SF), coupled with parallel factor (PARAFAC) analysis, principal component analysis (PCA) and Linear discriminant analysis (LDA) methods were used to differentiate 49 lager beer samples and monitor the effects of temperature and sunlight exposition on their composition. EEMs were decomposed into independent fluorescent components. The beer samples were characterized by the presence of excitation/emission (exc/em) peaks at 290/350, 315/345, 340/410, 375/455, 360/420, 400/460, and 437/525nm, which were ascribed, according to the known beer fluorescent components, respectively to aromatic amino acids, vitamin B6 (pyridoxal), vitamin B6 (pyridoxic acids), vitamin B3, iso-α-acids, vitamin B1, and vitamin B2. The variation of the relative concentration of iso-α-acids in the different beer brands presented the same trend with that of their relative IBU, thus revealing the potency of our method in the assessment of beer bitterness. The impact of temperature and sunlight was assessed by separately monitoring the modifications of the EEMs after 5h exposition to 40°C temperature and sunlight respectively. Noticeably a variation of the peaks intensity of the iso-α-acids, carbonyl and polyphenols compounds were observed, accompanied by a decrease of the alcohol content, thus indicating beer aging. This method can be useful for the identification and monitoring of beer state during the technological production cycle and storage. PRACTICAL APPLICATION: The present work demonstrates the potency of the fluorescence technique used together with chemometric methods to give valuable information on beer bitterness. Development of rapid quantitative methods for beer bitterness assessment is of great importance for brewing industries.

Magnetic Sensor-Based Multi-Vehicle Data Association

Sensors have been playing an increasingly important role in smart cities. Using small roadside magnetic sensors provides a cost-efficient method for monitoring vehicle traffic. However, there are significant challenges associated with vehicle data misalignment due to the timing-offsets between sensors and missed or increased data because of vehicle lane-changing. In this paper, we propose a novel traffic information acquisition and vehicle state estimation scheme using multiple road magnetic sensors. To efficiently solve the multi-sensor registration problem in the presence of timing-offset, we develop a linear discrimination analysis method to achieve vehicle separation and classification. To handle the situation of lane-changing, we propose a data smoothing technique based on a multi-hypotheses tracker that exploits vehicle correlation. The road density effect on the probability of correct data association is investigated, with numerical and experimental results provided. The results show that our proposed scheme can effectively detect vehicles with a 95.5% accuracy rate. It also outperforms some other speed sensing methods in terms of the vehicle speed estimation accuracy.

Target Threat Assessment in Air Combat Based on Improved Glowworm Swarm Optimization and ELM Neural Network

Target threat assessment technology is one of the key technologies of intelligent tactical aid decision-making system. Aiming at the problem that traditional beyond-visual-range air combat threat assessment algorithms are susceptible to complex factors, there are correlations between assessment indicators, and accurate and objective assessment results cannot be obtained. A target threat assessment algorithm based on linear discriminant analysis (LDA) and improved glowworm swarm optimization (IGSO) algorithm to optimize extreme learning machine (ELM) is proposed in this paper. Firstly, the linear discriminant analysis method is used to classify the threat assessment indicators, eliminate the correlation between the assessment indicators, and achieve dimensionality reduction of the assessment indicators. Secondly, a prediction model with multiple parallel extreme learning machines as the core is constructed, and the input weights and thresholds of extreme learning machines are optimized by the improved glowworm swarm optimization algorithm, and the weighted integration is carried out according to the training level of the kernel. Then, the threat assessment index functions of angle, speed, distance, altitude, and air combat capability are constructed, respectively, and the sample data of air combat target threat assessment are obtained by combining the structure entropy weight method. Finally, the air combat data is selected from the air combat maneuvering instrument (ACMI), and the accuracy and real-time performance of the LDA-IGSO-ELM algorithm are verified through simulation. The results show that the algorithm can quickly and accurately assess target threats.

Density-oriented linear discriminant analysis

The conventional Linear Discriminant Analysis (LDA) model has some challenges, such as sensitivity to the outlier, the singularity problem of the within-class scatter matrix, and Gaussian assumption of data within the same class. This paper proposes a robust LDA method that tries to solve the sensitivity to outliers and singularity problems. Specifically, we first use Bayesian risk to design the proposed method optimization problem. Then, the proposed Density-oriented LDA (DLDA) method used the data density as prior knowledge for robustness against outliers. The proposed method can classify non-linear and multi-mode distribution data sets. Furthermore, the proposed method can be employed for big data classification using the AdaBoost approach. Experimental results on synthetic and real data sets demonstrate the proposed DLDA method’s superiority over other competing methods.

Optimization of Electronic Nose Sensor Array for Tea Aroma Detecting Based on Correlation Coefficient and Cluster Analysis

The electronic nose system is widely used in tea aroma detecting, and the sensor array plays a fundamental role for obtaining good results. Here, a sensor array optimization (SAO) method based on correlation coefficient and cluster analysis (CA) is proposed. First, correlation coefficient and distinguishing performance value (DPV) are calculated to eliminate redundant sensors. Then, the sensor independence is obtained through cluster analysis and the number of sensors is confirmed. Finally, the optimized sensor array is constructed. According to the results of the proposed method, sensor array for green tea (LG), fried green tea (LF) and baked green tea (LB) are constructed, and validation experiments are carried out. The classification accuracy using methods of linear discriminant analysis (LDA) based on the average value (LDA-ave) combined with nearest-neighbor classifier (NNC) can almost reach 94.44~100%. When the proposed method is used to discriminate between various grades of West Lake Longjing tea, LF can show comparable performance to that of the German PEN2 electronic nose. The electronic nose SAO method proposed in this paper can effectively eliminate redundant sensors and improve the quality of original tea aroma data. With fewer sensors, the optimized sensor array contributes to the miniaturization and cost reduction of the electronic nose system.