Fuzzy Classification Method Research Articles

Classification of Landforms for Digital Soil Mapping in Urban Areas Using LiDAR Data Derived Terrain Attributes: A Case Study from Berlin, Germany

In this study, a knowledge-based fuzzy classification method was used to classify possible soil-landforms in urban areas based on analysis of morphometric parameters (terrain attributes) derived from digital elevation models (DEMs). A case study in the city area of Berlin was used to compare two different resolution DEMs in terms of their potential to find a specific relationship between landforms, soil types and the suitability of these DEMs for soil mapping. Almost all the topographic parameters were obtained from high-resolution light detection and ranging (LiDAR)-DEM (1 m) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)-DEM (30 m), which were used as thresholds for the classification of landforms in the selected study area with a total area of about 39.40 km2. The accuracy of both classifications was evaluated by comparing ground point samples as ground truth data with the classification results. The LiDAR-DEM based classification has shown promising results for classification of landforms into geomorphological (sub)categories in urban areas. This is indicated by an acceptable overall accuracy of 93%. While the classification based on ASTER-DEM showed an accuracy of 70%. The coarser ASTER-DEM based classification requires additional and more detailed information directly related to soil-forming factors to extract geomorphological parameters. The importance of using LiDAR-DEM classification was particularly evident when classifying landforms that have narrow spatial extent such as embankments and channel banks or when determining the general accuracy of landform boundaries such as crests and flat lands. However, this LiDAR-DEM classification has shown that there are categories of landforms that received a large proportion of the misclassifications such as terraced land and steep embankments in other parts of the study area due to the increased distance from the major rivers and the complex nature of these landforms. In contrast, the results of the ASTER-DEM based classification have shown that the ASTER-DEM cannot deal with small-scale spatial variation of soil and landforms due to the increasing human impacts on landscapes in urban areas. The application of the approach used to extract terrain parameters from the LiDAR-DEM and their use in classification of landforms has shown that it can support soil surveys that require a lot of time and resources for traditional soil mapping.

Wetland habitat stability assessment in hydro-geomorphological (HGM) and surface water availability (SWA) conditions in a lower Gangetic floodplain region of Eastern India

Floodplain wetlands in their optimum habitat condition act as the preventive mechanism from environmental degradation like pollution, lowering of groundwater table, flood, temperature control and others. Therefore, the protection and stability condition assessment of these wetlands are very much indispensable for the sake of the environment. In the present work, the habitat stability assessment of the wetlands of a floodplain region produced by River Ganga has been done considering the hydro-geomorphological (HGM) and surface water availability (SWA) parameters. The fuzzy classification (FC) and composite indexing (CI) method have been applied to perform the analysis. The result suggests that 16%–24% of wetland area is very highly prone to loss and 33%–36% area needs proper management whereas only 9%–11% wetlands are very highly stable. The wetlands have shown a rise in the average seasonal water level fluctuation from 2.18 m in 2014 to 3.38 m in 2018 which indicates more drying out condition during lean months. From morphogenetic perspective, nearly 43% of wetlands are riverine and in terms of HGM classification 77% of the wetlands are groundwater depressions (GWD). So, lack of water supply all throughout the year, seasonal water level fluctuation and absence of active river-wetland links are mainly responsible for the degradation of habitat stability condition of the wetlands. The results have been validated over different ground locations using kappa index and ROC curve method. It suggests that both these methods are very much accurate and between these two, FC method has given better result.

Object-oriented and fuzzy logic classification methods for mapping reforested areas with exotic species in Rio Canoas State Park—Santa Catarina, Brazil

Reforestation with exotic plans may alter the natural flora due to uncontrolled expansion of the inserted species. This study evaluated the potential of the object-oriented classification method using fuzzy logic algorithm for the differentiation of forest areas in intermediate/advanced stage and areas reforested with exotic species around the Rio Canoas State Park in Santa Catarina State of Brazil, using high spatial resolution SPOT6 imagery. The study region has regional importance for the preservation of mixed ombrophilous forest remnants and is belonging to the Biosphere Reserve of the Atlantic Rainforest, and hence, it is important to monitor the advance of exotic species in the region. The methodology consisted of the creation of the hierarchical network and process tree with numerous descriptor tests in Trimble Ecognition software, principal component analysis, multi-resolution segmentation algorithm and fuzzy logic functions. It was concluded that the use of principal components associated with the red band by a simple ratio of digital levels is extremely effective for identifying the areas reforested with exotic species. Fuzzy logic pertinence functions are the key in discriminating natural forest areas and areas reforested with exotic species in the study region accurately. The object-oriented classification was validated by points collected in the field and presented an overall accuracy level of 0.83 and Kappa index of 0.78, concluding that it is an efficient methodology in the delimitation of exotic species reforestation areas around Rio Canoas State Park.

Changes in agrarian structure in the EU during the period 2010-2016 in terms of typological groups of countries

The paper presents the changes in the spatial structure of agricultural holdings in the European Union between 2010 and 2016 from the perspective of typological groups of countries. The research was conducted based on Eurostat data. The holdings were divided into the following groups: up to 5 ha of agricultural land (AL), 5–20 ha, 20–50 ha, and over 50 ha. Based on the fuzzy classification method, 4 typological groups of countries with a similar spatial structure of holdings were distinguished. The intergroup diversity is high. The dynamics of changes in the number of holdings in particular countries per typological group was presented. A downward trend in the total number of holdings and smallholdings was observed, in particular in countries characterised by a fragmented structure of holdings. In these countries, an upward trend in the number of holdings of 20–50 ha and over 50 ha was noted. Between 2010 and 2016, the structure and composition of typological groups changed. There were also slight changes (in different directions) in the structural distance between the groups.

Response of a Coastal Groundwater System to Natural and Anthropogenic Factors: Case Study on East Coast of Laizhou Bay, China.

With a shifting climate pattern and enhancement of human activities, coastal areas are exposed to threats of groundwater environmental issues. This work takes the eastern coast of Laizhou Bay as a research area to study the response of a coastal groundwater system to natural and human impacts with a combination of statistical, hydrogeochemical, and fuzzy classification methods. First, the groundwater level dynamics from 1980 to 2017 were analyzed. The average annual groundwater level dropped 13.16 m with a descent rate of 0.379 m/a. The main external environmental factors that affected the groundwater level were extracted, including natural factors (rainfall and temperature), as well as human activities (irrigated area, water-saving irrigated area, sown area of high-water-consumption crops, etc.). Back-propagation artificial neural network was used to model the response of groundwater level to the above driving factors, and sensitivity analysis was conducted to measure the extent of impact of these factors on groundwater level. The results verified that human factors including irrigated area and water-saving irrigated area were the most important influencing factors on groundwater level dynamics, followed by annual precipitation. Further, groundwater samples were collected over the study area to analyze the groundwater hydrogeochemical signatures. With the hydrochemical diagrams and ion ratios, the formation of groundwater, the sources of groundwater components, and the main hydrogeochemical processes controlling the groundwater evolution were discussed to understand the natural background of groundwater environment. The fuzzy C-means clustering method was adopted to classify the groundwater samples into four clusters based on their hydrochemical characteristics to reveal the spatial variation of groundwater quality in the research area. Each cluster was spatially continuous, and there were great differences in groundwater hydrochemical and pollution characteristics between different clusters. The natural and human factors resulted in this difference were discussed based on the natural background of the groundwater environment, and the types and intensity of human activity.

The prioritization of failures within the automotive industry: The two-step failure mode and effect analysis integrated approach

Traditionally, in the automotive industry, the risk posed by failures in manufacturing is based on the conventional process failure mode and effect analysis. The market changes, as well as limited financial resources dedicated to business improvement, induce the need for employment of advanced management tools. The rating of failures is derived from the research using the suggested fuzzy classification method based on the Pareto analysis. It is assumed that the classification criterion should be determined as the product of the overall product choice and the risk priority numbers given by applying the traditional process failure mode and effect analysis. All the uncertainties that exist in the problem under consideration are represented by linguistic expressions that are modeled on the interval type-2 triangular fuzzy numbers. The overall product choice is based on a fuzzy analytical hierarchy process with interval type-2 triangular fuzzy numbers. The execution of management initiatives based on the priority of failures can result in the improvement of the manufacturing process and overall business efficiency. The proposed model is tested using real-life data from a single vehicle manufacturer operating in the Western Balkans and representing a part of a global automotive supply chain.

Comparisons of the prediction results of soil properties based on fuzzy c-means clustering and expert knowledge from laboratory Visible – Near-Infrared reflectance spectroscopy data

Soil organic matter and soil particle composition play extremely important roles in soil fertility, environmental protection, and sustainable agricultural development. Visible – near-infrared reflectance (Vis–NIR) spectroscopy is a rapid, effective, and low-cost analytical method to predict soil properties. In this study, laboratory Vis–NIR spectroscopy data were used to compare the differences among partial least squares regression (PLSR), artificial neural network (ANN) and multivariate adaptive regression splines (MARSplines) based on fuzzy c-means spectral clustering and expert knowledge classification methods for soil prediction. The results showed that (1) the sand content (R2 = 0.69–0.77) had the best prediction, followed by the silt (R2 = 0.56–0.71) and organic matter (R2 = 0.54–0.69) contents, whereas the clay content (R2 = 0.29–0.65) had the poorest prediction, (2) the performance of the models followed the order of PLSR > ANN > MARSplines, and (3) the accuracies of the organic matter and sand contents were higher when applying expert knowledge classification, whereas the prediction of the clay and silt contents was better when applying spectral clustering. However, the overall accuracy of the spectral clustering method was slightly better than that of expert classification. Our findings showed that the spectral cluster-based models produced effective and interpretable prediction results for estimating soil properties. Therefore, this approach should be considered when dealing with large and heterogeneous soil samples.

THE OPTIMIZATION METHOD OF FUZZY AUTOMATIC CLASSIFICATION IN THE PROBLEM OF COMBINING THE ASSESSMENTS OF TRAJECTOR MEASUREMENTS IN THE RADAR SYSTEM

The paper describes the application of the optimization method of fuzzy automatic classification in the problem of combining estimates of trajectory measurements in a radar system. By a radiolocation system the author mean an automated hierarchical technical complex that combines, using communication tools, a set of asynchronously functioning radiolocation tools, as well as central and intermediate points that collect, process and issue trajectory radiolocation information. It must be borne in mind that in conditions of tracking tight groups of air targets, with relatively small intervals and distances, it is not always possible to obtain trajectory information of the required quality. The main reason for this is the difficulty in determining the values of the correlation matrices of errors in estimating the parameters of the state vector of air targets. The task becomes more complicated as the number of intermediate processing points increases when it is brought to the final consumer. The main goal of the article is to increase the accuracy of estimates of trajectory measurements in a radiolocation system. The research is done by means of the mathematical tool of fuzz-set theory, namely, by optimizing fuzzy automatic classification. The article demonstrates that using fuzzy automatic classification under a priori parametrical uncertainty in the law of trajectory measurement errors, when determining weight coefficients, can improve the accuracy of estimates in these conditions up to 30 % compared with methods based on the application of the probabilistic approach. The results obtained allow us to justify the prospects of using optimization methods of fuzzy automatic classification in the tasks of processing trajectory information. In addition, the advantage of the proposed method is its low computational complexity and ease of implementation, which is especially important while maintaining a large number of airborne objects.

A Multilabel Fuzzy Relevance Clustering System for Malware Attack Attribution in the Edge Layer of Cyber-Physical Networks

The rapid increase in the number of malicious programs has made malware forensics a daunting task and caused users’ systems to become in danger. Timely identification of malware characteristics including its origin and the malware sample family would significantly limit the potential damage of malware. This is a more profound risk in Cyber-Physical Systems (CPSs), where a malware attack may cause significant physical damage to the infrastructure. Due to limited on-device available memory and processing power in CPS devices, most of the efforts for protecting CPS networks are focused on the edge layer, where the majority of security mechanisms are deployed. Since the majority of advanced and sophisticated malware programs are combining features from different families, these malicious programs are not similar enough to any existing malware family and easily evade binary classifier detection. Therefore, in this article, we propose a novel multilabel fuzzy clustering system for malware attack attribution. Our system is deployed on the edge layer to provide insight into applicable malware threats to the CPS network. We leverage static analysis by utilizing Opcode frequencies as the feature space to classify malware families. We observed that a multilabel classifier does not classify a part of samples. We named this problem the instance coverage problem. To overcome this problem, we developed an ensemble-based multilabel fuzzy classification method to suggest the relevance of a malware instance to the stricken families. This classifier identified samples of VirusShare, RansomwareTracker, and BIG2015 with an accuracy of 94.66%, 94.26%, and 97.56%, respectively.

MEASURING SIMILARITY BETWEEN BIOMEDICAL DATA BY USING FURIA ENSEMBLES RULE-BASED CLASSIFICATION

Similarity measures are essential to solve many pattern recognition problems such as classification, clustering, and retrieval problems. Various distance/similarity measures that is applicable to compare two probability density functions. Data comparison is widely used field in our society nowadays, and it is a very import part. To compare two objects is a common task that people from all walks of life would do. People always want or need to find the similarity between two different objects or the difference between two similar objects. Some different data may share some similarity in some given attribute(s). To compare with two datasets based on attributes by classification algorithms, for the attributes, we need to select them out by rules and the system is known as rule-based reasoning system or expert system which classifies a given test instance into a particular outcome from the learned rules. The test instance carries multiple attributes, which are usually the values of diagnostic tests. In this article, we are proposing a classifier ensemble-based method for comparison of two datasets or one dataset with different features. The ensemble data mining learning methods are applied for rule generation, and a multi-criterion evaluation approach is used for selecting reliable rules over the results of the ensemble methods. The efficacy of the proposed methodology is illustrated via an example of two disease datasets; it is a combined dataset with the same instances and normal attributes but the class in strictly speaking. This article introduces a fuzzy rule-based classification method called FURIA, to get the relationship between two datasets by FURIA rules. And find the similarity between these two datasets.

Detection and segmentation of cancer regions in cervical images using fuzzy logic and adaptive neuro fuzzy inference system classification method

AbstractCervical cancer is one of the most severe death causing cancers in developing countries. The mortality rates of the cervical cancer are high in developing countries due to their unawareness about such cancer. This article proposes an efficient Fuzzy logic and adaptive neuro fuzzy inference system (ANFIS) classification method based cancer region detection and segmentation in cervical images. The thick and thin edges are detected using fuzzy logic and these detected edges are fused pixel level image fusion technique. In this article, fuzzy rules are constructed for detecting edges for cancer region detection. Then, Gabor transform is applied on the fused cervical image for the transformation of pixels. The texture features are extracted from the Gabor transformed image and these features are classified using ANFIS classification approach. Further, morphological operations are used to segment the cancer regions in classified abnormal cervical image. The average classification rate of the proposed cervical cancer detection system is about 98.8%. The proposed cervical cancer segmentation methodology stated in this article achieves 98.1% of sensitivity, 99.4% of specificity, and 99.3% of accuracy.

Risk early warning method for distribution system with sources-networks-loads-vehicles based on fuzzy C-mean clustering

A risk probability classification model of distribution system with source-network-load-vehicle is established based on fuzzy C-means clustering and fuzzy mathematics in this paper. Monte Carlo simulation method is used to simulate various scenarios of operation and failure of lines, transformers, generators in distribution systems. The data needed for probability classification of voltage fluctuation, line overload, power loss and load loss of distribution system are obtained. For the severity of the accident, the membership functions of voltage fluctuation, line overload, power loss and load loss are constructed by using fuzzy distribution functions based on fuzzy classification method, and the corresponding risk severity classification model is constructed. Mamdani fuzzy reasoning is used to synthesize the risk probability and risk severity for determining the risk level. A risk early warning method for distribution system based on fuzzy C-means clustering is proposed. Taking IEEE-33, IEEE-39 and IEEE-118 systems as studying examples, the risk levels of voltage fluctuation, line overload, power loss and load loss are determined with the cases of normal operation and anticipated fault in distribution system.

Landcover classification of satellite images based on an adaptive interval fuzzy c-means algorithm coupled with spatial information

ABSTRACTLandcover classifications have large uncertainty related to the heterogeneity of similar objects and complex spatial correlations in satellite images, making it difficult to obtain ideal classification results using traditional classification methods. Therefore, to address the uncertainty in landcover classifications based on remotely sensed information, we propose a novel fuzzy c-means algorithm, which integrates adaptive interval-valued modelling and spatial information. It dynamically adjusts the interval width according to the fuzzy degree of the target membership without pre-setting any parameters, controls the fuzziness of the target, and mines the inherent distribution of the data. Furthermore, reliability-based spatial correlation modelling is used to describe the spatial relationship of the target and to improve both robustness and accuracy of the algorithm. Experimental data consisting of SPOT5 (10-m spatial resolution) or Thematic Mapper (30-m spatial resolution) satellite data for three case study areas in China are used to test this algorithm. Compared with other state-of-the-art fuzzy classification methods, our algorithm markedly improved the ground-object separability. Moreover, it balanced improvement of pixel separability and suppression of heterogeneity of intra-class objects, producing more compact landcover areas and clearer boundaries between classes.

Fuzzy Classification Methods Based Diagnosis of Parkinson's disease from Speech Test Cases.

Together with the Alzheimer's disease, Parkinson's disease is considered as one of the two serious known neurodegenerative diseases. Physicians find it hard to predict whether a given patient has already developed or is expected to develop the Parkinson's disease in the future. To overcome this difficulty, it is possible to develop a computing model, which analyzes the data related to a given patient and predicts with acceptable accuracy when he/she is anticipated to develop the Parkinson's disease. This paper contributes an attractive prediction framework based on some machine learning approaches for distinguishing people with Parkinsonism from healthy individuals. Several fuzzy classifiers such as Inductive Fuzzy Classifier, Fuzzy Rough Classifier and two types of neuro-fuzzy classifiers have been employed. The fuzzy classifiers utilized in this study have been tested using the "Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set" of 40 subjects available on the UCI repository. The results achieved show that FURIA, MLP- Bagging - SGD, genfis2 and scg1 performed the best among the fuzzy rough, WEKA, adaptive neuro-fuzzy and neuro-fuzzy classifiers, respectively. The worst performance belongs to nearest neighborhood, IBK, genfis3 and scg3 among the formerly mentioned classifiers. The results reported in this paper are better in comparison to the results reported in Sakar et al., where the same dataset was used, with utilization of different classifiers. This demonstrates the applicability and effectiveness of the fuzzy classifiers used in this study as compared to the non-fuzzy classifiers used by Sakar et al.

Identifying traffic of same keys in cryptographic communications using fuzzy decision criteria and bit-plane measures

The use of same keys for different messages is not safe in cryptography to secure cryptographic communications even if encryption algorithm is strong enough and possesses good cryptographic properties. Such communications can be analyzed to find meaningful information by cryptanalysts or adversaries. Use of same keys may happens if keys are not managed in cipher systems appropriately by customers. One should evaluate ciphers thoroughly and assure for non-repetition of keys prior to its usage for secure communications. The paper presents a methodology to identify and segregate traffic of cryptographic communications of images encrypted with same keys by exploiting bit-plane image characteristics and applying Fuzzy decision criteria. Results presented in the paper shows that the proposed Fuzzy classification method is able to identify images encrypted with same keys successfully and it seems very useful to consider for various pattern recognition and image analysis problems.

A Preferential Interval-Valued Fuzzy C-Means Algorithm for Remotely Sensed Imagery Classification

Remotely sensed imagery classification have a large amount of uncertainty related to the intraclass heterogeneity and the interclass ambiguity of objects. Fuzzy set theory can address the uncertainty effectively, while interval-valued model can improve the separability of samples. Therefore, we propose a novel interval-valued fuzzy c-means algorithm, which integrates the interval-valued model and preferential adaptive method. It preferentially adjusts the interval width according to MSE (mean-square-error) and boundary factor for determining the optimal set of features for the data. In this paper, it is proved that the method can make the intraclass MSE and boundary factor always proportional to the separability of objects, so that it can dynamically adjust the interval-valued separability by controlling the interval width. Experimental data consisting of SPOT5 (10-m spatial resolution) satellite data for three case study areas in China are used to test this algorithm. Compared with other state-of-the-art fuzzy classification methods, our algorithm demonstrates the markedly improved overall accuracy and Kappa coefficients.

On Wavelet Based Enhancing Possibilities of Fuzzy Classification Methods

On Wavelet Based Enhancing Possibilities of Fuzzy Classification Methods

Genders prediction from indoor customer paths by Levenshtein-based fuzzy kNN

Companies have an advantage over the competitors if they can present customized offers to customers. Demographic information of customers is critical for the companies to develop individualized systems. While current technologies make it easy to collect customer data, the main problem is that demographic data are usually incomplete. Hence, several methods are developed to predict unknown genders of customers. In this study, customer genders are predicted from their paths in a shopping mall using fuzzy sets. A fuzzy classification method based on Levenshtein distance is developed for string data that refer to the indoor customer paths. Although there are several ways to predict the gender, no study has focused on path-based gender classification. The originality of the research is to classify customer data into the gender classes using indoor paths.

Analytic hierarchy process-fuzzy sorting: An analytic hierarchy process–based method for fuzzy classification in sorting problems

Analytic Hierarchy Process (AHP) is a well-founded and popular method in the Multi-Criteria Decision Analysis (MCDA) field. AHPSort, a recently introduced sorting variant, uses crisp class-assignment of alternatives. This can sometimes be misleading, especially for alternatives near the border of two classes. This paper aims at making the class assignment process in AHPSort more flexible by using fuzzy sets theory, which facilitates soft transitions between classes and provides additional information about the membership of alternatives in each class that can be used to fine-tune actions beyond the crisp sorting process. This essentially complements the ordinal information of its crisp variant with cardinal information as to the degree of membership of an alternative to each class. The applicability of the proposed approach is illustrated in a case study that regards the classification of London boroughs according to their safety levels.

Research on real-time network\xa0data mining technology for big data

The data distribution in big data environment is very different, and it is difficult to mine the data because of the strong interference of redundant data and frequent items. The traditional data mining algorithm uses closed frequent item feature extraction algorithm. Due to the uneven distribution of web data in big data environment, the mining accuracy of closed frequent item feature extraction is not high. A real-time web data mining model is proposed based on high order spectral feature fuzzy neural network learning in big data environment. The transmission channel model and statistical time series model of web data under big data environment are constructed, and the redundant information flow is removed and reprocessed, and the web data after redundant filtering is analyzed by fusion clustering. The feature of high order spectrum is extracted, and the optimal mining of web data is realized by using fuzzy neural network learning classification method. The simulation results show that this web data mining method has good timeliness, high mining precision, and superior performance.