Classification Success Rate Research Articles

A Saccharide Chemosensor Array Developed Based on an Indicator Displacement Assay Using a Combination of Commercially Available Reagents.

Herein, a very simple colorimetric chemosensor array is reported for saccharides (D-glucose, D-fructose, D-xylose, D-galactose, D-mannose, L-rhamnose, and N-acetyl-D-gluosamine). While various types of chemosensors for saccharides have been investigated extensively to-this-date, tremendous additional efforts are still required on a regular basis for the syntheses of new chemosensors. Complicated syntheses would be a bottleneck, given that artificial receptor-based chemosensing systems are not so popular in comparison to biomaterial-based (e.g., enzyme-based) sensing systems. Toward this end, chemosensor array systems using molecular self-assembled materials can avoid the abovementioned synthetic efforts and achieve simultaneous qualitative and quantitative detection of a number of guest saccharides. Using a practical approach, we focus on an indicator displacement assay (IDA) to fabricate a chemosensor array for colorimetric saccharide sensing. On this basis, 3-nitrophenylboronic acid (3-NPBA) spontaneously reacts with catechol dyes such as alizarin red S (ARS), bromopyrogallol red (BPR), pyrogallol red (PR), and pyrocatechol violet (PV), and yields boronate ester derivatives with color changes. The addition of saccharides into the aqueous solution of the boronate esters induces color recovery owing to the higher binding affinity of 3-NPBA for saccharides, thus resulting in the release of dyes. By employing this system, we have succeeded in discriminating saccharides qualitatively and quantitatively with a classification success rate of 100%. Most importantly, our chemosensor array has been fabricated by only mixing low cost commercially available reagents in situ, which means that complicated synthetic processes are avoided for saccharide sensing. We believe this simple colorimetric assay that uses only commercially available reagents can create new, user-friendly supramolecular sensing pathways for saccharides.

Mean centred clustering: improving melody classification using time- and frequency-domain supervised clustering

This paper reports a new approach for clustering melodies in audio music collections of both western as well as Indian background and its application to genre classification. A simple yet effective new classification technique called mean centred clustering (MCC) is discussed. The proposed technique maximizes the distance between different clusters and reduces the spread of data in individual clusters. The use of MCC as a preprocessing technique for conventional classifiers like artificial neural network (ANN) and support vector machine (SVM) is also demonstrated. It is observed that the MCC-based classifier outperforms the classifiers based on conventional techniques such as Principal Component Analysis (PCA) and discrete cosine transform (DCT). Extensive simulation results obtained on different data sets of western genre (ISMIR) and classical Indian ragas are used to validate the efficiency of proposed MCC-based clustering algorithm and ANN/SVM classifiers based on MCC. As an additional endeavour, the performance of MCC on preprocessed data from PCA and DCT is studied. Based on simulation results, it is concluded that the application of MCC on DCT coefficients resulted in the highest overall classification success rate over different architectures of the classifiers.

Research on Classification and Recognition of Driving Styles Based on Feature Engineering

Accurate classification and the effective recognition of driving styles are critical for improving control performance of the vehicle powertrain. In this research, a set of driving style classification and recognition methods is built based on the feature engineering. First, a specified road test is conducted considering the influence factors, and meanwhile, the corresponding driving data is collected, followed by a detailed evaluation of the driving styles. Then, the information entropy is applied to discretize the driving data, including the speed, acceleration, and opening degree of the accelerator pedal, and 44 feature quantities are extracted to characterize the driving style. By analyzing strong correlation and redundancy among the constructed feature quantities, the principal component analysis (PCA) is employed to reduce the dimension, and the fuzzy c-means (FCM) clustering algorithm is leveraged to classify the driving style. The successful classification rate reaches 92.16%, which is improved by 9.81% in comparison with traditional features. Finally, a parameter identification algorithm based on the support vector machine (SVM) is applied to identify the classified driving style, and the recognition accuracy reaches 92.86%, which is improved by 7.15% in comparison with traditional features, proving the feasibility of the proposed algorithm.

PV shading fault detection and classification based on I-V curve using principal component analysis: Application to isolated PV system

Health monitoring and diagnosis of photovoltaic (PV) systems is becoming crucial to maximise the power production, increase the reliability and life service of PV power plants. Operating under faulty conditions, in particular under shading, PV plants have remarkable shape of current-voltage (I-V) characteristics in comparison to reference condition (healthy operation). Based on real electrical measurements (I-V), the present work aims to provide a very simple, robust and low cost Fault Detection and Classification (FDC) method for PV shading faults. At first, we extract the features for different experimental tests under healthy and shading conditions to build the database. The features are then analysed using Principal Component Analysis (PCA). The accuracy of the data classification into the PCA space is evaluated using the confusion matrix as a metric of class separability. The results using experimental data of a 250 Wp PV module are very promising with a successful classification rate higher than 97% with four different configurations. The method is also cost effective as it uses only electrical measurements that are already available. No additional sensors are required.

Chemometric Analysis of Mid-Wave Infrared Spectral Reflectance Data for Sulphide Ore Discrimination

Despite significant recent advancements in the sensor technologies, the use of sensors for raw material characterization in the mining industry remains limited. The aim of the present study was to assess the utility of applying the mid-wave infrared (MWIR) reflectance data acquired by the use of a handheld Fourier-transform infrared spectrometer (FTIR), combined with partial least squares-discriminant analysis (PLS-DA), for the characterization of a polymetallic sulphide ore deposit. In achieving the study objectives, focus was given to the MWIR portion of the FTIR dataset, as it is the least explored region of the infrared spectrum in mineral characterization studies. Three datasets—covering different wavelength ranges—were generated from the FTIR spectral data, namely the full FTIR range (2.5–15 µm), MWIR (2.5–7 µm) and long-wave infrared (LWIR: 7–15 µm), in order to investigate the associated information level of each defined wavelength region separately. Design of experiment was developed to determine the optimal data filtering techniques. Using the processed data and PLS-DA, a series of calibration and prediction models were developed for ore and waste materials separately. As the models applied to the MWIR data showed a successful classification rate of 86.3% for sulphide ore–waste discrimination, similarly using the full spectral FTIR dataset, a correct classification rate of 89.5% was achieved. This indicates that MWIR spectral range includes informative signals that are sufficient for classifying the material into ore or waste. The proposed approach could be extended for automating the sulphide ore–waste discrimination process, thus greatly benefiting marginally economical mining operations.

A classification of meteor radio echoes based on artificial neural network

Abstract An artificial neural network is described for classification of meteor trails into the distinct overdense, intermediate and underdense trail categories. The neural network was trained and on model data obtained using the “KAMET” program and tested on real data. The best result of classification success rate of 95% without according to the heights of the formation of meteor trails. Results of classification with according to the heights of the formation of meteor trails are 82% - 91%.

Improved method of heuristic classification of vowels from an acoustic signal

This paper describes research in the field of the improved methodology of the classification of vowels /a, a:/, /$\varepsilon$, $\varepsilon$:/, /ı, i:/, /o, o:/, and /u, u:/ (vowel symbols according to IPA, i.e. International Phonetic Alphabet). The aim is to develop an improved method enabling the automatic allocation of vowel symbols to the corresponding time segments of acoustic recordings of an undisturbed speech signal. The combined classification method is based on finding frequencies of the first two local maxims (formants) in a smoothed linear predictive amplitude spectrum (LPC, linear predictive coding) and zero-crossing values of each speech active voiced short-term segment of the recording. Based on these monitored values, simple heuristic conditions are arranged for the classification of the respective vowel. Implementation of the algorithm was realized using the MATLAB environment and its Graphical User Interface (GUI) was used for the user interaction. Verification of the success rate of vowel classification was done using recordings of forty speakers (twenty men and twenty women), where each speaker repeated the vowels repeatedly with short successive pauses. The success rate of recognizing vowels is classified and evaluated based on results obtained from our designed method.

Ligand-Capped Ultrapure Metal Nanoparticle Sensors for the Detection of Cutaneous Leishmaniasis Disease in Exhaled Breath

Human cutaneous leishmaniasis, although designated as one of the most neglected tropical diseases, remains underestimated due to its misdiagnosis. The diagnosis is mainly based on the microscopic detection of amastigote forms, isolation of the parasite, or the detection of Leishmania DNA, in addition to its differential clinical characterization; these tools are not always available in routine daily practice, and they are expensive and time-consuming. Here, we present a simple-to-use, noninvasive approach for human cutaneous leishmaniasis diagnosis, which is based on the analysis of volatile organic compounds in exhaled breath with an array of specifically designed chemical gas sensors. The study was realized on a group of n = 28 volunteers diagnosed with human cutaneous leishmaniasis and a group of n = 32 healthy controls, recruited in various sites from Tunisia, an endemic country of the disease. The classification success rate of human cutaneous leishmaniasis patients achieved by our sensors test was 98.2% accuracy, 96.4% sensitivity, and 100% specificity. Remarkably, one of the sensors, based on CuNPs functionalized with 2-mercaptobenzoxazole, yielded 100% accuracy, 100% sensitivity, and 100% specificity for human cutaneous leishmaniasis discrimination. While AuNPs have been the most extensively used in metal nanoparticle-ligand sensing films for breath sensing, our results demonstrate that chemical sensors based on ligand-capped CuNPs also hold great potential for breath volatile organic compounds detection. Additionally, the chemical analysis of the breath samples with gas chromatography coupled to mass spectrometry identified nine putative breath biomarkers for human cutaneous leishmaniasis.

Distinction between mixed genus bacteria using infrared spectroscopy and multivariate analysis

Bacterial infections are significant causes of serious human health problems. Different bacterial pathogens might have similar symptoms, and it is important to detect the cause of the infection early in order to enable effective treatment. In many infections, a mixture of different bacteria might exist in the same tested sample. To treat such infections effectively, it is very important to identify the various types of infecting bacteria in the sample. In this pioneering study, we examined the potential of Fourier transform infrared (FTIR) microscopy for accurate identification and differentiation between different bacteria in experimentally mixed samples of bacteria in the genus level in time span of about 30 min. We have measured the FTIR spectra of bacteria in pure form as well as in various mixtures. Principal components analysis (PCA) was applied on the spectra of various classes, followed by linear discriminant analysis (LDA) as a linear classifier. Our results show that it is possible to differentiate between mixed categories of bacteria with high rates of success. The classification rate was higher when the mixed samples included Gram-positive and Gram-negative types. When the mixing range was comparable ([0.5,0.5] and [0.6,0.4]), a classification success rate > 95% was achieved using only the first 20 PCs.

Comparison of variable selection methods prior to linear discriminant analysis classification of synthetic phenethylamines and tryptamines

Identification of emerging synthetic designer drugs is challenging in the absence of reference materials for subsequent mass spectral comparison. In this work, linear discriminant analysis (LDA) models were developed and validated for the characterization of compounds according to structural class based on mass spectral features. A set of synthetic phenethylamines and tryptamines was analyzed by gas chromatography-mass spectrometry (GC–MS) and the resulting spectra were probed to identify characteristic variables (m/z values) for model development. Two approaches were used to select characteristic variables. First, ions known to be characteristic of each compound class were selected, resulting in a total of 13 variables that were used to develop an LDA model. Following cross validation of the model, a test set of phenethylamines and tryptamines was classified, resulting in a successful classification rate of 93%. In the second approach, principal components analysis (PCA) was used as a more objective method for variable selection. With this approach, a total of 9 variables were selected and the resulting LDA model generated a successful classification rate of 86%.While the classification success of each LDA model was similar, the PCA method for variable selection is substantially less time consuming than the more detailed approach that requires probing mass spectra for characteristic features. Classification models such as those reported here have potential utility for the class characterization of emerging analogs for which reference materials are not yet available.

Evaluating the key assumptions underlying dendro-provenancing: How to spruce it up with a scissor plot

The pairwise statistical comparison of ring-width series is the basic analysis of dendro-provenancing studies. It is assumed that statistical proximity indicates similar provenance, but this assumption often remains untested. Especially for small areas with high topographic complexity, it is unknown to what extent statistical proximity and geographical provenance are correlated.In this paper, dendro-provenancing is framed as a search for statistical Nearest Neighbors. The ‘k-Nearest Neighbors leave one-out cross-validation’ process (k-NN) is proposed as a method for validating dendro-provenancing approaches. Furthermore, it allows researchers to consistently compare and evaluate different proximity measures with respect to their suitability for dendro-provenancing. The validation process is demonstrated on a data set of 401 ring-width series of Norway spruce (Picea abies (L.) H. Karst.) encompassing 15 sites along elevational gradients in north-eastern Switzerland. Moreover, a new type of plot, the so-called scissor plot, is introduced to visualize the k-NN validation process.Results indicate that dendro-provenancing depends heavily on differences in between sites high-frequency signal. Mean classification success for the relevant stages of the k-NN (CSR¯open)11CSR¯open is a figure for the classification success rate of a k-NN and is described in detail in the Methods section. ranged from 71.8% to 79.2% for the best performing measures. Classification errors occurred mainly between sites at elevations of 1000–1198 m a.s.l. At all other elevations and between different regions of the study area, only moderate differences in classification performance were detected. Thus, the results indicate that dendro-provenancing may be principally feasible even in a small region as studied here.

Comparison of otolith shape descriptors and morphometrics for stock discrimination of yellow croaker along the Chinese coast

This study compared and evaluated the efficiency of two otolith shape descriptors (i.e., the elliptic Fourier transform (EFT) and discrete wavelet transform (DWT)) and morphometrics for stock discrimination. To accomplish this, sample fish from three stocks of yellow croaker Larimichthys polyactis along the Chinese coast (LDB stock from the Liaodong Bay of the Bohai Sea, JZB stock from the Jiaozhou Bay of the Yellow Sea and CJE stock from the Changjiang River estuary of the East China Sea) were used for otolith morphology analyses. The results showed that morphometrics produced an overall classification success rate of 70.8% in contrast with success rates of 80.0% or 82.0% obtained using EFT or DWT, respectively. This suggests that the two shape descriptors comparably discriminated among the stocks and performed more efficiently than morphometrics. During data adjustment and acquisition, some size variables were excluded from the subsequent discriminant analysis for stock discrimination because they were statistically “ineffective,” which could reduce the efficiency of morphometrics and lead to relatively low overall classification success. Both EFT and DWT retain the contour coefficients and thus provide a detailed description of otolith shape, which could improve discriminatory efficiency compared with morphometrics.

Using Short-wave Infrared Range Spectrometry Data to Determine Brick Characteristics

ABSTRACTCharacterizing material strength in-situ for existing structures poses a major problem for a range of civil engineering applications including structural modelling for tunnelling-vulnerability assessment and pre-earthquake resiliency evaluation, especially for unreinforced masonry buildings. Present methods require expensive testing equipment often requiring access to the structure and possible destruction of historic material. This article introduces spectrometry as a non-destructive means for identifying different brick clays and their firing levels, both of which influence the masonry’s mechanical behavior. The experiments herein considered bricks of 2 clay groups (red and yellow) fired at 3 kiln temperatures (700ºC, 950ºC, 1,060ºC). Samples were examined via spectrometry within the short-wave infrared range (1,300–2,200 nm). A Partial Least Square Discriminant Analysis (PLSDA) model was calibrated using 96 samples and tested on a set of 48 samples, resulting in a 98% success rate in classification of the two clay types and a 100% success rate for classification among the 3 firing levels. The ability of the PLSDA model to reliably distinguish well-fired bricks from other samples, irrespective of raw material configuration, shows the potential to use this approach as a new, non-destructive means for in-situ assessment of brick for architectural conservation, as well as for safety and serviceability assessments.

Mechanical property characterization of hundreds of single nuclei based on microfluidic constriction channel.

As label-free biomarkers, the mechanical properties of nuclei are widely treated as promising biomechanical markers for cell type classification and cellular status evaluation. However, previously reported mechanical parameters were derived from only around 10 nuclei, lacking statistical significances due to low sample numbers. To address this issue, nuclei were first isolated from SW620 and A549 cells, respectively, using a chemical treatment method. This was followed by aspirating them through two types of microfluidic constriction channels for mechanical property characterization. In this study, hundreds of nuclei were characterized, producing passage times of 0.5 ± 1.2 s for SW620 nuclei in type I constriction channel (n = 153), 0.045 ± 0.047 s for SW620 nuclei in type II constriction channel (n = 215) and 0.50 ± 0.86 s for A549 nuclei in type II constriction channel. In addition, neural network based pattern recognition was used to classify the nuclei isolated from SW620 and A549 cells, producing successful classification rates of 87.2% for diameters of nuclei, 85.5% for passage times of nuclei and 89.3% for both passage times and diameters of nuclei. These results indicate that the characterization of the mechanical properties of nuclei may contribute to the classification of different tumor cells.

Rotation invariant curvelet based image retrieval & classification via Gaussian mixture model and co-occurrence features

Demand for better retrieval methods continue to outstrip the capabilities of available technologies despite the rapid growth of new feature extraction techniques. Extracting discriminatory features that contain texture specific information are of crucial importance in image indexing. This paper presents a novel rotation invariant texture representation model based on the multi-resolution curvelet transform via co-occurrence and Gaussian mixture features for image retrieval and classification. To extract these features, curvelet transform is applied and the coefficients are obtained at each scale and orientation. The Gaussian mixture model (GMM) features are computed from each of the sub bands and co-occurrence features are computed for only specific sub band. Rotation invariance is provided by applying cycle-shift around the GMM features. The proposed method is evaluated on well-known databases such as Brodatz, Outex_TC_00010, Outex_TC_00012, Outex_TC_00012horizon, Outex_TC_00012tl84, Vistex and KTH-TIPS. When the feature vector is analyzed in terms of its size, it is observed that its dimension is smaller than that of the existing rotation-invariant variants and it has a very good performance. Simulation results show a good performance achieved by combining different techniques with the curvelet transform. Proposed method results in high degree of success rate in classification and in precision-recall value for retrieval.

A fuzzy hierarchy-based pattern matching technique for melody classification

Classification of classical melodic structures by style, composer, genre, period, etc., is a rather complex task. The level of difficulty varies across melodic frameworks. It would be interesting to see how we can impart this ability to a machine. This paper reports an improved pattern matching technique for composer and raga classification using a fuzzy analytical hierarchy process-based approach. The technique makes use of class-specific patterns extracted from a pattern discovery technique known as Structure Induction Algorithm for r superdiagonals and compactness trawler. Further, to represent inexact matches a modified matching technique is proposed to assign weights to the exact matching scores in a probabilistic manner. Subsequently, the weighted scores are fuzzified to quantify the extent of match. Finally, the fuzzy scores are aggregated and classified on the basis of minimum Euclidean distance from an ideal solution in the pattern space. Experiments conducted on datasets containing a wide range of melodies from classical western and classical Indian background show that the proposed technique exhibits consistently better classification success rate compared to the exact n-Gram-based approach and a widely used matching algorithm based on Levenshtein distance.

Wavelet and kernel dimensional reduction on arrhythmia classification of ECG signals

Electrocardiogram (ECG) monitoring is continuously required to detect cardiac ailments. At times it is challenging to interpret the differences in the P- QRS-T curve. The proposed approach aims to show the excellence of kernel capabilities of Kernel Principal Component Analysis (KPCA) and Kernel Independent Component Analysis (KICA) in the wavelet domain. In this work, experiments are performed using five different categories of cardiac beats. The supervised classifiers like feed-forward neural network (FNN), backpropagation neural network (BPNN), and K nearest neighbor (KNN) statistically evaluates the impact of discrete wavelet with KPCA and KICA on extracted beats. The performance evaluation also compares the outcomes with existing techniques. The obtained results justify the supremacy of the combination of wavelet, kernel, and KNN approach, yielding a 99.7 % classification success rate. The five-fold crossvalidation scheme is used for measuring the efficacy of classifiers.

A novel classifier model for mass classification using BI-RADS category in ultrasound images based on Type-2 fuzzy inference system

Ultrasound imaging is an imaging technique for early detection of breast cancer. Breast Imaging Reporting and Data System (BI-RADS) lexicon, developed by The American College of Radiology, provides a standard for expert doctors to interpret the ultrasound images of breast cancer. This standard describes the features to classify the tumour as benign or malignant and it also categorizes the biopsy requirement as a percentage. Biopsy is an invasive method that doctors use for diagnosis of breast cancer. Computer-aided detection (CAD)/diagnosis systems that are designed to include the feature standards used in benign/malignant classification help the doctors in diagnosis but they do not provide enough information about the BI-RADS category of the mass. These systems classify the benign tumours with 90% biopsy possibility (BI-RADS-4) and with 2% biopsy possibility (BI-RADS-2) in the same category. There are some studies in the literature that make category classification via commonly used classifier methods but their success rates are low. In this study, a two-layer, high-success-rate classifier model based on Type-2 fuzzy inference is developed, which classifies the tumour as benign or malignant with its BI-RADS category by incorporating the opinions of the expert doctors. A 99.34% success rate in benign/malignant classification and a 92% success rate in category classification (BI-RADS 2, 3, 4, 5) were obtained in the accuracy tests. These results indicate that the CAD system is valuable as a means of providing a second diagnostic opinion when radiologists carry out mass diagnosis.

Proposal of an empirical site classification method based on target simulated horizontal over vertical spectral ratio

Nowadays, most of the site classifications schemes are based on the predominant period of the site as determined from the average horizontal to vertical spectral ratios of seismic motion or microtremor. However, the difficulty lies in the identification of the predominant period in particular if the observed average response spectral ratio does not present a clear peak but rather a broadband amplification or multiple peaks. In this work, based on the Eurocode-8 (2004) site classification, and assuming bounded random fields for both shear and compression waves-velocities, damping coefficient, natural period and depth of soil profile, one propose a new site-classification approach, based on “target” simulated average $$ H/V $$ spectral ratios, defined for each soil class. Taking advantage of the relationship of Kawase et al. (Bull Seismol Soc Am 101:2001–2014, 2011), which link the $$ H/V $$ spectral ratio to the horizontal ( $$ HTF $$ ) over the vertical ( $$ VTF $$ ) transfer functions, statistics of $$ H/V $$ spectral ratio via deterministic visco-elastic seismic analysis using the wave propagation theory are computed for the 4 soil classes. The obtained results show that $$ H/V $$ and $$ HTF $$ have amplitudes and shapes remarkably different among the four soil classes and exhibit fundamental peaks in the period ranges remarkably similar. Moreover, the “target” simulated average $$ H/V $$ spectral ratios for the 4 soil classes are in good agreement with the experimental ones obtained by Zhao et al. (Bull Seismol Soc Am 96:914–925, 2006) from the abundant and reliable Japanese strong motions database Kik-net, Ghasemi et al. (Soil Dyn Earthq Eng 29:121–132, 2009) from the Iranian strong motion data, and Di Alessandro et al. (Bull Sesismol Soc Am 106:2, 2011. https://doi.org/10.1785/0120110084 ) from the Italian strong motion data. In addition to the 4 EC-8 standard soil classes (A, B, C and D), the superposition of the 4 target $$ H/V $$ reveals 3 new boundary site classes; AB, BC and CD, for overlapping $$ V_{s,30} $$ ranges when the predominant peak is not clearly consistent with any of the 4 proposed classes. Finally, one proposes a site classification index based on the ratio between the cross-correlation and the mean quadratic error between the in situ $$ H/V $$ spectral ratio and the “target” one. In order to test the reliability of the proposed approach, data from 139 sites were used, 132 collected from the Kik-net network database from Japan and 7 from Algeria. The site classification success rate per site class are around 93, 82, 89 and 100% for rock, hard soil, medium soil and soft soil, respectively. Zhao et al. (2006) found an average success for the 4 classes of soil close to 60%, similar to what one found in the present study (63%) without considering the new soil classes, but much smaller if one considers them (86%). In the absence of $$ V_{s,30} $$ data, the proposed approach can be an alternative to site classification.

Classification of metallic and non-metallic fractions of e-waste using thermal imaging-based technique

Abstract Electronic waste (e-waste) is generated at a rapid pace due to technological advancement and thereby reduced obsolescence age of electrical and electronic equipment (EEE). E-waste comprises of many useful recyclable materials such as metallic fractions (MFs), like aluminum and copper and non-metallic fractions (NMFs), such as plastic, printed circuit boards (PCB) and glass. Classification of MFs and NMFs from e-waste is of great significance from the viewpoint of recycling of materials and resource recovery. In this paper, we focus on the classification of MFs and NMFs from e-waste using thermal imaging-based technique operated in the long-wave infrared range (LWIR) 8–15 μm. We use a feature vector comprising of mean intensity, standard deviation and the image-sharpness extracted from the thermograms of individual materials present in e-waste. We developed a classification model to classify the feature vectors into broad categories of metal, PCB, plastic, and glass. We conducted several experiments on simulated e-waste to validate the developed approach and obtained a classification success rate in the range of 84–96%. We believe that the proposed approach is a viable solution for multi-material classification of e-waste into broad categories and can be scaled up to fit for an e-waste recycling plant.