Total Accuracies Research Articles

Brittle fracture analysis of blunt V-notches under compression

Brittle fracture was investigated both experimentally and theoretically in blunt V-notches under compression. A new test specimen, called flattened V-notched semi-disk (FVSD) specimen, was suggested for conducting fracture tests on PMMA under compression for different notch angles and various notch radii with the aim to measure experimentally the compressive notch fracture toughness. The experimental results were theoretically estimated by means of two stress-based brittle fracture criteria, namely the point-stress (PS) and the mean-stress (MS) criteria. With total accuracies of 91% and 90% for the PS and the MS criteria, respectively; it was found that both the criteria provide very good predictions to the experimental results.

Evaluation of a commercial electronic nose system coupled with universal gas sensing chamber for sensing indicator compounds associated with meat safety

This study was conducted to evaluate the performance of a commercial electronic nose (Cyranose 320™) for sensing indicator compounds (ethanol and acetic acid) associated with spoiled beef. The present study reported the sensitivity of an array of 32 sensors to ethanol and acetic acid. Different vapor concentrations of ethanol (37, 100, 250 and 500 ppm) and acetic acid (38, 75, 100, 200 and 300 ppm) were tested to evaluate the performance of the commercial system. An in-house designed universal gas sensing and characterization system was coupled with the electronic nose system to generate the desired gas concentration. The raw smell print patterns were obtained and analyzed for individual and multiple detectors. Tukey’s multiple comparison technique was performed to analyze the response of individual detectors. Area above and below the baseline were selected as two features for pair wise comparison of the detectors. Different sensors showed different responses between various concentrations of gases. Analysis of multiple detectors was performed using linear and quadratic discriminant analysis (LDA and QDA) along with bootstrap. LDA along with bootstrap provided the highest total classification accuracies of 94.34 % between 100 and 200 ppm of acetic acid. QDA provided higher total classification accuracy of 89.69 % at lower concentration level of 38 and 75 ppm for acetic acid and 84.78 % between 37 and 100 ppm of ethanol. Hence, QDA was a better model of choice at lower concentrations. This study proved non-selective nature of sensors and showed that simultaneous use of multiple sensor information provided better classification accuracy for discriminating various gas concentrations as compared to using individual sensor output.

A consecutive self-proliferate silver carp (Hypophthalmichthys molitrix) variety created through artificial meiotic gynogenesis

Abstract In this research, meiotic gynogenesis (meio-gynogenesis) was used in our silver carp ( Hypophthalmichthys molitrix ) breeding program. Three natural sex-reversed male individuals were found in a second generation meio-gynogenetic strain, and these were used to construct self-proliferate strain. Through morphological trait selection and growth rate comparison, an excellent variety was established, which was named the “Changfeng silver carp” (CF variety). In this study, we compare the genetic, morphological traits and growth rate between the CF variety and the common silver carp species. The average genetic identity of the CF variety is 0.98, and the ratios of full length/body height and body length/body height are 5.87% and 7.21%, respectively, which are significantly higher than those of the common silver carp. These data indicate that the caudal fin of the CF variety is shorter than that of the common silver carp. Principal component analysis (PCA) showed that the morphology between CF variety and the common species is diverged at principal component 1 (PC1), and stepwise discriminate analysis showed that the CF variety and common species can be discriminated by the combined usage of full length, body height and head length, the respective total discrimination accuracies of which are 90.9% (original) and 90.7% (cross-validation). Growth rate comparison tests in two consecutive years proved that there is no significant difference ( P > 0.05) at age of one year, while the growth rate of the CF variety is 12.27–17.88% faster than that of the common species at the age of two years. These results demonstrate that the combined usage of meio-gynogenesis and morphological traits selection is a feasible and effective method to create an excellent and creditable variety, especially for fish with a relatively long sexual maturity cycle.

CarSPred: A Computational Tool for Predicting Carbonylation Sites of Human Proteins

Protein carbonylation is one of the most pervasive oxidative stress-induced post-translational modifications (PTMs), which plays a significant role in the etiology and progression of several human diseases. It has been regarded as a biomarker of oxidative stress due to its relatively early formation and stability compared with other oxidative PTMs. Only a subset of proteins is prone to carbonylation and most carbonyl groups are formed from lysine (K), arginine (R), threonine (T) and proline (P) residues. Recent advancements in analysis of the PTM by mass spectrometry provided new insights into the mechanisms of protein carbonylation, such as protein susceptibility and exact modification sites. However, the experimental approaches to identifying carbonylation sites are costly, time-consuming and capable of processing a limited number of proteins, and there is no bioinformatics method or tool devoted to predicting carbonylation sites of human proteins so far. In the paper, a computational method is proposed to identify carbonylation sites of human proteins. The method extracted four kinds of features and combined the minimum Redundancy Maximum Relevance (mRMR) feature selection criterion with weighted support vector machine (WSVM) to achieve total accuracies of 85.72%, 85.95%, 83.92% and 85.72% for K, R, T and P carbonylation site predictions respectively using 10-fold cross-validation. The final optimal feature sets were analysed, the position-specific composition and hydrophobicity environment of flanking residues of modification sites were discussed. In addition, a software tool named CarSPred has been developed to facilitate the application of the method. Datasets and the software involved in the paper are available at https://sourceforge.net/projects/hqlstudio/files/CarSPred-1.0/.

Model identification for gas condensate reservoirs by using ANN method based on well test data

The well testing technique has been frequently used in order to identify hydrocarbon reservoir models and estimate the associated parameters such as permeability, skin factor, etc. The analysis of well test data acquired from gas condensate reservoirs is basically different from oil and dry gas reservoirs often exhibiting a complex behavior due to the formation of condensate inside the reservoir. The first step in well test analysis is the detection of reservoir model and its boundaries usually performed through trial-and-error procedures. Previous investigations indicate that the radial composite model is the best feasible model for well test analysis of gas condensate reservoirs. The radial composite model refers to those reservoirs consisting of two separate regions: (1) a circular inner zone with the well at the center, and (2) an infinite outer zone. The best multi-layer perceptron (MLP) configuration is also selected through evaluating the accuracy criteria of various developed MLP networks i.e., measuring the mean relative (MRE) and mean square errors (MSE). The total classification accuracies (TCAs) of two methods used in this study indicate that the coupled MLP clustering model (with a TCA equal to 93.3%) has a better performance than that of the single MLP (with a TCA of 88.65%).

Closed-form expressions of mode I apparent notch fracture toughness for key-hole notches

Two closed-form expressions were developed in this research to estimate the mode I apparent notch fracture toughness of brittle materials weakened by key-hole notches based on the well-established brittle fracture criteria, namely, the point stress and the mean stress. The theoretical models were verified using the experimental results reported in open literature dealing with tensile fracture in rectangular isostatic graphite plates containing central key-hole notches of various notch tip radii. A very good agreement was found to exist between the predictions of both the models and the experimental results. The results showed that while the accuracy of each model was different for various notch tip radii, total accuracies of the two models were almost equal (both about 93%) demonstrating their effectiveness. Using such expressions, it is expected that one can simply estimate the load-carrying capacity of brittle and quasi-brittle components weakened by key-hole notches under mode I loading.

Stress-based criteria for brittle fracture in key-hole notches under mixed mode loading

Abstract Two stress-based failure criteria were developed in the present research to predict mixed mode I/II brittle fracture in engineering components weakened by a key-hole notch. The first criterion was based on the well-established maximum tangential stress (MTS) concept, successfully proposed and utilized several times in recent years for different notch features. The second one was on the basis of the mean-stress (MS) concept which has been frequently used for predicting pure mode I fracture in notched domains. The results of the criteria were represented in the form of fracture curves and the curves of fracture initiation angle in terms of the notch stress intensity factors. To verify the validity of the fracture models, the theoretical predictions were compared with a large bulk of experimental data, reported in literature, on the fracture of rectangular isostatic graphite plates weakened by central key-hole notches of five different tip radii. It was found that while the total accuracies of the criteria are very good, for small notch tip radii, the MTS criterion provides generally better mixed mode notch fracture toughness results than the MS criterion. Conversely, the MS criterion works much better than the MTS model for larger notch tip radii. Dealing with fracture initiation angle, both the criteria could estimate the experimental results successfully.

Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures

The vegetation in the forest-tundra ecotone zone is expected to be highly affected by climate change and requires effective monitoring techniques. Airborne laser scanning (ALS) has been proposed as a tool for the detection of small pioneer trees for such vast areas using laser height and intensity data. The main objective of the present study was to assess a possible improvement in the performance of classifying tree and nontree laser echoes from high-density ALS data. The data were collected along a 1000 km long transect stretching from southern to northern Norway. Different geostatistical and statistical measures derived from laser height and intensity values were used to extent and potentially improve more simple models ignoring the spatial context. Generalised linear models (GLM) and support vector machines (SVM) were employed as classification methods. Total accuracies and Cohen’s kappa coefficients were calculated and compared to those of simpler models from a previous study. For both classification methods, all models revealed total accuracies similar to the results of the simpler models. Concerning classification performance, however, the comparison of the kappa coefficients indicated a significant improvement for some models both using GLM and SVM, with classification accuracies >94%.

Discrimination of tooth layers and dental restorative materials using cutting sounds.

Dental restoration begins with removing carries and affected tissues with air-turbine rotary cutting handpieces, and later restoring the lost tissues with appropriate restorative materials to retain the functionality. Most restoration materials eventually fail as they age and need to be replaced. One of the difficulties in replacing failing restorations is discerning the boundary of restorative materials, which causes inadvertent removal of healthy tooth layers. Developing an objective and sensor-based method is a promising approach to monitor dental restorative operations and to prevent excessive tooth losses. This paper has analyzed cutting sounds of an air-turbine handpiece to discriminate between tooth layers and two commonly used restorative materials, amalgam and composite. Support vector machines were employed for classification, and the averaged short-time Fourier transform coefficients were selected as the features. The classifier performance was evaluated from different aspects such as the number of features, feature scaling methods, classification schemes, and utilized kernels. The total classification accuracies were 89% and 92% for cases included composite and amalgam materials, respectively. The obtained results indicated the feasibility and effectiveness of the proposed method.

Locating apoptosis proteins by incorporating the signal peptide cleavage sites into the general form of Chou's Pseudo amino acid composition

AbstractApoptosis proteins play an essential role in the development and homeostasis of an organism. The accurate prediction of subcellular location for apoptosis proteins is helpful for understanding the mechanism of programmed cell death and their biological functions. In this article, a new apoptosis proteins localization algorithm, named PSSP, is proposed based on the predicted cleavage sites of primary protein sequences. First, protein chains are divided into N‐terminal signal parts and mature protein parts according to their predicted cleavage sites by SignalP. Then, amino acid composition (ACC) of the individual subsequence together with pseudo‐ACC and stereochemical properties of whole chain were extracted to represent a given protein sequence. Jackknife test by support vector machine on three broadly used datasets (ZD98, ZW225, and CL317 datasets) of apoptosis proteins demonstrated that the total accuracies by this approach are 93.9, 87.6, and 91.5%, respectively. In addition, an independent nonapoptosis benchmark dataset (NNPSL) was also used to evaluate the performance of this method, and predictive accuracies for eukaryotic and prokaryotic proteins are also comparable to existing methods. © 2013 Wiley Periodicals, Inc.

LiDAR-Landsat data fusion for large-area assessment of urban land cover: Balancing spatial resolution, data volume and mapping accuracy

The structural characteristics of Light Detection and Ranging (LiDAR) data are increasingly used to classify urban environments at fine scales, but have been underutilized for distinguishing heterogeneous land covers over large urban regions due to high cost, limited spectral information, and the computational difficulties posed by inherently large data volumes. Here we explore tradeoffs between potential gains in mapping accuracy with computational costs by integrating structural and intensity surface models extracted from LiDAR data with Landsat Thematic Mapper (TM) imagery and evaluating the degree to which TM, LiDAR, and LiDAR-TM fusion data discriminated land covers in the rapidly urbanizing region of Charlotte, North Carolina, USA. Using supervised maximum likelihood (ML) and classification tree (CT) methods, we classified TM data at 30m and LiDAR data and LiDAR-TM fusions at 1m, 5m, 10m, 15m and 30m resolutions. We assessed the relative contributions of LiDAR structural and intensity surface models to classification map accuracy and identified optimal spatial resolution of LiDAR surface models for large-area assessments of urban land cover. ML classification of 1m LiDAR-TM fusions using both structural and intensity surface models increased total accuracy by 32% compared to LiDAR alone and by 8% over TM at 30m. Fusion data using all LiDAR surface models improved class discrimination of spectrally similar forest, farmland, and managed clearings and produced the highest total accuracies at 1m, 5m, and 10m resolutions (87.2%, 86.3% and 85.4%, respectively). At all resolutions of fusion data and using either ML or CT classifier, the relative contribution of the LiDAR structural surface models (canopy height and normalized digital surface model) to classification accuracy is greater than the intensity surface. Our evaluation of tradeoffs between data volume and thematic map accuracy for this study system suggests that a spatial resolution of 5m for LiDAR surface models best balances classification performance and the computational challenges posed by large-area assessments of land cover.

Detecting bunch withering disorder in date fruit by near infrared spectroscopy

This study introduces the application of near infrared spectroscopy (NIRs) to detect bunch withering disorder in date fruit (cv. Mazafati). The samples included intact as well as infected date fruits at different stages of ripening. Chemometric evaluation of the data was performed by soft independent modeling of class analogy (SIMCA), partial least squares discriminant analysis (PLS-DA), and principal components analysis combined with artificial neural networks (PCA–ANN). The PLS-DA algorithm was able to provide models with the best classification performance, followed by SIMCA and then PCA–ANN. The maturity stage of samples influenced the performance of the classification methods. The classification accuracy for the late harvested samples was better than those harvested at normal time and the combined data set in all classification analyses. The total accuracies of 82%, 93% and 86%, respectively for normal, late and combined data sets demonstrate that NIRs with PLS-DA has a strong potential to detect the bunch withering disorder in date fruit.

Application of <i>k</i>-means and Gaussian mixture model for classification of seismic activities in Istanbul

Abstract. Two unsupervised pattern recognition algorithms, k-means, and Gaussian mixture model (GMM) analyses have been applied to classify seismic events in the vicinity of Istanbul. Earthquakes, which are occurring at different seismicity rates and extensions of the Thrace-Eskisehir Fault Zone and the North Anatolian Fault (NAF), Turkey, are being contaminated by quarries operated around Istanbul. We have used two time variant parameters, complexity, the ratio of integrated powers of the velocity seismogram, and S/P amplitude ratio as classifiers by using waveforms of 179 events (1.8 < M < 3.0). We have compared two algorithms with classical multivariate linear/quadratic discriminant analyses. The total accuracies of the models for GMM, k-means, linear discriminant function (LDF), and quadratic discriminant function (QDF) are 96.1%, 95.0%, 96.1%, 96.6%, respectively. The performances of models are discussed for earthquakes and quarry blasts separately. All methods clustered the seismic events acceptably where QDF slightly gave better improvements compared to others. We have found that unsupervised clustering algorithms, for which no a-prior target information is available, display a similar discriminatory power as supervised methods of discriminant analysis.

Predicting Apoptosis Protein Subcellular Location with PseAAC by Incorporating Tripeptide Composition

The function of the protein is closely correlated with its subcellular localization. Probing into the mechanism of protein sorting and predicting protein subcellular location can provide important clues or insights for understanding the function of proteins. In this paper, we introduce a new PseAAC approach to encode the protein sequence based on the physicochemical properties of amino acid residues. Each of the protein samples was defined as a 146D (dimensional) vector including the 20 amino acid composition components and 126 adjacent triune residues contents. To evaluate the effectiveness of this encoding scheme, we did jackknife tests on three datasets using the support vector machine algorithm. The total prediction accuracies are 84.9%, 91.2%, and 92.6%, respectively. The satisfactory results indicate that our method could be a useful tool in the area of bioinformatics and proteomics.

Identification of protein-RNA interaction sites using the information of spatial adjacent residues

BackgroundProtein-RNA interactions play an important role in numbers of fundamental cellular processes such as RNA splicing, transport and translation, protein synthesis and certain RNA-mediated enzymatic processes. The more knowledge of Protein-RNA recognition can not only help to understand the regulatory mechanism, the site-directed mutagenesis and regulation of RNA–protein complexes in biological systems, but also have a vitally effecting for rational drug design.ResultsBased on the information of spatial adjacent residues, novel feature extraction methods were proposed to predict protein-RNA interaction sites with SVM-KNN classifier. The total accuracies of spatial adjacent residue profile feature and spatial adjacent residues weighted accessibility solvent area feature are 78%, 67.07% respectively in 5-fold cross-validation test, which are 1.4%, 3.79% higher than that of sequence neighbour residue profile feature and sequence neighbour residue accessibility solvent area feature.ConclusionsThe results indicate that the performance of feature extraction method using the spatial adjacent information is superior to the sequence neighbour information approach. The performance of SVM-KNN classifier is little better than that of SVM. The feature extraction method of spatial adjacent information with SVM-KNN is very effective for identifying protein-RNA interaction sites and may at least play a complimentary role to the existing methods.

Predictive QSAR modeling of phosphodiesterase 4 inhibitors

A series of diverse organic compounds, phosphodiesterase type 4 (PDE-4) inhibitors, have been modeled using a QSAR-based approach. 48 QSAR models were compared by following the same procedure with different combinations of descriptors and machine learning methods. QSAR methodologies used random forests and associative neural networks. The predictive ability of the models was tested through leave-one-out cross-validation, giving a Q 2 = 0.66–0.78 for regression models and total accuracies Ac = 0.85–0.91 for classification models. Predictions for the external evaluation sets obtained accuracies in the range of 0.82–0.88 (for active/inactive classifications) and Q 2 = 0.62–0.76 for regressions. The method showed itself to be a potential tool for estimation of IC 50 of new drug-like candidates at early stages of drug development.

Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer Program

The National Agricultural Statistics Service (NASS) of the US Department of Agriculture (USDA) produces the Cropland Data Layer (CDL) product, which is a raster-formatted, geo-referenced, crop-specific, land cover map. CDL program inputs include medium resolution satellite imagery, USDA collected ground truth and other ancillary data, such as the National Land Cover Data set. A decision tree-supervised classification method is used to generate the freely available state-level crop cover classifications and provide crop acreage estimates based upon the CDL and NASS June Agricultural Survey ground truth to the NASS Agricultural Statistics Board. This paper provides an overview of the NASS CDL program. It describes various input data, processing procedures, classification and validation, accuracy assessment, CDL product specifications, dissemination venues and the crop acreage estimation methodology. In general, total crop mapping accuracies for the 2009 CDLs ranged from 85% to 95% for the major crop categories.

Comparative study of discretization methods of microarray data for inferring transcriptional regulatory networks

BackgroundMicroarray data discretization is a basic preprocess for many algorithms of gene regulatory network inference. Some common discretization methods in informatics are used to discretize microarray data. Selection of the discretization method is often arbitrary and no systematic comparison of different discretization has been conducted, in the context of gene regulatory network inference from time series gene expression data.ResultsIn this study, we propose a new discretization method "bikmeans", and compare its performance with four other widely-used discretization methods using different datasets, modeling algorithms and number of intervals. Sensitivities, specificities and total accuracies were calculated and statistical analysis was carried out. Bikmeans method always gave high total accuracies.ConclusionsOur results indicate that proper discretization methods can consistently improve gene regulatory network inference independent of network modeling algorithms and datasets. Our new method, bikmeans, resulted in significant better total accuracies than other methods.

Fourier transform infrared spectroscopy (FTIR) as a tool for discriminating Salmonella typhimurium contaminated beef

Detection of beef contamination from harmful pathogens will be helpful in protecting the consumer safety and controlling the outbreaks. In this paper, the potential of Fourier transform infrared spectroscopy (FTIR) was investigated to discriminate the Salmonella contaminated packed beef. A suitable headspace sampling system was designed and used to collect the headspace volatiles from the packed meat to the FTIR gas cell. Spectral signatures of headspace volatiles of meat packages were used to classify the packed meat samples as contaminated or not. FTIR spectrum was divided into several regions in order to reduce the dimensionality as well as to select the regions based on the absorbance properties of various volatiles present in headspace of meat package. Principal component analysis was performed on the entire spectrum (4000–500 cm−1) as well as on the selected sub-regions of entire spectrum. Two statistical classification techniques (linear and quadratic discriminate analysis) were used to develop classification models. The statistical models were validated using bootstrap cross validation technique. The total average classification accuracies were evaluated in terms of coefficient of variance (% CV). Based on the mean of total average classification accuracies and its % CV calculated from five similarly conducted experiments, it was found that the statistical models developed on a part of the spectra (500–850 cm−1) and full spectra (4000–500 cm−1) can be used as potential classification models for non-destructive discrimination of Salmonella contaminated packed beef samples from uncontaminated ones. These results need to be further validated on dataset with larger sample size.

Mapping a wetland complex in the Brazilian savannah using an Ikonos image: assessing the potential of a new region-based classifier

The Pandeiros is a unique wetland in northern Minas Gerais, Brazil. Even though it is an official wildlife sanctuary, it suffers from increasing degradation because of livestock grazing and other forms of human activity. The absence of specific laws defining and protecting wetlands in Brazil is partly responsible for this situation. Having no official designation, most environments of the Pandeiros have not yet been identified or characterized as wetlands. This article presents a comparison between an unsupervised region-based classification approach and traditional supervised and unsupervised classification techniques for mapping different environments within this complex wetland system. All three classification methods were tested and their results compared with field data and with an interpreted reference map. The results suggest that the traditional supervised classification approach and the new region-based approach have good potential for identifying the main vegetal physiognomies, but the latter yielded superior results, with an estimated accuracy of 95% compared with 88% for the former. The region-based approach had the advantage of a much superior spatial consistency and allowed easier visual interpretation of the classified image. In a second accuracy assessment, we compared the results with a visually interpreted reference map and obtained total accuracies of 70%, 41%, and 39% for the region-based, maximum likelihood, and unsupervised ISODATA algorithms, respectively.