Soft Classification Approach Research Articles

A 2-Tier Bengali Dataset for Evaluation of Hard and Soft Classification Approaches

Document classification is an open problem in library, information, and computer sciences towards assigning documents to one or more classes. The interest of linguistic researchers in this domain has increased day by day due to interesting applications like language identification, readability assessment, sentiment analysis, spam filtering, etc. However, researchers focussing on natural language processing of resource-scaring languages have faced many hurdles due to the absence of benchmark datasets. Bengali is among the most-spoken resource-scaring or low-resource language. Although Bengali NLP researchers have endeavoured towards creating their own datasets, they are only useful for performance evaluation of their proposed document classification techniques only. Therefore, there is a gap in the literature on the availability of benchmark datasets. To overcome this barrier, this paper presents a benchmark dataset for Bengali document classification, which is publicly accessible and freely available. This dataset consists of a two-tier architecture, the first-tier for hard classification and the second-tier for soft classification techniques. Hard classification techniques follow supervised learning based models for the classification of documents, while on the other hand, soft classification techniques follow unsupervised learning based models for the clustering of documents. The proposed dataset consists of thirteen unique characteristics. This paper also introduces four new feature sets to evaluate the performance of the proposed dataset, namely: location revealing factor, part of speech tagging factor, relative frequency, and prominence factor.

Assessing the Fractional Abundance of Highly Mixed Salt-Marsh Vegetation Using Random Forest Soft Classification

Coastal salt marshes are valuable and critical components of tidal landscapes, currently threatened by increasing rates of sea level rise, wave-induced lateral erosion, decreasing sediment supply, and human pressure. Halophytic vegetation plays an important role in salt-marsh erosional and depositional patterns and marsh survival. Mapping salt-marsh halophytic vegetation species and their fractional abundance within plant associations can provide important information on marsh vulnerability and coastal management. Remote sensing has often provided valuable methods for salt-marsh vegetation mapping; however, it has seldom been used to assess the fractional abundance of halophytes. In this study, we developed and tested a novel approach to estimate fractional abundance of halophytic species and bare soil that is based on Random Forest (RF) soft classification. This approach can fully use the information contained in the frequency of decision tree “votes” to estimate fractional abundance of each species. Such a method was applied to WorldView-2 (WV-2) data acquired for the Venice lagoon (Italy), where marshes are characterized by a high diversity of vegetation species. The proposed method was successfully tested against field observations derived from ancillary field surveys. Our results show that the new approach allows one to obtain high accuracy (6.7% < root-mean-square error (RMSE) < 18.7% and 0.65 < R2 < 0.96) in estimating the sub-pixel fractional abundance of marsh-vegetation species. Comparing results obtained with the new RF soft-classification approach with those obtained using the traditional RF regression method for fractional abundance estimation, we find a superior performance of the novel RF soft-classification approach with respect to the existing RF regression methods. The distribution of the dominant species obtained from the RF soft classification was compared to the one obtained from an RF hard classification, showing that numerous mixed areas are wrongly labeled as populated by specific species by the hard classifier. As for the effectiveness of using WV-2 for salt-marsh vegetation mapping, feature importance analyses suggest that Yellow (584–632 nm), NIR 1 (near-infrared 1, 765–901 nm) and NIR 2 (near-infrared 2, 856–1043 nm) bands are critical in RF soft classification. Our results bear important consequences for mapping and monitoring vegetation-species fractional abundance within plant associations and their dynamics, which are key aspects in biogeomorphic analyses of salt-marsh landscapes.

A genetic algorithm based approach to estimate the volume of a drinking water reservoir in Chennai city, South India, using multi-spectral satellite images

This paper is concerned with the use of satellite image processing and remote sensing approaches to determine the water-spread area and capacity of a drinking water reservoir in Poondi, near Chennai City, south India. Estimation of water-spread area and volume of the reservoirs using traditional methods like field surveys, acoustic surveys and hydrographic surveys is time-consuming, laborious and expensive. To overcome these problems, many researchers have used satellite images and the per-pixel (hard classification), the sub-pixel (soft classification) and the super resolution mapping approaches. The conventional hard and soft classification approaches do not give accurate results due to the presence of mixed pixels in the image scene of the periphery of the reservoir. In this work, a per-pixel algorithm (Maximum Likelihood), a sub-pixel algorithm (Fuzzy C Means) and a super resolution mapping algorithm (Genetic algorithm) are developed and the water-spread area is estimated for the reservoir using multi-date Landsat8 OLI images. The volume of the reservoir at different water levels are estimated using the water-spread area and the Trapezoidal formula. The capacity estimated from satellite image-derived area is compared with the capacity data obtained from the Poondi reservoir authority. The error in estimation due to the per-pixel approach is 16.74%, while it is 9.06% for the sub-pixel approach and a mere 3.25% for the super-resolution approach. Thus, the super-resolution mapping approach results in minimum error when compared to the sub-pixel approach which in turn gives lesser error result when comparing with the per-pixel approach.

An integrated soft and hard classification approach for evaluating urban expansion from multisource remote sensing data: a case study of the Beijing–Tianjin–Tangshan metropolitan region, China

ABSTRACTIntegrating soft and hard classification to monitor urban expansion can effectively provide comprehensive urban growth information to urban planners. In this study, both the impervious surface coverage (as a soft classification result) and land cover (as a hard classification result) in the Beijing–Tianjin–Tangshan metropolitan region (BTTMR), China, were extracted from multisource remote sensing data from 1990 to 2015. Then, we evaluated urban expansion based on centre migration, standard deviation ellipse, and spatial autocorrelation metrics. Furthermore, the differences between the soft and hard classification results were analysed at the landscape scale. The results showed that (1) the impervious surface area increased considerably over the past 25 years. Notably, the areas of urban built-up land and industrial production land increased rapidly, while those of ecological land and agricultural production land seriously decreased. (2) The distribution of impervious surfaces was closely related to the regional economic development plan of ‘One Axis, Two Wing, and Multi-Node’ in the BTTMR. (3) The contributions of different land use types to impervious surface growth ranked from high to low as follows: urban built-up land, rural residential land, industrial production land, agricultural production land, and ecological land. (4) The landscape metrics varied considerably based on the hard and soft classification results and were sensitive to different factors.

Automatic emotion detection in text streams by analyzing Twitter data

Techniques to detect the emotions expressed in microblogs and social media posts have a wide range of applications including, detecting psychological disorders such as anxiety or depression in individuals or measuring the public mood of a community. A major challenge for automated emotion detection is that emotions are subjective concepts with fuzzy boundaries and with variations in expression and perception. To address this issue, a dimensional model of affect is utilized to define emotion classes. Further, a soft classification approach is proposed to measure the probability of assigning a message to each emotion class. We develop and evaluate a supervised learning system to automatically classify emotion in text stream messages. Our approach includes two main tasks: an offline training task and an online classification task. The first task creates models to classify emotion in text messages. For the second task, we develop a two-stage framework called EmotexStream to classify live streams of text messages for the real-time emotion tracking. Moreover, we propose an online method to measure public emotion and detect emotion burst moments in live text streams.

Region-based Segmentation of Social Images Using Soft KNN Algorithm

Social image data is very useful to solve many real world problems. In this paper, a novel soft classification approach is proposed to deal with the problem of vision segmentation in social networks. Proposed approach is inspired by the k-nearest neighbour and soft classification concepts. K-nearest neighbour is one of the popular and simplest classification algorithms. Soft classification has provision for assigning more than one class label to a single object. Here, soft classification concept is incorporated in k-nearest neighbour algorithm to detect the ambiguous regions of the image. Experimentation is carried out on the images collected from social networks. Three social image datasets i.e. synthetic, standard and real-world are used. Proposed approach performed much better as compared to the traditional k-nearest neighbour approach. It is useful for accomplishing various tasks like fashion analysis, emotion detection, event detection, etc. through object detection and recognition.

SVM-based soft classification of urban tree species using very high-spatial resolution remote-sensing imagery

ABSTRACTClassification from remote-sensing data has proved to be fast and effective for mapping tree species. However, the interference from background noise and the weak spectral separability among most tree species have negative impacts on classification accuracy and may make conventional classification methods inappropriate. To solve this problem, a soft classification approach is presented. It consists of the technologies of soft partition, defuzzifying, and feature-location analyses (referred to here as F-L analyses). The soft partition is conducted by combined binary support vector machines, enabling a natural prototype of fuzzy clusters to be formed. Unsure members (members means both patches and pixels) in the clustering prototype can be defuzzified afterwards. F-L analyses run through the entire process in two ways: (1) by adding density description to feature space for classification and (2) through density-constrained defuzzifying. The former can enrich the feature space, thus making the soft partition perform better. By using the latter, the credibility of a class label is indicated by several weighted fuzzy measures in the form of hierarchical densities, thereby reducing the uncertainty of the defuzzifying. Experiments indicate that only 63% of members on average are surely allocated in a clustering prototype and the remainder can be ensured by the explored defuzzifying approach. The mean overall accuracy (OA) of the defuzzified members is very close to that of the originally allocated sure ones. A comparative assessment shows that the mean OA and mean kappa statistic value of members defuzzified using the explored fuzzy measure are, on average, 3.84 and 4.89% respectively higher than those using conventional maximum membership measures. Experiments also show that the former is superior to the latter in regard to the formation of complete tree crown objects.

Sub Pixel Classification of High Resolution Satellite Imagery

The emergences of more Earth observation satellites have increased the use of satellite imagery in applications like Land cover detection, environment monitoring etc. The information is generally extracted from satellite images by classification techniques. A common Problem associated with classification process is frequent occurrence of mixed pixel. Mixed Pixels are major cause of uncertainty in image classification process. Soft classifiers provide quantitative presence of a class in a pixel but the spatial location of this class remains unexplored. Subpixel classification and swapping have evolved as a latest technique to generate superior subpixel swapping images by considering output of soft classification process. SRM algorithms are mainly classified as spatial optimization based and regression based approaches. However the spatial optimization techniques are more applicable. The major drawback of conventional techniques is non-random allocation of classes to sub pixels which leads to iterative procedure of optimization that is time taking. In this paper, the proposed method performs an initial non-random allocation of classes to sub pixel and optimization procedure adapted is performed to overcome multiple and non-allocated sub pixels to simplify SRM approach and curtail processing time. Proposed method uses soft classification approaches for generating fractional maps which is provided as input to SRM method. Early allocation of sub pixels is achieved based on amount of attractiveness to neighborhood pixels. General Terms Subpixel targets, full pixel, soft classification, and high resolution images etc.

Temporal MODIS data for identification of wheat crop using noise clustering soft classification approach

In this study, temporal MODIS-Terra MOD13Q1 data have been used for identification of wheat crop uniquely, using the noise clustering (NC) soft classification approach. This research also optimises the selection of date combination and vegetation index for classification of wheat crop. First, a separability analysis is used to optimise the date combination for each case of number of dates and vegetation index. Then, these scenes have undergone for NC soft classification. The resolution parameter (δ) was optimised for the NC classifier and found to be a value of 1.6 × 104 for wheat crop identification. Classified outputs were analysed by receiver operating characteristics (ROC) analysis for sub-pixel detection. Highest area under the ROC curve was found for soil-adjusted vegetation index corresponding to the three different phenological stages data sets. From this study, the data sets corresponding to the Sowing, Flowering and Maturity phenological stages of wheat crop were found more suitable to identify it uniquely.

Characterizing Vocal Repertoires--Hard vs. Soft Classification Approaches.

To understand the proximate and ultimate causes that shape acoustic communication in animals, objective characterizations of the vocal repertoire of a given species are critical, as they provide the foundation for comparative analyses among individuals, populations and taxa. Progress in this field has been hampered by a lack of standard in methodology, however. One problem is that researchers may settle on different variables to characterize the calls, which may impact on the classification of calls. More important, there is no agreement how to best characterize the overall structure of the repertoire in terms of the amount of gradation within and between call types. Here, we address these challenges by examining 912 calls recorded from wild chacma baboons (Papio ursinus). We extracted 118 acoustic variables from spectrograms, from which we constructed different sets of acoustic features, containing 9, 38, and 118 variables; as well 19 factors derived from principal component analysis. We compared and validated the resulting classifications of k-means and hierarchical clustering. Datasets with a higher number of acoustic features lead to better clustering results than datasets with only a few features. The use of factors in the cluster analysis resulted in an extremely poor resolution of emerging call types. Another important finding is that none of the applied clustering methods gave strong support to a specific cluster solution. Instead, the cluster analysis revealed that within distinct call types, subtypes may exist. Because hard clustering methods are not well suited to capture such gradation within call types, we applied a fuzzy clustering algorithm. We found that this algorithm provides a detailed and quantitative description of the gradation within and between chacma baboon call types. In conclusion, we suggest that fuzzy clustering should be used in future studies to analyze the graded structure of vocal repertoires. Moreover, the use of factor analyses to reduce the number of acoustic variables should be discouraged.

Entropy based determination of optimal principal components of Airborne Prism Experiment (APEX) imaging spectrometer data for improved land cover classification

Abstract. Hyperspectral data finds applications in the domain of remote sensing. However, with the increase in amounts of information and advantages associated, come the "curse" of dimensionality and additional computational load. The question most often remains as to which subset of the data best represents the information in the imagery. The present work is an attempt to establish entropy, a statistical measure for quantifying uncertainty, as a formidable measure for determining the optimal number of principal components (PCs) for improved identification of land cover classes. Feature extraction from the Airborne Prism EXperiment (APEX) data was achieved utilizing Principal Component Analysis (PCA). However, determination of optimal number of PCs is vital as addition of computational load to the classification algorithm with no significant improvement in accuracy can be avoided. Considering the soft classification approach applied in this work, entropy results are to be analyzed. Comparison of these entropy measures with traditional accuracy assessment of the corresponding „hardened‟ outputs showed results in the affirmative of the objective. The present work concentrates on entropy being utilized for optimal feature extraction for pre-processing before further analysis, rather than the analysis of accuracy obtained from principal component analysis and possibilistic c-means classification. Results show that 7 PCs of the APEX dataset would be the optimal choice, as they show lower entropy and higher accuracy, along with better identification compared to other combinations while utilizing the APEX dataset.

Moist deciduous forest identification using MODIS temporal indices data

The present research aims to extract moist deciduous forest (MDF) from Moderate Resolution Imaging Spectroradiometer (MODIS) temporal data by using the fuzzy c-means (FCM)-based noise clustering (NC) soft classification approach. Seven-date temporal MODIS data were used to identify MDF, and temporal Advanced Wide Field Sensor (AWiFS) data were used as reference data for testing. Different types of spectral indices were used to generate the temporal data set combinations for both MODIS and AWiFS. The NC resolution parameter delta was optimized to achieve the best output. It was found that for both AWiFS and MODIS data, optimum NC outputs were obtained when reached close to 105. For assessment of the accuracy, NC classified outputs were optimized using the entropy approach. The optimized data set of AWiFS was then used for assessing the accuracy of the optimized data set of MODIS using fuzzy error matrix (FERM), composite operators (MIN-MIN, MIN-PROD, and MIN-LEAST), and a sub-pixel confusion-uncertainty matrix (SCM). It was found that the temporal data set combination corresponding to ‘Three’ date yields the highest overall accuracy for all accuracy assessment techniques. In all cases, the ‘Three’ date combination corresponds to the three scenes pertaining to different phenological activity of the MDF. This ‘Three’ date combination, along with the soil-adjusted vegetation index (SAVI), yielded the highest overall accuracy values, namely 94.88% and 94.84% for MIN-LEAST and MIN-PROD, respectively.

Earthquake damage identification: a case study using soft classification approach

The October 8, 2005, Kashmir earthquake (M w 7.6) affected the rough mountainous regions of India and Pakistan with poor accessibility, and thus, no proper comprehensive ground survey was possible. However, due to the ability of remote sensing technology to acquire spectral measurements of damaged areas at various spatial and temporal scales, extraction of damaged areas can be carried out quickly and with great reliability. The fuzzy-based classifiers [Possibilistic c-Means (PCM), noise cluster (NC), and NC with entropy (NCE)] were applied to identify 2005 Kashmir earthquake, induced landslides, as well as built-up damage (BD) areas, as soft computing approaches using supervised classification. Results indicate that for the identification of landslides and BD areas, NCE classifier generated the best outputs, while for the identification of built-up undamaged areas, NC classifier generated the best output. Further, it was found that the proposed Class Based Sensor Independent (CBSI) technique can improve spectral information of specific class for better identification.

Study of soft classification approaches for identification of earthquake-induced liquefied soil

The existence of mixed pixels led to the development of several approaches for soft (or fuzzy) classification in which each pixel is allocated to all classes in varying proportions. However, while the proportions of each land cover within each pixel may be predicted, the spatial location of each land cover within each pixel is not. There exist many different potential techniques for sub-pixel mapping from remotely sensed imagery to identify specific class. The fuzzy-based possibilistic c-means (PCM), noise cluster (NC) and noise cluster with entropy (NCE) classifiers were applied to identify the Bhuj, India (2001), earthquake induced soil liquefaction and compared as soft computing approaches via supervised classification. The soil liquefaction identification was empirically investigated and compared with class-based sensor-independent (CBSI) spectral band ratio using Landsat-7 temporal images. It has been found that CBSI-based temporal indices yield the better results for identification of liquefied soil areas while it was easily separated with pre-earthquake existing water body in that area. The NCE classifier performed better for conventional temporal indices, while NC classifier performed better for soil liquefaction and PCM classifier performed better for water body identification with CBSI temporal indices.

Evaluation of fuzzy-based classifiers for cotton crop identification

In this study, an evaluation of fuzzy-based classifiers for specific crop identification using multi-spectral temporal data spanning over one growing season has been carried out. The temporal data sets have been georeferenced with 0.3 pixel rms error. Temporal information of cotton crop has been incorporated through the following five indices: simple ratio (SR), normalized difference vegetation index (NDVI), transformed normalized difference vegetation index (TNDVI), soil-adjusted vegetation index (SAVI) and triangular vegetation index (TVI), to study the effect of indices on classified output. For this purpose, a comparative study between two fuzzy-based soft classification approaches, possibilistic c-means (PCM) and noise classifier (NC), was undertaken. In this study, advanced wide field sensor (AWiFS) data for soft classification and linear imaging self scanner sensor (LISS III) data for soft testing purpose from Resourcesat-1 (IRS-P6) satellite were used. It has been observed that NC fuzzy classifier using TNDVI temporal index – dataset 2, which comprises four temporal images performs better than PCM classifier giving highest fuzzy overall accuracy of 96.03%.

Fuzzy Based Approach for Moist Deciduous Forest Identification Using MODIS Temporal Data

Fuzzy based soft classification have been used immensely for handling the mixed pixel and hence to extract the single class of interest. The present research attempts to extract the moist deciduous forest from MODIS temporal data using the Possibilistic c-Means (PCM) soft classification approach. Temporal MODIS (7 dates) data were used to identify moist deciduous forest and temporal AWiFS (7 dates) data were used as reference data for testing. The Simple Ratio (SR), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and Transformed Normalized Difference Vegetation Index (TNDVI) were used to generate the temporal vegetation indices for both the MODIS and the AWiFS datasets. It was observed from the research that the MODIS temporal NDVI data set1, which contain the minimum number of images and avoids the temporal images corresponding to the highest frequency stages of onset of greenness (OG) and end of senescence (ES) activity of moist deciduous forest have been found most suitable data set for identification of moist deciduous forest with the maximum fuzzy overall accuracy of 96.731 %.

Combined target factor analysis and Bayesian soft-classification of interference-contaminated samples: Forensic Fire Debris Analysis

A Bayesian soft classification method combined with target factor analysis (TFA) is described and tested for the analysis of fire debris data. The method relies on analysis of the average mass spectrum across the chromatographic profile (i.e., the total ion spectrum, TIS) from multiple samples taken from a single fire scene. A library of TIS from reference ignitable liquids with assigned ASTM classification is used as the target factors in TFA. The class-conditional distributions of correlations between the target and predicted factors for each ASTM class are represented by kernel functions and analyzed by Bayesian decision theory. The soft classification approach assists in assessing the probability that ignitable liquid residue from a specific ASTM E1618 class, is present in a set of samples from a single fire scene, even in the presence of unspecified background contributions from pyrolysis products. The method is demonstrated with sample data sets and then tested on laboratory-scale burn data and large-scale field test burns. The overall performance achieved in laboratory and field test of the method is approximately 80% correct classification of fire debris samples.

Effect on specific crop mapping using WorldView-2 multispectral add-on bands: soft classification approach

In this study, new add-on bands in a multispectral dataset of WorldView-2, DigitalGlobe's second next-generation satellite, have been evaluated. For extraction of a specific agriculture crop at a time, WorldView-2 multispectral single, as well as two-date data sets, were used. For this purpose, a class-based sensor independent spectral band ratio normalized difference vegetation index (NDVI) (CBSI-NDVI) and its possibilistice fuzzy classification approach was used. Different agriculture crops selected for the study were sugarcane, late wheat, cauliflower, berseem (fodder), early wheat and ratoon. It is found that bands four and eight with temporal data are good for extracting sugarcane, while bands four, eight and five, seven with temporal data are suitable for late wheat and bands four and eight work well for cauliflower. Similarly, bands five, seven and five, eight with temporal data are good for extracting berseem (fodder), bands four, eight work for early wheat with temporal data and for ratoon four, six single date or four, six and four, eight temporal data. This suitability of bands has been observed with respect to a maximum membership value difference, as well as maximum entropy difference, between the two closest agriculture crops. Thus, it can be concluded that existing bands five, seven and new bands four, six, eight in WorldView-2 are important for identifying and mapping crops mentioned in this study. This indicates new bands, especially four, six, eight introduced in WorldView-2, are more effective than existing bands in QuickBird for mapping specific crops.

Dealing with vagueness in complex forest landscapes: A soft classification approach through a niche-based distribution model

The increasing interest in biodiversity conservation has led to the development of new approaches to facilitate ecologically based conservation policies and management plans. In this context, the development of effective methods for the classification of forest types constitutes a crucial issue as forests represent the most widespread vegetation structure and play a key role in ecosystem functioning. In this study a maximum entropy approach (Maxent) to forest type classification in a complex Mediterranean area, has been investigated. Maxent, a niche-based model of species/habitat distribution, allowed researchers to estimate the potential distribution of four forest types: Holm oak, Mixed oak, Mixed broadleaved and Riparian forests. The Maxent model's internal tests have proved a powerful tool for estimating the model's accuracy and analyzing the effects of the most important variables in the produced models. Moreover the comparison with a spectral response-based fuzzy classification, showed a higher accuracy in the Maxent outputs, demonstrating how the use of environmental variables, combined with spectral information in the classification of natural or semi-natural land cover classes, improves map accuracies. The modeling approach followed by this study, taking into account the uncertainty proper of the natural ecosystems and the use of environmental variables in land cover classification, can represent a useful approach to making more efficient and effective field inventories and to developing effective conservation policies.

Simultaneous latent fingerprint recognition

Abstract Simultaneous latent fingerprints are clusters of friction ridge impressions deposited concurrently in a crime scene. The analysis of these impressions is a complex task to infer individualization, exclusion or categorize as inconclusive. The problem is further compounded when distinctive features in each latent fingerprint in the cluster are of varying quality or none of the fingerprint has the requisite number of features to reliably arrive at a conclusion. Recently, SWGFAST (Scientific Working Group on Friction Ridge Analysis, Study and Technology) proposed a draft standard for simultaneous impression examination. The approach is manual and requires known reference ten-print for comparing with an unknown simultaneous latent fingerprint. This paper proposes a semi-automatic approach to process and analyze simultaneous latent fingerprints. The proposed algorithm demonstrates that comparisons can be made from a database of ten-prints for a more comprehensive search instead of the time consuming manual approach used by latent fingerprint examiners. The algorithm was implemented using several soft computing and classification approaches and the performance was compared using the simultaneous latent fingerprint database. The results show that 2 ν-SVM with RBF kernel gave the best results both in terms of time and accuracy.