Search

In the mining process of coal, oil, and natural gas, there are often a large number of toxic, hazardous and explosive gases, which pose a greater safety hazard. These gases usually exist in the form of mixtures. Accurately identifying the composition of the mixed gas is of great significance to the prevention of safety accidents. In order to improve the accuracy of the component recognition of the mixed gas, this paper proposes a mixed gas component recognition algorithm based on the combination of principal component analysis (PCA) and k-nearest neighbor algorithm (KNN). PCA is used to extract the characteristics of the sensor array signal to obtain the characteristic value of the gas, and then KNN is used to realize the recognition of the gas type. The results show that the recognition rate of the feature quantity after dimensionality reduction as input is higher than that before dimensionality reduction. Finally, PCA and KNN algorithm and PCA and support vector machine (SVM) algorithm are compared for the recognition rate of mixed gas. Experimental results show that the proposed method has a recognition rate of 96.88% for mixed gas components.

Gases in the real environment always exist in the form of mixtures, and effective identification of gas types to reduce the occurrence of safety incidents has become an important direction in the field of gas analysis research. This paper proposes a mixed gas identification method based on PCA and PSO-LSSVM. This method uses principal component analysis (PCA) to reduce the dimensionality of the sensor array output signal, and uses the Relief algorithm to select data. The particle swarm algorithm is used to iteratively optimize the relevant parameters in the least squares support vector machine model, and the PSO-LSSVM model is constructed to qualitatively analyze the composition of the mixed gas. This article uses a public data set of mixed gases of ethylene, methane and carbon monoxide to conduct experiments. The experimental results show that the method used in this paper can effectively identify the type of mixed gas, and the recognition accuracy rate reaches 91.67%. The method proposed in this paper can provide a research foundation for the follow-up analysis of the mixed gas concentration.

Chemical gas sensor array is a common information acquisition device in current machine olfactory systems. However, due to the characteristics of the sensitive materials in the chemical gas sensor, the measurement quality of sensor array decreases in long-term practical application, which gradually affects the analytical results of the machine olfactory system as the time goes on. The self-validating sensor has fault detection and isolation module, fault diagnosis module, fault recovery module and uncertainty analysis module. These functions of self-validating sensor are suitable for monitoring the reliability of the chemical sensor array. In this paper, the self-validating sensor technology is introduced into chemical gas sensor array to improve the measurement quality, so as to improve the overall performance of machine olfactory system. A prototype of self-validating chemical sensor array is designed to illustrate the feasibility of its application in machine olfactory system.

With the development of urbanization, more and more attention has been paid to the problem of urban air pollution. The expansion of city scale results in the dynamic change of pollutant distribution. The monitoring equipment based on optical analysis instrument cannot meet the new demand of spatiotemporal dynamic monitoring of pollution gas distribution in the region. The portable air pollution monitoring equipment can realize the regional monitoring of pollutants and is easy to form a monitoring network. A prototype of a portable air pollution monitoring system based on chemical sensor array is designed in this paper. The monitoring system is mounted in a portable case and can monitor the working state of the system and the process of gas measurement through the touch screen. The instrument can monitor the concentration of environmental pollution gas in real time and display the concentration change curve. It is also equipped with 4G wireless module, which can transmit the pollution gas information remotely. The reliability and effectiveness of the designed monitoring system are proved by testing under laboratory conditions.

Existing deep convolutional neural network-based survival analysis neither consider the modern attention mechanism nor use 3D tomographic medical images such as magnetic resonance images (MRI). This paper for the first time presents a 3D deep convolutional neural network using attention mechanism for survival prediction from multiparametric MRI in glioblastoma (GBM) patients. The attention module is incorporated into the residual network to enhance the representation power of meaningful features while suppress unimportant ones. The proposed model achieves an C-index of 0.71 in the training dataset and 0.68 in an independent test dataset, which outperforms both the traditional Cox model (0.60,0.54) and the non-attentive model (0.63,0.61). It indicates that the proposed 3D attention network has the potential of offering better performance in predicting survival using MRI than traditional survival analysis.

This paper identifies a MR imaging radiomics signature for prediction of overall survival (OS) in patients with glioblastoma multiforme (GBM). A fully-automatic radiomics model is presented, including automatic tumor segmentation, high-throughput features extraction, features selection, and multi-feature signature identification. The automatic GBM segmentation method employs a random forest classifier with a CRF spatial regulation where the importances of the multi-modality features are considered. After feature selection, a 4-feature radiomics signature is identified based on training data and further confirmed on independent validation data. The proposed signature succeeds to stratify patients into prognostically high-risk and low-risk groups, indicating the potential to facilitate the preoperative patient care of GBM patients.

Magnetic resonance amide proton transfer (APT) imaging has proved its potential for detecting tumors and evaluating treatment response by depicting chemical exchange saturation transfer effect between the endogenous protein/peptide amide proton and bulk water. However, conventional asymmetry analysis for APT effect measurement is susceptible to concomitant contributions, particular semisolid magnetic transfer (MT) and nuclear overhauser effect. In this study, dominant saturation transfer (ST) effects, including direct water saturation and MT, were estimated from a sum of two Lorentzian functions. APT effect was then quantified by subtracting the Z-spectrum with the two ST effects. Feasibility of the method in the assessment of glioma therapeutic response was investigated in a rodent model at 3 Tesla.

This paper proposes a fully-automatic method for extraction of high-throughput MRI radiomics features in Glioblastoma Multiforme (GBM). First, the tumor subregions are automatically segmented from multi- modality MR images using a proposed random forest classifier with a conditional random field spatial regulation, where the importances of the multi-modality features are considered. Within the segmented subregions, 44928 high-order texture features are extracted at different voxel sizes by using different quantization methods with varying gray levels. The DICE score, sensitivity and specificity of the proposed automatic segmentation algorithm are calculated. The reproducibility of the extracted features against the changes in voxel sizes, quantization methods and gray levels are assessed quantitatively. The proposed radiomics method can be used for exploring of imaging biomarker and facilitate the pre-treatment care of GBM patients.

Machine Olfaction is a bionic detection technique that adopts electronic device to simulate biological olfactory system. As an information acquisition device, MOS gas sensor array is an important component of machine olfactory system. In this paper, a novel gas concentration estimation method based on multivariate relevance vector machine (MVRVM) is proposed for mixed gas detection by using MOS gas sensor array. The proposed method utilizes the excellent multivariate regression analysis performance of MVRVM to estimate any one analyte concentration in the mixed gas. To demonstrate the performance of proposed gas concentration estimation method, a machine olfactory system is designed and implemented. Gas concentration experiments with methane and carbon monoxide gas mixture as the research object were performed in the above machine olfactory system. Experimental results show that the proposed method can provide a good solution for mixed gas concentration estimation in the aspects of estimated accuracy and computational complexity.

The vibration signals of rolling bearing have the characteristics of nonlinearity and nonstationarity, in which a large number of working condition informations on rolling bearing are contained. By using vibration signals of rolling bearing, a novel rolling bearing fault diagnosis method based on ensemble empirical mode decomposition and permutation entropy (EEMD-PE) coupled with multiclass relevance vector machines (M-RVM) is proposed in this paper. The proposed method can decompose the vibration signals of rolling bearing to a series of intrinsic mode functions (IMFs) that contain different fault features of rolling bearing by using the self-adaptive decomposition ability of EEMD. Permutation entropy (PE) is used to extract the feature of each IMF and the fault feature vector of vibration singal is constituted by the PE values of IMFs. The M-RVM classifier is built by the feature vectors extracted from rolling bearing vibration samples in different fault modes. Moreover, the multiple faults identification result can be implemented by the MRVM classifier in the form of probability output. The experimental results demonstrate that the proposed fault diagnosis method is capable of effectively extracting fault features in vibration signal and improving the fault identification accuracy compared with the existing bearing fault diagnosis methods.

A novel self-validating strategy using grey bootstrap method (GBM) is proposed for data validation and dynamic uncertainty estimation of self-validating sensor. The failure detection, isolation, and recovery (FDIR) of self-validating sensor based on GM(1,1) predictor can simultaneously detect and isolate fault and accomplish failure recovery with high accuracy and good timeliness. Furthermore, the proposed FDIR scheme has good effectiveness of discriminating between fault-free signals with sudden changes and undoubted faults. In dynamic measurement process, because of unknown prior information about probability density functions (PDFs) of uncertainty sources, the uncertainty cannot be estimated by Guide to the Expression of Uncertainty in Measurement (GUM). The GBM can evaluate the measurement uncertainty by poor information and small sample. Experiment results show that the GBM strategy provides a good solution to data validation and dynamic uncertainty estimation of self-validating sensor.