Search

By the end of 2020, over 16,300 Massive Open Online Courses (MOOCs) from 950 universities worldwide had enrolled over 180 million students. Interest in MOOCs has been matched by significant research on the topic, including a considerable number of reviews. This study uses Machine Learning techniques and human expert supervision to generate a comprehensive systematic literature mapping review that overcomes some limitations of the traditional ones and provides a broader overview of the content and main topics studied in the specialized literature devoted to MOOCs. The sample consisted of 6320 publications automatically classified within six research topics, denominated by human experts: institutional approach, pedagogical approach, evaluation, analytics, participation, and educational resources. The content analysis of the topics identified was conducted using visual network analysis, which supported the identification of different thematic sub-clusters and endorsed the classification. Results from the review show that the lowest production of MOOC papers is within the topics of the pedagogical approach and educational resources. In contrast, participation and evaluation are the most frequent ones. In addition, the most cited papers are on the topics of analytics and resources, being the pedagogical approach and the institutional approach the less cited. This highlights the need for more MOOC research from a pedagogical perspective and calls upon the presence of educators. [ABSTRACT FROM AUTHOR]

Shale gas reservoirs are contributing a major role in overall hydrocarbon production, especially in the United States, and due to the intense development of such reservoirs, it is a must thing to learn the productive methods for modeling production and performance evaluation. Consequently, one of the most adopted techniques these days for the sake of production performance analysis is the utilization of artificial intelligence (AI) and machine learning (ML). Hydrocarbon exploration and production is a continuous process that brings a lot of data from sub-surface as well as from the surface facilities. Availability of such a huge data set that keeps on increasing over time enhances the computational capabilities and performance accuracy through AI and ML applications using a data-driven approach. The ML approach can be utilized through supervised and unsupervised methods in addition to artificial neural networks (ANN). Other ML approaches include random forest (RF), support vector machine (SVM), boosting technique, clustering methods, and artificial network-based architecture, etc. In this paper, a systematic literature review is presented focused on the AI and ML applications for the shale gas production performance evaluation and their modeling. [ABSTRACT FROM AUTHOR]

One of the significant challenges in the sports industry is identifying the factors influencing match results and their respective weightage. For appropriate recommendations to the team management and the team players, there is a need to predict the match and quantify the important factors for which prediction models need to be developed. The second thing required is identifying talented and emerging players and performing an associative analysis of the important factors to the match-winning outcome. This paper formulates a hybrid machine learning-clustering-associative rules model. This paper also implements the framework for cricket matches, one of the most popular sports globally watched by billions around the world. We predict the match outcome for One day Internationals (ODIs) and Twenty 20 s (T20s) (two formats of Cricket representing fifty over and twenty over versions respectively) adopting state-of-the-art machine learning algorithms, Random Forest, Gradient Boosting, and Deep neural networks. The variable importance is computed using machine-learning techniques and further statistically validated through the regression model. The emerging talented players are identified by clustering. Association rules are generated for determining the best possible winning outcome. The results show that environmental conditions are equally crucial for determining a match result, as are internal quantitative factors. The model is thus helpful for both team management and for players to improve their winning strategy and also for discovering emerging players to form an unbeatable team. [ABSTRACT FROM AUTHOR]

The circular economy and its various recirculation loops have become a major study subject over recent years, particularly in the field of agriculture, which is a significant source of waste production. There have been several studies focused on transforming agricultural lignocellulosic waste with "sustainable" processes: economically viable, socially accepted, and environmentally friendly. Thanks to "life cycle thinking", it is possible to assess these potential environmental impacts. However, these environmental analyses generally require a massive volume of specific data, the collection of which can be time-consuming and tedious, or impossible to practice. On the other hand, scientific articles describing the processes for the valorization of agricultural by-products are intriguing but rarely exploited sources of data. In this paper, a hybridization of data science techniques and environmental analysis was proposed to improve life cycle analysis (LCA) thanks to Machine Learning (ML). ML part of the proposed approach is based on unsupervised learning, which is composed of two methods: dimension reduction using the Multidimensional Scaling and clustering technique using k-means. Composed of five steps and dedicated to researchers or R&D engineers, the approach is oriented towards offering a decision on technologies and processes for waste to energy in the early eco-design step. The case study in the domain of pre-treatment processes for corn stover and rice straw is detailed. The results show that all impacts that concern the chemical pollution of soil and water are found in the same cluster. Other impacts are detected in the same cluster which is related to the land use and the land transformation. In the same vein, two purely mechanical pre-treatments have been identified and grouped by Multidimensional Scaling and k-means. [ABSTRACT FROM AUTHOR]

Tensor factorization has been widely applied in computer vision and machine learning area. Nonnegative Tucker decomposition (NTD) is a popular tensor factorization technique. However, it neglects the geometrical structure of the data space and the available label information of sample data, lowering the data representation performance. To overcome this defect, in this paper, we propose a novel semi-supervised NTD method, named graph regularized discriminative nonnegative Tucker decomposition (GDNTD), which incorporates the graph construction of the data space and the available label information of the sample data into NTD. Specifically, a graph construction is utilized to preserve the geometric structure between data by a graph regularization term. Then, a label matrix is presented for guiding the data representation by a label constraint regularization term. Finally, based on the NTD property of maintaining the internal structure of data, the graph regularizer and the label regularizer are integrated into NTD to generate the proposed method. Thus, GDNTD can extract the part-based representation, preserve the local geometrical structure of the data space, and improve the discriminative ability of the learned model simultaneously, greatly boosting the model's data representation performance. We test the proposed method through a set of evaluations on four image datasets. Experimental results show that the GDNTD method outperforms state-of-the-art approaches, demonstrating its strong potential for data representation. [ABSTRACT FROM AUTHOR]

We revisit the problem of fair clustering, first introduced by Chierichetti et al. (Fair clustering through fairlets, 2017), which requires each protected attribute to have approximately equal representation in every cluster, i.e., a Balance property. Existing solutions to fair clustering are either not scalable or do not achieve an optimal trade-off between clustering objectives and fairness. In this paper, we propose a new notion of fairness which we call τ -ratio fairness, that strictly generalizes the Balance property and enables a fine-grained efficiency vs. fairness trade-off. Furthermore, we show that a simple greedy round-robin-based algorithm achieves this trade-off efficiently. Under a more general setting of multi-valued protected attributes, we rigorously analyze the theoretical properties of the proposed algorithm, the Fair Round-Robin Algorithm for Clustering Over-End ( FRAC OE ). We also propose a heuristic algorithm, Fair Round-Robin Algorithm for Clustering (FRAC), that applies round-robin allocation at each iteration of a vanilla clustering algorithm. Our experimental results suggest that both FRAC and FRAC OE outperform all the state-of-the-art algorithms and work exceptionally well even for a large number of clusters. [ABSTRACT FROM AUTHOR]

Software is playing a growing role in many safety-critical applications, and software systems dependability is a major concern. Predicting faulty modules of software before the testing phase is one method for enhancing software reliability. The ability to predict and identify the faulty modules of software can lower software testing costs. Machine learning algorithms can be used to solve software fault prediction problem. Identifying the faulty modules of software with the maximum accuracy, precision, and performance are the main objectives of this study. A hybrid method combining the autoencoder and the K-means algorithm is utilized in this paper to develop a software fault predictor. The autoencoder algorithm, as a preprocessor, is used to select the effective attributes of the training dataset and consequently to reduce its size. Using an autoencoder with the K-means clustering method results in lower clustering error and time. Tests conducted on the standard NASA PROMIS data sets demonstrate that by removing the inefficient elements from the training data set, the proposed fault predictor has increased accuracy (96%) and precision (93%). The recall criteria provided by the proposed method is about 87%. Also, reducing the time necessary to create the software fault predictor is the other merit of this study. [ABSTRACT FROM AUTHOR]

Density-based clustering has received increasing attention for its ability to handle clusters of arbitrary shapes. However, it still has difficulties in mining clusters of arbitrary densities, especially the clusters of sparse regions in the presence of dense regions. To address this problem, this paper presents a new concept called density decreased chain on the mutual k-NN graph. It starts with the local density center whose density is the highest in the data points connected to this center. Based on the density decreased chain, the concept of the core point is redefined. The density of the core point is close to that of the local density center on the same density decreased chain as the core point. According to its definition, the core point in the data with arbitrary densities can be well identified because the local density centers exist in both sparse and dense regions. Further, intra-cluster density decreased chain is defined to mine subclusters in the core points. After forming the subclusters, the remaining data point is hierarchically assigned to one of these subclusters by the density decreased chains containing this remaining data point. The experiments illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of e & i Elektrotechnik und Informationstechnik is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Machine learning-based predictive modeling is to develop machine learning-based or data-driven models to predict failures before they occur and estimate the remaining useful life or time to failure (TTF) accurately. Accurate TTF estimation plays a vital role in predictive maintenance or PHM (Prognostic and Health Management). Despite the availability of large amounts of data and a variety of powerful data analysis methods, predictive models developed for PHM still fail to provide accurate and precise TTF estimations. This paper addresses this problem by integrating machine learning algorithms such as classification, regression and clustering. A classification system is used to determine the likelihood of component failures such that rough indications of TTF are provided. Clustering and SVM-based local regression are then introduced to refine the time to failure estimations provided by the classification system. The paper illustrates the applicability of the proposed approach through a real world aerospace application with details on data pre-processing requirements. The results demonstrate that the proposed method can reduce uncertainty in estimating time to failure, which in turn helps augment the usefulness of predictive maintenance. [ABSTRACT FROM AUTHOR]

In machine learning, a data set is often viewed as a point set distributed on a manifold. Using Euclidean norms to measure the proximity of this data set reduces the efficiency of learning methods. Also, many algorithms like Laplacian Eigenmaps or spectral clustering that require to measure similarity assume the k-Nearest Neighbors of any point are quite equal to the local neighborhood of the point on the manifold using Euclidean norms. In this paper, we propose a new method that intelligently transforms data on an unknown manifold to an n-sphere by the conformal stereographic projection, which preserves the angles and similarities of data in the original manifold. Therefore similarities represent actual similarities of the data in the original space. Experimental results on various problems, including clustering and manifold learning, show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Speech enhancement has substantial interest in the utilization of speaker identification, video-conference, speech transmission through communication channels, speech-based biometric system, mobile phones, hearing aids, microphones, voice conversion etc. Pattern mining methods have a vital step in the growth of speech enhancement schemes. To design a successful speech enhancement system consideration to the background noise processing is needed. A substantial number of methods from traditional techniques and machine learning have been utilized to process and remove the additive noise from a speech signal. With the advancement of machine learning and deep learning, classification of speech has become more significant. Methods of speech enhancement consist of different stages, such as feature extraction of the input speech signal, feature selection, feature selection followed by classification. Deep learning techniques are also an emerging field in the classification domain, which is discussed in this review. The intention of this paper is to provide a state-of-the-art summary and present approaches for using the widely used machine learning and deep learning methods to detect the challenges along with future research directions of speech enhancement systems. [ABSTRACT FROM AUTHOR]

Although data mining problems require a flat mining table as input, in many real-world applications analysts are interested in finding patterns in a relational database. To this end, new methods and software have been recently developed that automatically add attributes (or features) to a target table of a relational database which summarize information from all other tables. When attributes are automatically constructed by these methods, selecting the important attributes is particularly difficult, because a large number of the attributes are highly correlated. In this setting, attribute selection techniques such as the Least Absolute Shrinkage and Selection Operator (lasso), elastic net, and other machine learning methods tend to under-perform. In this paper, we introduce a novel attribute selection procedure, where after an initial screening step, we cluster the attributes into different groups and apply the group lasso to select both the true attributes groups and then the true attributes. The procedure is particularly suited to high dimensional data sets where the attributes are highly correlated. We test our procedure on several simulated data sets and a real-world data set from a marketing database. The results show that our proposed procedure obtains a higher predictive performance while selecting a much smaller set of attributes when compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization and its graph regularized extensions have received significant attention in machine learning and data mining. However, existing approaches are sensitive to outliers and noise due to the utilization of the squared loss function in measuring the quality of graph regularization and data reconstruction. In this paper, we present a novel robust graph regularized NMF model (RGNMF) to approximate the data matrix for clustering. Our assumption is that there may exist some entries of the data corrupted arbitrarily, but the corruption is sparse. To address this problem, an error matrix is introduced to capture the sparse corruption. With this sparse outlier matrix, a robust factorization result could be obtained since a much cleaned data could be reconstructed. Moreover, the ℓ1-norm function is used to alleviate the influence of unreliable regularization which is incurred by unexpected graphs. That is, the sparse error matrix alleviates the impact of noise and outliers, and the ℓ1-norm function leads to a faithful regularization since the influence of the unreliable regularization errors can be reduced. Thus, RGNMF is robust to unreliable graphs and noisy data. In order to solve the optimization problem of our method, an iterative updating algorithm is proposed and its convergence is also guaranteed theoretically. Experimental results show that the proposed method consistently outperforms many state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Wireless sensor network is effective for data aggregation and transmission in IoT environment. Here, the sensor data often contain a significant amount of noises or redundancy exists, and thus, the data are aggregated to extract meaningful information and reduce the transmission cost. In this paper, a novel data aggregation scheme is proposed based on clustering of the nodes and extreme learning machine (ELM) which efficiently reduces redundant and erroneous data. Mahalanobis distance-based radial basis function is applied to the projection stage of the ELM to reduce the instability of the training process. Kalman filter is also used to filter the data at each sensor node before transmitted to the cluster head. Computer simulation with real datasets shows that the proposed scheme consistently outperforms the existing schemes in terms of clustering accuracy of the data and energy efficiency of WSN. [ABSTRACT FROM AUTHOR]

Recognizing malware before its installation plays a crucial role in keeping an android device safe. In this paper we describe a supervised method that is able to analyse multiple information (e.g. permissions, api calls and network addresses) that can be retrieved through a broad static analysis of android applications. In particular, we propose a novel multi-view machine learning approach to malware detection, which couples knowledge extracted via both clustering and classification. In an assessment, we evaluate the effectiveness of the proposed method using benchmark Android applications and established machine learning metrics. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method for finding interesting behaviour in complex systems based on compression. A new clustering algorithm has been designed and applied specifically for clustering 1D elementary cellular automata behaviour using the prediction by partial matching (PPM) compression scheme, with the results gathered to find interesting behaviours. This new algorithm is then compared with other clustering algorithms in Weka and the new algorithm is found to be more effective at grouping behaviour that is visually similar in output. Using PPM compression, the rate of change of the cross-entropy with respect to time is calculated. These values are used in combination with a clustering algorithm, such as k-means, to create a new set of clusters for cellular automata. An analysis of the data in each cluster is then used to determine if a cluster can be classed as interesting. The clustering algorithm itself was able to find unusual behaviours, such as rules 167 and 181 which have output that is slightly different from all the other Sierpiński Triangle-like patterns, because their apexes are off-centre by one cell. When comparing the new algorithm with other established ones, it was discovered that the new algorithm was more effective in its ability to group interesting and unusual cellular automata behaviours together. [ABSTRACT FROM AUTHOR]

Personalized recommendation systems have emerged as useful tools for recommending the appropriate items to individual users. However, in such situations, some items tend to be consumed by groups of users, such as tourist attractions or television programs. With this purpose in mind, Group Recommender Systems (GRSs) are tailored to help groups of users to find suitable items according to their preferences and needs. In general, these systems often confront the sparsity problem, which negatively affects their efficiency. With the increase in the number of users, items, groups, and ratings in the system. Data becomes too big to be processed efficiently by traditional systems. Thus, there is an increasing need for distributed recommendation approaches able to manage the issues related to Big Data and sparsity problem. In this paper, we propose a distributed group recommendation system, which is designed based on Apache Spark to handle large-scale data. It integrates a novel proposed recommendation method, a dimension reduction technique, with supervised and unsupervised learning for dealing efficiently with the curse of dimensionality problem, detecting the groups of users, and improving the prediction quality. Experimental results on three real-world data sets show that our proposal is significantly better than other competitors. [ABSTRACT FROM AUTHOR]

In the context of computer experiments, metamodels are largely used to represent the output of computer codes. Among these models, Gaussian process regression (kriging) is very efficient see e.g Snelson (Flexible and efficient Gaussian process models for machine learning. ProQuest LLC, Ann Arbor, MI. Thesis (Ph.D.)–University of London, University College London, London, 2008). In high dimension that is with a large number of input variables, but with few observations, the estimation of the parameters with a classical anisotropic kriging can be completely inaccurate. Because there are equal numbers of ranges and input variables the optimization space becomes too large compared to available information. One way to overcome this drawback is to use an isotropic kernel that only depends on one parameter. However this model is too restrictive. The aim of this paper is twofold. Our first objective is to propose a smooth kernel with as few parameters as warranted. We introduce a kernel which is a tensor product of few isotropic kernels built on well-chosen subgroup of variables. The main difficulty is to find the number and the composition of the groups. Our second objective is to propose algorithmic strategies to overcome this difficulty. Four forward strategies are proposed. They all start with the simplest isotropic kernel and stop when the best model according to BIC criterion is found. They all show very good accuracy results on simulation test cases. But one of them is more efficient. Tested on a real data set, our kernel shows very good prediction results. [ABSTRACT FROM AUTHOR]

The global k-means algorithm is an incremental approach to clustering that dynamically adds one cluster center at a time through a deterministic global search procedure from suitable initial positions, and employs k-means to minimize the sum of the intra-cluster variances. However the global k-means algorithm sometimes results singleton clusters and the initial positions sometimes are bad, after a bad initialization, poor local optimal can be easily obtained by k-means algorithm. In this paper, we modified the global k-means algorithm to eliminate the singleton clusters at first, and then we apply MinMax k-means clustering error method to global k-means algorithm to overcome the effect of bad initialization, proposed the global Minmax k-means algorithm. The proposed clustering method is tested on some popular data sets and compared to the k-means algorithm, the global k-means algorithm and the MinMax k-means algorithm. The experiment results show our proposed algorithm outperforms other algorithms mentioned in the paper. [ABSTRACT FROM AUTHOR]

Twin support vector machine (TWSVM) and twin support vector regression (TSVR) are newly emerging efficient machine learning techniques which offer promising solutions for classification and regression challenges respectively. TWSVM is based upon the idea to identify two nonparallel hyperplanes which classify the data points to their respective classes. It requires to solve two small sized quadratic programming problems (QPPs) in lieu of solving single large size QPP in support vector machine (SVM) while TSVR is formulated on the lines of TWSVM and requires to solve two SVM kind problems. Although there has been good research progress on these techniques; there is limited literature on the comparison of different variants of TSVR. Thus, this review presents a rigorous analysis of recent research in TWSVM and TSVR simultaneously mentioning their limitations and advantages. To begin with, we first introduce the basic theory of support vector machine, TWSVM and then focus on the various improvements and applications of TWSVM, and then we introduce TSVR and its various enhancements. Finally, we suggest future research and development prospects. [ABSTRACT FROM AUTHOR]

With the rapid increase of user access, load balancing in cloud data center has become an important factor affecting cluster stability. From the point of view of green scheduling, this paper proposed a virtual machine intelligent scheduling strategy based on machine learning algorithm to achieve load balancing of cloud data center. Firstly, a load forecasting algorithm based on genetic algorithm (SVR_GA), k-means clustering algorithm based on optimized min-max, and adaptive differential evolution algorithm (ESA_DE) to enhance local search ability are proposed to solve the load imbalance problem in cloud data center. The experimental results showed that compared with other classical algorithms, the proposed virtual machine scheduling strategy reduces the number of virtual machine migration by 94.5% and the energy consumption of cloud data center by 49.13%. [ABSTRACT FROM AUTHOR]

This paper presents a teaching learning based algorithm for solving optimization problems. This algorithm is inspired through classroom teaching pattern either students can learn from teachers or from other students. But, the teaching learning based optimization (TLBO) algorithm suffers with premature convergence and lack of tradeoff between local search and global search. Hence, to address the above mentioned shortcomings of TLBO algorithm, a chaotic version of TLBO algorithm is proposed with different chaotic mechanisms. Further, a local search method is also incorporated for effective tradeoff between local and global search and also to improve the quality of solution. The performance of proposed algorithm is evaluated on some benchmark test functions taken from Congress on Evolutionary Computation 2014 (CEC'14). The results revealed that proposed algorithm provides better and effective results to solve benchmark test functions. Moreover, the proposed algorithm is also applied to solve clustering problems. It is found that proposed algorithm gives better clustering results in comparison to other algorithms. [ABSTRACT FROM AUTHOR]

Co-clustering is known to be a very powerful and efficient approach in unsupervised learning because of its ability to partition data based on both the observations and the variables of a given dataset. However, in high-dimensional context co-clustering methods may fail to provide a meaningful result due to the presence of noisy and/or irrelevant features. In this paper, we tackle this issue by proposing a novel co-clustering model which assumes the existence of a noise cluster, that contains all irrelevant features. A variational expectation-maximization-based algorithm is derived for this task, where the automatic variable selection as well as the joint clustering of objects and variables are achieved via a Bayesian framework. Experimental results on synthetic datasets show the efficiency of our model in the context of high-dimensional noisy data. Finally, we highlight the interest of the approach on two real datasets which goal is to study genetic diversity across the world. [ABSTRACT FROM AUTHOR]

Feature embedding is an emerging research area which intends to transform features from the original space into a new space to support effective learning. Many feature embedding algorithms exist, but they often suffer from several major drawbacks, including (1) only handle single feature types, or users have to clearly separate features into different feature views and supply such information for feature embedding learning; (2) designed for either supervised or unsupervised learning tasks, but not for both; and (3) feature embedding for new out-of-training samples have to be obtained through a retraining phase, therefore unsuitable for online learning tasks. In this paper, we propose a generalized feature embedding algorithm, GEL, for both supervised, unsupervised, and online learning tasks. GEL learns feature embedding from any type of data or data with mixed feature types. For supervised learning tasks with class label information, GEL leverages a Class Partitioned Instance Representation (CPIR) process to arrange instances, based on their labels, as a dense binary representation via row and feature vectors for feature embedding learning. If class labels are unavailable, CPIR is naturally degenerated and treats all instances as one class. Based on the CPIR representation, GEL uses eigenvector decomposition to convert the proximity matrix into a low-dimensional space. For new out-of-training samples, their low-dimensional representation are derived through a direct conversion without a retraining phase. The learned numerical embedding features can be directly used to represent instances for effective learning. Experiments and comparisons on 28 datasets, including categorical, numerical, and ordinal features, demonstrate that embedding features learned from GEL can effectively represent the original instances for clustering, classification, and online learning. [ABSTRACT FROM AUTHOR]

Machine Learning techniques have been useful in almost every field of concern. Data Mining, a branch of Machine Learning is one of the most extensively used techniques. The ever-increasing demands in the field of medicine are being addressed by computational approaches in which Big Data analysis, image processing and data mining are on top priority. These techniques have been exploited in the domain of ophthalmology for better retinal fundus image analysis. Blood vessels, one of the most significant retinal anatomical structures are analysed for diagnosis of many diseases like retinopathy, occlusion and many other vision threatening diseases. Vessel segmentation can also be a pre-processing step for segmentation of other retinal structures like optic disc, fovea, microneurysms, etc. In this paper, blood vessel segmentation is attempted through image processing and data mining techniques. The retinal blood vessels were segmented through color space conversion and color channel extraction, image pre-processing, Gabor filtering, image postprocessing, feature construction through application of principal component analysis, k-means clustering and first level classification using Naïve-Bayes classification algorithm and second level classification using C4.5 enhanced with bagging techniques. Association of every pixel against the feature vector necessitates Big Data analysis. The proposed methodology was evaluated on a publicly available database, STARE. The results reported 95.05% accuracy on entire dataset; however the accuracy was 95.20% on normal images and 94.89% on pathological images. A comparison of these results with the existing methodologies is also reported. This methodology can help ophthalmologists in better and faster analysis and hence early treatment to the patients. [ABSTRACT FROM AUTHOR]

One of the most important composite indicators (CIs) to assess the development of countries or regions is the human development index (HDI) which is used by the United Nations (UN) to rank countries. HDI has three dimensions including healthy life, population education, and standard of living. A total of four different sub-indicators are defined for these three dimensions. The UN evaluates and ranks all countries using a simple arithmetic or geometric average of the sub-indicators and then categorizes the countries into four different groups based on their HDI scores. To measure the HDI, the benefit-of-the-doubt (BOD) model is used by researchers instead of the geometric mean. The conventional BOD model has some main drawbacks. The first is not accounting for data uncertainty, and the second is evaluating countries using different weights for the same sub-indicators. Furthermore, BOD model is not capable of predicting countries' future HDI scores. To overcome these deficiencies, this paper proposes a common weight fuzzy BOD (CWFBOD) model to measure the HDI scores. First, to take into account the uncertainty, data are considered fuzzy numbers, and a fuzzy BOD model (FBOD) is introduced. Then, to find a set of common weights for the three dimensions of HDI, the proposed FBOD model is transformed into a multiple-objective CWFBOD model. To convert and solve the multiple objective CWFBOD model to a single objective model, a fuzzy theory approach is used. In addition, of predicting the future HDI scores of countries, an artificial neural network (ANN) is designed and trained, where the original data on sub-indicators health, education, and income are considered as the features, and the HDI scores generated by CWBOD are assumed as the target of ANN. Finally, this study applies the fuzzy C-Means clustering technique to cluster all countries into four different clusters based on the HDI scores generated by FBOD and CWFBOD models. To illustrate the ability of the proposed methodology, the HDI scores of 190 countries during the period of 2015–2021 have been estimated and predicted. The results show that the proposed integrated methodology can be effectively used to estimate and predict the HDI scores as well as to cluster countries. [ABSTRACT FROM AUTHOR]

Facility location problems form a broad class of optimization problems extremely popular in combinatorial optimization and operations research. In every facility location problem, one must locate a set of facilities in order to satisfy the demands of customers so as some certain objective function be optimal. Besides numerous applications in public and private sectors, the problems are widely used in machine learning. For example, clustering can be viewed as a facility location problem where we need to partition a set of customers into clusters assigned to open facilities. In this survey we briefly look at how the ideas and approaches arisen in the field of facility location led to modern, popular machine learning algorithms supported by many data mining and machine learning software packages. We also review the state-of-the-art of exact methods and heuristics, as well as some extensions of the basic problems and algorithms in applied machine learning tasks. Note that the main emphasis lies here on discrete facility location problems which, for example, underlie many widely used clustering algorithms (PAM, affinity propagation, etc.). Since the high computational complexity of the conventional facility location-based clustering algorithms hinders their application to modern large-scale real-life datasets; we also survey some modern approaches to implementation of the algorithms for these large data collections. [ABSTRACT FROM AUTHOR]

Similarity measures are central to many machine learning algorithms. There are many different similarity measures, each catering for different applications and data requirements. Most similarity measures used with numerical data assume that the attributes are interval scale. In the interval scale, it is assumed that a unit difference has the same meaning irrespective of the magnitudes of the values separated. When this assumption is violated, accuracy may be reduced. Our experiments show that removing the interval scale assumption by transforming data to ranks can improve the accuracy of distance-based similarity measures on some tasks. However the rank transform has high time and storage overheads. In this paper, we introduce an efficient similarity measure which does not consider the magnitudes of inter-instance distances. We compare the new similarity measure with popular similarity measures in two applications: DBScan clustering and content based multimedia information retrieval with real world datasets and different transform functions. The results show that the proposed similarity measure provides good performance on a range of tasks and is invariant to violations of the interval scale assumption. [ABSTRACT FROM AUTHOR]

Background: With the rapid accumulation of biological datasets, machine learning methods designed to automate data analysis are urgently needed. In recent years, so-called topic models that originated from the field of natural language processing have been receiving much attention in bioinformatics because of their interpretability. Our aim was to review the application and development of topic models for bioinformatics. Description: This paper starts with the description of a topic model, with a focus on the understanding of topic modeling. A general outline is provided on how to build an application in a topic model and how to develop a topic model. Meanwhile, the literature on application of topic models to biological data was searched and analyzed in depth. According to the types of models and the analogy between the concept of document-topic-word and a biological object (as well as the tasks of a topic model), we categorized the related studies and provided an outlook on the use of topic models for the development of bioinformatics applications. Conclusion: Topic modeling is a useful method (in contrast to the traditional means of data reduction in bioinformatics) and enhances researchers' ability to interpret biological information. Nevertheless, due to the lack of topic models optimized for specific biological data, the studies on topic modeling in biological data still have a long and challenging road ahead. We believe that topic models are a promising method for various applications in bioinformatics research. [ABSTRACT FROM AUTHOR]

To be successful, cybercriminals must figure out how to scale their scams. They duplicate content on new websites, often staying one step ahead of defenders that shut down past schemes. For some scams, such as phishing and counterfeit goods shops, the duplicated content remains nearly identical. In others, such as advanced-fee fraud and online Ponzi schemes, the criminal must alter content so that it appears different in order to evade detection by victims and law enforcement. Nevertheless, similarities often remain, in terms of the website structure or content, since making truly unique copies does not scale well. In this paper, we present a novel optimized combined clustering method that links together replicated scamwebsites, even when the criminal has taken steps to hide connections. We present automated methods to extract key website features, including rendered text, HTML structure, file structure, and screenshots. We describe a process to automatically identify the best combination of such attributes to most accurately cluster similar websites together. To demonstrate the method's applicability to cybercrime, we evaluate its performance against two collected datasets of scam websites: fake escrow services and high-yield investment programs (HYIPs). We show that our method more accurately groups similar websites together than those existing general-purpose consensus clustering methods. [ABSTRACT FROM AUTHOR]

A detailed study of stellar populations in Milky Way (MW) satellite galaxies remains an observational challenge due to their faintness and fewer spectroscopically confirmed member stars. We use unsupervised machine learning methods to identify new members for nine nearby MW satellite galaxies using Gaia data release-3 (Gaia DR3) astrometry, the Dark Energy Survey (DES) and the DECam Local Volume Exploration Survey (DELVE) photometry. Two density-based clustering algorithms, DBSCAN and HDBSCAN, have been used in the four-dimensional astrometric parameter space ( α 2016 , δ 2016 , μ α cos δ , μ δ ) to identify member stars belonging to MW satellite galaxies. Our results indicate that we can recover more than 80% of the known spectroscopically confirmed members in most satellite galaxies and also reject 95–100% of spectroscopic non-members. We have also added many new members using this method. We compare our results with previous studies using photometric and astrometric data and discuss the suitability of density-based clustering methods for MW satellite galaxies. [ABSTRACT FROM AUTHOR]

Image segmentation of heterogeneous comparable objects lying beneath the earth's surface is a fundamental but challenging research area in remote sensing. Learning approaches are used in remote sensing image segmentation to improve segmentation accuracy at the expense of time and a large amount of data, but their performance need to be finely classified due to information diversity constraints. In this work, we proposed an novel feature based fuzzy C-means-extreme learning machine (FBFCM-ELM) algorithm for remote sensing image segmentation in which the classification based on entropy, intensity, and edge features is performed in such a way that it updates the intensity value to preserve the most local characteristics in the image while still being able to clearly distinguish the image's boundaries by assigning the pixel values of each cluster to the peak value of the cluster's sub-histogram. Using FBFCM, features are extracted and used as reliable samples for ELM training. Undetermined segmented pixels are obtained using the trained ELM classifier. Experiments performed over number of images that confirmed the proposed method yields a better segmented RGB image, as evidenced by observable details, edges, and improved appearance that resembles the ground truth image and outperforms state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Feature Selection (FS) is choosing a subcategory of features purposed to construct a machine learning model. Among the copious existing FS algorithms, Binary Particle Swarm Optimization Algorithm (BPSO) is prevalent with applications in several domains. However, BPSO suffers from premature convergence that affects exploration, resulting in dilapidation. In this current work, we boost the exploration of BPSO, incorporating the intelligence of crows to hide their food sources from other crows and predators and maintain diversity by implementing a clustering strategy. The clustering technique guarantees that the starting population is evenly distributed over the feature space while including more promising features. Additionally, suppose a crow realizes another crow or a predator is tracking it. In that case, the crow moves randomly to evict the stalker, leading to a better exploration of unexplored regions within the search space. We named the proposed method Hybrid Particle Swarm Optimization and Crow Search Algorithm with clustering initialization strategy (HPSOCSA-CIS). To evaluate the performance of HPSOCSA-CIS, 15 standard UCI datasets are utilized, and the outcomes are compared with recently proposed hybrid and standard optimization algorithms. From observation, HPSOCSA-CIS outperforms the comparing approaches for feature selection challenges on representative datasets that fall in the three-category based on dimensions. The HPSOCSA-CIS improves performance in terms of mean classification accuracy by 8.87%, 17.5%, and 21.90% on Low, medium, and high dimensional datasets, respectively. [ABSTRACT FROM AUTHOR]

Households are becoming increasingly heterogeneous. While previous studies have revealed many important insights (e.g., wealth effect, income effect), they could only incorporate two or three variables at a time. However, in order to have a more detailed understanding of complex household heterogeneity, more variables should be considered simultaneously. In this study, we argue that advanced clustering techniques can be useful for investigating high-dimensional household heterogeneity. A deep learning-based clustering method is used to effectively handle the high-dimensional balance sheet data of approximately 50,000 households. The employment of appropriate dimension-reduction techniques is the key to incorporate the full joint distribution of high-dimensional data in the clustering step. Our study suggests that various variables should be used together to explain household heterogeneity. Asset variables are found to be crucial for understanding heterogeneity within wealthy households, while debt variables are more important for those households that are not wealthy. In addition, relationships with sociodemographic variables (e.g., age, education, and family size) were further analyzed. Although clusters are found only based on financial variables, they are shown to be closely related to most sociodemographic variables. [ABSTRACT FROM AUTHOR]

Unsupervised learning algorithms are widely used for many important statistical tasks with numerous applications in science and industry. Yet despite their prevalence, they have attracted remarkably little philosophical scrutiny to date. This stands in stark contrast to supervised and reinforcement learning algorithms, which have been widely studied and critically evaluated, often with an emphasis on ethical concerns. In this article, I analyze three canonical unsupervised learning problems: clustering, abstraction, and generative modeling. I argue that these methods raise unique epistemological and ontological questions, providing data-driven tools for discovering natural kinds and distinguishing essence from contingency. This analysis goes some way toward filling the lacuna in contemporary philosophical discourse on unsupervised learning, as well as bringing conceptual unity to a heterogeneous field more often described by what it is not (i.e., supervised or reinforcement learning) than by what it is. I submit that unsupervised learning is not just a legitimate subject of philosophical inquiry but perhaps the most fundamental branch of all AI. However, an uncritical overreliance on unsupervised methods poses major epistemic and ethical risks. I conclude by advocating for a pragmatic, error-statistical approach that embraces the opportunities and mitigates the challenges posed by this powerful class of algorithms. [ABSTRACT FROM AUTHOR]

Data obtained from additive manufactured components can be analyzed to gain a better understanding of the manufacturing physics and to improve the quality of the parts. However, additive manufacturing is a complex process with many sensitivities. Machine learning has recently been used in additive manufacturing to model and evaluate processes. It is not possible to provide a single regression model to predict mechanical behavior as the properties will vary based on the component geometry and in regions within a component. To provide a separate regression model for each region, it is better to categorize several regions for multiple geometries by their post- fabrication properties (maximum and minimum principal stresses and distortion). Clustering is a method for analyzing the quality of parts with similar characteristics in diverse areas. Twenty-three distinct geometries with numerous geometric characteristics, each experiencing a different history of heat during fabrication (due to their thickness and material distribution), are analyzed in this study. Three different clustering methods are employed (self-organizing map, k-means clustering, and fuzzy c-means clustering). The results are presented in two parts. For the first case, a localized approach is taken, where a comprehensive data set is utilized. The observed maximum coefficient of variance is 0.07969. For the second case, each shape is considered as an instance (sample) with general geometric characteristics. Similar trends between different clustering methods were extracted for the global approach, highlighting the potential of this method, but the clustering results are dependent on the clustering method. According to these results, the analysis of the local data provides a deeper understanding of post-fabrication properties clustering. Additional geometric-based characteristics will be developed to refine and improve the global approach. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a new distributed learning framework that is different from traditional distributed machine learning: (1) differences in communication, computing, and storage performance among devices (device heterogeneity), (2) differences in data distribution and data volume (data heterogeneity), and (3) high communication consumption. Under heterogeneous conditions, the data distribution of clients varies greatly, which leads to the problem that the convergence speed of the training model decreases and the training model cannot converge to the global optimal solution. In this work, an FL algorithm based on stratified sampling and regularization (FedSSAR) is proposed. In FedSSAR, a density-based clustering method is used to divide the overall client into different clusters, then, some available clients are proportionally extracted from different clusters to participate in training which realizes unbiased sampling for the overall client and reduces the aggregation weight variance of the client. At the same time, when calculating the model local loss function, we limit the update direction of the model by a regular term, so that heterogeneous clients are optimized in the globally optimal direction. We prove the convergence of FedSSAR theoretically and experimentally, and demonstrate the superiority of FedSSAR by comparing it with other FL algorithms on public datasets. [ABSTRACT FROM AUTHOR]

Background: We are living in an age where data is everywhere and grows up in a very speedy way. Thanks to sensors, mobile phones and social networks, we can gather a hug amount of information to understand human behavior as well as his individual life. In healthcare system, big data analytics and machine learning algorithms prove their effectiveness and efficiency in saving lives and predicting new diseases. This triggered the idea of taking advantages of those tools and algorithms to create systems that involve both doctors and patients in the treatment of disease, predict outcomes and use real-time risk factors from sensors and mobile phones. Methods: We distinguish three types of data: data from sensors, data from mobile phones and data registered or updated by the patient in a mobile app we created. We take advantages from IoT systems such as Raspberry Pi to collect and process data coming from sensors. All data collected is sent to a NoSql Server to be then analyzed and processed in Databricks Spark. K-means centroid clustering algorithms is used to build the predictive model, create partitions and make predictions. To validate results in term of efficiency and effectiveness, we used clustering validations techniques: Random K, Silhouette and Elbow methods. Results: The main contribution of our work is the implementation of a new system that has the capability to be applied in several prediction disease researches using Big Data Analytics and IoT. Also, comparing to other studies in literature that use only medical or maternal risk factors from echography; our work had the advantage to use real-time risk factors (maternal and medical) gathered from sensors, react in advance and track diseases. As a case study, we create an e-monitoring real-time miscarriage prediction system to save baby's lives and help pregnant women. In fact, doctors receive the results of clustering and track theirs patient through our mobile app to react in term of miscarriage to avoid non-suitable outcomes. While pregnant women receive only advices based on their behaviors. The system uses 15 real-time risk factors and our dataset contains more than 1,000,000 JSON files. Elbow method affirm three as the optimal number of clusters and we reach 0.99 as a value of Silhouette method, which is a good sign that clusters are well separated and matched. [ABSTRACT FROM AUTHOR]

The k-means algorithm is widely used for clustering, compressing, and summarizing vector data. We present a fast and memory-efficient GPU-based algorithm for exact k-means, Asynchronous Selective Batched K-means (ASB K-means). Unlike most GPU-based k-means algorithms that require loading the whole dataset onto the GPU for clustering, the amount of GPU memory required to run our algorithm can be chosen to be much smaller than the size of the whole dataset. Thus, our algorithm can cluster datasets whose size exceeds the available GPU memory. The algorithm works in a batched fashion and applies the triangle inequality in each k-means iteration to omit a data point if its membership assignment, i.e., the cluster it belongs to, remains unchanged, thus significantly reducing the number of data points that need to be transferred between the CPU's RAM and the GPU's global memory and enabling the algorithm to very efficiently process large datasets. Our algorithm can be substantially faster than a GPU-based implementation of standard k-means even in situations when application of the standard algorithm is feasible because the whole dataset fits into GPU memory. Experiments show that ASB K-means can run up to 15x times faster than a standard GPU-based implementation of k-means, and it also outperforms the GPU-based k-means implementation in NVIDIA's open-source RAPIDS machine learning library on all the datasets used in our experiments. [ABSTRACT FROM AUTHOR]

As unsupervised learning algorithm, clustering algorithm is widely used in data processing field. Density-based spatial clustering of applications with noise algorithm (DBSCAN), as a common unsupervised learning algorithm, can achieve clusters via finding high-density areas separated by low-density areas based on cluster density. Different from other clustering methods, DBSCAN can work well for any shape clusters in the spatial database and can effectively cluster exceptional data. However, in the employment of DBSCAN, the parameters, EPS and MinPts, need to be preset for different clustering object, which greatly influences the performance of the DBSCAN. To achieve automatic optimization of parameters and improve the performance of DBSCAN, we proposed an improved DBSCAN optimized by arithmetic optimization algorithm (AOA) with opposition-based learning (OBL) named OBLAOA-DBSCAN. In details, the reverse search capability of OBL is added to AOA for obtaining proper parameters for DBSCAN, to achieve adaptive parameter optimization. In addition, our proposed OBLAOA optimizer is compared with standard AOA and several latest meta heuristic algorithms based on 8 benchmark functions from CEC2021, which validates the exploration improvement of OBL. To validate the clustering performance of the OBLAOA-DBSCAN, 5 classical clustering methods with 10 real datasets are chosen as the compare models according to the computational cost and accuracy. Based on the experimental results, we can obtain two conclusions: (1) the proposed OBLAOA-DBSCAN can provide highly accurately clusters more efficiently; and (2) the OBLAOA can significantly improve the exploration ability, which can provide better optimal parameters. [ABSTRACT FROM AUTHOR]

As combinatorial optimization is one of the main quantum computing applications, many methods based on parameterized quantum circuits are being developed. In general, a set of parameters are being tweaked to optimize a cost function out of the quantum circuit output. One of these algorithms, the Quantum Approximate Optimization Algorithm stands out as a promising approach to tackling combinatorial problems. However, finding the appropriate parameters is a difficult task. Although QAOA exhibits concentration properties, they can depend on instances characteristics that may not be easy to identify, but may nonetheless offer useful information to find good parameters. In this work, we study unsupervised Machine Learning approaches for setting these parameters without optimization. We perform clustering with the angle values but also instances encodings (using instance features or the output of a variational graph autoencoder), and compare different approaches. These angle-finding strategies can be used to reduce calls to quantum circuits when leveraging QAOA as a subroutine. We showcase them within Recursive-QAOA up to depth 3 where the number of QAOA parameters used per iteration is limited to 3, achieving a median approximation ratio of 0.94 for MaxCut over 200 Erdős-Rényi graphs. We obtain similar performances to the case where we extensively optimize the angles, hence saving numerous circuit calls. [ABSTRACT FROM AUTHOR]

In hierarchical clustering, the most important factor is the selection of the linkage method which is the decision of how the distances between clusters will be calculated. It extremely affects not only the clustering quality but also the efficiency of the algorithm. However, the traditional linkage methods do not consider the effect of the objects around cluster centers. Based on this motivation, in this article, we propose a novel linkage method, named k-centroid link, in order to provide a better solution than the traditional linkage methods. In the proposed k-centroid link method, the dissimilarity between two clusters is mainly defined as the average distance between all pairs of k data objects in each cluster, which are the k closest ones to the centroid of each cluster. In the experimental studies, the proposed method was tested on 24 different publicly available benchmark datasets. The results demonstrate that by hierarchical clustering via the k-centroid link method, it is possible to obtain better performance in terms of clustering quality compared to the conventional linkage methods such as single link, complete link, average link, mean link, centroid link, and the Ward method. [ABSTRACT FROM AUTHOR]

Feedback is an essential component of learning environments. However, providing feedback in populated classes can be challenging for teachers. On the one hand, it is unlikely that a single kind of feedback works for all students considering the heterogeneous nature of their needs. On the other hand, delivering personalized feedback is infeasible and time-consuming. Available automated feedback systems have helped solve the problem to some extent. However, they can provide personalized feedback only after a draft is submitted. To help struggling students during the writing process, we can use machine learning to cluster students who benefit the same from feedback using keystroke logs. We can apply the results in automated feedback systems that provide process feedback. In this study, we aim to find homogeneous student profiles based on their writing process indicators. We use fourteen process indicators to find clusters in the data set. We used these measures in a four-stage analysis, including (a) data preprocessing, (b) dimensionality reduction, (c) clustering, and (d) the analysis of the writing quality. Clustering techniques identified five different profiles: Strategic planners, Rapid writers, Emerging planners, Average writers, and Low-performing writers. We further validated the emerged profiles by comparing them concerning students' writing quality. The present work broadens our knowledge of how students interact with writing tasks and addresses how variations in writing behaviors lead to qualitatively different products. We discuss the theoretical underpinnings and potentials of finding profiles of students during writing in higher education. [ABSTRACT FROM AUTHOR]

Automated community detection is an important problem in the study of complex networks. The idea of community detection is closely related to the concept of data clustering in pattern recognition. Data clustering refers to the task of grouping similar objects and segregating dissimilar objects. The community detection problem can be thought of as finding groups of densely interconnected nodes with few connections to nodes outside the group. A node similarity measure is proposed here that finds the similarity between two nodes by considering both neighbors and non-neighbors of these two nodes. Subsequently, a method is introduced for identifying communities in complex networks using this node similarity measure and the notion of data clustering. The significant characteristic of the proposed method is that it does not need any prior knowledge about the actual communities of a network. Extensive experiments on several real world and artificial networks with known ground-truth communities are reported. The proposed method is compared with various state of the art community detection algorithms by using several criteria, viz. normalized mutual information, f-measure etc. Moreover, it has been successfully applied in improving the effectiveness of a recommender system which is rapidly becoming a crucial tool in e-commerce applications. The empirical results suggest that the proposed technique has the potential to improve the performance of a recommender system and hence it may be useful for other e-commerce applications. [ABSTRACT FROM AUTHOR]

This study aimed to determine the discriminatory power of textural features to differentiate the sorghum grains subjected to normal, mild deficit, and severe deficit irrigation. The studies were carried out with the use of image processing, discrimination analysis, analysis of variance and cluster analysis using the selected texture parameters calculate for images from individual color channels L, a, b, R, G, B, U, V, S, X, Y and Z. The results indicated that different levels of irrigation can discriminate the sorghum grain with an accuracy of up to about 100%. Most of the genotypes for each level of irrigation were different in the terms of values of textural features and formed separate homogeneous groups. Drought is one of the limiting factors contributing to a decrease in sorghum grain productivity and nutritional quality, especially when it is cultivated in a marginal area. Therefore, low-quality grains produced under water stress should be recognized before they enter into the food and feed chain. The application of image analysis based on textures of sorghum grain images proved to be useful for the discrimination of sorghum grains subjected to drought stress. The applied procedure provided the fast, objective results that may be applied in practice for screening distinguishing the sorghum grains with different irrigation levels. [ABSTRACT FROM AUTHOR]

Clustering algorithms help identify homogeneous subgroups from data. In some cases, additional information about the relationship among some subsets of the data exists. When using a semi-supervised clustering algorithm, an expert may provide additional information to constrain the solution based on that knowledge and, in doing so, guide the algorithm to a more useful and meaningful solution. Such additional information often takes the form of a cannot-link constraint (i.e., two data points cannot be part of the same cluster) or a must-link constraint (i.e., two data points must be part of the same cluster). A key challenge for users of such constraints in semi-supervised learning algorithms, however, is that the addition of inaccurate or conflicting constraints can decrease accuracy and little is known about how to detect whether expert-imposed constraints are likely incorrect. In the present work, we introduce a method to score each must-link and cannot-link pairwise constraint as likely incorrect. Using synthetic experimental examples and real data, we show that the resulting impact score can successfully identify individual constraints that should be removed or revised. [ABSTRACT FROM AUTHOR]

Clustering, a traditional machine learning method, plays a significant role in data analysis. Most clustering algorithms depend on a predetermined exact number of clusters, whereas, in practice, clusters are usually unpredictable. Although the Elbow method is one of the most commonly used methods to discriminate the optimal cluster number, the discriminant of the number of clusters depends on the manual identification of the elbow points on the visualization curve. Thus, experienced analysts cannot clearly identify the elbow point from the plotted curve when the plotted curve is fairly smooth. To solve this problem, a new elbow point discriminant method is proposed to yield a statistical metric that estimates an optimal cluster number when clustering on a dataset. First, the average degree of distortion obtained by the Elbow method is normalized to the range of 0 to 10. Second, the normalized results are used to calculate the cosine of intersection angles between elbow points. Third, this calculated cosine of intersection angles and the arccosine theorem are used to compute the intersection angles between elbow points. Finally, the index of the above-computed minimal intersection angles between elbow points is used as the estimated potential optimal cluster number. The experimental results based on simulated datasets and a well-known public dataset (Iris Dataset) demonstrated that the estimated optimal cluster number obtained by our newly proposed method is better than the widely used Silhouette method. [ABSTRACT FROM AUTHOR]

Text document classification and clustering is an important learning task which fits to both data mining and machine learning areas. The learning task throws several challenges when it is required to process high dimensional text documents. Word distribution in text documents plays a very key role in learning process. Research related to high dimensional text document classification and clustering is usually limited to application of traditional distance functions and most of the research contributions in the existing literature did not consider the word distribution in documents. In this research, we propose a novel similarity function for feature pattern clustering and high dimensional text classification. The similarity function proposed is used to carry supervised learning based dimensionality reduction. The important feature of this work is that the word distribution before and after dimensionality reduction is the same. Experiment results prove the proposed approach achieves dimensionality reduction, retains the word distribution and obtained better classification accuracies compared to other measures. [ABSTRACT FROM AUTHOR]

Contraction Clustering (RASTER) is a single-pass algorithm for density-based clustering of 2D data. It can process arbitrary amounts of data in linear time and in constant memory, quickly identifying approximate clusters. It also exhibits good scalability in the presence of multiple CPU cores. RASTER exhibits very competitive performance compared to standard clustering algorithms, but at the cost of decreased precision. Yet, RASTER is limited to batch processing and unable to identify clusters that only exist temporarily. In contrast, S-RASTER is an adaptation of RASTER to the stream processing paradigm that is able to identify clusters in evolving data streams. This algorithm retains the main benefits of its parent algorithm, i.e. single-pass linear time cost and constant memory requirements for each discrete time step within a sliding window. The sliding window is efficiently pruned, and clustering is still performed in linear time. Like RASTER, S-RASTER trades off an often negligible amount of precision for speed. Our evaluation shows that competing algorithms are at least 50% slower. Furthermore, S-RASTER shows good qualitative results, based on standard metrics. It is very well suited to real-world scenarios where clustering does not happen continually but only periodically. [ABSTRACT FROM AUTHOR]