Data Streaming with Affinity Propagation

Recently a new clustering algorithm called “affinity propagation” (AP) has been proposed, which efficiently clustered sparsely related data by passing messages between data points. However, we want to cluster large scale data where the similarities are not sparse in many cases. This paper presents two variants of AP for grouping large scale data with a dense similarity matrix. The local approach is partition affinity propagation (PAP) and the global method is landmark affinity propagation (LAP). PAP passes messages in the subsets of data first and then merges them as the number of initial step of iterations; it can effectively reduce the number of iterations of clustering. LAP passes messages between the landmark data points first and then clusters non-landmark data points; it is a large global approximation method to speed up clustering. Experiments are conducted on many datasets, such as random data points, manifold subspaces, images of faces and Chinese calligraphy, and the results demonstrate that the two approaches are feasible and practicable.

Affinity Propagation is one of the fundamental clustering algorithms used in various Web-based systems and applications. Although Affinity Propagation finds highly accurate clusters, it is computationally expensive to apply Affinity Propagation to a large dataset since it requires iterative computations for all possible pairs of data objects in the dataset. To address the aforementioned issue, this paper presents efficient Affinity Propagation algorithms, namely \textit{C-AP}. In order to increase the clustering speed, C-AP employs \textit{cell-based index} to reduce the number of the computed data object pairs in the clustering procedure. By using the cell-based index, C-AP efficiently detects unnecessary pairs, which do not contribute to its clustering result. For further reducing the computation time, we also present an extension of our algorithm named \textit{Parallel C-AP} that utilizes thread-parallelization techniques. As a result, C-AP and Parallel C-AP detects the same clusters as those of Affinity Propagation with much shorter computation time. Extensive evaluations demonstrate the performance superiority of our proposed algorithms over the state-of-the-art algorithms.

In the field of mechanical fault diagnosis, in order to improve the diagnosis accuracy with high feature dimension, a method of features linear fusion method based on AP(Affinity propagation clustering) and AASC(Affinity Aggregation for Spectral Clustering) algorithm was proposed. Low dimension space was obtained by AP clustering, then using AASC algorithm to fuse this selected features, and gained a new feature, meanwhile which can be used independently as a new feature. In the phase of experiment, this method was compared with respectively LPP and PCA, it’s result indicates that this method is excellent in improving diagnosis accuracy.

An automatic affinity propagation clustering based on improved equilibrium optimizer and t-SNE for high-dimensional data

With the proliferation of smartphones and wearable devices having Micro-Electro-Mechanical Systems (MEMS) sensors built in, data samples of linear acceleration and angular velocity can be collected almost anytime anywhere. These motion data can be used to identify various types of human motions and to detect the anomaly of individuals movements. This work presents attempts to use the unsupervised Affinity Propagation (AP) clustering algorithm and the supervised Support Vector Machine (SVM) classification algorithm to identify four types of human gait motions: walking, jogging, climbing upstairs and downstairs. Features of three-dimensional linear acceleration that can enable the algorithms to identify these motion types correctly were selected by analyzing the variation of the feature values among different motion types. Efficacy of Affinity Propagation (AP), Linear and Non-linear Support Vector Machine (SVM) algorithms were also studied by comparing their ratios of correct, false positive, false negative and F1 score classification. This preliminary study demonstrated Linear SVM achieved the best performance, followed by Affinity Propagation. Quite surprisingly, Non-linear SVM appeared to be inferior to the other two algorithms.

A vast amount of time-series data is generated from multiple fields. Mining these data can uncover hidden patterns and behavior characteristics. The analysis of such data is complex because they are voluminous and have high dimensions. Clustering can provide a preprocessing step to extract insights. However, clustering such data poses challenges, as many existing algorithms are not efficient enough to handle them. In addition, many traditional and modern clustering algorithms need help with parameter-tuning problems. Ensemble clustering, an amalgamation of clustering algorithms, has emerged as a promising method for improving the accuracy, stability, and robustness of clustering solutions. This study presents Ensemble clustering using Affinity Propagation (ECAP). AP is efficient because it does not require the number of clusters to be specified a priori, allowing the data to reveal its structure. When used in an ensemble framework, the inherent strengths of AP are amplified by integrating multiple clustering results. This aggregation mitigates the influence of any single, potentially suboptimal clustering outcome, leading to more stable and reliable clusters. Extensive experiments were performed on four real-world datasets for rand index, homogeneity, completeness, and V-measure to determine the efficacy of the proposed approach. The results show that the proposed method outperforms AP, Kmeans, and spectral clustering.

The affinity propagation (AP) clustering algorithm has received much attention in the past few years. AP is appealing because it is efficient, insensitive to initialization, and it produces clusters at a lower error rate than other exemplar-based methods. However, its single-exemplar model becomes inadequate when applied to model multisubclasses in some situations such as scene analysis and character recognition. To remedy this deficiency, we have extended the single-exemplar model to a multi-exemplar one to create a new multi-exemplar affinity propagation (MEAP) algorithm. This new model automatically determines the number of exemplars in each cluster associated with a super exemplar to approximate the subclasses in the category. Solving the model is NP--hard and we tackle it with the max-sum belief propagation to produce neighborhood maximum clusters, with no need to specify beforehand the number of clusters, multi-exemplars, and superexemplars. Also, utilizing the sparsity in the data, we are able to reduce substantially the computational time and storage. Experimental studies have shown MEAP's significant improvements over other algorithms on unsupervised image categorization and the clustering of handwritten digits.

Clustering data into meaningful subsets is a major task in scientific data analysis. To date, various strategies ranging from model-based approaches to data-driven schemes, have been devised for efficient and accurate clustering. One important class of clustering methods that is of a particular interest is the class of exemplar-based approaches. This interest primarily stems from the amount of compressed information encoded in these exemplars that effectively reflect the major characteristics of the respective clusters. Affinity propagation (AP) has proven to be a powerful exemplar-based approach that refines the set of optimal exemplars by iterative pairwise message updates. However, a critical limitation is its inability to capitalize on known networked relations between data points often available for various scientific datasets. To mitigate this shortcoming, we propose geometric-AP, a novel clustering algorithm that effectively extends AP to take advantage of the network topology. Geometric-AP obeys network constraints and uses max-sum belief propagation to leverage the available network topology for generating smooth clusters over the network. Extensive performance assessment reveals a significant enhancement in the quality of the clustering results when compared to benchmark clustering schemes. Especially, we demonstrate that geometric-AP performs extremely well even in cases where the original AP fails drastically.

Recently, Frey & Dueck proposed a novel clustering algorithm named affinity propagation (AP), which has been shown to be powerful as it costs much less time and reaches much lower error. However, its convergence property has not been studied in theory. In this paper, we focus on convergence property of the algorithm. The properties of the decision matrix when the affinity propagation algorithm converges are given, and the criterion that affinity propagation without the damping factor oscillates is obtained. Based on such results, we point out that damping factor might be important to alleviate oscillation of the affinity propagation, but it is not necessary to add a tiny amount of noise to a similarity matrix.

In the future robots will have to operate autonomously for long periods of time. To achieve this, they need to be able to learn directly from their environment without human supervision. The use of clustering methods is one possibility to tackle this challenge. Here we present extensions to affinity propagation, a clustering algorithm proposed by Frey and Dueck [5], which makes it suitable for real-time and long-term use in robotics applications. The proposed extension, called meta-point affinity propagation, introduces so called meta-points which increase the performance of the clustering and allows for incremental usage. Additionally we propose a method that enables us to obtain probabilistic cluster assignments from any affinity propagation based clustering method.We show experimental results on the quality and speed of meta-point affinity propagation as well as the probabilistic cluster assignments. Furthermore, we demonstrate how meta-point affinity propagation allows us to process data sets much larger then what affinity propagation is able to handle.

Affinity propagation (AP) algorithm, as a novel clustering method, does not require the users to specify the initial cluster centers in advance, which regards all data points as potential exemplars (cluster centers) equally and groups the clusters totally by the similar degree among the data points. But in many cases there exist some different intensive areas within the same data set, which means that the data set does not distribute homogeneously. In such situation the AP algorithm cannot group the data points into ideal clusters. In this paper, we proposed an extended AP clustering algorithm to deal with such a problem. There are two steps in our method: firstly the data set is partitioned into several data density types according to the nearest distances of each data point; and then the AP clustering method is, respectively, used to group the data points into clusters in each data density type. Two experiments are carried out to evaluate the performance of our algorithm: one utilizes an artificial data set and the other uses a real seismic data set. The experiment results show that groups are obtained more accurately by our algorithm than OPTICS and AP clustering algorithm itself.

Fault diagnosis plays an important role in complicated industrial process. It is a challenging task to detect, identify and locate faults quickly and accurately for large-scale process system. To solve the problem, a novel MultiBoost-based integrated ENN (extension neural network) fault diagnosis method is proposed. Fault data of complicated chemical process have some difficult-to-handle characteristics, such as high-dimension, non-linear and non-Gaussian distribution, so we use margin discriminant projection(MDP) algorithm to reduce dimensions and extract main features. Then, the affinity propagation (AP) clustering method is used to select core data and boundary data as training samples to reduce memory consumption and shorten learning time. Afterwards, an integrated ENN classifier based on MultiBoost strategy is constructed to identify fault types. The artificial data sets are tested to verify the effectiveness of the proposed method and make a detailed sensitivity analysis for the key parameters. Finally, a real industrial system—Tennessee Eastman (TE) process is employed to evaluate the performance of the proposed method. And the results show that the proposed method is efficient and capable to diagnose various types of faults in complicated chemical process.

Cooperative caching is a promising technology for enhancing user experience and reducing redundant transmissions through the participation of multiple caching nodes. In this paper, we design a clustering algorithm for the sectionalized caching, in which each user divides its caching space into two parts and the contents cached in these two parts are determined according to the individual interest and the joint interest of all users in the same cluster respectively. Different to most of the existing works forming the clusters based on the interest similarity of all files, we adopt the piecewise interest similarity as the criterion of clustering, which takes advantage of the content diversity and contributes to the reduction of the transmission delay. We measure the gain of the cooperation between two users and obtain the piecewise interest similarity for two users accordingly. Since the gain of clustered caching highly depends on the formed cluster structure, we estimate the gain of the clustered caching based on the piecewise interest similarities by online learning and propose an affinity propagation (AP) based clustering algorithm. Finally, our proposed clustering algorithm is evaluated by simulation to show its superiority over the conventional clustering algorithms.

BackgroundThe proportion of people living with dementia (PLWD) is increasing due to aging global populations. Frailty is a complex, multifactorial, and age‐related state of increased vulnerability commonly co‐occurring with Alzheimer’s disease (AD) and vascular dementia (VaD). Variability in frailty levels of PLWD motivates deeper investigation into dementia’s presenting characteristics. Machine learning techniques applied to large medical datasets can identify characterize disease phenotypes. Therefore, the aim of this study is to use unsupervised machine learning to discover frailty‐related clusters in AD and VaD.MethodWe will use data from the United Kingdom Biobank (UKBB), a large‐scale prospective cohort database which includes more than 500,000 participants aged 40‐69 years at baseline. The data include electronic health records, brain magnetic resonance imaging, polygenic risk scores, and frailty index scores. We will select features for clustering using principal component analysis. Clustering algorithms will include k‐means, affinity propagation, and latent class analysis. After cluster characterization, we will evaluate the association between clusters and prevalent AD (n = 2,634) and VaD (n = 1,664) using logistic regression models. Regression models will be stratified by sex and adjusted for age. Receiver‐operating curve will be plotted, and area‐under the curve will be compared using C‐statistics. This study is supported by the Canadian Consortium on Neurodegeneration in Aging Trainee Synapse Project Funds. Our data application has been approved by UKBB.ResultWe expect that the clustering algorithms will reveal several clusters of similar PLWD and allow evaluations based on shared patterns of regional brain atrophy, the degree of frailty, and polygenic risk. In addition, we also expect that clusters characterized by high frailty levels will be associated with prevalent AD and VaD.ConclusionFrailty is an important factor in the clinical evaluation of PLWD. The use of unsupervised machine learning techniques may reveal distinct high‐risk clusters that are related to prevalent AD and VaD. This work may improve early identification of PLWD and aid in the development of personalized care and therapy for people at risk of AD and VaD.

SummaryWireless sensor networks (WSNs), eg, industrial WSNs, require reliability and real‐time communication. Clustering technique together with schedule‐based access can provide the benefits, such as energy saving, reliability, and timeliness. However, integrating above two technologies into WSNs requires sophistical time slot allocation mechanism. To simplify the time slot allocation, the paper proposes a distributed interference‐free clustering algorithm for WSNs. The algorithm is inspired by affinity propagation (AP) clustering algorithm. By adapting and improving the original AP algorithm, the proposed clustering algorithm aims to jointly optimize energy saving and coverage issues while providing interference free between clusters. The performance analysis demonstrates that it can achieve high receiving rate (reliability), low delay (real time), and low‐energy consumption.