Accuracy Of Classification Algorithms Research Articles

Paddy Seed Classification and Identifying Varieties using Random Assessment Classification

The current research work focuses in developing an accurate and efficient classification and feature extraction algorithm for paddy seed image analysis. The paddy images that are preprocessed by applying hybrid mediangaustransform algorithms were segmented using Paddysegmatch algorithm. The resultant image’s features are extracted by applying the proposed enhanced rapid SURF feature extraction including various features of image. Later, the paddy seeds are classified to form different categories by applying the proposed Random Assessment Classification algorithm. Experimental results on Paddy seed realtime image analysis database show that the proposed method performs better classification accuracy compared with SVM and KNN classification algorithms.

Weighted Rough Set Theory for Fetal Heart Rate Classification

A novel weighted rough set-based classification approach is introduced for the evaluation of fetal nature acquired from a CardioTocoGram (CTG) signal. The classification is essential to anticipate newborn's well-being, particularly for the life-threatening cases. CTG monitoring comprises of electronic fetal heart rate (FHR), fetal activities and the uterine contraction (UC) signals. These signals are extensively used as a part of the pregnancy and give extremely significant data on fetal health. The obtained data from these recordings can be utilized to anticipate the condition of the newborn baby, which gives an open door for early medication before perpetual deficiency to the fetus. The dimension of the obtained features from CTG is high and decreases the accuracy of classification algorithms. In this article, supervised particle swarm optimization (PSO) with a rough set-based dimensionality reduction method is used to find a minimal set of significant features from CTG extracted features. The proposed weighted rough set classifier (WRSC) method is utilized for predicting the fetal condition as normal and pathological states. The performance of the proposed WRSC algorithm is compared with various classification algorithms such as bijective soft set neural network classifier (BISONN), rough set-based classifier (RST), multi-layered perceptron (MLP), decision table (DT), Java repeated incremental pruning (JRIP) classifier, J48 and Naïve Bayes (NB) classifiers. The experimental results demonstrated that the proposed algorithm is capable of forecasting the fetal state with 98.5% classification accuracy, and the results show that the proposed classification algorithm performed considerably superior than other classification techniques.

SVM Optimization Based on PSO and AdaBoost to Increasing Accuracy of CKD Diagnosis

Classification is data mining techniques which used for the purposes of diagnosis in the medical field as measured by the high accuracy produced. The accuracy of classification algorithm is influenced by the use of features and dimensions in dataset. In this study, Chronic Kidney Disease (CKD) dataset was used where the data is one of the high dimension datasets. Support Vector Machine (SVM) algorithm is used because its ability to handle high-dimensional data. In the dataset, it consists of 24 attributes and 1 class which if all are used results accuracy of classification will be diminished. Method for selecting features with Particle Swarm Optimization (PSO) is applied to reduce redundant features and produce optimal features. In addition, ensemble AdaBoost also applied in this research to increase performance of entirety classification algorithm. The results showed that the optimization of SVM algorithm by using PSO as a selection and ensemble feature of AdaBoost with an average of selected features of 18 features could increase the accuracy of 36.20% to 99.50% in the diagnosis of CKD compared to the SVM algorithm without optimization only resulting in accuracy 63.30%. This research can be used as a reference for further research in focusing on the preprocessing stage.

Oil Rig Recognition Using Convolutional Neural Network on Sentinel-1 SAR Images

Recent advances in deep learning for automatic target recognition have inspired studies for maritime surveillance with synthetic aperture radar (SAR). In this context, oil rigs monitoring is of particular interest. There are offshore platforms of different types and sizes which poses challenges for classification methods. In this letter, we compare the recognition of oil rigs on Sentinel-1 SAR images, discriminating them from false alarms, through a convolutional neural network with a different number of layers named models VGG-16 and VGG-19. We used the Sentinel-1 GRD product, which has a resolution of about 20 m, with VV and VH channel image data sets separated to observe polarization influences on target recognition. The experiments show that the VH polarization image embedding contributes with the best classification values, with the mean global accuracy of fifty random sampling tests equal to 86.4% and 84.1% using the VGG-16 and VGG-19 architectures, respectively, to extract features and feed a logistic regression classifier method. Results suggest that these approaches are a useful alternative for maritime surveillance employing SAR images of medium resolution and large swaths. Furthermore, the database balancing for wind conditions did not provide significant contributions to the accuracy of classification algorithms.

Accuracy of Classification Algorithms for Diabetes Prediction

The illness that happens in the human body because of enormous amounts of sugar in the blood, i.e., when the human body has elevated amounts of glucose in the blood is Diabetes Mellitus all the more ordinarily referred to just as diabetes. The diverse most usually happening assortments of diabetes are Prediabetes, Type2, Type 1 and Gestational Diabetes. Type 2 diabetes, is interminable and generally happens, when the human body does not usefully utilize the hormone, insulin, which is created by it. The Type 1 assortment happens when the pancreatic organ doesn't deliver enough insulin as is required by the human body.Prediabetes is one that occurs when the blood sugar levels are very high but not as much when compared to the Type 2 variety. Gestational diabetes usually affects pregnant women and here also the blood sugar levels are very high. According to the global report by the WHO (World Health Organization), around 422 million people suffer from the disease and a worrying 1.6 million odd deaths are credited only to diabetes every year. However, timely diagnosis of the disease and care of patients through simple lifestyle measures has proven to keep this deadly disease in check. The main challenge for doctors however, is the tedious process of identifying the factors that cause the occurrence of this disease, in an effective and timely manner. During the recent times this challenge is being addressed through Data Mining and Machine Learning techniques. The main aim of this experimentation is for designing a prediction model which can, with utmost accuracy, diagnose the occurrence of diabetes in patient. These training models have been designed using the WEKA tool and four supervised machine learning classification algorithms such as Naïve Bayes, J48, SVM and Neural Networks have been used to predict the onset of diabetes at an early stage. The dataset used here is the Pima Indian Diabetes training Dataset abbreviated as PIDD, which has been acquired from the UCI repository. Chi-squared tests have been applied on this dataset to obtain only those attributes that have the highest tendency of causing diabetes in patients. The performance of each of the classification algorithms have been compared and analyzed based on Accuracy, F-measure, Recall, Precision and ROC curves.

Speeding up k-Nearest Neighbors classifier for large-scale multi-label learning on GPUs

Multi-label classification is one of the most dynamically growing fields of machine learning, due to its numerous real-life applications in solving problems that can be described by multiple labels at the same time. While most of works in this field focus on proposing novel and accurate classification algorithms, the issue of the computational complexity on growing dataset sizes is somehow marginalized. Owning to the ever-increasing capabilities of data capturing, we are faced with the problem of large-scale data mining that forces learners to be not only highly accurate, but also fast and scalable on high-dimensional spaces of instances, features, and labels. In this paper, we propose a highly efficient parallel approach for computing the multi-label k-Nearest Neighbor classifier on GPUs. While this method is highly effective due to its accuracy and simplicity, its computational complexity makes it prohibitive for large-scale data. We propose a four-step implementation that takes an advantage of the GPU architecture, allowing for an efficient execution of the multi-label k-Nearest Neighbors classifier without any loss of accuracy. Experiments carried out on a number of real and artificial benchmarks show that we are able to achieve speedups up to 200 times when compared to a sequential CPU execution, while efficiently scaling up to varying number of instances and features.

Remote Sensing of Watershed: Spectral Ratioing Study for Watershed Management

River catchments are basic hydrologic units and are important from the point of view of water budget management. There are longitudinal and seasonal variations in the catchment due spatio-temporal differences in terms of lithology, rainfall condition, intensity, land use land cover. Geospatial techniques and satellite data provide cost effective information about watershed. It is easy and profitable to use these techniques as data acquisition is easy, processing is fast Ratioing is one of the digital image processing technique useful to extract information about catchment characteristics and parameters for watershed development and planning. Indices give subtle tonal variations to identify the features spectrally. It de-emphasizes the effect of sun illumination, effect of topographic factors and highlights the region as per spectral properties of specific features. It enhances the quality of image to study the features in detail. These indices are also used to improve the accuracy of classification algorithms. For the current study Landsat-8 OLI used to study NDMI, EVI2, EBI, BSI, MNDWI and MODIS product MOD11A2 and MOD13A2 has used to study TCI, VCI and VHI indices. The study indicates that indices are one of the good techniques to extract spatially and temporally varying features. NDMI provides moisture condition information across watershed. EBAI and BSI highlights built up area and give idea about impervious surface. BSI gives information about bare soil where erosion mostly very common. EVI2 enhance the vegetation and MNDWI emphasize the waterbodies which seasonally varies. TCI, VCI and VHI useful to study drought conditions. The correlation between TCI and VHI, VCI and VHI studied to get information about drought. The above indices useful to study and extract several parameters to study runoff, erosion, sedimentation, ground water condition etc. Indices provide unidealistic information at various wavelengths. Repetitive coverage allows to monitoring dynamic features like water, vegetation, soil. Indices enhance the spectral information, increase the reparability of the classes of interest, and improve the quality of mapping. Such kind of technique’s are beneficial for conservation and management of the earth resources for local government bodies to conserve the water and to reduce the intensity of the drought.

Extraction of Urban Objects in Cloud Shadows on the basis of Fusion of Airborne LiDAR and Hyperspectral Data

Feature extraction in cloud shadows is a difficult problem in the field of optical remote sensing. The key to solving this problem is to improve the accuracy of classification algorithms by fusing multi-source remotely sensed data. Hyperspectral data have rich spectral information but highly suffer from cloud shadows, whereas light detection and ranging (LiDAR) data can be acquired from beneath clouds to provide accurate height information. In this study, fused airborne LiDAR and hyperspectral data were used to extract urban objects in cloud shadows using the following steps: (1) a series of LiDAR and hyperspectral metrics were extracted and selected; (2) cloud shadows were extracted; (3) the new proposed approach was used by combining a pixel-based support vector machine (SVM) and object-based classifiers to extract urban objects in cloud shadows; (4) a pixel-based SVM classifier was used for the classification of the whole study area with the selected metrics; (5) a decision-fusion strategy was employed to get the final results for the whole study area; (6) accuracy assessment was conducted. Compared with the SVM classification results, the decision-fusion results of the combined SVM and object-based classifiers show that the overall classification accuracy is improved by 5.00% (from 87.30% to 92.30%). The experimental results confirm that the proposed method is very effective for urban object extraction in cloud shadows and thus improve urban applications such as urban green land management, land use analysis, and impervious surface assessment.

Machine Learning Classification of First-Onset Drug-Naive MDD Using Structural MRI

It is hard to differentiate adolescent Major Depressive Disorder (MDD) patients from healthy adolescent controls based on structural MRI research findings, as the clinical characteristics of the patient group are heterogeneous, and the neuroimaging study results are ambiguous. We aimed to determine whether it is possible to reliably train a highly accurate predictive classification algorithm, even with the first onset of drug-naive adolescent MDD, solely using structural magnetic resonance imaging and without using any other clinical data from the patients. We also estimated the probability of the subject belonging to the predicted class to quantify the confidence of the prediction. Medication-naive adolescent patients in their first episode of MDD and healthy volunteers, matched for age, sex, and years of education, were prospectively recruited. Twenty-seven patients and 27 controls participated in the study. The two most significant variables were the standard deviations of intensity of the right ventral diencephalon and thickness of the superior segment of the circular sulcus of the insula. A participant is diagnosed as having MDD when the variation of either intensity in the right ventral diencephalon region or thickness of the superior segment of the circular sulcus of the insula increases. Structural brain changes can be used to build an accurate classification model for machine learning, even when the duration of illness is relatively short and the influence of MDD on the brain structure is minimal.

LipoFNT: Lipoylation Sites Identification with Flexible Neural Tree

Lysine lipoylation is a special type of posttranslational modification in both prokaryotes’ and eukaryotes’ proteomics researches. Such a modification takes part in several significant biological processions and plays a key role in the cellular level. In order to construct and design an accurate classification algorithm for identifying lipoylation sites in the protein level, the computational approaches should be taken into account in this field. Meanwhile, several factors plays different role in the identification of modification sites. Considering such a situation, the foundational elements of the effective identification of modification sites are the available feature description and the high effective classification. With these two elements, the distinguishing between the lipoylation samples and the nonlipoylation samples can be treated as a typical classification issue in the field of machine learning. In this work, we have proposed a method named LipoFNT, which employed the two featuring sets, including the Position‐Specific Scoring Matrix and bi‐profile Bayesian, as the classification features. And then, the flexible neural tree algorithm is utilized to deal with the imbalance classification issue in lipoylation modification sample dataset. The proposed method can achieve 81.07% in sn%, 80.29% in sp, 80.68% in Acc, 0.8076 in F1, and 0.6136 in MCC, respectively. Meanwhile, we have demonstrated the relationship between the lengths of peptide and identification of modification sites.

An Image Classification Method Based on Deep Neural Network with Energy Model

The development of deep learning has revolutionized image recognition technology. How to design faster and more accurate image classification algorithms has become our research interests. In this paper, we proposed a new model called stochastic depth networks with deep energy model (SADIE), and the model improved stochastic depth neural network with deep energy model to provide attributes of images and analysis their characteristics. The approach we adopted is to perform pre-processing such as image segmentation and denoising, and then normalize the data. We also explored the possibility of using Adam and SGD combination optimization in deep neural networks. Finally, we use training data to train our network based on deep energy model and testing data to verify the performance of the model. The results we finally obtained in this research include the Classified labels of images. The impacts of our obtained results show that our model has high accuracy and performance.

DETECTION OF SUSPICIOUS TERRORIST EMAILS USING TEXT CLASSIFICATION: A REVIEW

This paper provides a comprehensive review and analysis of the detection of suspicious terrorist electronic mails (emails) using various phases and methods of text classification. We explored, analyzed, and compared different datasets, features, feature extraction techniques, feature representation techniques, feature selection schemes, text classification techniques, and performance measurement metrics used in the detection of suspicious terrorist e-mails. 30 articles were retrieved from 6 well-known academic databases after rigorous selection. From the study, we found that researchers often generate their own e-mails dataset since there is no public dataset is available in the research area of detecting suspicious terrorist e-mails. In most of the studies, researchers used content and context-based features to detect terrorist e-mails. Our findings also show that the most commonly used feature extraction techniques are the bag of words and n-gram, the most typically applied feature representation schemes are binary representation and term frequency, the most usually adopted feature selection method is information gain,, the most common and most accurate text classification algorithms are naive bayes, decision trees, and support vector machines, and the widely employed performance measurement metrics are accuracy, precision, and recall. Open research challenges and research issues that involve significant research efforts are also summarized in this review for future researchers in the area of suspicious terrorist e-mail detection using text classification techniques where the critical analysis presented in this paper also provides valuable insights to guide these researchers. Finally, the indicated issues and challenges presented in this paper can be used as future research directions in this area.

Assessment of Aquatic Weed in Irrigation Channels Using UAV and Satellite Imagery

Irrigated agriculture requires high reliability from water delivery networks and high flows to satisfy demand at seasonal peak times. Aquatic vegetation in irrigation channels are a major impediment to this, constraining flow rates. This work investigates the use of remote sensing from unmanned aerial vehicles (UAVs) and satellite platforms to monitor and classify vegetation, with a view to using this data to implement targeted weed control strategies and assessing the effectiveness of these control strategies. The images are processed in Google Earth Engine (GEE), including co-registration, atmospheric correction, band statistic calculation, clustering and classification. A combination of unsupervised and supervised classification methods is used to allow semi-automatic training of a new classifier for each new image, improving robustness and efficiency. The accuracy of classification algorithms with various band combinations and spatial resolutions is investigated. With three classes (water, land and weed), good accuracy (typical validation kappa >0.9) was achieved with classification and regression tree (CART) classifier; red, green, blue and near-infrared (RGBN) bands; and resolutions better than 1 m. A demonstration of using a time-series of UAV images over a number of irrigation channel stretches to monitor weed areas after application of mechanical and chemical control is given. The classification method is also applied to high-resolution satellite images, demonstrating scalability of developed techniques to detect weed areas across very large irrigation networks.

An Expert Diagnostic System to Automatically Identify Asthma and Chronic Obstructive Pulmonary Disease in Clinical Settings

Respiratory diseases such as asthma and chronic obstructive pulmonary disease (COPD), are affecting a huge percentage of the world’s population with mortality rates exceeding those of lung cancer and breast cancer combined. The major challenge is the number of patients who are incorrectly diagnosed. To address this, we developed an expert diagnostic system that can differentiate among patients with asthma, COPD or a normal lung function based on measurements of lung function and information about patient’s symptoms. To develop accurate classification algorithms, data from 3657 patients were used and then independently verified using data from 1650 patients collected over a period of two years. Our results demonstrate that the expert diagnostic system can correctly identify patients with asthma and COPD with sensitivity of 96.45% and specificity of 98.71%. Additionally, 98.71% of the patients with a normal lung function were correctly classified, which contributed to a 49.23% decrease in demand for conducting additional tests, therefore decreasing financial cost.

Ensemble swarm behaviour based feature selection and support vector machine classifier for chronic kidney disease prediction

Kidney Disease and kidney failure is the one of the complicated and challenging health issues regarding human health. Without having any symptoms few diseases are detected in later stages which results in dialysis. Advanced excavating technologies can always give various possibilities to deal with the situation by determining important realations and associations in drilling down health related data. The prediction accuracy of classification algorithms depends upon appropriate Feature Selection (FS) algorithms decrease the number of features from collection of data. FS is the procedure of choosing the most relevant features, removing irrelevant features. To identify the Chronic Kidney Disease (CKD), Hybrid Wrapper and Filter based FS (HWFFS) algorithm is proposed to reduce the dimension of CKD dataset. Filter based FS algorithm is performed based on the three major functions: Information Gain (IG), Correlation Based Feature Selection (CFS) and Consistency Based Subset Evaluation (CS) algorithms respectively. Wrapper based FS algorithm is performed based on the Enhanced Immune Clonal Selection (EICS) algorithm to choose most important features from the CKD dataset. The results from these FS algorithms are combined with new HWFFS algorithm using classification threshold value. Finally Support Vector Machine (SVM) based prediction algorithm be proposed in order to predict CKD and being evaluated on the MATLAB platform. The results demonstrated with the purpose of the SVM classifier by using HWFFS algorithm provides higher prediction rate in the diagnosis of CKD when compared to other classification algorithms.

A filtering algorithm for high-resolution flow traces to improve water end-use analysis

Abstract One of the main difficulties encountered when designing automatic tools for water end-use identification is the inherent noise present in recorded flow traces. Noise is mainly caused by the inability of the monitoring equipment to accurately register water consumption and data-loggers to register, without distortion, the signal received from the water meter. A universal filtering algorithm has been developed to remove noise and simplify water consumption flow traces with the aim of improving future automatic end-use identification algorithms. The performance of the proposed filtering methodology is assessed through the analysis of 21,647 events. Water consumption data were sourced from two different water end-use studies, having consumers and monitoring equipment with dissimilar characteristics. The results obtained show that the algorithm is capable of removing an average of 70% of the data points that constitute the flow traces of the complex events examined. The simplified flow traces allow for faster and more accurate disaggregation and classification algorithms, without losing significant information or distorting the original signal. The ability of the proposed filtering algorithm to fit the original flow traces was benchmarked using the Kling–Gupta efficiency coefficient, obtaining an average value above 0.79.

Identification of stable areas in unreferenced laser scans for automated geomorphometric monitoring

Abstract. Current research questions in the field of geomorphology focus on the impact of climate change on several processes subsequently causing natural hazards. Geodetic deformation measurements are a suitable tool to document such geomorphic mechanisms, e.g. by capturing a region of interest with terrestrial laser scanners which results in a so-called 3-D point cloud. The main problem in deformation monitoring is the transformation of 3-D point clouds captured at different points in time (epochs) into a stable reference coordinate system. In this contribution, a surface-based registration methodology is applied, termed the iterative closest proximity algorithm (ICProx), that solely uses point cloud data as input, similar to the iterative closest point algorithm (ICP). The aim of this study is to automatically classify deformations that occurred at a rock glacier and an ice glacier, as well as in a rockfall area. For every case study, two epochs were processed, while the datasets notably differ in terms of geometric characteristics, distribution and magnitude of deformation. In summary, the ICProx algorithm's classification accuracy is 70 % on average in comparison to reference data.

Visualization and Sonification of Long-Term Epilepsy Electroencephalogram Monitoring

Long-term electroencephalogram (EEG) monitoring is effective for epilepsy diagnosis. However, it also takes a lot of time for clinicians to correctly interpret the long-time recordings. Real-time computer-based EEG monitoring and classification systems have attracted recently the attention of researchers to help clinicians locate online possible epileptic-form EEG signals. In this paper, we first present an accurate and fast EEG classification algorithm that can recognize three types of EEG signals: normal, spike, and seizure. 16-channel bipolar EEG recordings of epilepsy patients are preprocessed, segmented, and ensemble empirical mode decomposed (EEMD) into intrinsic mode functions (IMFs). Features are extracted and linear discriminant analysis (LDA) is applied to train two classifiers: one is for seizure and non-seizure discrimination, and the other is for normal and spike discrimination. In order to furthermore help the clinicians, the results of LDA are visualized and sonified. The changes of the discriminant in the LDA on continuous EEG segments are backtracked to each feature, and thus to each EEG channel. Accordingly, contours of the changes in EEG channels are depicted. At the same time, sinusoidal waves in 440 or 880 Hz are played when EEG segments are classified into spike or seizure respectively. In the experiment, EEG recordings of six subjects (two normal and four seizure patients) are examined. The experiment result shows that the accuracy of the proposed epileptic EEG classification algorithm is relatively high. In addition, the visualization and sonification algorithms of epileptic-form EEG may greatly help clinicians localize the focus of seizure and nurses take care of seizure patients, immediately.

A decision analytic approach to predicting quality of life for lung transplant recipients: A hybrid genetic algorithms-based methodology

Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.

Application of Abundance Map Reference Data for Spectral Unmixing

Reference data (“ground truth”) maps have traditionally been used to assess the accuracy of classification algorithms. These maps typically classify pixels or areas of imagery as belonging to a finite number of ground cover classes, but do not include sub-pixel abundance estimates; therefore, they are not sufficiently detailed to directly assess the performance of spectral unmixing algorithms. Our research aims to efficiently generate, validate, and apply abundance map reference data (AMRD) to airborne remote sensing scenes. Scene-wide AMRD for this study were generated using the remotely sensed reference data (RSRD) technique, which spatially aggregates classification or unmixing results from fine scale imagery (e.g., 1-m GSD) to co-located coarse scale imagery (e.g., 10-m GSD or larger). Validation of the accuracy of these methods was previously performed for generic 10 m × 10 m coarse scale imagery, resulting in AMRD with known accuracy. The purpose of this paper was to apply this previously validated AMRD to specific examples of airborne coarse scale imagery. Application of AMRD involved three main parts: (1) spatial alignment of coarse and fine scale imagery; (2) aggregation of fine scale abundances to produce coarse scale imagery specific AMRD; and (3) demonstration of comparisons between coarse scale unmixing abundances and AMRD. Spatial alignment was performed using our new scene-wide spectral comparison (SWSC) algorithm, which aligned imagery with accuracy approaching the distance of a single fine scale pixel. We compared simple rectangular aggregation to coarse sensor point-spread function (PSF) aggregation, and found that PSF returned lower error, but that rectangular aggregation more accurately estimated true AMRD at ground level. We demonstrated various metrics for comparing unmixing results to AMRD, including several new techniques which adjust for known error in the reference data itself. These metrics indicated that fully constrained linear unmixing of AVIRIS imagery across all three scenes returned an average error of 10.83% per class and pixel. Our reference data research has demonstrated a viable methodology to efficiently generate, validate, and apply AMRD to specific examples of airborne remote sensing imagery, thereby enabling direct quantitative assessment of spectral unmixing performance.