Proposed Classification Procedure Research Articles

A New Procedure for Unsupervised Clustering Based on Combination of Artificial Neural Networks

Classification methods have become one of the main tools for extracting essential information from multivariate data. New classification algorithms are continuously being proposed and created. This paper presents a classification procedure based on a combination of Kohonen and probabilistic neural networks. Its applicability and efficiency are estimated using model data sets (iris flowers data set, wine data set, data with a two-hierarchical structure), then compared with the traditional clustering algorithms (hierarchical clustering, k-means clustering, fuzzy k-means clustering). The algorithm was designed as M-script in Matlab 7.11b software. It was shown that the proposed classification procedure has a great advantage over traditional clustering methods.

Performance‐based seismic classification of acceleration‐sensitive non‐structural elements

AbstractThis paper presents a general seismic classification procedure for acceleration‐sensitive non‐structural elements (NSEs) based on seismic qualification shake table testing and provides an application example for electrical cabinets in Italy. The proposed seismic classification procedure requires the definition of a set of required response spectra (RRS) for qualification shake table testing defined at different seismic hazard levels and the definition of a formal procedure to generate a test input motion. Each required response spectrum at a given seismic hazard level is then linked to different class levels and the requirements that an NSE should present to achieve each class level are defined. Using this framework, a seismic classification procedure for NSEs is developed for Italy, in which, the RRS are defined according to a peak floor spectral acceleration seismic hazard map of the territory so as to predefine regions in which an NSE belonging to a given class can be installed or not according to either a life safety performance objective or a continuous operation performance objective. Also, the limitations of the proposed seismic classification procedure are outlined. Finally, a nominal application example is presented in which four electrical cabinet specimens were tested on a shake table and their class levels were defined. The results of the application example are used to nominally show how the proposed classification procedure could be applied to discriminate between different types of the same NSE depending on the specific desired application.

A multi-temporal phenology based classification approach for Crop Monitoring in Kenya

The SBAM (Satellite Based Agricultural Monitoring) project, funded by the Italian Space Agency aims at: developing a validated satellite imagery based method for estimating and updating the agricultural areas in the region of Central-Africa; implementing an automated process chain capable of providing periodical agricultural land cover maps of the area of interest and, possibly, an estimate of the crop yield. The project aims at filling the gap existing in the availability of high spatial resolution maps of the agricultural areas of Kenya. A high spatial resolution land cover map of Central-Eastern Africa including Kenya was compiled in the year 2000 in the framework of the Africover project using Landsat images acquired, mostly, in 1995. We investigated the use of phenological information in supporting the use of remotely sensed images for crop classification and monitoring based on Landsat 8 and, in the near future, Sentinel 2 imagery. Phenological information on crop condition was collected using time series of NDVI (Normalized Difference Vegetation Index) based on Landsat 8 images. Kenyan countryside is mainly characterized by a high number of fragmented small and medium size farmlands that dramatically increase the difficulty in classification; 30 m spatial resolution images are not enough for a proper classification of such areas. So, a pan-sharpening FIHS (Fast Intensity Hue Saturation) technique was implemented to increase image resolution from 30 m to 15 m. Ground test sites were selected, searching for agricultural vegetated areas from which phenological information was extracted. Therefore, the classification of agricultural areas is based on crop phenology, vegetation index behaviour retrieved from a time series of satellite images and on AEZ (Agro Ecological Zones) information made available by FAO (FAO, 1996) for the area of interest. This paper presents the results of the proposed classification procedure in comparison with land cover maps produced in the past years by other projects. The results refer to the Nakuru County and they were validated using field campaigns data. It showed a satisfactory overall accuracy of 92.66 % which is a significant improvement with respect to previous land cover maps.

An Operational Framework for Mapping Irrigated Areas at Plot Scale Using Sentinel-1 and Sentinel-2 Data

In this study, we present an operational methodology for mapping irrigated areas at plot scale, which overcomes the limitation of terrain data availability, using Sentinel-1 (S1) C-band SAR (synthetic-aperture radar) and Sentinel-2 (S2) optical time series. The method was performed over a study site located near Orléans city of north-central France for four years (2017 until 2020). First, training data of irrigated and non-irrigated plots were selected using predefined selection criteria to obtain sufficient samples of irrigated and non-irrigated plots each year. The training data selection criteria is based on two irrigation metrics; the first one is a SAR-based metric derived from the S1 time series and the second is an optical-based metric derived from the NDVI (normalized difference vegetation index) time series of the S2 data. Using the newly developed irrigation event detection model (IEDM) applied for all S1 time series in VV (Vertical-Vertical) and VH (Vertical-Horizontal) polarizations, an irrigation weight metric was calculated for each plot. Using the NDVI time series, the maximum NDVI value achieved in the crop cycle was considered as a second selection metric. By fixing threshold values for both metrics, a dataset of irrigated and non-irrigated samples was constructed each year. Later, a random forest classifier (RF) was built for each year in order to map the summer agricultural plots into irrigated/non-irrigated. The irrigation classification model uses the S1 and NDVI time series calculated over the selected training plots. Finally, the proposed irrigation classifier was validated using real in situ data collected each year. The results show that, using the proposed classification procedure, the overall accuracy for the irrigation classification reaches 84.3%, 93.0%, 81.8%, and 72.8% for the years 2020, 2019, 2018, and 2017, respectively. The comparison between our proposed classification approach and the RF classifier built directly from in situ data showed that our approach reaches an accuracy nearly similar to that obtained using in situ RF classifiers with a difference in overall accuracy not exceeding 6.2%. The analysis of the obtained classification accuracies of the proposed method with precipitation data revealed that years with higher rainfall amounts during the summer crop-growing season (irrigation period) had lower overall accuracy (72.8% for 2017) whereas years encountering a drier summer had very good accuracy (93.0% for 2019).

Longitudinal multivariate normative comparisons.

Motivated by the Multicenter AIDS Cohort Study (MACS), we develop classification procedures for cognitive impairment based on longitudinal measures. To control family-wise error, we adapt the cross-sectional multivariate normative comparisons (MNC) method to the longitudinal setting. The cross-sectional MNC was proposed to control family-wise error by measuring the distance between multiple domain scores of a participant and the norms of healthy controls and specifically accounting for intercorrelations among all domain scores. However, in a longitudinal setting where domain scores are recorded multiple times, applying the cross-sectional MNC at each visit will still have inflated family-wise error rate due to multiple testing over repeated visits. Thus, we propose longitudinal MNC procedures that are constructed based on multivariate mixed effects models. A test procedure is adapted from the cross-sectional MNC to classify impairment on longitudinal multivariate normal data. Meanwhile, a permutation procedure is proposed to handle skewed data. Through simulations we show that our methods can effectively control family-wise error at a predetermined level. A dataset from a neuropsychological substudy of the MACS is used to illustrate the applications of our proposed classification procedures.

A classifier under the strongly spiked eigenvalue model in high-dimension, low-sample-size context

We consider the classification of high-dimensional data under the strongly spiked eigenvalue (SSE) model. We create a new classification procedure on the basis of the high-dimensional eigenstructure in high-dimension, low-sample-size context. We propose a distance-based classification procedure by using a data transformation. We also prove that our proposed classification procedure has consistency property for misclassification rates. We discuss performances of our classification procedure in simulations and real data analyses using microarray data sets.

A Light-Weight Change Detection Method Using YCbCr-Based Texture Consensus Model

Background subtraction is a prerequisite and often the very first step employed in several high-level and real-time computer vision applications. Several parametric and non-parametric change detection algorithms employing multiple feature spaces have been proposed to date but none has proven to be robust against all challenges that can possibly be posed in a complex real-time environment. Amongst the varied challenges posed, illumination variations, shadows, dynamic backgrounds, camouflaged and bootstrapping artifacts are some of the well-known problems. This paper presents a light-weight hybrid change detection algorithm that integrates a novel combination of RGB color space and conditional YCbCr-based XCS-LBP texture descriptors (YXCS-LBP) into a modified pixel-based background model. The conditional employment of light-weight YXCS-LBP texture features with the modified Visual background extractor (ViBe) aiming at reduction in false positives, produces outperforming results without incurring much memory and computational cost. The random and time-subsampled update strategy employed with the proposed classification procedure ensures the efficient suppression of shadows and bootstrapping artifacts along with the complete retention of long-term static objects in the foreground masks. Comprehensive performance analysis of the proposed technique on publicly available Change Detection dataset (2014 CDnet dataset) demonstrates the superiority of the proposed technique over different state-of-the-art-methods against varied challenges.

Design and implementation of secure ATM system using machine learning and crypto–stego methodology

The crucial prerequisite in these days is to get rid of various forms of attacks. Nowadays, for financial transaction, automated teller machines (ATMs) are the mostly used gadgets in which personal identification numbers (PINs) are generally used for transaction. But personal identification numbers (PINs) are not secured from many types of threats (spoofing, eavesdropping, man-in-the middle attack etc.), which can affect the security of the confidential and private information. Due to this reason, different biometric systems gain popularity worldwide for their behavioral and physiological features. However, the current biometric systems, for example, iris, palm, faces fingerprints or voice are extremely complex to use and have different disadvantages. In order to overcome these disadvantages a new concept has been introduced in this paper, for authentication in ATM a finger vein authentication method and for information (finger vein image) transfer a combined approach of steganography and cryptography scheme is used. Finger vein authentication system is implemented by the combination of machine learning and image processing procedure. For the purpose of information (finger vein image) transfer, a combined approach of light-weight cryptography and steganography (variable MSB–LSB algorithm) has been proposed. For finger-vein authentication system, the experiment shows that in proposed classification procedure (one-versus-one and one-versus-all) the average recognition accuracy is 98.75% and 97.92% and the execution time is 0.168 s and 0.187 s respectively. For transferring finger vein image, light-weight cryptography and variable MSB–LSB algorithm are proposed, because light weight cryptography is superior to traditional cryptography in terms of time consumption and variable MSB–LSB algorithm is superior to simple LSB in different aspects such as randomness, security and amount of space consumed.

Quality control of hazelnuts by means of NMR measurements

Hazelnuts are widely used in the confectionary industry for their flavour and taste. In order to guarantee a suitable level of quality, several standards have been defined by international organizations and producing countries. They define the minimum quality requirements of the fruits in terms of dimension, aspect, level of moisture, hidden defects. In this framework, our proposal is related to the set-up of an in-line classification system, based on low field NMR, able to detect the hidden defects of the hazelnuts. The proposed classification procedure is based on the CPMG sequence and the analysis of the transverse relaxation decay. The procedure includes three steps in which different features are detected: (i) moisture content, (ii) kernel development and (iii) healthy detection (presence of mould). Experimental results showed a very good capability to correctly detect the hidden defects, obtaining a sensitivity of 95%, with a specificity (correct detection of the healthy hazelnuts) around the 80%.

Time Series Classification using Fuzzy Cognitive Maps

This paper presents a time-series classification method based on fuzzy cognitive maps. We advocate that fuzzy cognitive maps provide a sound representation of time series, and we can construct a classification mechanism based on them. The classifier has to distinguish maps constructed for time series belonging to different classes. The proposed classification procedure evaluates similarity of fuzzy cognitive maps, and it is done by comparing weight matrices based on the same set of concepts. A weight matrix describes relationships between concepts in a map. Concepts represent the underlying data, because they are extracted via a data-driven clustering procedure. Each data point of a time series is related to each concept, and we evaluate the strength of relationships with a membership function. This paper investigates performance of the proposed approach on a suite of real-world datasets. We compare classification accuracy of our method with 37 state-of-the-art time-series classification methods. Experiments show that the proposed method is performing well. In many cases, it is better than its competitors.

CLASSIFICATION OF LIDAR DATA OVER BUILDING ROOFS USING K-MEANS AND PRINCIPAL COMPONENT ANALYSIS

Abstract: The classification is an important step in the extraction of geometric primitives from LiDAR data. Normally, it is applied for the identification of points sampled on geometric primitives of interest. In the literature there are several studies that have explored the use of eigenvalues to classify LiDAR points into different classes or structures, such as corner, edge, and plane. However, in some works the classes are defined considering an ideal geometry, which can be affected by the inadequate sampling and/or by the presence of noise when using real data. To overcome this limitation, in this paper is proposed the use of metrics based on eigenvalues and the k-means method to carry out the classification. So, the concept of principal component analysis is used to obtain the eigenvalues and the derived metrics, while the k-means is applied to cluster the roof points in two classes: edge and non-edge. To evaluate the proposed method four test areas with different levels of complexity were selected. From the qualitative and quantitative analyses, it could be concluded that the proposed classification procedure gave satisfactory results, resulting in completeness and correctness above 92% for the non-edge class, and between 61% to 98% for the edge class.

DSP-based arrhythmia classification using wavelet transform and probabilistic neural network

Abstract A large part of the biomedical research spectrum is dedicated to develop electrocardiogram (ECG) signal processing techniques to contribute to early diagnosis. However, it is common to find that ECG analysis methods reported are confined to off-line PC host operation. The authors present an arrhythmia classification method implemented on a Digital Signal Processing (DSP) platform intended for on-line, real-time ambulatory operation to classify eight heartbeat conditions: normal sinus rhythm (N), auricular fibrillation (AF), premature atrial contraction (PAC), left bundle branch block (LBBB), right bundle branch block (RBBB), premature ventricular contraction (PVC), sinoauricular heart block (SHB) and supraventricular tachycardia (SVT). The algorithm uses a wavelet transform process based on quadratic wavelets for identifying individual ECG waves and obtain a fiducial marker array. Classification is conducted by means of a Probabilistic Neural Network. The algorithm is tested with 17 ECG records obtained from the PhysioNet repository. The proposed classification procedure was tested initially on MATLAB and the results where compared with the equivalent analogue data fed to a DSP-based ECG data acquisition prototype through an arbitrary waveform generator. The results derived from confusion matrix tests yielded on-line classification accuracy of 92.69% (AF), 97.15% (N), 76.82% (PAC), 91.06% (LBBB), 87.5% (RBBB), 71.04% (PVC), 91.94% (SHB) and 95.45% (SVT), overall classification rate of 92.746% and 100% agreement between the MATLAB and on-line DSP implementations. The results suggest that the method and prototype presented may be suitable for being implemented on wearable sensing applications auxiliary for on-line, real-time diagnosis.

Distance-based linear discriminant analysis for interval-valued data

Interval-valued observations arise in many real-life situations as either the precise representation of the objective entity or the representation of incomplete knowledge. Thus given p features observed over a sample of objects belonging to one of two possible classes, each observation can be perceived as a non-empty closed and bounded hyperrectangle on Rp. The aim of the paper is to suggest a p-dimensional classification method for random intervals when two or more classes are considered, by the generalization of Fisher’s procedure for linear discriminant analysis. The idea consists of finding a directional vector which maximizes the ratio of the dispersion between the classes and within the classes of the observed hyperrectangles. A classification rule for new observations is also provided and some simulations are carried out to compare the behavior of the proposed classification procedure with respect to other methods known from the literature. Finally, the suggested methodology are applied on a real-life situation example.

Optimal Classification Policy and Comparisons for Highly Reliable Products

In the current competitive marketplace, manufacturers need to classify products in a short period of time, according to market demand. Hence, it is a challenge for manufacturers to implement a classification test that can distinguish the different grades of a product quickly and efficiently. For highly reliable products, if quality characteristics exist whose degradation over time can be related to the lifetime of the product, the degradation model can then be constructed based on the degradation data. In this study, we propose a general degradation model using a Gaussian mixture process that simultaneously considers unit-to-unit variability, within-unit variability and measurement error. Then, by adopting the concept of linear discriminant analysis, we propose a three-step classification policy to determine the optimal coefficients, the optimal cutoff points and the optimal test stopping time. In addition, we use an analytic approach to compare the efficiency of our proposed procedure with the methods that are reported in the previous literature under small sample size cases. Analytical comparisons provide functional equations under different assumptions. The solutions are found to elucidate the foundation between different methods proposed in recent studies. Finally, several data sets are used to illustrate the proposed classification procedure.

Classification of airborne laser scanning point clouds based on binomial logistic regression analysis

This article presents a newly developed procedure for the classification of airborne laser scanning (ALS) point clouds, based on binomial logistic regression analysis. By using a feature space containing a large number of adaptable geometrical parameters, this new procedure can be applied to point clouds covering different types of topography and variable point densities. Besides, the procedure can be adapted to different user requirements. A binomial logistic model is estimated for all a priori defined classes, using a training set of manually classified points. For each point, a value is calculated defining the probability that this point belongs to a certain class. The class with the highest probability will be used for the final point classification. Besides, the use of statistical methods enables a thorough model evaluation by the implementation of well-founded inference criteria. If necessary, the interpretation of these inference analyses also enables the possible definition of more sub-classes. The use of a large number of geometrical parameters is an important advantage of this procedure in comparison with current classification algorithms. It allows more user modifications for the large variety of types of ALS point clouds, while still achieving comparable classification results. It is indeed possible to evaluate parameters as degrees of freedom and remove or add parameters as a function of the type of study area. The performance of this procedure is successfully demonstrated by classifying two different ALS point sets from an urban and a rural area. Moreover, the potential of the proposed classification procedure is explored for terrestrial data.

Statistical classification of gaussian spatial data generated by conditional autoregressive model

Given training sample, the problem of classifying Gaussian spatial data into one of two populations specified by conditional autoregressive model (CAR) with different mean functions is considered. This paper concerns with classification procedures associated with Bayes Discriminant Function (BDF) under deterministic spatial sampling design. In the case of complete parametric certainty, the overall misclassification probability associated with aforementioned BDF is derived. This is the extension of the previous one to the CAR case. Spatial weights based on inverse of Euclidean distance and the second and third order neighbourhood schemes on regular 2-dimensional lattice are used for illustrative examples. The effect of the spatial sampling design, Mahalanobis distances and prior probabilities on the performance of proposed classification procedure is numerically evaluated.

Functional Data Classification of Variable Stars

This paper considers a problem of classification of variable stars based on functional data analysis. For a better understanding of galaxy structure and stellar evolution, various approaches for classification of variable stars have been studied. Several features that explain the characteristics of variable stars (such as color index, amplitude, period, and Fourier coefficients) were usually used to classify variable stars. Excluding other factors but focusing only on the curve shapes of variable stars, Deb and Singh (2009) proposed a classification procedure using multivariate principal component analysis. However, this approach is limited to accommodate some features of the light curve data that are unequally spaced in the phase domain and have some functional properties. In this paper, we propose a light curve estimation method that is suitable for functional data analysis, and provide a classification procedure for variable stars that combined the features of a light curve with existing functional data analysis methods. To evaluate its practical applicability, we apply the proposed classification procedure to the data sets of variable stars from the project STellar Astrophysics and Research on Exoplanets (STARE).

Modelling of Diffusing Capacity Measurement Results in Lung Microangiopathy Patients

Lung microangiopathy is a little known negative influence of diabetes mellitus on the functioning of the lungs. In current medical practice lung microangiopathy is diagnosed by comparing two measurements of lung diffusing capacity - once with the subject standing and once with the subject lying down. The necessity to take two measurements is inconvenient. The aim of this study is to design a supportive method for diagnosing lung microangiopathy. This will be based on routinely performed pulmonary measurements as well as on investigation of process modelling and data processing. A model of the diffusion of oxygen from the alveoli to the blood has been described with a set of differential equations. The idea of the proposed model is based on the physiological analysis of the oxygen flow (caused by a concentration gradient) and on general knowledge regarding the kinetics of associating oxygen with haemoglobin. The model parameters are estimated using diffusing capacity and alveolar volume measurements - routinely performed in pulmonary tests. The model parameter estimates proved good candidates for the binary classification of the presence or absence of microangiopathy. The proposed classification procedure, based on parameter values and established diagnostic thresholds, gives sensitivity Sens = 79.34% and specificity Spec = 87.08%. The results of classification with the use of diffusing capacity measurement are worse: Sens = 62.12% and Spec = 79.89%. The proposed classification procedure is based on the model parameters. These have proved to be sensitive indicators of lung microangiopathy. Close to 80% of microangiopathy cases have been classified as such. Less than 20% were false alarms. The oxygen pathway model allows for simulations. Blood saturation and oxygen partial pressure have been simulated for the organism's various needs for oxygen, both for the normal and the impaired alveoli-capillary barrier.

Optimization-Based Model Fitting for Latent Class and Latent Profile Analyses.

Statisticians typically estimate the parameters of latent class and latent profile models using the Expectation-Maximization algorithm. This paper proposes an alternative two-stage approach to model fitting. The first stage uses the modified k-means and hierarchical clustering algorithms to identify the latent classes that best satisfy the conditional independence assumption underlying the latent variable model. The second stage then uses mixture modeling treating the class membership as known. The proposed approach is theoretically justifiable, directly checks the conditional independence assumption, and converges much faster than the full likelihood approach when analyzing high-dimensional data. This paper also develops a new classification rule based on latent variable models. The proposed classification procedure reduces the dimensionality of measured data and explicitly recognizes the heterogeneous nature of the complex disease, which makes it perfect for analyzing high-throughput genomic data. Simulation studies and real data analysis demonstrate the advantages of the proposed method.

A classification procedure for highly imbalanced class sizes

This article develops an effective procedure for handling two-class classification problems with highly imbalanced class sizes. In many imbalanced two-class problems, the majority class represents “normal” cases, while the minority class represents “abnormal” cases, detection of which is critical to decision making. When the class sizes are highly imbalanced, conventional classification methods tend to strongly favor the majority class, resulting in very low or even no detection of the minority class. The research objective of this article is to devise a systematic procedure to substantially improve the power of detecting the minority class so that the resulting procedure can help screen the original data set and select a much smaller subset for further investigation. A procedure is developed that is based on ensemble classifiers, where each classifier is constructed from a resized training set with reduced dimension space. In addition, how to find the best values of the decision variables in the proposed classification procedure is specified. The proposed method is compared to a set of off-the-shelf classification methods using two real data sets. The prediction results of the proposed method show remarkable improvements over the other methods. The proposed method can detect about 75% of the minority class units, while the other methods turn out much lower detection rates.