Classification of data from electronic nose using relevance vector machines

To evaluate the quality of beef seasonings, the aroma profiles of high-grade, medium-grade, and lower-grade beef seasonings were characterized by sensory evaluation, gas chromatography-mass spectrometry (GC-MS) and an electronic nose. Sensory evaluation indicated significant differences in the three grades of beef seasonings whose high-grade samples got the highest score of the aroma properties of beef, fat, vegetable, soy sauce, and overall flavor and the lowest score of the aroma of gamey. A total of 57 volatile compounds that included aldehydes, acids, alkenes, nitrogen- and sulfur-containing compounds, phenols, alcohols, and ketones were identified by solid-phase micro-extraction gas chromatography-mass spectrometry (SPME/GC-MS). The volatile compounds showed good correlation with seven sensory attributes according to the partial least square regression (PLSR) models. Electronic nose data were processed by principal component analysis (PCA) and cluster analysis (CA). According to the obtained results, electronic nose and SPME/GC-MS combined with multivariate statistical analysis were effective identification tools for the quality discrimination of beef seasonings.

The study of lithium-ion battery management has always been a hot issue in energy field. Predicting the remaining useful life (RUL) helps to know the time of maintenance and replacement in advance so that users can be avoided from unexpected battery fault. In this paper, a RUL prediction method on the basis of a sparse probability model in the Bayesian framework which is Relevance Vector Machine (RVM) is proposed. Hybrid kernel function is introduced to ensure the prediction accuracy. A newly heuristic algorithm Cuckoo Search (CS) is adopted to intelligently determine all the kernel parameters along with the weight of each kernel function. Contrast experiments show that our proposed approach based on hybrid kernel RVM with CS (CS-HKRVM) outperforms the basic machine learning algorithms including single kernel RVM, Back Propagation Neural Network and Support Vector Machine. The hybrid kernel RVM with particle swarm optimization (PSO) is also conducted in order to demonstrate that CS is more effective and accurate than PSO in searching for the optimal solution of prediction model construction.

Power system fault type classification and location prediction is critical in assessing the reliability of the power system, and later restoring it to a stable operating point followed by a fault. State of the art methods include sequence component, impedance measurement from the origin of the fault, and traveling wave based methods for fault type detection and classification problem. It is important to identify and classify the fault as quickly as possible for restoring power system stability to normal operation. Machine Learning and Deep Learning methods allow the analysis of large data of fault voltages and currents by using fast and efficient algorithms. These methods require large amount of data, however, with the recent advances in the field of power system, data acquisition using smart meters and Phasor Measurement Units (PMU), huge amount of system-wide data can be made available to analyze the problem of fault type classification and location prediction. This paper presents a comparative study of Stochastic Gradient Descent (SGD) based Deep Neural Network (DNN) and Machine Learning (ML) applied to power system fault type and location prediction problem. DNN architecture uses 10 hidden layers, each layer having 60 units with hyperbolic tangent as activation function, and a combination of Support Vector Machine (SVM) and Principal Component Analysis (PCA) method are considered. Comparative results in terms of time taken to run the algorithms, and accuracy of the results obtained are presented for a 3 machine 9 bus system. Results indicate that SVM method is an optimal choice for fault classification with high accuracy for location prediction and low computational requirements compared with DNN.

This article adopts three soft computing techniques including support vector machine (SVM), least square support vector machine (LSSVM) and relevance vector machine (RVM) for prediction of status of epimetemorphic rock slope. The input variables of SVM, LSSVM and RVM are bulk density, height, inclination, cohesion and internal friction angle. There are 53 datasets which have been used to develop the SVM, LSSVM and RVM models. The developed SVM, LSSVM and RVM give equations for prediction of status of epimetemorphic rock slope. The performance of SVM, LSSVM and RVM is 100%. A comparative study has been presented between the developed SVM, LSSVM and RVM. The results confirm that the developed SVM, LSSVM and RVM are effective tools for prediction of status of epimetemorphic rock slope.

This paper proposes a method of applying Support Vector Machines to network-based Intrusion Detection System (SVM IDS). Support vector machines(SVM) is a learning technique which has been successfully applied in many application areas. Intrusion detection can be considered as two-class classification problem or multi-class classification problem. We used dataset from 1999 KDD intrusion detection contest. SVM IDS was learned with triaing set and tested with test sets to evaluate the performance of SVM IDS to the novel attacks. And we also evaluate the importance of each feature to improve the overall performance of IDS. The results of experiments demonstrate that applying SVM in Intrusion Detection System can be an effective and efficient way for detecting intrusions.

Application of support vector machines and relevance vector machines in predicting uniaxial compressive strength of volcanic rocks

Lithological classification is a pivotal aspect in the field of geology, and traditional field surveys are inefficient and challenging in certain areas. Remote sensing technology offers advantages such as high efficiency and wide coverage, providing a solution to the aforementioned issues. The aim of this study is to apply remote sensing technology for lithological classification and attempt to enhance the accuracy of classification. Taking a study area in Jixi, Heilongjiang Province, China, as an example, lithological classification is conducted using high-resolution satellite remote sensing data from GF-2 and texture data based on gray-level co-occurrence matrix (GLCM). By comparing the accuracy of lithological classification using different methods, the support vector machine (SVM) method with the highest overall accuracy is selected for further investigation. Subsequently, this study compares the effects of combining GF-2 data with different texture data, and the results indicate that combining textures can effectively improve the accuracy of lithological classification. In particular, the combination of GF-2 and the Dissimilarity index performs the best among single-texture combinations, with an overall accuracy improvement of 7.8630% (increasing from 74.6681% to 82.5311%) compared to using only GF-2 data. In the multi-texture combination dataset, the Mean index is crucial for enhancing classification accuracy. Selecting appropriate textures for combination can effectively improve classification accuracy, but it is important to note that excessive overlaying of textures may lead to a decrease in accuracy. Furthermore, this study employs principal component analysis (PCA) and independent component analysis (ICA) to process the GF-2 data and combines the resulting PCA and ICA datasets with different texture data for lithological classification. The results demonstrate that combining PCA and ICA with texture data further enhances classification accuracy. In conclusion, this study demonstrates the application of remote sensing technology in lithological classification, with a focus on exploring the application value of different combinations of multispectral data, texture data, PCA data, and ICA data. These findings provide valuable insights for future research in this field.

In order to quickly distinguish infertile eggs from fertile eggs, the hyperspectral imaging technology consisting of imaging and spectral information was used for detecting the fertile information of eggs. Before hatching eggs were incubated, a hyperspectral imaging system (wavelength between 400 to 1 000 nm) was used to acquire the images one-by-one manually. The characteristic information of ratios of length to short axis, elongation, roundness and the ratios of the yolk area to the whole area was extracted based on the images. The normalization method was used as the spectral data preprocessing, and then 155 spectral characteristic variables were extracted from 520 nm waveband through the correlation coefficient method. Principal component analysis (PCA) method was adopted to reduce the dimensions of image-spectrum fusion information; the top six principal components were extracted. Support vector machine (SVM) method was used to establish classification of fertile and infertile eggs models, which are based on image, spectrum and image-spectrum fusion information respectively. The accuracy rates of the SVM models were 84.00%, 90.00% and 93.00% respectively. The experimental results show that the model based on image-spectrum fusion information technology is superior to the single information model. Hyperspectral transmission imaging technology is effective and feasible to detect the fertile hatching eggs before incubation. Keywords: hyperspectral image, hatching eggs, information fusion, nondestructive detection DOI: 10.3965/j.ijabe.20150804.1672 Citation: Zhu Z H, Liu T, Xie D J, Wang Q H, Ma M H. Nondestructive detection of infertile hatching eggs based on spectral and imaging information. Int J Agric & Biol Eng, 2015; 8(4): 69－76.

This study proposes a model to predict the height for water-conducting fractured zone using easily obtained parameters which is Relevance Vector Machine (RVM) based on Principal Component Analysis (PCA). PCA was used to reduce the several factors affecting the water conducted fractured zone height to a few principal components. A nonlinear mapping relationship between the water conducted fractured zone height and principal components was established by using RVM model, and corresponding results of water conducted fractured zone height prediction is inferred. Applying this method to specific examples, comparison and analysis the predicted results of Back Propagation (BP), Partial Least Squares (PLS), Partial Least Squares-Back Propagation (PLS-BP) and Particle swarm optimization-Radial Basis Function (PSO-RBF) methods under the same learning sample conditions, the results reflect that the PCA-RVM prediction method reduces several influencing factors into a few principal components reasonably by analyzing the correlation and contribution rate of various factors, which is significantly better than the remaining 4 methods in information screening. The prediction results of each method show that the PCA-RVM method has the advantages of high precision, small discreteness and high reliability, providing a new method for the prediction of the water conducted fractured zone height.

The aim of the present study was to develop an electronic nose for the quality control of red meat. Electronic nose and bacteriological measurements are performed to analyse samples of beef and sheep meat stored at 4°C for up to 15 days. Principal component analysis (PCA) and support vector machine (SVM) based classification techniques are used to investigate the performance of the electronic nose system in the spoilage classification of red meats. The bacteriological method was selected as the reference method to consistently train the electronic nose system. The SVM models built classified meat samples based on the total microbial population into "unspoiled" (microbial counts < 6 log10 cfu/g) and "spoiled" (microbial counts ≥ 6 log10 cfu/g). The preliminary results obtained by the bacteria total viable counts (TVC) show that the shelf-life of beef and sheep meats stored at 4 °C are 7 and 5 days, respectively. The electronic nose system coupled to SVM could discriminate between unspoiled/ spoiled beef or sheep meats with a success rate of 98.81 or 96.43 %, respectively. To investigate whether the results of the electronic nose correlated well with the results of the bacteriological analysis, partial least squares (PLS) calibration models were built and validated. Good correlation coefficients between the electronic nose signals and bacteriological data were obtained, a clear indication that the electronic nose system can become a simple and rapid technique for the quality control of red meats.

We present a probabilistic ranking-driven classifier for the detection of video semantic concept, such as airplane, building, etc. Most existing concept detection systems utilize Support Vector Machines (SVM) to perform the detection and ranking of retrieved video shots. However, the margin maximization principle of SVM does not perform ranking optimization but merely classification error minimization. To tackle this problem, we exploit the sparse Bayesian kernel model, namely the relevance vector machine (RVM), as the classifier for semantic concept detection. Based on automatic relevance determination principle, RVM outputs the posterior probabilistic prediction of the semantic concepts. This inference output is optimal for ranking the target video shots, according to the Probabilistic Ranking Principle. The probability output of RVM on individual uni-modal features also facilitates probabilistic fusion of multi-modal evidences to minimize Bayes risk. We demonstrate both theoretically and empirically that RVM outperforms SVM for video semantic concept detection. The testings on TRECVID 07 dataset show that RVM produces statically significant improvements in MAP scores over the SVM-based methods.

In this paper, we evaluate the use of an electronic nose (EN) containing 13 conducting polymer gas sensors to discriminate between patterns of volatile organic compounds (VOCs) emitted by plants. The VOC patterns examined were produced by tomato, cucumber and pepper plants under both healthy and infected or infested conditions. Leaves from the plants were subjected to mechanical damage or pest and disease attacks (i.e. spider mites infested or mildew infected) and others were judged against undamaged healthy leaves. Support vector machines (SVMs) with linear, polynomial and Gaussian radial basis function (RBF) kernels were used to process and classify the raw data collected. The SVM illustrated an ability to discriminate between different VOC patterns and hence was able to classify correctly the infected leaves using the EN data. The results indicate that the array of 13 EN gas sensors can discriminate among VOC patterns from undamaged and artificially damaged leaves of the three plant species. This study demonstrates the potential application of such an EN technology coupled with suitable pattern recognition and signal processing methods to be used as a real time pest and disease detection system in the greenhouse environment.

In this paper, we develop a low-cost portable spectrometer based on Support Vector Machines (SVM) method. The purpose of the spectrometer development is for halal food research project. The portable spectrometer uses various light-emitting diodes (LEDs), light sensor and Arduino microcontroller. The initial research of the spectrometer is testing various oil, such as palm oil, olive oil, sesame oil, soybean oil, and lard. The waveform analysis of each oil can be distinguished by spectroscopy method. But, by using Support Vector Machines (SVM) method the various oil can be distinguished and classified better. The data measurement, classification, and graphical interface result show on the interface of Raspberry Pi based on Python 2.7. Thus, the spectrometer can be used for lard detection.

Freshness is a key value for access fish quality; fish freshness could be determined by volatile compounds during storage. An electronic nose was constructed with virtual instrument and four commercial tin dioxide-based gas sensors array. Fresh water fish silver carp was stored at 4°C and tested by headspace method. A weighted piece of fish is introduced into a sensor's chamber and the signals of the sensors due to the fish emissions are recorded as function of time. Unsupervised method PCA (principal component analysis) was employed to discriminate among fresh, semi-fresh and deteriorate fish. PCR (principal component regression), PLS (partial least square) and BP-ANN (artificial neural network) method were used to build mathematic model to predict TVB-N (total volatile basic nitrogen). The results indicated that PCA method can discriminate fresh, semi-fresh and deteriorate fish, which indicated the electronic nose response correlated with the loss of fish freshness. The correlation coefficients of predicted and measured TVB-N value of PCR, PLS and BP-ANN model were 0.898, 0.922 and 0.976, which indicated that the BP-ANN method has the highest predicted accuracy for electronic nose.

Brillouin optical correlation-domain sensing enables high-speed Brillouin gain spectrum (BGS) measurement at random positions along the optical fiber. To extract the Brillouin frequency shift (BFS) that reflects the real-time strain information, machine learning methods of principal components analysis (PCA) and support vector machine (SVM) are used in the signal processing for the BGSs. The performances of dimensionality reduction by PCA and SVM based on classification and regression are analyzed and compared. The experiment demonstrates an 8 kHz BGS acquisition repetition rate and an average BFS extraction time of 0.0104 ms, which is 27.3 times faster than the conventional method with no PCA. The proposed methods realize a real-time dynamic strain measurement at the frequency of 40 Hz.