Cluster-based Classification Research Articles

Introjective and anaclitic psychopathology in self-narratives: Idiographic assessment with Hermans’ Self-Confrontation Method

Within a hybrid framework of attachment and depression theory, we investigated whether introjective and anaclitic vulnerabilities can be detected in a person’s self-narrative as elicited with the Self-Confrontation Method (SCM). One hundred participants held a thorough self-investigation with one of five trainees, in which every person formulated ‘valuations’ (i.e., short sentences about personally relevant concerns) and, subsequently, rated to what degree certain feelings were evoked by every separate text. We extracted several measures from these idiographic data, including scales representing the prominence of certain themes according to the SCM typology (e.g., ‘unfulfilled longing and loss’, ‘anger and opposition’, and ‘powerlessness and isolation’). By analyzing the correlational patterns of the aggregated SCM-based measures and the questionnaire-based measures about attachment orientation and depressive personality vulnerability, we uncovered meaningful relationships. The results of a canonical correlational analysis indicated that an intensified sense of ‘powerlessness and isolation’ is a sign of a general psychopathological vulnerability (related to depression), ‘anger and opposition’ is associated with introjective features (distrust in others and need for control), and ‘unfulfilled longing and loss’ is associated with anaclitic features (pleasing and dependency). In an exploratory qualitative study, we used a cluster-based classification into attachment groups for the exhaustive screening of the content of negative valuations of (a selection of) insecurely attached persons (n = 15). This hermeneutic approach disclosed characteristic themes for each of the preoccupied, dismissive-avoidant and fearful-avoidant attachment styles which are discussed in great detail.

Data Stream Classification by Dynamic Incremental Semi-Supervised Fuzzy Clustering

A data stream classification method called DISSFCM (Dynamic Incremental Semi-Supervised FCM) is presented, which is based on an incremental semi-supervised fuzzy clustering algorithm. The method assumes that partially labeled data belonging to different classes are continuously available during time in form of chunks. Each chunk is processed by semi-supervised fuzzy clustering leading to a cluster-based classification model. The proposed DISSFCM is capable of dynamically adapting the number of clusters to data streams, by splitting low-quality clusters so as to improve classification quality. Experimental results on both synthetic and real-world data show the effectiveness of the proposed method in data stream classification.

Sequence and Structure Properties Uncover the Natural Classification of Protein Complexes Formed by Intrinsically Disordered Proteins via Mutual Synergistic Folding.

Intrinsically disordered proteins mediate crucial biological functions through their interactions with other proteins. Mutual synergistic folding (MSF) occurs when all interacting proteins are disordered, folding into a stable structure in the course of the complex formation. In these cases, the folding and binding processes occur in parallel, lending the resulting structures uniquely heterogeneous features. Currently there are no dedicated classification approaches that take into account the particular biological and biophysical properties of MSF complexes. Here, we present a scalable clustering-based classification scheme, built on redundancy-filtered features that describe the sequence and structure properties of the complexes and the role of the interaction, which is directly responsible for structure formation. Using this approach, we define six major types of MSF complexes, corresponding to biologically meaningful groups. Hence, the presented method also shows that differences in binding strength, subcellular localization, and regulation are encoded in the sequence and structural properties of proteins. While current protein structure classification methods can also handle complex structures, we show that the developed scheme is fundamentally different, and since it takes into account defining features of MSF complexes, it serves as a better representation of structures arising through this specific interaction mode.

Robust hierarchical clustering for novelty identification in sensor networks: With applications to industrial systems

The paper proposes a new, robust cluster-based classification technique for Novelty Identification in sensor networks that possess a high degree of correlation among data streams. During normal operation, a uniform cluster across objects (sensors) is generated that indicates the absence of novelties. Conversely, in presence of novelty, the associated sensor is clustered distinctly from the remaining sensors, thereby isolating the data stream which exhibits the novelty. It is shown how small perturbations (stemming from noise, for instance) can affect the performance of traditional clustering methods, and that the proposed variant exhibits a robustness to such influences. Moreover, the proposed method is compared with a recently reported technique, and shown that it performs 365% faster computationally. To provide an application case study, the technique is used to identify emerging fault modes in a sensor network on a sub-15MW industrial gas turbine in presence of other abrupt, but normal changes that visually might otherwise be interpreted as malfunctions.

Knocking on Heaven’s Door: User preferences on digital cultural distribution

This paper explores the social, demographic and attitudinal basis of consumer support of a Copyright Compensation System (CCS), which, for a small monthly fee would legalise currently infringing online social practices such as private copying from illegal sources and online sharing of copyrighted works. We do this by first identifying how different online and offline, legal and illegal, free and paying content acquisition channels are used in the media market using a cluster-based classification of respondents. Second, we assess the effect of cultural consumption on the support for a shift from the status quo towards alternative, CCS-based forms of digital cultural content distribution. Finally, we link these two analyses to identify the factors that drive the dynamics of change in digital cultural consumption habits. Our study shows significant support to a CCS compared to the status quo by both occasional and frequent buyers of cultural goods, despite the widespread adoption of legal free and paying online services by consumers. The nature of these preferences are also explored with the inclusion of consumer preference intensities regarding certain CCS attributes. Our results have relevant policy implications, for they outline CCS as a reform option. In particular, they point evidence-based copyright reform away from its current direction in the EU of stronger enforcement measures, additional exclusive rights, and increased liability and duties of care for online platforms. This work shows that CCS may be an apt policy tool to hinder piracy and potentially increase right holder revenues, while respecting fundamental rights and promoting technological development.

Wearable System for Biosignal Acquisition and Monitoring Based on Reconfigurable Technologies.

Wearable monitoring devices are now a usual commodity in the market, especially for the monitoring of sports and physical activity. However, specialized wearable devices remain an open field for high-risk professionals, such as military personnel, fire and rescue, law enforcement, etc. In this work, a prototype wearable instrument, based on reconfigurable technologies and capable of monitoring electrocardiogram, oxygen saturation, and motion, is presented. This reconfigurable device allows a wide range of applications in conjunction with mobile devices. As a proof-of-concept, the reconfigurable instrument was been integrated into ad hoc glasses, in order to illustrate the non-invasive monitoring of the user. The performance of the presented prototype was validated against a commercial pulse oximeter, while several alternatives for QRS-complex detection were tested. For this type of scenario, clustering-based classification was found to be a very robust option.

Cluster-Based Differentiation of the Socioeconomic Development Level for Municipal Units in the Steppe Regions of European Russia

The article provides insight into the features of economic development in the steppe regions of European Russia. Russia’s steppe zone is regarded not only as a natural and geographical formation, but also as a socioeconomic space with specific problems. The paper presents the results of an analysis of socioeconomic development indicators for municipal units in the steppe regions of European Russia. Clustering-based classification was performed for the federal subjects forming the steppe space. The classification revealed the asymmetry of the economic potential common to the steppe regions of European Russia, which is a decrease in the level of economic development from west to east. The analysis identified regions of advanced development of municipalities: Krasnodar krai, Belgorod oblast, and Samara oblast, and depressed regions: the Republic of Kalmykia, Orenburg oblast, Saratov oblast, and Volgograd oblast. The position of the depressed regions limits the opportunities for integration with the Republic of Kazakhstan and development of cross-border cooperation in analogy with Euroregions. The work differentiates the municipal units based on attracted investments and industrial and agricultural production. The unevenness of economic development in the steppe regions of the Russian Federation manifests itself in polarization of economic indicators of the leading municipalities, the growth of which is primarily determined by natural-resource and spatial factors and sociodemographic reasons. The effect of space shrinkage of socioeconomic development of municipal units in the steppe zone is observed. This is reflected in the rural depopulation, which covers a considerable area, and decline in practical use of the territory. The effect of mutual influence has been revealed, which means that underperforming municipal units found at the periphery of growing regions are primarily border with depressed neighbors.

Classification of patients with bipolar disorder using k-means clustering.

IntroductionBipolar disorder (BD) is a heterogeneous disorder needing personalized and shared decisions. We aimed to empirically develop a cluster-based classification that allocates patients according to their severity for helping clinicians in these processes.MethodsNaturalistic, cross-sectional, multicenter study. We included 224 subjects with BD (DSM-IV-TR) under outpatient treatment from 4 sites in Spain. We obtained information on socio-demography, clinical course, psychopathology, cognition, functioning, vital signs, anthropometry and lab analysis. Statistical analysis: k-means clustering, comparisons of between-group variables, and expert criteria.Results and discussionWe obtained 12 profilers from 5 life domains that classified patients in five clusters. The profilers were: Number of hospitalizations and of suicide attempts, comorbid personality disorder, body mass index, metabolic syndrome, the number of comorbid physical illnesses, cognitive functioning, being permanently disabled due to BD, global and leisure time functioning, and patients’ perception of their functioning and mental health. We obtained preliminary evidence on the construct validity of the classification: (1) all the profilers behaved correctly, significantly increasing in severity as the severity of the clusters increased, and (2) more severe clusters needed more complex pharmacological treatment.ConclusionsWe propose a new, easy-to-use, cluster-based severity classification for BD that may help clinicians in the processes of personalized medicine and shared decision-making.

Software Fault Prediction Using Filtering Feature Selection in Cluster-Based Classification

The high accuracy of software fault prediction can help testing effort and improving software quality. Previous researchers had proposed the combination of Entropy-Based Discretization (EBD) and Cluster-Based Classification (CBC). However, the irrelevant and redundant features in software fault dataset tend to decrease the prediction accuracy value. This study proposes improvement of CBC outcomes by integrating filtering feature selection methods. Filtering feature selection methods that will be integrated with CBC i.e. Information Gain (IG), Gain Ratio (GR), and One-R (OR). Based on the research using 2 datasets NASA public MDP (i.e. PC2 and PC3), the result shows that the combination of CBC and IG yields the best average accuracy value compared to GR and OR. It generates 67.52% average of probability detection (pd) and 37.42% average of probability false alarm (pf). While CBC without feature selection yields 65.38% average pd and 49.95% average pf. It can be concluded that IG can improve CBC outcomes by increasing 2.14% average pd and reducing 12.53% average pf

A competitive model of popularity prediction using correlation matrix

With the rapid development of network, big data has become an important research field for many areas such as data mining, machine learning, information diffusion, the internet of things, and social networks. The multimedia information spreads faster since the rise of social network where people can create and share images, video and audio contents. More and more people share and comment on the web through the mobile terminal to express their mends. Online content captures online behavior of users who communicate or interact on a diversity of issues and topics. How to predict the popularity of the online content happened recently is a hot topic and lots of people are trying to find out the law of information diffusion hidden in it. However, many models assume that information spreads with no external interference in social networks. The research on competitive diffusion is still at the primary stage. The main contribution of this paper is to solve the problem that there are few or no work for popularity prediction based on multi-information, and propose a model based on competitive matrix with a cluster-based news classification approach. The goal of this paper is to accurately estimate the popularity of a given viral topic at final based on the observation of its historical characteristics. And this model is mainly based on the competitive matrix and gradient descent method. Also, the capability of this method provides a better performance in the popularity prediction according to an empirical study.

Perbaikan Prediksi Kesalahan Perangkat Lunak Menggunakan Seleksi Fitur dan Cluster-Based Classification

High balance value of software fault prediction can help in conducting test effort, saving test costs, saving test resources, and improving software quality. Balance values in software fault prediction need to be considered, as in most cases, the class distribution of true and false in the software fault data set tends to be unbalanced. The balance value is obtained from trade-off between probability detection (pd) and probability false alarm (pf). Previous researchers had proposed Cluster-Based Classification (CBC) method which was integrated with Entropy-Based Discretization (EBD). However, predictive models with irrelevant and redundant features in data sets can decrease balance value. This study proposes improvement of software fault prediction outcomes on CBC by integrating feature selection methods. Some feature selection methods are integrated with CBC, i.e. Information Gain (IG), Gain Ration (GR), One-R (OR), Relief-F (RFF), and Symmetric Uncertainty (SU). The result shows that combination of CBC with IG gives best average balance value, compared to other feature selection methods used in this research. Using five NASA public MDP data sets, the combination of IG and CBC generates 63.91% average of balance, while CBC method without feature selection produce 54.79% average of balance. It shows that IG can increase CBC balance average by 9.12%.

Learning cluster-based classification systems with ant colony optimization algorithms

Classification is a data mining task the goal of which is to learn a model, from a training dataset, that can predict the class of a new data instance, while clustering aims to discover natural instance-groupings within a given dataset. Learning cluster-based classification systems involves partitioning a training set into data subsets (clusters) and building a local classification model for each data cluster. The class of a new instance is predicted by first assigning the instance to its nearest cluster and then using that cluster’s local classification model to predict the instance’s class. In this paper, we present an ant colony optimization (ACO) approach to building cluster-based classification systems. Our ACO approach optimizes the number of clusters, the positioning of the clusters, and the choice of classification algorithm to use as the local classifier for each cluster. We also present an ensemble approach that allows the system to decide on the class of a given instance by considering the predictions of all local classifiers, employing a weighted voting mechanism based on the fuzzy degree of membership in each cluster. Our experimental evaluation employs five widely used classification algorithms: naive Bayes, nearest neighbour, Ripper, C4.5, and support vector machines, and results are reported on a suite of 54 popular UCI benchmark datasets.

Anomaly-based network IDS false alarm filter using cluster-based alarm classification approach

Anomaly-based network IDS false alarm filter using cluster-based alarm classification approach

Data mining methods for knowledge discovery in multi-objective optimization: Part B - New developments and applications

The first part of this paper served as a comprehensive survey of data mining methods that have been used to extract knowledge from solutions generated during multi-objective optimization. The current paper addresses three major shortcomings of existing methods, namely, lack of interactiveness in the objective space, inability to handle discrete variables and inability to generate explicit knowledge. Four data mining methods are developed that can discover knowledge in the decision space and visualize it in the objective space. These methods are (i) sequential pattern mining, (ii) clustering-based classification trees, (iii) hybrid learning, and (iv) flexible pattern mining. Each method uses a unique learning strategy to generate explicit knowledge in the form of patterns, decision rules and unsupervised rules. The methods are also capable of taking the decision maker’s preferences into account to generate knowledge unique to preferred regions of the objective space. Three realistic production systems involving different types of discrete variables are chosen as application studies. A multi-objective optimization problem is formulated for each system and solved using NSGA-II to generate the optimization datasets. Next, all four methods are applied to each dataset. In each application, the methods discover similar knowledge for specified regions of the objective space. Overall, the unsupervised rules generated by flexible pattern mining are found to be the most consistent, whereas the supervised rules from classification trees are the most sensitive to user-preferences.

Clustering-based classification of road traffic accidents using hierarchical clustering and artificial neural networks

Artificial neural networks (ANNs) have been widely used in predicting the severity of road traffic crashes. All available information about previously occurred accidents is typically used for building a single prediction model (i.e., classifier). Too little attention has been paid to the differences between these accidents, leading, in most cases, to build less accurate predictors. Hierarchical clustering is a well-known clustering method that seeks to group data by creating a hierarchy of clusters. Using hierarchical clustering and ANNs, a clustering-based classification approach for predicting the injury severity of road traffic accidents was proposed. About 6000 road accidents occurred over a six-year period from 2008 to 2013 in Abu Dhabi were used throughout this study. In order to reduce the amount of variation in data, hierarchical clustering was applied on the data set to organize it into six different forms, each with different number of clusters (i.e., clusters from 1 to 6). Two ANN models were subsequently built for each cluster of accidents in each generated form. The first model was built and validated using all accidents (training set), whereas only 66% of the accidents were used to build the second model, and the remaining 34% were used to test it (percentage split). Finally, the weighted average accuracy was computed for each type of models in each from of data. The results show that when testing the models using the training set, clustering prior to classification achieves (11%–16%) more accuracy than without using clustering, while the percentage split achieves (2%–5%) more accuracy. The results also suggest that partitioning the accidents into six clusters achieves the best accuracy if both types of models are taken into account.

On Using a Clustering Approach for Global Climate Classification

Abstract Classifying the land surface into climate types provides means of diagnosing relations between Earth’s physical and biological systems and the climate. Global climate classifications are also used to visualize climate change. Clustering climate datasets provides a natural approach to climate classification, but the rule-based Köppen–Geiger classification (KGC) is the one most widely used. Here, a comprehensive approach to the clustering-based classification of climates is presented. Local climate is defined as a multivariate time series of mean monthly climatic variables and the authors propose to use dynamic time warping (DTW) as a measure of dissimilarity between local climates. Also discussed are the choice of climatic variables, the importance of their proper normalization, and the advantage of using distance-based clustering algorithms. Using the WorldClim global climate dataset and different combinations of clustering parameters, 32 different clustering-based classifications are calculated. These classifications are compared between themselves and to the KGC using the information-theoretic V measure. It is found that the best classifications are obtained using three climate variables (temperature, precipitation, and temperature range), a data normalization that takes into account the skewed distribution of precipitation values, and the partitioning around medoids clustering algorithm. Two such classifications are compared in detail between each other and to the KGC. About half of the climate types found by clustering can be matched to the familiar KGC classes, but the rest differ in their climatic character and spatial distribution. Finally, it is demonstrated that clustering-based classification results in climate types that are internally more homogeneous and externally more distinct than climate types in the KGC.

Knocking on Heaven's Door - User Preferences on Digital Cultural Distribution

This paper explores the social, demographic and attitudinal basis of consumer support to a change from the status quo in digital cultural distribution. First we identify how different online and offline, legal and illegal, free and paying content acquisition channels are used in the Dutch media market using a cluster-based classification of respondents according to their cultural consumption. Second, we assess the effect of cultural consumption on the support to the introduction of a Copyright Compensation System (CCS), which, for a small monthly fee would legalize currently infringing online social practices such as private copying from illegal sources and online sharing of copyrighted works. Finally, we link these two analyses to identify the factors that drive the dynamics of change in digital cultural consumption habits.

Multi-period classification: learning sequent classes from temporal domains

As the majority of real-world decisions change over time, extending traditional classifiers to deal with the problem of classifying an attribute of interest across different time periods becomes increasingly important. Tackling this problem, referred to as multi-period classification, is critical to answer real-world tasks, such as the prediction of upcoming healthcare needs or administrative planning tasks. In this context, although existing research provides principles for learning single labels from complex data domains, less attention has been given to the problem of learning sequences of classes (symbolic time series). This work motivates the need for multi-period classifiers, and proposes a method, cluster-based multi-period classification (CMPC), that preserves local dependencies across the periods under classification. Evaluation against real-world datasets provides evidence of the relevance of multi-period classifiers, and shows the superior performance of the CMPC method against peer methods adapted from long-term prediction for multi-period tasks with a high number of periods.

CEAI: CCM-based email authorship identification model

In this paper we present a model for email authorship identification (EAI) by employing a Cluster-based Classification (CCM) technique. Traditionally, stylometric features have been successfully employed in various authorship analysis tasks; we extend the traditional feature set to include some more interesting and effective features for email authorship identification (e.g., the last punctuation mark used in an email, the tendency of an author to use capitalization at the start of an email, or the punctuation after a greeting or farewell). We also included Info Gain feature selection based content features. It is observed that the use of such features in the authorship identification process has a positive impact on the accuracy of the authorship identification task. We performed experiments to justify our arguments and compared the results with other base line models. Experimental results reveal that the proposed CCM-based email authorship identification model, along with the proposed feature set, outperforms the state-of-the-art support vector machine (SVM)-based models, as well as the models proposed by Iqbal et al. (2010, 2013) [1,2]. The proposed model attains an accuracy rate of 94% for 10 authors, 89% for 25 authors, and 81% for 50 authors, respectively on Enron dataset, while 89.5% accuracy has been achieved on authors’ constructed real email dataset. The results on Enron dataset have been achieved on quite a large number of authors as compared to the models proposed by Iqbal et al. [1,2].

Remote chlorophyll-a estimates for inland waters based on a cluster-based classification

Accurate estimates of chlorophyll-a concentration (Chl-a) from remotely sensed data for inland waters are challenging due to their optical complexity. In this study, a framework of Chl-a estimation is established for optically complex inland waters based on combination of water optical classification and two semi-empirical algorithms. Three spectrally distinct water types (Type I to Type III) are first identified using a clustering method performed on remote sensing reflectance (Rrs) from datasets containing 231 samples from Lake Taihu, Lake Chaohu, Lake Dianchi, and Three Gorges Reservoir. The classification criteria for each optical water type are subsequently defined for MERIS images based on the spectral characteristics of the three water types. The criteria cluster every Rrs spectrum into one of the three water types by comparing the values from band 7 (central band: 665nm), band 8 (central band: 681.25nm), and band 9 (central band: 708.75nm) of MERIS images. Based on the water classification, the type-specific three-band algorithms (TBA) and type-specific advanced three-band algorithm (ATBA) are developed for each water type using the same datasets. By pre-classifying, errors are decreased for the two algorithms, with the mean absolute percent error (MAPE) of TBA decreasing from 36.5% to 23% for the calibration datasets, and from 40% to 28% for ATBA. The accuracy of the two algorithms for validation data indicates that optical classification eliminates the need to adjust the optimal locations of the three bands or to re-parameterize to estimate Chl-a for other waters. The classification criteria and the type-specific ATBA are additionally validated by two MERIS images. The framework of first classifying optical water types based on reflectance characteristics and subsequently developing type-specific algorithms for different water types is a valid scheme for reducing errors in Chl-a estimation for optically complex inland waters.