Semi-supervised Affinity Propagation Research Articles

Workload forecasting and energy state estimation in cloud data centres: ML-centric approach

Resource management in data centres continues to be a critical problem due to increased infrastructure complexity and dynamic workload conditions. Workload and energy consumption prediction are crucial for efficient resource management decisions in cloud data centres. Existing solutions only consider forecasting the usage of virtual machine resources such as CPU and memory; they do not consider provisioned resources (CPU and memory) and disk, network transmission rates, which significantly affect the energy consumption of the host as well. VM-level energy consumption can be estimated for automated energy management decisions in modern data centres. However, it is not easy to measure energy for VM devices such as CPU, memory, and disk at the software level. In this way, we propose an ML-based model to predict load and energy to aid resource management decisions. For modelling workload predictions, we investigated several distinctive ML algorithms such as Linear Regression (LR), Ridge Regression (RR), ARD Regression (ARDR), ElasticNet (EN) and deep learning (DL) algorithm like Gated Recurrent Unit (GRU). The model’s predictions are measured using standard evaluation metrics like root mean square error (RMSE). We have discovered that GRU has performed very well by accomplishing the most negligible RMSE value for all the workload performances based on experimental results. For energy state estimation, we propose four diverse clustering algorithms, including, semi-supervised affinity propagation based on transfer learning (TSSAP), CLA based on transfer learning (TCLA), kmeans based on transfer learning (TKmeans), P-teda based on transfer learning (TP-teda) to discover similar groups of VMs dependent on features that may influence energy consumption as opposed to estimating it for each VM. The TSSAP has acquired promising clustering accuracy with 87.48% and 53.80% in identifying the VM classes which have been calculated using standard metric such as micro-precision for the chosen workload in compassion to affinity propagation (AP) and the average of other proposed clustering algorithms respectively.

Modified semi-supervised affinity propagation clustering with fuzzy density fruit fly optimization

Affinity propagation (AP) is a clustering method that takes as input measures of similarity between pairs of data points. As the oscillations and preference value need to be preset, the algorithm precision could not be controlled exactly. To improve the performance of AP, this study utilizes priori pairwise constraints to obtain the reliable similarity matrix named semi-supervised affinity propagation (SAP). To find the best solution in domain of preference value, this study also proposes an improved fruit fly optimization (IFO) to optimize the unknown parameters of the SAP model. The IFO algorithm has introduced the fuzzy density mechanism to enhance the searching capacities of fruit fly individuals. The benchmark functions experiments indicate that the IFO algorithm has better precision and convergence speed than other compared swarm intelligence algorithms. We used SAP that based on IFO to identify UCI datasets and synthetic datasets. The simulation results show that proposed clustering algorithm produces significantly better clustering quality and accuracy results. In addition, we utilized the improved model to analyse the seismic data. The clustering results indicated that the proposed model had the better research potential and the good application value.

RETRACTED ARTICLE: A study on e-commerce customer segmentation management based on improved K-means algorithm

With the continuous popularization of the network, the customer resources have to be valued if enterprises want to occupy a certain share in the field of e-commerce. However, the traditional clustering analysis method has obvious lag for the segmentation of e-commerce customers. Therefore, accurate and efficient customer segmentation management should be carried out for the large and complex data information of current e-commerce enterprises, so as to realize customer retention and potential customer mining and promote the efficient development of enterprises. On the basis of customer segmentation theory, for the shortcomings of traditional K-means algorithm, a new SAPK + K-means algorithm based on semi-supervised Affinity Propagation combined with classic K-means algorithm is proposed in combination with AP algorithm, which is applied to e-commerce customers for segmentation management. The results show that when the SAPK + K-means algorithm clusters the iris dataset and the ionosphere dataset, the clustering time is longer than the K-means algorithm and the AP algorithm, but the algorithm error rate in the standard data is significantly reduced and the correct number of clusters can be obtained. The main steps of SAPK + K-means algorithm applied to customer segmentation management including data acquisition, cluster analysis and analysis and evaluation of clustering results. The SAPK + K-means algorithm clusters the data information of an e-commerce customer to obtain four different customer types and proposes corresponding strategies for each type of customer. It is concluded that the SAPK + k-means algorithm can significantly improve the clustering quality of customer data information and improve the effectiveness of activities of e-commerce enterprises.

Clustering ECG heartbeat using improved semi‐supervised affinity propagation

The electrocardiogram (ECG) has become an important tool for the diagnosis of cardiovascular diseases. As long-term ECG recordings become more common, driven partly by the development of intelligent hardware, the requirement for automatic ECG analysis continues to grow. Research has attempted to use the expert knowledge to optimise ECG-related algorithms, however, visual analysis of long-term ECG is tedious and operator dependent. In previous studies, an ECG beat clustering approach based on self-organising maps has been applied to reduce the amount of time the operator must to spend. This unsupervised approach partitions the ECG beats into 25 groups, however, the cluster number (25) does not accurately reflect the actual number of categories. In this study, an integrated method is presented for the clustering of ECG beats based on an improved semi-supervised affinity propagation algorithm with independent component analysis. Using the MIT-BIH arrhythmia database, the authors find that the resulting clusters to exhibit a high degree of precision. The integrated method outperforms other conventional methods in the MIT-BIH database, and has great theoretical and practical significance in the field of cardiac disease.

Image Clustering Using Active-Constraint Semi-Supervised Affinity Propagation

Image clustering is an effective way to discover and analyze large quantities of image data. The HSV color space is particularly advantageous in image feature extraction because of its relatively prominent feature vector. The objective of this study is to develop an image clustering method using the active-constraint semi-supervised affinity propagation (ACSSAP) algorithm. The algorithm adds supervision to the affinity propagation (AP) clustering algorithm with pairwise constraints and uses active learning to guide the AP clustering algorithm. Active learning of pairwise constraints leads to an adjustment of the similarity matrix in AP at each iteration. In the experiments, the advantage of HSV space is analyzed and the ACSSAP algorithm is evaluated for data sets of different sizes in comparison with other algorithms. The result demonstrates that the ACSSAP has better performance.

Semi-supervised affinity propagation based on density peaks

Semi-supervised affinity propagation based on density peaks

Modeling of complex industrial process based on active semi-supervised clustering

Since industrial processes have a wide range of operating conditions, it is difficult to build a single global model that describes a process. One solution that is widely used in control engineering practice is to combine multiple models based on collected process data. For this approach to be successful, it is important to cluster the data before the modeling. In this study, pairwise constraints and an active-learning method were incorporated into the affinity propagation algorithm, resulting in a new method called active semi-supervised affinity propagation (ASSAP) clustering. To apply ASSAP to the modeling of industrial processes, an active-learning strategy is firstly used to obtain constraints on data based on the angle of change between two data points and the probability of their belonging to the same class, and then the constraints are used to adjust the clustering process so as to improve the clustering precision. Finally, the least-squares-support-vector-machine (LS-SVM) is used to build a submodel for each cluster of data points, and then all the sub-models are integrated into a model for the whole data set.Verification of the ASSAP method was carried out on data from the UCI (University of California, Irvine) Machine Learning Repository and Olivetti dataset. In addition, ASSAP and LS-SVM are combined to be applied to the data of the combustion process of a coke oven. The result shows the effectiveness of the method of modeling of complex industrial process based on ASSAP.

Adaptive semi-supervised affinity propagation clustering algorithm based on structural similarity

Adaptive semi-supervised affinity propagation clustering algorithm based on structural similarity

Bayesian Enhanced α-Expansion Move Clustering with Loose Link Constraints

Pairwise link constraints, as an auxiliary information, can help improve the clustering performances a lot. Yet, among them loose link constraints can be acquired more easily and cheaply and hence are more widely utilized in practical applications compared with strong link constraints. Therefore, in this paper, we focus on exemplar-based clustering with loose link constraints. Based on Bayesian probabilistic framework, we naturally integrate the Enhanced α–Expansion Move (EEM) clustering algorithm with loose link constraints, and accordingly propose the Bayesian Enhanced α-Expansion Move Clustering (BEEMLC) algorithm with Loose Link Constraints. The proposed clustering algorithm BEEMLC can exhibit the very applicability of the enhanced α-expansion move clustering in the following two aspects: 1) BEEMLC originates from EEM yet retains the basic spirit of the optimization algorithm contained in EEM. In fact, we directly add a penalty term about loose link constraints into the objective function. Therefore it indeed inherits the advantages of EEM in improving clustering performance but extends such advantages into clustering with loose link constraints. 2) In contrast to other semi-supervised Affinity Propagation clustering algorithms, BEEMLC indeed deals with loose link constraints rather than strong link constraints only. Experiments on benchmarking and real-world datasets, as well as the application of user interactive image segmentation, have shown comparable and even better performance of BEEMLC, compared with other state-of-the-art exemplar-based clustering algorithms.

Semisupervised Affinity Propagation Based on Normalized Trivariable Mutual Information for Hyperspectral Band Selection

The high dimensionality of hyperspectral images brings a heavy burden for image processing. Band selection is a common technique for dimensionality reduction. Since the labels of hyperspectral images are difficult to collect, a new semisupervised band selection method based on affinity propagation (AP) is proposed. AP, an exemplar-based clustering method, is famous due to fast execution time and low reconstruction error. For band selection, AP involves two key issues: band correlation and band preference. In this paper, a new normalized trivariable mutual information (normalized TMI, NTMI) is devised to measure band correlation for classification. NTMI considers not only band redundancy but also band synergy, and overcomes the sensitivity of TMI to the discriminative abilities of bands. Band preference is defined by the discriminative ability and informative amount of each band. Since the clustering methods are easily disturbed by noisy bands, a new statistical-based method for band correlation and band preference is devised. It can automatically remove noisy bands beforehand by exploiting the continuity property of bands. Finally, the proposed method can select highly discriminative and informative bands, and remove highly redundant bands. Experimental results on hyperspectral images demonstrate the effectiveness of the proposed semisupervised band selection method.

Estimation of the Grain-Size Distribution Using Semisupervised Affinity Propagation

AbstractThe grain-size distribution can play an important role in the sediment movement and the bedload transport rate. However, it still remains an important and challenging issue in the study of river behavior. Accurate estimation of the grain-size distribution is desired, while simultaneously one expects to spend much less time on it. Recently image analysis and machine learning techniques facilitated grain identification and measurement on images. In this paper, a semisupervised affinity propagation model (SAPM) oriented to images method is proposed for automatic extraction of the grain-size distribution based on photographs sampled from Wenchuan and Yingxiu in China where landslides and mudslides usually take place. The model to estimate the grain-size distribution is developed and the corresponding algorithm is illustrated in detail. The experiments are finished in both lab and field, and the proposed algorithm is compared with traditional methods. The proposed algorithm produces much better results...

A Fast Semi-supervised Affinity Propagation Community Detection Algorithm

A Fast Semi-supervised Affinity Propagation Community Detection Algorithm

Semi-Supervised Affinity Propagation with Soft Instance-Level Constraints.

Soft-constraint semi-supervised affinity propagation (SCSSAP) adds supervision to the affinity propagation (AP) clustering algorithm without strictly enforcing instance-level constraints. Constraint violations lead to an adjustment of the AP similarity matrix at every iteration of the proposed algorithm and to addition of a penalty to the objective function. This formulation is particularly advantageous in the presence of noisy labels or noisy constraints since the penalty parameter of SCSSAP can be tuned to express our confidence in instance-level constraints. When the constraints are noiseless, SCSSAP outperforms unsupervised AP and performs at least as well as the previously proposed semi-supervised AP and constrained expectation maximization. In the presence of label and constraint noise, SCSSAP results in a more accurate clustering than either of the aforementioned established algorithms. Finally, we present an extension of SCSSAP which incorporates metric learning in the optimization objective and can further improve the performance of clustering.

Improving Wi-Fi Indoor Positioning via AP Sets Similarity and Semi-Supervised Affinity Propagation Clustering

Indoor localization techniques using Wi-Fi fingerprints have become prevalent in recent years because of their cost-effectiveness and high accuracy. The most common algorithm adopted for Wi-Fi fingerprinting is weighted K-nearest neighbors (WKNN), which calculates K-nearest neighboring points to a mobile user. However, existing WKNN cannot effectively address the problems that there is a difference in observed AP sets during offline and online stages and also not all the K neighbors are physically close to the user. In this paper, similarity coefficient is used to measure the similarity of AP sets, which is then combined with radio signal strength values to calculate the fingerprint distance. In addition, isolated points are identified and removed before clustering based on semi-supervised affinity propagation. Real-world experiments are conducted on a university campus and results show the proposed approach does outperform existing approaches.

Full Text Clustering and Relationship Network Analysis of Biomedical Publications

Rapid developments in the biomedical sciences have increased the demand for automatic clustering of biomedical publications. In contrast to current approaches to text clustering, which focus exclusively on the contents of abstracts, a novel method is proposed for clustering and analysis of complete biomedical article texts. To reduce dimensionality, Cosine Coefficient is used on a sub-space of only two vectors, instead of computing the Euclidean distance within the space of all vectors. Then a strategy and algorithm is introduced for Semi-supervised Affinity Propagation (SSAP) to improve analysis efficiency, using biomedical journal names as an evaluation background. Experimental results show that by avoiding high-dimensional sparse matrix computations, SSAP outperforms conventional k-means methods and improves upon the standard Affinity Propagation algorithm. In constructing a directed relationship network and distribution matrix for the clustering results, it can be noted that overlaps in scope and interests among BioMed publications can be easily identified, providing a valuable analytical tool for editors, authors and readers.

Semi-supervised Affinity Propagation Clustering Algorithm Based on Stratified Combination

针对近邻传播(AP)聚类算法的计算复杂度和准确性，该文提出一种分层组合的半监督近邻传播聚类算法(SAP-SC)。算法引入分层聚类的思想，将一次AP聚类过程等分成若干层聚类，使得处理过程简单、易于实现；每层只关注聚类困难的数据点，并通过构造成对点约束和使用子簇标签映射进行半监督学习；基于组合提升的方法将各层聚类结果加权叠加，从而提升了算法的准确性能。理论分析和实验结果表明：算法在聚类准确性和计算复杂度方面有了较大改进。

A Novel Image Retrieval Algorithm Based on K-Neighbor Semi-Supervised Affinity Propagation Algorithm

A Novel Image Retrieval Algorithm Based on <i>K</i>-Neighbor Semi-Supervised Affinity Propagation Algorithm

Constraint projections for semi-supervised affinity propagation

Affinity propagation (AP) is introduced as an unsupervised learning algorithm for exemplar-based clustering. A few methods are stated to extend the AP model to account for semi-supervised clustering. In this paper, constraint (cannot-link and must-link) projections are illustrated for semi-supervised AP (CPSSAP), a hierarchical semi-supervised clustering algorithm. It is flexible for the relaxation of some constraints during the learning stage. First, the data points of instance-level constraints and other data points are together projected in a lower dimensional space guided by the constraints. Then, AP is performed on the new data points in the lower dimensional space. Finally, a few datasets are chosen for experimentation from the UCI machine learning repository. The results show that CPSSAP performs better than some existing algorithms. Furthermore, visualizations of the original data and data after the projections show that the data points overlap less after the constraint projections of the datasets.

Wavelength Selection of Hyperspectral Scattering Image Using New Semi-supervised Affinity Propagation for Prediction of Firmness and Soluble Solid Content in Apples

Hyperspectral scattering image technology is an effective method for nondestructive measurement of internal qualities of agricultural products. However, hyperspectral scattering images contain a large number of redundant data that affect the detection performance and efficiency. A new semi-supervised affinity propagation (AP) (NSAP) algorithm coupled with partial least square regression was proposed to select the feature wavelengths from the hyperspectral scattering profiles of “Golden Delicious” apples for predicting apple firmness and soluble solid content (SSC). Six hundred apples were analyzed in the experiment, 400 of which were used for the calibration model and the remaining 200 apples were used for the prediction model. Compared with full wavelengths, the number of effective wavelengths for apple firmness and SSC prediction selected by NSAP, respectively, decreased to 28 and 40 %. The root mean square error of prediction decreased from 6.6 to 6.1 N and from 0.66 to 0.63 %, respectively, whereas the correlation coefficient increased from 0.840 to 0.862 and from 0.876 to 0.890, respectively. Better prediction accuracy was achieved by the prediction model using selected wavelengths by NSAP than that by traditional AP, SAP, and genetic algorithm. The NSAP approach provided an effective means of wavelength selection using hyperspectral scattering image technique.