Principle Component Analysis Model Research Articles

Multirate Mixture Probability Principal Component Analysis for Process Monitoring in Multimode Processes

In the multirate sampling processes, the process data are usually collected from various operating conditions and display multimodal characteristics. To monitor these multirate multimode processes, a multirate mixture probability principal component analysis model is proposed for process modeling and fault detection. In this model, the local multirate models are built first for each mode and all of them are subsequently fused with the mixture modeling approach. Such model is able to deal with multirate data with various amount of sampling rates, contributing to a remarkable fault detection and mode identification performance by utilizing all the available measurements even if some variables are unobserved. Then the expectation <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$-$</tex-math> </inline-formula> maximum algorithm is utilized to estimate all the model parameters in the probabilistic framework and the corresponding monitoring method is also developed based on the constructed models. Finally, the effectiveness of the proposed method is demonstrated through a PRONTO benchmark and a real multimode ammonia synthesis process. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Motivated by the practical problem of ununiform sampling intervals in multimode processes, this paper proposes a novel multirate mixture probability principle component analysis model for processes modeling and monitoring. In this model, all the available observations with different sampling rates can be incorporated, which contributes greatly to capturing the multimodal characteristics within the industrial processes. Such ability is the key to realize multimode process monitoring, evaluation, fault diagnosis, and process optimization. In addition, although this paper only focuses on the continuous multirate data in industry, it is equally applicable to other forms of multirate data, such as images and videos.

Analysis of the quality, source identification and apportionment of the groundwater in a typical arid and semi-arid region

A detailed and thorough study of the quality and its distribution, source identification and apportionment of groundwater, as the major or even sole selection of clean water in Songyuan City (a typical arid and semi-arid district in China), is needed for local sustainable development. The groundwater quality was evaluated using a vague set (VS)-technique for order of preference by similarity to ideal scheme (TOPSIS) model to determine its contamination status. Additionally, to explore the source and quantitative analysis of the driving factors of the groundwater chemistry in Songyuan City, a hydrochemical graphical method and a Principle Component Analysis (PCA) and Positive Matrix Factorization (PMF) model were employed. Regarding the quality of the groundwater in Songyuan, 74.5% of the samples were categorized into Grade I–III (Excellent, Good, and Moderate) water, indicating that the majority of the groundwater can be used directly. Moreover, the confined water tended to be cleaner and more appropriate for use in comparison with the phreatic water in Songyuan City. The PCA and PMF model and hydrochemical graphs demonstrated water–rock interactions and the evaporation process acted as the main factor, which was followed by anthropogenic activities as they contributed 50.1% and 20.4% of the total, respectively. Besides, the fluoride and iron contamination mainly caused by geogenic processes cannot be ignored as they were identified as the two driving factors that controlled the water quality, accounting for 20.2% and 9.3%, respectively. The mutual influence of the natural geological processes and human interventions contribute to the groundwater deterioration in Low Plain. Furthermore, the inappropriate well-forming techniques (without water-stop processes) in Qianan County was the main reason for the low-quality of deep Neogene confined water. This research provides useful information and directions for the local government to carry out corresponding and effective groundwater remediation strategies.

Energy consumption mode identification and monitoring method of process industry system under unstable working conditions

Process industry systems under unstable working conditions are prone to potential anomalies, deviating from the original transition trajectory, and taking longer than expected to return to stability due to persistent disturbances from uncertainties and experience-based regulation errors. The energy waste caused by this situation has not received sufficient attention, and cannot be addressed by existing energy consumption monitoring methods. Herein, an energy consumption mode (ECM) identification and monitoring method under unstable working conditions is proposed, consisting of ECM identification model and multi-mode dynamic monitoring model, focusing on the variation rules of the correlation between energy consumption and other states of the system. In the ECM identification stage, the ECM correlation parameters that reflect the comprehensive production information are selected. Then, given the transfer characteristics of ECM, a Hidden Semi-Markov Model (HSMM) is constructed to fit the migration between modes and the duration within modes. The Variational Bayesian Gaussian Mixture Model is introduced to improve the HSMM, which solves the problem of lacking prior knowledge of ECM and achieves the automatic classification and online identification of ECM. In the dynamic monitoring stage of multi-ECMs, a series of dynamic kernel principle component analysis models are established, and the corresponding monitoring thresholds are set for each ECM. By calculating the maximum of the posteriori probability and the mode thresholds, the ECMs under unstable conditions can be accurately identified and automatically monitored. Compared with previous methods, the proposed method reduces the false detection rate and missed detection rate of abnormal ECM identification to 1.04% and 1.31% in the actual slag grinding production process, which proves its effectiveness.

The impact of strategic competitive innovation on the financial performance of SMEs during COVID-19 pandemic period

PurposeThe purpose of this paper is to reveal the impact of strategic competitive innovation types on the financial performance of SMEs during a very critical period: the COVID-19 pandemic. Four strategic competitive innovation types are considered in this study: marketing innovation, organizational innovation, product innovation and processes innovation.Design/methodology/approachTo examine empirically the relationship between strategic competitiveness and financial performance, data were collected from a sample of 426 Lebanese SMEs belonging to seven different sectors.FindingsThe empirical findings of principle component analysis model (PCA) and multiple regression model (MR) reveal that the ability to innovate is essential to an SME’s survival during a crisis. The results of this study confirm the existence of a positive impact of marketing innovation and processes innovation on the financial performance of SMEs during the COVID-19 pandemic.Practical implicationsMoreover, results suggest that, in Lebanese SMEs, product innovation and organizational innovation do not have any impact on the financial performance during the pandemic period.Originality/valueThis research focused on strategic competitive innovation as a broadly considered essential condition for the survival of SMEs during the COVID-19 crises.

Variable Selection in the Regularized Simultaneous Component Analysis Method for Multi-Source Data Integration

Interdisciplinary research often involves analyzing data obtained from different data sources with respect to the same subjects, objects, or experimental units. For example, global positioning systems (GPS) data have been coupled with travel diary data, resulting in a better understanding of traveling behavior. The GPS data and the travel diary data are very different in nature, and, to analyze the two types of data jointly, one often uses data integration techniques, such as the regularized simultaneous component analysis (regularized SCA) method. Regularized SCA is an extension of the (sparse) principle component analysis model to the cases where at least two data blocks are jointly analyzed, which - in order to reveal the joint and unique sources of variation - heavily relies on proper selection of the set of variables (i.e., component loadings) in the components. Regularized SCA requires a proper variable selection method to either identify the optimal values for tuning parameters or stably select variables. By means of two simulation studies with various noise and sparseness levels in simulated data, we compare six variable selection methods, which are cross-validation (CV) with the “one-standard-error” rule, repeated double CV (rdCV), BIC, Bolasso with CV, stability selection, and index of sparseness (IS) - a lesser known (compared to the first five methods) but computationally efficient method. Results show that IS is the best-performing variable selection method.

Classification of crop flours based on protein contents using near infra-red spectroscopy and principle component analysis

Indonesia has abundant crops that can be used as carbohydrate sources. Those crops are made into flour to prolong the shelf life, as well to ease for handling and cooking. Crops as carbohydrate sources are usually high energy but low protein. The aim of this research was to classify flours made of various crops using near infra-red spectroscopy (NIRS) and principle component analysis (PCA). The samples used in this study were six types of flour made of banana, breadfruit, taro, arrowroot, purple sweet potato, and modified cassava (mocaf). The reflectance data were taken using the NIRFlex N500 Fiber Optic Solids Cell at wavelengths of 1000-2500 nm. The spectral obtained were pre-processed and analyzed using The Unscrambler X version 10.5.1. Three pre-processing methods were used, i.e. 1st Savitzky Golay Derivative, Normalization, and Standard Normal Variate (SNV). PCA was able to classify flours based on types of crops. The best transformation was SNV which was able to classify all groups of samples with 100% success rate. PCA model was also able to differentiate low and high protein level of samples aligned with the chemical analysis.

Discrimination of vegetable oil types using Fourier transforms near infrared spectroscopy coupled with pattern recognition techniques

The aim of this research was to investigate the potential of near infrared spectroscopy (NIRs) coupled with pattern recognition techniques for discriminating of vegetable oil types (i.e. coconut oil, olive oil, rice bran oil, sesame oil, soybean oil and sun flower oil). Principle component analysis (PCA) was performed for clustering vegetable oil types. Five of supervised pattern recognition techniques such as soft independent modelling of class analogies (SIMCA), Partial least squares-discriminant analysis (PLS-DA), k-nearest neighbor (k-NN), support vector machine (SVM) and artificial neural network (ANN) were used to identify vegetable oil types. The PCA model could separate coconut oil from other vegetable oils. Two PLS-DA and SVM models showed 100% of precision, recall F-measure and accuracy for all vegetable oil whilst remainder techniques achieved a satisfactory classified performance. All supervised models could discriminate coconut oil from other oils with precision, recall F-Measure and accuracy of 100%. It seems that NIRs technique coupled with pattern recognition techniques is possible for discriminating vegetable oil types.

Solar absorption chiller performance prediction based on the selection of principal component analysis

In this paper, a method to predict the performance of an absorption chiller using solar thermal collectors as the energy input is analyzed rigorously. Artificial Neural Network (ANN) is developed based on experimental data to predict the performance of the solar absorption chiller system at Universitas Indonesia. In order to perform ANN accurately, some parameters such as chilled water inlet and outlet temperatures, cooling water inlet and outlet temperatures, solar hot water inlet and outlet temperatures, hot water inlet and outlet temperatures, ambient temperature and fuel consumption flow rate are chosen as the input variables. In addition, a Principle Component Analysis (PCA) is used to reduce the number of input variables for performance prediction. Without sacrificing the ANN's prediction accuracy, PCA identified the sensitive variables from all input variables. The developed ANN model combined with PCA (ANN + PCA) shows good performance which has a comparable error with ANN model, specifically the configuration 9–6-2 (9 neurons, 6 inputs, 2 outputs) of the ANN + PCA model leads to a COP root-mean-square error of 0.0145.

An Integrated Machine Learning Algorithm for Separating the Long-Term Deflection Data of Prestressed Concrete Bridges

Deflection is one of the key indexes for the safety evaluation of bridge structures. In reality, due to the changing operational and environmental conditions, the deflection signals measured by structural health monitoring systems are greatly affected. These ambient changes in the system often cover subtle changes in the vibration signals caused by damage to the system. The deflection signals of prestressed concrete (PC) bridges are regarded as the superposition of different effects, including concrete shrinkage, creep, prestress loss, material deterioration, temperature effects, and live load effects. According to multiscale analysis theory of the long-term deflection signal, in this paper, an integrated machine learning algorithm that combines a Butterworth filter, ensemble empirical mode decomposition (EEMD), principle component analysis (PCA), and fast independent component analysis (FastICA) is proposed for separating the individual deflection components from a measured single channel deflection signal. The proposed algorithm consists of four stages: (1) the live load effect, which is a high-frequency signal, is separated from the raw signal by a Butterworth filter; (2) the EEMD algorithm is used to extract the intrinsic mode function (IMF) components; (3) these IMFs are utilized as input in the PCA model and some uncorrelated and dominant basis components are extracted; and (4) FastICA is applied to derive the independent deflection component. The simulated results show that each individual deflection component can be successfully separated when the noise level is under 10%. Verified by a practical application, the algorithm is feasible for extracting the structural deflection (including concrete shrinkage, creep, and prestress loss) only caused by structural damage or material deterioration.

Prediction of Hourly Indoor Carbon Monoxide Concentrations by Using Multivariate Methods with Sensitivity Analysis Technique

Precise site prediction of indoor hourly carbon monoxide (CO) concentrations in school buildings is a key issue in air quality research nowadays due to its impact on children’s health. In this study multivariate statistical methods, multiple linear regression (MLR) and principle component analysis (PCA), were employed to predict hourly indoor CO concentration in Gaza Strip, Palestine. Measurements were carried in 12 schools from October 2012 to May 2013 (one academic year). The results suggested that the selected models are effective forecasting tools and hence can be applicable for short-term forecasting of indoor CO level. The predicted indoor CO concentration values agree strongly well with the measured data with high coefficients of determination (R2) 0.869, 0.870 for MLR and PCA-MLR (PCR) respectively. Overall, results showed that PCA model combined with MLR improved MLR model of predicting indoor CO concentration, with reduced errors by as much as 7.14%.

Source and chemical species characterization of PM10 and human health risk assessment of semi-urban, urban and industrial areas of West Bengal, India

Levels of particulate matter of size ten micron (PM10) in outdoor air, potential PM10-bound seven metals - manganese, zinc, cadmium, lead, copper, nickel and cobalt - and twelve water-soluble organic and inorganic ionic components - fluoride, acetate, chloride, nitrite, bromide, nitrate, phosphate, sulfate, oxalate, sodium, potassium and calcium - were investigated during two different season. Atmospheric PM10 samples were collected concurrently from three different sites, i.e., Durgapur (Industrial), Berhampore (Urban) and Bolpur (Semi-urban), West Bengal, India, during summer (April–June 2014) and winter (December 2014–February 2015). Average PM10 levels were found to be in the range of 189.58–219.96 μg/m3 at the semi-urban site, 293.41–324.27 μg/m3 at the urban site and 316.93–344.69 μg/m3 at the industrial site during summer and winter season respectively. Data on metals and water soluble ions were analyzed statistically (Principal Component Analysis and Factor Analysis) for their source identification and apportionment in the study areas. Principle component analysis models, from three different sites, identified four different factors which share common sources, viz., soil & road re-suspension, motor vehicle and traffic, waste dumping, biomass aerosols, and construction. The pollution load and health risk assessments of selected metals were undertaken in three different sites, within children and adults of the study areas, and were found to be within the safe range. Furthermore, an attempt has also been made to provide basic information on pollution, their sources and exposure pathways for humans in the vicinity of semi-urban, urban and industrial regions.

An efficient VRF system fault diagnosis strategy for refrigerant charge amount based on PCA and dual neural network model

A fault detection and diagnosis (FDD) strategy is critical for the refrigerant charge amount (RCA) fault since improper RCA may affect the operational performance of a variable refrigerant flow system. The author’s former work proposes a FDD strategy for the RCA fault. However, three aspects of the former FDD strategy need improvement, i.e. model performance evaluation, more feature information preservation and fault diagnosis accuracy (FDA), especially for the undercharge fault. Firstly, with regard to the model performance evaluation, the concept of a confidence space is proposed to evaluate the FDD model. Secondly, principle component analysis (PCA) is used to reduce the dimension of all feature variables to improve the computational efficiency while preserving almost all feature information. Finally, in order to improve the FDA for the undercharge fault, a dual neural network model for the RCA fault diagnosis strategy has been adopted. The results show that a confidence space can effectively reflect the reliability of fault diagnosis, and the PCA reduces nearly half of the dimension while preserving more than 97% of the feature information, more importantly, the dual neural network improves the correct classification ratio (CCR) more than 9% for three classes (undercharge, normal charge, overcharge), with CCR for the undercharge fault improving by 26.8%.

Abstract TMEM-037: GENE EXPRESSION ANALYSIS IDENTIFIES IMMUNOLOGICAL MRNA UP REGULATION IN CELLS IN THE ASCITES OF SEROUS OVARIAN CANCER AS COMPARED TO MATCHED PRIMARY TUMOR

Abstract BACKGROUND: Ovarian cancer patients with advanced disease frequently develop ascites. It is currently unclear to what extent the molecular phenotype of the cells in ascites differs from that of the primary ovarian tumor. There is also speculation that the tumor cells in ascites may represent a more treatment resistant cell population. An improved understanding of the biology of the cellular environment in ovarian cancer-related ascites may reveal opportunities to develop new targeted therapies that may not be apparent through analysis of the primary tumor alone. The aim of the study was to evaluate potential biological differences between the cellular environment of primary ovarian tumors and that of the ascites fluid. METHODS: We performed mRNA expression in n=12 matched pairs of primary serous OVCA tumor and the cellular component of ascites using the HTG Edge System and the EdgeSeq Oncology Biomarker Panel assay. After normalization, log expression values for 2650 genes were compared between tumor and ascites samples using principle component analysis (PCA) modeling. The molecular profiles of primary tumor and ascites were compared using a t-test. Additionally, the CiberSort algorithm was applied to estimate the relative composition of tumor infiltrating lymphocytes in tumor and ascites samples. RESULTS: PCA modeling demonstrated a clear difference between the primary tumor and ascites samples using all genes. A group comparison (q&amp;lt;0.01, FDR corrected p-value, fold change &amp;gt;2) indicated that 49 genes were differentially expressed between primary tumor and ascites samples. Ascites samples showed significantly higher expression of T-cell markers, CD2, CD3D, CD4, and CD8A, as well as the monocyte/macrophage markers CD14, CCL4, CD163, CCR1, IL10, and ITGAM. CiberSort analysis revealed a high proportion of eosinophils (p &amp;lt;2 x 10^-7) and monocytes (p&amp;lt;0.0002) in ascites as compared to tumor while resting mast cells were proportionately greater in the tumor samples (p &amp;lt; 4 x 10^-5). CONCLUSIONS: In this study, we report a significant difference in mRNA expression between primary tumors from serous OVCA and ascites. Ascites samples were found to have higher expression of T cell, monocyte and macrophage mRNA. Interestingly, ascites samples also expressed an increased proportion of eosinophils as compared to primary tumor. Eosinophils have been suggested to be essential for CD8+ T-cell mediated tumor rejection and have been associated with improved outcomes in prognosis. We also report an increased proportion of resting mast cells in primary tumor. Mast cells are increasingly thought to play a role in the regulation of tumor growth. In summary, this study demonstrates that molecular profile of cells in ascites is different than that of primary tumor and that this difference is potentially due to immune modulators. Citation Format: Sharon E. Robertson, MD, MPH, Douglas C. Marchion, PhD, Yin Xiong, PhD, Anders E. Berglund, PhD, Anthony M. Magliocco, MD. GENE EXPRESSION ANALYSIS IDENTIFIES IMMUNOLOGICAL MRNA UP REGULATION IN CELLS IN THE ASCITES OF SEROUS OVARIAN CANCER AS COMPARED TO MATCHED PRIMARY TUMOR [abstract]. In: Proceedings of the 11th Biennial Ovarian Cancer Research Symposium; Sep 12-13, 2016; Seattle, WA. Philadelphia (PA): AACR; Clin Cancer Res 2017;23(11 Suppl):Abstract nr TMEM-037.

Fault diagnosis of Pakistan Research Reactor-2 with data-driven techniques

In nuclear reactors, safety is of prime importance in their operation. Fault detection and isolation (FDI) methods are making their applications to improve safety, reliability and availability of nuclear reactors. Among various FDI techniques, data-driven techniques are best suited for fault diagnosis of nuclear reactors because process data is available to sensors, both in normal operation and under faulty conditions. Among data-driven techniques, principle component analysis (PCA) and Fisher discriminant analysis (FDA) have been successfully applied to many industrial processes. In this paper, PCA and FDA are applied for fault detection and fault isolation in Pakistan Research Reactor-2 (PARR-2) for known faults of control rod withdrawal and external reactivity insertion. PCA model is developed using training data set obtained during normal operation of PARR-2. It is then applied to test data set collected from the reactor during control rod withdrawal fault and external reactivity insertion fault. Likewise, FDA model is constructed for the above mentioned faults using the training data set and applied to the test data for fault isolation. The results demonstrate that PCA is successful in detection of both the faults. Additionally, FDA not only detects faults, but it is also successful in isolation/localization of the two faults in PARR-2.

A novel thresholding based algorithm for detection of vertical root fracture in nonendodontically treated premolar teeth

In this paper, an efficient algorithm is proposed for detection of vertical root fractures (VRFs) in periapical (PA), and cone-beam computed tomography (CBCT) radiographs of nonendodontically treated premolar teeth. PA and CBCT images are divided into some sub-categories based on the fracture space between the two fragments as small, medium, and large for PAs and large for CBCTs. These graphics are first denoised using the combination of block matching 3-D filtering, and principle component analysis model. Then, we proposed an adaptive thresholding algorithm based on the modified Wellner model to segment the fracture and canal. Finally, VRFs are identified with a high accuracy through applying continuous wavelet transform on the segmented radiographs and choosing the most optimal value for sub-images based on the lowest interclass variance. Performance of the proposed algorithm is evaluated utilizing the different tested criteria. Results illustrate that the range of specificity deviations for PA and CBCT radiographs are 99.69 ± 0.22 and 99.02 ± 0.77, respectively. Furthermore, the sensitivity changes from 61.90 to 77.39 in the case of PA and from 79.54 to 100 in the case of CBCT. Based on our statistical evaluation, the CBCT imaging has the better performance in comparison with PA ones, so this technique could be a useful tool for clinical applications in determining the VRFs.

An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm

Detecting the faults at the incipient stage is important for keeping chiller systems healthy and saving energy and maintenance cost. Traditional principle component analysis (PCA) and support vector data description (SVDD) methods are insensitive to two common faults, condenser fouling (CdF) and refrigerant leakage (RfL). To improve the fault detection performance, this study proposed a PCA-R-SVDD based method. Instead of principle component subspace (PCs), it develops a SVDD model in the residual subspace (Rs) using the PCA modeling residual data. The SVDD based distance based monitoring statistic was used for fault detection. The proposed method shows significant improvement comparing with the traditional methods due to the better fault data distribution and tighter monitoring statistic. It is sensitive to six common faults. At least 50% of the fault data can be correctly detected even at the least severe fault level. Centrifugal chiller experimental data from the ASHRAE Research Project 1043 (RP-1043) was used to evaluate the methods.

Distinguishing isomeric aldohexose-ketohexose disaccharides by electrospray ionization mass spectrometry in positive mode.

The identification of the structure of carbohydrates is challenging because of their complex composition of monosaccharide units, linkage position and anomeric configuration. We used a combination of principle component analysis (PCA) and tandem mass spectrometry (MS/MS), including collision-induced dissociation (CID) and higher energy collision dissociation (HCD), to distinguish four aldohexose-ketohexose isomers, sucrose, turanose, maltulose, and palatinose, which are composed of glucose and fructose. The electrospray ionization (ESI)-MS/MS spectra of the lithium and sodium adducts of the glucopyranosyl fructose (Glc-Fru) isomers were recorded on two independent mass spectrometers using CID (MicroTOF QII) and HCD (Q-Exactive Orbitrap). The differences between the fragment ions were evaluated by the PCA models. The glycosidic bond cleavage mechanism of lithiated sucrose was verified by a deuterium-labeling experiment combined with density functional theory calculations (Gaussian 09). The main fragment ions in the MS/MS spectra from the glycosidic bond decomposition, cross-ring cleavage (-90 Da), and dehydration of the precursor ions of m/z 349 ([M+Li](+)) and m/z 365 ([M+Na](+)) were observed. Surprisingly, cross-ring cleavage and dehydration of the precursor ions were rarely observed in both lithiated and sodiated sucrose. There were significant differences in the fragmentation patterns and relative abundances of fragment ions in second-order mass spectrometry, which allowed discriminant models to be constructed for the alkali adducts and collision modes. Glc-Fru isomers were discriminated in the PCA score plots for their lithium and sodium adducts by using different collision modes. The results showed that HCD-MS/MS is an ideal tool for differentiating lithium adducts, whereas, CID-MS/MS is better for discriminating sodium adducts. The hydrogen migration of the hydroxyl group at C3 of the fructose unit caused the glycosidic bond decomposition of lithiated sucrose.

Quality Evaluation of Vacuum Microwave‐Dried Immature Vegetable Soybean (Glycine Max [L.] Merr.)

AbstractThe main physiochemical indices related to evaluating the quality of vacuum microwave‐dried immature vegetable soybean were investigated by a combination of correlation analysis and principle component analysis (PCA). The results showed that in the 2.94–7.71% range, the moisture content of dried products was significantly related to L* and had a positive correlation with a* the rehydration ratio was significantly related to a* and had a positive correlation with b*, and L* was related to a* and had a positive correlation with total soluble solids (TSS). Six principal components could reflect most details with a cumulative contribution rate of 87.11%, where a*, rehydration ratio, TSS, yield, moisture content, hardness, fracturability and vitamin C content were the key factors. Through a comprehensive evaluation, Sudou No. 4, Sudou No. 8, Tongdou No. 5, Huaidou No. 8 and Xudou No. 17 were selected as the appropriate varieties for dry processing. The PCA model established was highly consistent with the results of sensory evaluation.Practical ApplicationsBeyond different drying methods, particular varieties have important impacts on the quality of dried products. This work evaluates the quality of different varieties of vacuum microwave‐dried immature vegetable soybean with principle component analysis, elucidates the main physiochemical factors affecting the quality of dried products and constructs the evaluation model. As a consequence, this work will provide information relevant to the selection of dried products for maintaining good soybean processing quality.

Semiquantitative Computed Tomography Characteristics for Lung Adenocarcinoma and Their Association With Lung Cancer Survival

BackgroundComputed tomography (CT) characteristics derived from noninvasive images that represent the entire tumor might have diagnostic and prognostic value. The purpose of this study was to assess the association of a standardized set of semiquantitative CT characteristics of lung adenocarcinoma with overall survival. Patients and MethodsAn initial set of CT descriptors was developed to semiquantitatively assess lung adenocarcinoma in patients (n = 117) who underwent resection. Survival analyses were used to determine the association between each characteristic and overall survival. Principle component analysis (PCA) was used to determine characteristics that might differentiate histological subtypes. ResultsCharacteristics significantly associated with overall survival included pleural attachment (P < .001), air bronchogram (P = .03), and lymphadenopathy (P = .02). Multivariate analyses revealed pleural attachment was significantly associated with an increased risk of death overall (hazard ratio [HR], 3.21; 95% confidence interval [CI], 1.53-6.70) and among patients with lepidic predominant adenocarcinomas (HR, 5.85; 95% CI, 1.75-19.59), and lymphadenopathy was significantly associated with an increased risk of death among patients with adenocarcinomas without a predominant lepidic component (HR, 3.07; 95% CI, 1.09-8.70). A PCA model showed that texture (ground-glass opacity component) was most important for separating the 2 subtypes. ConclusionA subset of the semiquantitative characteristics described herein has prognostic importance and provides the ability to distinguish between different histological subtypes of lung adenocarcinoma.

Optimization Study on the Space and Depth of Subsurface Drainage Tubes for Greenhouse Salty Soils: A 3-Year Field Experiment in South of China

A well-designed subsurface drainage system with reasonable drain space and depth contributes to large ratio of desalination and high crop yield. In order to find out the optimal space and depth of subsurface drainage tubes for tomato cultivation in greenhouse salty soils in south of China, drainage treatments with different buried methods were designed, the tomato quality, yield, Irrigation Water Use Efficiency (IWUE) and surface soil electricity conductivity in the treatments were observed during 2010 to 2012 growth seasons and the principle component analysis model and projection pursuit model were used to select the treatment with best comprehensive effects. Results showed that: (1) The tomato yield was increased by 14.21 to 50.29% during the growth seasons; (2) Surface soil EC decreased significantly, although in the process of experiments, surface soil EC of some treatments showed a temporary rise; (3) Under the same buried depth, the closer arrangement of subsurface drainage tubes appeared to be more effective for the yield gaining and topsoil desalination; (4) T7 was proved to be the optimal treatment according to the calculations of projection pursuit model, the comprehensive effects of which were the best, mainly embodying in improving the tomato quality, increasing the yield and IWUE and reducing salinity in topsoil. In this study, 0.8m depth combining with 4m space was selected as the optimized layout of subsurface drainage tubes for the tomato cultivation in greenhouse salty soils of south China.