Search

Unsupervised learning is a type of machine learning that learns from data without human supervision. Unsupervised feature selection (UFS) is crucial in data analytics, which plays a vital role in enhancing the quality of results and reducing computational complexity in huge feature spaces. The UFS problem has been addressed in several research efforts. Recent studies have witnessed a surge in innovative techniques like nature-inspired algorithms for clustering and UFS problems. However, very few studies consider the UFS problem as a multi-objective problem to find the optimal trade-off between the number of selected features and model accuracy. This paper proposes a multi-objective symbiotic organism search algorithm for unsupervised feature selection (SOSUFS) and a symbiotic organism search-based clustering (SOSC) algorithm to generate the optimal feature subset for more accurate clustering. The efficiency and robustness of the proposed algorithm are investigated on benchmark datasets. The SOSUFS method, combined with SOSC, demonstrated the highest f-measure, whereas the KHCluster method resulted in the lowest f-measure. SOSFS effectively reduced the number of features by more than half. The proposed symbiotic organisms search-based optimal unsupervised feature-selection (SOSUFS) method, along with search-based optimal clustering (SOSC), was identified as the top-performing clustering approach. Following this, the SOSUFS method demonstrated strong performance. In summary, this empirical study indicates that the proposed algorithm significantly surpasses state-of-the-art algorithms in both efficiency and effectiveness. Unsupervised learning in artificial intelligence involves machine-learning techniques that learn from data without human supervision. Unlike supervised learning, unsupervised machine-learning models work with unlabeled data to uncover patterns and insights independently, without explicit guidance or instruction. [ABSTRACT FROM AUTHOR]

Since failure of steam turbines occurs frequently and can causes huge losses for thermal plants, it is important to identify a fault in advance. A novel clustering fault diagnosis method for steam turbines based on t-distribution stochastic neighborhood embedding (t-SNE) and extreme gradient boosting (XGBoost) is proposed in this paper. First, the t-SNE algorithm was used to map the high-dimensional data to the low-dimensional space; and the data clustering method of K-means was performed in the low-dimensional space to distinguish the fault data from the normal data. Then, the imbalance problem in the data was processed by the synthetic minority over-sampling technique (SMOTE) algorithm to obtain the steam turbine characteristic data set with fault labels. Finally, the XGBoost algorithm was used to solve this multi-classification problem. The data set used in this paper was derived from the time series data of a steam turbine of a thermal power plant. In the processing analysis, the method achieved the best performance with an overall accuracy of 97% and an early warning of at least two hours in advance. The experimental results show that this method can effectively evaluate the condition and provide fault warning for power plant equipment. [ABSTRACT FROM AUTHOR]

Current edge devices for neural networks such as FPGA, CPLD, and ASIC can support low bit-width computing to improve the execution latency and energy efficiency, but traditional linear quantization can only maintain the inference accuracy of neural networks at a bit-width above 6 bits. Different from previous studies that address this problem by clipping the outliers, this paper proposes a two-stage quantization method. Before converting the weights into fixed-point numbers, this paper first prunes the network by unstructured pruning and then uses the K-means algorithm to cluster the weights in advance to protect the distribution of the weights. To solve the instability problem of the K-means results, the PSO (particle swarm optimization) algorithm is exploited to obtain the initial cluster centroids. The experimental results on baseline deep networks such as ResNet-50, Inception-v3, and DenseNet-121 show the proposed optimized quantization method can generate a 5-bit network with an accuracy loss of less than 5% and a 4-bit network with only 10% accuracy loss as compared to 8-bit quantization. By quantization and pruning, this method reduces the model bit-width from 32 to 4 and the number of neurons by 80%. Additionally, it can be easily integrated into frameworks such as TensorRt and TensorFlow-Lite for low bit-width network quantization. [ABSTRACT FROM AUTHOR]

While there are several ways to identify customer behaviors, few extract this value from information already in a database, much less extract relevant characteristics. This paper presents the development of a prototype using the recency, frequency, and monetary attributes for customer segmentation of a retail database. For this purpose, the standard K-means, K-medoids, and MiniBatch K-means were evaluated. The standard K-means clustering algorithm was more appropriate for data clustering than other algorithms as it remained stable until solutions with six clusters. The evaluation of the clusters' quality was obtained through the internal validation indexes Silhouette, Calinski Harabasz, and Davies Bouldin. When consensus was not obtained, three external validation indexes were applied: global stability, stability per cluster, and segment-level stability across solutions. Six customer segments were obtained, identified by their unique behavior: lost customers, disinterested customers, recent customers, less recent customers, loyal customers, and best customers. Their behavior was evidenced and analyzed, indicating trends and preferences. The proposed method combining recency, frequency, monetary value (RFM), K-means clustering, internal indices, and external indices achieved return rates of 17.50%, indicating acceptable selectivity of the customers. [ABSTRACT FROM AUTHOR]

Clustering is a critical part of many tasks and, in most applications, the number of clusters in the data are unknown and must be estimated. This paper presents an Extreme Value Theory-based approach to threshold selection for clustering, proving that the "correct" linkage distances must follow a Weibull distribution for smooth feature spaces. Deep networks and their associated deep features have transformed many aspects of learning, and this paper shows they are consistent with our extreme-linkage theory and provide Unreasonable Clusterability. We show how our novel threshold selection can be applied to both classic agglomerative clustering and the more recent FINCH (First Integer Neighbor Clustering Hierarchy) algorithm. Our evaluation utilizes over a dozen different large-scale vision datasets/subsets, including multiple face-clustering datasets and ImageNet for both in-domain and, more importantly, out-of-domain object clustering. Across multiple deep features clustering tasks with very different characteristics, our novel automated threshold selection performs well, often outperforming state-of-the-art clustering techniques even when they select parameters on the test set. [ABSTRACT FROM AUTHOR]

Accurate sizing systems of a population permit the minimization of the production costs of the textile apparel industry and allow firms to satisfy their customers. Hence, information about human body shapes needs to be extracted in order to examine, compare and classify human morphologies. In this paper, we use topological data analysis to study human body shapes. Persistence theory applied to anthropometric point clouds together with clustering algorithms show that relevant information about shapes is extracted by persistent homology. In particular, the homologies of human body points have interesting interpretations in terms of human anatomy. In the first place, anomalies of scans are detected using complete-linkage hierarchical clusterings. Then, a discrimination index shows which type of clustering separates gender accurately and if it is worth restricting to body trunks or not. Finally, Ward-linkage hierarchical clusterings with Davies–Bouldin, Dunn and Silhouette indices are used to define eight male morphotypes and seven female morphotypes, which are different in terms of weight classes and ratios between bust, waist and hip circumferences. The techniques used in this work permit us to classify human bodies and detect scan anomalies directly on the full human body point clouds rather than the usual methods involving the extraction of body measurements from individuals or their scans. [ABSTRACT FROM AUTHOR]

Determining the optimal feature set is a challenging problem, especially in an unsupervised domain. To mitigate the same, this paper presents a new unsupervised feature selection method, termed as densest feature graph augmentation with disjoint feature clusters. The proposed method works in two phases. The first phase focuses on finding the maximally non-redundant feature subset and disjoint features are added to the feature set in the second phase. To experimentally validate, the efficiency of the proposed method has been compared against five existing unsupervised feature selection methods on five UCI datasets in terms of three performance criteria, namely clustering accuracy, normalized mutual information, and classification accuracy. The experimental analyses have shown that the proposed method outperforms the considered methods. [ABSTRACT FROM AUTHOR]

Diabetic foot is one of the main complications observed in diabetic patients; it is associated with the development of foot ulcers and can lead to amputation. In order to diagnose these complications, specialists have to analyze several factors. To aid their decisions and help prevent mistakes, the resort to computer-assisted diagnostic systems using artificial intelligence techniques is gradually increasing. In this paper, two different models for the classification of thermograms of the feet of diabetic and healthy individuals are proposed and compared. In order to detect and classify abnormal changes in the plantar temperature, machine learning algorithms are used in both models. In the first model, the foot thermograms are classified into four classes: healthy and three categories for diabetics. The second model has two stages: in the first stage, the foot is classified as belonging to a diabetic or healthy individual, while, in the second stage, a classification refinement is conducted, classifying diabetic foot into three classes of progressive severity. The results show that both proposed models proved to be efficient, allowing us to classify a foot thermogram as belonging to a healthy or diabetic individual, with the diabetic ones divided into three classes; however, when compared, Model 2 outperforms Model 1 and allows for a better performance classification concerning the healthy category and the first class of diabetic individuals. These results demonstrate that the proposed methodology can be a tool to aid medical diagnosis. [ABSTRACT FROM AUTHOR]

In recent years, new metaheuristic algorithms have been developed taking as reference the inspiration on biological and natural phenomena. This nature-inspired approach for algorithm development has been widely used by many researchers in solving optimization problems. These algorithms have been compared with the traditional ones and have demonstrated to be superior in many complex problems. This paper attempts to describe the algorithms based on nature, which are used in optimizing fuzzy clustering in real-world applications. We briefly describe the optimization methods, the most cited ones, nature-inspired algorithms that have been published in recent years, authors, networks and relationship of the works, etc. We believe the paper can serve as a basis for analysis of the new area of nature and bio-inspired optimization of fuzzy clustering. [ABSTRACT FROM AUTHOR]

Clustering constitutes a well-known problem of division of unlabelled dataset into disjoint groups of data elements. It can be tackled with standard statistical methods but also with metaheuristics, which offer more flexibility and decent performance. The paper studies the application of the clustering algorithm—inspired by the territorial behaviors of predatory animals—named the Predatory Animals Algorithm (or, in short: PAA). Besides the description of the PAA, the results of its experimental evaluation, with regards to the classic k-means algorithm, are provided. It is concluded that the application of newly-created nature-inspired technique brings very promising outcomes. The discussion of obtained results is followed by areas of possible improvements and plans for further research. [ABSTRACT FROM AUTHOR]

In this paper we present the PHOCS-2 algorithm, which extracts a "Predicted Hierarchy Of ClassifierS". The extracted hierarchy helps us to enhance performance of flat classification. Nodes in the hierarchy contain classifiers. Each intermediate node corresponds to a set of classes and each leaf node corresponds to a single class. In the PHOCS-2 we make estimation for each node and achieve more precise computation of false positives, true positives and false negatives. Stopping criteria are based on the results of the flat classification. The proposed algorithm is validated against nine datasets. [ABSTRACT FROM AUTHOR]

When an event occurs in the real world, numerous news reports describing this event start to appear on different news sites within a few minutes of the event occurrence. This may result in a huge amount of information for users, and automated processes may be required to help manage this information. In this paper, we describe a clustering system that can cluster news reports from disparate sources into event-centric clusters-i.e., clusters of news reports describing the same event. A user can identify any RSS feed as a source of news he/she would like to receive and our clustering system can cluster reports received from the separate RSS feeds as they arrive without knowing the number of clusters in advance. Our clustering system was designed to function well in an online incremental environment. In evaluating our system, we found that our system is very good in performing fine-grained clustering, but performs rather poorly when performing coarser-grained clustering. [ABSTRACT FROM AUTHOR]

The RACCROCHE pipeline reconstructs ancestral gene orders and chromosomal contents of the ancestral genomes at all internal vertices of a phylogenetic tree. The strategy is to accumulate a very large number of generalized adjacencies, phylogenetically justified for each ancestor, to produce long ancestral contigs through maximum weight matching. It constructs chromosomes by counting the frequencies of ancestral contig co-occurrences on the extant genomes, clustering these for each ancestor and ordering them. The main objective of this paper is to closely simulate the evolutionary process giving rise to the gene content and order of a set of extant genomes (six distantly related monocots), and to assess to what extent an updated version of RACCROCHE can recover the artificial ancestral genome at the root of the phylogenetic tree relating to the simulated genomes. [ABSTRACT FROM AUTHOR]

In modern production systems, scheduling problems have to be solved in consideration of frequently changing demands and varying production parameters. This paper presents a approach combining forecasting and classification techniques to predict uncertainty from demands, and production data with heuristics, metaheuristics, and discrete event simulation for obtaining machine schedules. The problem is a hybrid flow shop with two stages, machine qualifications, skipping stages, and uncertainty in demands. The objective is to minimize the makespan. First, based on the available data of past orders, jobs that are prone to fluctuations just before or during the production phase are identified by clustering algorithms, and production volumes are adjusted accordingly. Furthermore, the distribution of scrap rates is estimated, and the quantiles of the resulting distribution are used to increase corresponding production volumes to prevent costly rescheduling resulting from unfulfilled demands. Second, Shortest Processing Time (SPT), tabu search, and local search algorithms are developed and applied. Third, the best performing schedules are evaluated and selected using a detailed simulation model. The proposed approach is validated on a real-world production case. The results show that the price for a very robust schedule that avoids underproduction with a high probability can significantly increase the makespan. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach for selecting a subset of features in semi-supervised datasets where only some of the patterns are labeled. The whole process is completed in two phases. In the first phase, i.e., Phase-I, the whole dataset is divided into two parts: The first part, which contains labeled patterns, and the second part, which contains unlabeled patterns. In the first part, a small number of features are identified using well-known maximum relevance (from first part) and minimum redundancy (whole dataset) based feature selection approaches using the correlation coefficient. The subset of features from the identified set of features, which produces a high classification accuracy using any supervised classifier from labeled patterns, is selected for later processing. In the second phase, i.e., Phase-II, the patterns belonging to the first and second part are clustered separately into the available number of classes of the dataset. In the clusters of the first part, take the majority of patterns belonging to a cluster as the class for that cluster, which is given already. Form the pairs of cluster centroids made in the first and second part. The centroid of the second part nearest to a centroid of the first part will be paired. As the class of the first centroid is known, the same class can be assigned to the centroid of the cluster of the second part, which is unknown. The actual class of the patterns if known for the second part of the dataset can be used to test the classification accuracy of patterns in the second part. The proposed two-phase approach performs well in terms of classification accuracy and number of features selected on the given benchmarked datasets. [ABSTRACT FROM AUTHOR]

As of today, bioinformatics is one of the most exciting fields of scientific research. There is a wide-ranging list of challenging problems to face, i.e., pairwise and multiple alignments, motif detection/discrimination/classification, phylogenetic tree reconstruction, protein secondary and tertiary structure prediction, protein function prediction, DNA microarray analysis, gene regulation/regulatory networks, just to mention a few, and an army of researchers, coming from several scientific backgrounds, focus their efforts on developing models to properly address these problems. In this paper, we aim to briefly review some of the huge amount of machine learning methods, developed in the last two decades, suited for the analysis of gene microarray data that have a strong impact on molecular biology. In particular, we focus on the wide-ranging list of data clustering and visualization techniques able to find homogeneous data groupings, and also provide the possibility to discover its connections in terms of structure, function and evolution. [ABSTRACT FROM AUTHOR]

Clustering is one of the main tasks of machine learning. Internal clustering validation indexes (CVIs) are used to measure the quality of several clustered partitions to determine the local optimal clustering results in an unsupervised manner, and can act as the objective function of clustering algorithms. In this paper, we first studied several well-known internal CVIs for categorical data clustering, and proved the ineffectiveness of evaluating the partitions of different numbers of clusters without any inter-cluster separation measures or assumptions; the accurateness of separation, along with its coordination with the intra-cluster compactness measures, can notably affect performance. Then, aiming to enhance the internal clustering validation measurement, we proposed a new internal CVI—clustering utility based on the averaged information gain of isolating each cluster (CUBAGE)—which measures both the compactness and the separation of the partition. The experimental results supported our findings with regard to the existing internal CVIs, and showed that the proposed CUBAGE outperforms other internal CVIs with or without a pre-known number of clusters. [ABSTRACT FROM AUTHOR]

This paper proposes the Bayesian Extreme Learning Machine Kohonen Network (BELMKN) framework to solve the clustering problem. The BELMKN framework uses three levels in processing nonlinearly separable datasets to obtain efficient clustering in terms of accuracy. In the first level, the Extreme Learning Machine (ELM)-based feature learning approach captures the nonlinearity in the data distribution by mapping it onto a d-dimensional space. In the second level, ELM-based feature extracted data is used as an input for Bayesian Information Criterion (BIC) to predict the number of clusters termed as a cluster prediction. In the final level, feature-extracted data along with the cluster prediction is passed to the Kohonen Network to obtain improved clustering accuracy. The main advantage of the proposed method is to overcome the problem of having a priori identifiers or class labels for the data; it is difficult to obtain labels in most of the cases for the real world datasets. The BELMKN framework is applied to 3 synthetic datasets and 10 benchmark datasets from the UCI machine learning repository and compared with the state-of-the-art clustering methods. The experimental results show that the proposed BELMKN-based clustering outperforms other clustering algorithms for the majority of the datasets. Hence, the BELMKN framework can be used to improve the clustering accuracy of the nonlinearly separable datasets. [ABSTRACT FROM AUTHOR]