Adaptive Affinity Propagation Research Articles

Fast screening of lithium-ion batteries for second use with pack-level testing and machine learning

Fast and accurate screening of retired lithium-ion batteries is critical to an efficient and reliable second use with improved performance consistency, contributing to the sustainability of renewable energy sources. However, time-consuming testing, representative criteria extraction, and large module-to-module inconsistencies at the end of first life all pose great challenges for fast screening. This paper proposes a fast screening approach with pack-level testing and machine learning to evaluate and classify module-level aging, where disassembly of the battery pack and individual testing of modules are not required. Dynamic characteristic-based criteria are designed to extract the comprehensive performance of the retired modules, making the approach applicable for battery packs with module state-of-charge inconsistencies up to 30%. Adaptive affinity propagation clustering is utilized to classify the modules and further accelerate the screening progress. The proposed approach is implemented and validated by conducting pack-level and module-level experiments with a retired battery pack consisting of 95 modules connected in series. The proposed approach screening time is reduced by at least 50% compared with approaches that require module-level testing. Reasonable static performance consistency and better dynamic performance consistency, as well as higher screening stability, are achieved, achieving the average overall performance improvement of 18.94%, 4.83% and 34.41% compared with the three benchmarks, respectively. Its adaptability to a larger current rate shows promise for large-scale applications in second-use screening.

Signal enhancement in wireless sensor networks based on adaptive filters

Wireless sensor networks are widely used in communication, medical treatment, radar and detection. With the vigorous development of computer science and intelligent technology, wireless sensor networks are also constantly improving in the development. Sensor networks are prone to noise interference when input signals, which will affect the estimation accuracy of the network. In order to enhance the signal of sensor network and improve its accuracy, a distributed filtering algorithm based on fusion adaptive weighting is proposed. Before building the model, the experiment first studied the three traditional adaptive filtering algorithms, LMS, RLS and AP, as the basis for building the experimental model. Then, combined with the distributed characteristics of the sensor network, the attributes of the nodes and their influence in the network were considered in the experiment, and the importance and support of the nodes were linearly weighted to obtain the estimated certainty of each sensor node to the target. Finally, a fusion adaptive weighted distributed filtering algorithm is constructed in the experiment. The simulation experiment verifies that the constructed model can reduce the noise interference to a certain extent, which is conducive to the enhancement of its network signal, and its error estimation accuracy is also improved.

Applying machine learning to understand water security and water access inequality in underserved colonia communities

This paper explores the application of machine learning to enhance our understanding of water accessibility issues in underserved communities called colonias located along the northern part of the United States–Mexico border. We analyzed >2000 such communities using data from the Rural Community Assistance Partnership (RCAP) and applied hierarchical clustering and the adaptive affinity propagation algorithm to automatically group colonias into clusters with different water access conditions. The Gower distance was introduced to make the algorithm capable of processing complex datasets containing both categorical and numerical attributes. To better understand and explain the clustering results derived from the machine learning process, we further applied a decision tree analysis algorithm to associate the input data with the derived clusters, to identify and rank the importance of factors that characterize different water access conditions in each cluster. Our results complement experts' priority rankings of water infrastructure needs, providing a more in-depth view of the water insecurity challenges that the colonias suffer from. As an automated and reproducible workflow combining a series of tools, the proposed machine learning pipeline represents an operationalized solution for conducting data-driven analysis to understand water access inequality. This pipeline can be adapted to analyze different datasets and decision scenarios.

An Image Segmentation Method Based on the Law of Universal Gravitation and Adaptive Affinity Propagation Spectrum Clustering

There are many problems of division in natural and social sciences, and with the development of science and technology, the requirement for division is also increasing. It is difficult to divide accurately by experience and expertise alone, and the most important research branch of the division problem is the clustering algorithm. It is to group similar samples into one class and divide the elements with large differences into different classes. Due to the simplicity and efficiency of the clustering algorithm, it is widely used in image segmentation. The conventional Spectral Clustering (SC) algorithm cannot recognize nonconvex data and has the disadvantage of strong dependence on biased parameter values. To address this problem, the Gravity-based Adaptive Spectral Clustering (GASC) algorithm is proposed in this study. Based on the conventional SC algorithm, the algorithm uses gravity to calculate the similarity (gravity) between data, and uses information entropy and adaptive enhancement (AdaBoost) algorithms to obtain the weights of correct cluster sampling points and wrong cluster sampling points in each cluster, so as to reduce the dependence of the algorithm on bias parameters and reduce the number of wrongly divided sample points. Meanwhile, the GASC algorithm is applied to image segmentation. The implementation process includes three stages: image preprocessing, feature extraction, and clustering. The comparison experiments show that the mean values of normalization and accuracy of the GASC algorithm are improved compared with other clustering algorithms, and the segmentation accuracy for images is higher.

Automatic Diagnosis of Microgrid Networks’ Power Device Faults Based on Stacked Denoising Autoencoders and Adaptive Affinity Propagation Clustering

This paper presents a model based on stacked denoising autoencoders (SDAEs) in deep learning and adaptive affinity propagation (adAP) for bearing fault diagnosis automatically. First, SDAEs are used to extract potential fault features and directly reduce their high dimension to 3. To prove that the feature extraction capability of SDAEs is better than stacked autoencoders (SAEs), principal component analysis (PCA) is employed to compare and reduce their dimension to 3, except for the final hidden layer. Hence, the extracted 3-dimensional features are chosen as the input for adAP cluster models. Compared with other traditional cluster methods, such as the Fuzzy C-mean (FCM), Gustafson–Kessel (GK), Gath–Geva (GG), and affinity propagation (AP), clustering algorithms can identify fault samples without cluster center number selection. However, AP needs to set two key parameters depending on manual experience—the damping factor and the bias parameter—before its calculation. To overcome this drawback, adAP is introduced in this paper. The adAP clustering algorithm can find the available parameters according to the fitness function automatic. Finally, the experimental results prove that SDAEs with adAP are better than other models, including SDAE-FCM/GK/GG according to the cluster assess index (Silhouette) and the classification error rate.

Joint Point-Interval Prediction and Optimization of Wind Power Considering the Sequential Uncertainties of Stepwise Procedure

To support high-level wind energy utilization, wind power prediction has become a more and more attractive topic. To improve prediction accuracy and flexibility, joint point-interval prediction of wind power via a stepwise procedure is studied in this paper. Firstly, time-information-granularity (TIG) is defined for ultra-short-term wind speed prediction. Hidden features of wind speed in TIGs are extracted via principal component analysis (PCA) and classified via adaptive affinity propagation (ADAP) clustering. Then, Gaussian process regression (GPR) with joint point-interval estimation ability is adopted for stepwise prediction of the wind power, including wind speed prediction and wind turbine power curve (WTPC) modeling. Considering the sequential uncertainties of stepwise prediction, theoretical support for an uncertainty enlargement effect is deduced. Uncertainties’ transmission from single-step or receding multi-step wind speed prediction to wind power prediction is explained in detail. After that, normalized indexes for point-interval estimation performance are presented for GPR parameters’ optimization via a hybrid particle swarm optimization-differential evolution (PSO-DE) algorithm. K-fold cross validation (K-CV) is used to test the model stability. Moreover, due to the timeliness of data-driven GPR models, an evolutionary prediction mechanism via sliding time window is proposed to guarantee the required accuracy. Finally, measured data from a wind farm in northern China are acquired for validation. From the simulation results, several conclusions can be drawn: the multi-model structure has insignificant advantages for wind speed prediction via GPR; joint point-interval prediction of wind power is realizable and very reasonable; uncertainty enlargement exists for stepwise prediction of wind power while it is more significant after receding multi-step prediction of wind speed; a reasonable quantification mechanism for uncertainty is revealed and validated.

A new method of multi- atlas segmentation of right ventricle based on cardiac film magnetic resonance images

Segmentation of right ventricle (RV) in a cine cardiac magnetic resonance (CMR) image is essential for the diagnosis and therapy of cardiac diseases. Traditional image segmentation methods fail to achieve high accuracy due to the complex structure of RV. Multi-atlas frame, which transforms the segmentation into registration and fusion, has become one of the main segmentation methods of RV in recent years. In this paper, we suggest a new multi-atlas frame for the automatical and accurate segmentation of RV. Firstly, an adaptive affinity propagation algorithm is used to obtain a series of atlases, in which the atlas set most similar to the target image based on hausdorff distance and normalized mutual information is selected. Then, the target image is registered onto the selected atlas by using multi-resolution strategy-based affine transform and Diffeomorphic demons algorithm to generate a deformation field, which is applied to the label image to obtain coarse segmentation results of RV. Finally, the Consensus Level, Labeler Accuracy and Truth Estimation (COLLATE) algorithm is used to fuse the coarse segmentation result to obtain the RV. The 30 cine CMR datasets are applied to the retrospective analysis. The comparison between RV value from the present algorithm and that from the manual segmentation shows that the average dice index and hausdorff distance are 0.84 and 11.46 mm, respectively, the correlation coefficients and deviation means of endo-diastolic volume, endo-systolic volume and ejection fraction are 0.94, 0.90, 0.86, and 2.5113, –3.4783, 0.0341, respectively. Compared with convolutional neural networks, the new multi-atlas frame has an endo-systolic volume close to the manual result. The results show that the suggested method improves the accuracy and robustness of segmentation of RV from the effective atlas selection and multi-resolution Diffeomorphic demons algorithm-based registration, and it promises to be applied to clinical diagnosis.

Multi-Objective Optimization of Time-of-Use Price for Tertiary Industry Based on Generalized Seasonal Multi- Model Structure

In the smart grid, the demand-side management of power load plays an essential role to improve power load curve where time-of-use (TOU) price incentive is widely used to mobilize the multi-time-scale response ability of demand-side. Considering the seasonal and daily characteristics of user power load, in this paper, the dynamic multi-objective optimization of TOU price under multi-model structure is mainly studied. First, the preprocessing of raw power load data is systematically discussed, including abnormal data elimination and missing data reconstruction. Then, combining adaptive affinity propagation (adAP) clustering and fuzzy k-nearest neighbor (FKNN) clustering, generalized seasons are divided while peak-flat-valley time periods are redivided for each season. Subsequently, a frequency-separated demand response model structure involving steady-state and uncertainty terms is built to approach actual user load response with balanced model complexity and accuracy. For each seasonal model using this structure, the multi-objective optimization problem of TOU price is formed where non-dominated sorting genetic algorithm-II (NSGA-II) with probabilistic deviation sorting order strategy is proposed to select the balance optimal solutions. Finally, the effectiveness of the above methods is validated. The simulation results show that if the optimized seasonal TOU prices are adopted, the power load curve can be obviously improved increasing load rate, reducing electricity price expenditure, and ensuring user satisfaction degree.

EVALUATION OF THE CLUSTERING PERFORMANCE OF AFFINITY PROPAGATION ALGORITHM CONSIDERING THE INFLUENCE OF PREFERENCE PARAMETER AND DAMPING FACTOR

Abstract: The identification of significant underlying data patterns such as image composition and spatial arrangements is fundamental in remote sensing tasks. Therefore, the development of an effective approach for information extraction is crucial to achieve this goal. Affinity propagation (AP) algorithm is a novel powerful technique with the ability of handling with unusual data, containing both categorical and numerical attributes. However, AP has some limitations related to the choice of initial preference parameter, occurrence of oscillations and processing of large data sets. This paper evaluates the clustering performance of AP algorithm taking into account the influence of preference parameter and damping factor. The study was conducted considering the AP algorithm, the adaptive AP and partition AP. According to the experiments, the choice of preference and damping greatly influences on the quality and the final number of clusters.

Optimization of Traveling Salesman Problem based on Adaptive Affinity Propagation and Ant Colony Algorithms

Optimization of Traveling Salesman Problem based on Adaptive Affinity Propagation and Ant Colony Algorithms

Adaptive affinity propagation algorithm based on new strategy of dynamic damping factor and preference

The affinity propagation algorithm has been extensively applied in various fields. However, it is still faces two severe challenges in actual applications: one is that the algorithm may be nonconvergent; and the other is that the convergence speed is low. Aiming at solving these two problems, an adaptive affinity propagation algorithm based on a new strategy of dynamic damping factor and preference is proposed in this paper. On one hand, the dynamic damping factor changes the factor value according to the check state of oscillation to eliminate and escape from the oscillation. On the other hand, dynamic preference adjusts the value of the preference based on the bisection and memory tuple to reduce the search scope of the target preferences continuously. Simulation results show that the proposed algorithms can solve the potential nonconvergence problem effectively and reduce the time consumed significantly. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

A Preference Model on Adaptive Affinity Propagation

In recent years, two new data clustering algorithms have been proposed. One of them isAffinity Propagation (AP). AP is a new data clustering technique that use iterative message passing and consider all data points as potential exemplars. Two important inputs of AP are a similarity matrix (SM) of the data and the parameter ”preference” p. Although the original AP algorithm has shown much success in data clustering, it still suffer from one limitation: it is not easy to determine the value of the parameter ”preference” p which can result an optimal clustering solution. To resolve this limitation, we propose a new model of the parameter ”preference” p, i.e. it is modeled based on the similarity distribution. Having the SM and p, Modified Adaptive AP (MAAP) procedure is running. MAAP procedure means that we omit the adaptive p-scanning algorithm as in original Adaptive-AP (AAP) procedure. Experimental results on random non-partition and partition data sets show that (i) the proposed algorithm, MAAP-DDP, is slower than original AP for random non-partition dataset, (ii) for random 4-partition dataset and real datasets the proposed algorithm has succeeded to identify clusters according to the number of dataset’s true labels with the execution times that are comparable with those original AP. Beside that the MAAP-DDP algorithm demonstrates more feasible and effective than original AAP procedure.

AAP: An Adaptive Image Segmentation Algorithm Based on AP Clustering

Pre-specified number of categories, the initial classification center is one of the issues cannot be avoided to clustering-based image segmentation algorithm. In view of this, this paper presents Adaptive Affinity Propagation (AAP) clustering image segmentation algorithm. It adaptively calculates preference in Affinity Propagation clustering using the integral characteristic of image and applies this method to image segmentation. The results of experiments demonstrated that the new method segments image more accurate than classical K-Means and FCM clustering method.

PMA Partition Method of Water Distribution Network Combined with Gragh Theory

A method are proposed combining PMA partition and graph theory with four parts. Using adaptive Affinity Propagation (AP) clustering algorithm with consideration of economic benefit to preliminarily partition water distribution network(WDN) and reasonably determine the partition number. Calculate the shortest path between the clustering centre and water source by Dijkstra algorithm and determine water supply inlet of each region. Establish topology discrete optimization model to determine partition boundary, then applying simulated annealing algorithm to solve the model. Vertically and horizontally combining the partitioned areas to ensure the safety of water supply. This method has been applied to the WDN of Y city to control the pressure for the areas with a certain results.

A New Positioning Scheme Exploiting RSS Difference of Arrival in Indoor Environments

Three basic properties of radio signal, such as received signal strength (RSS), time of flight, and angle of arrival, are commonly used in estimation of distance for positioning of a target. Among them, the positioning technique based on RSS attracts much more interests of researchers due to its high feasibility in realization. However, the performance of the conventional positioning scheme based on RSS is significantly degraded than that of TOA or fingerprinting scheme because of error components from multipath and shadowing effects. In this paper, the RSS-based positioning scheme, which defines RSS difference of arrival (RDOA) likewise time difference of arrival (TDOA) to mitigate error components, is proposed and its performance of position estimation is experimentally analyzed in indoor environments. The performance of the proposed RDOA scheme is compared with that of conventional scheme likewise TOA scheme with respect to the fixed AP selection case, the base AP changing case, and the adaptive AP selection case, respectively. According to the experiment results, it is shown that a high accuracy in position estimation also can be achieved with the RDOA scheme compared to the conventional scheme likewise TOA, while the RDOA scheme can provide less standard deviation than the conventional scheme.

Adaptive affinity propagation method based on improved cuckoo search

Affinity propagation (AP) is an efficient clustering technique to deal with datasets of many instances; however, it has oscillations and its preference value needs to be preset. This study proposes an improved cuckoo search (ICS) technique to solve the AP model. The ICS algorithm utilizes quaternions to represent individuals that are to be optimized. The variable step length of Lévy flights and a method of discovering probability are also proposed. The proposed adaptive AP based on ICS is utilized (or tested) to identify four standard test datasets, such as face images and handwritten digits. The proposed method produces highly accurate results.

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

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

Performance Evaluation of Affinity Propagation Approaches on Data Clustering

Classical techniques for clustering, such as k-means clustering, are very sensitive to the initial set of data centers, so it need to be rerun many times in order to obtain an optimal result. A relatively new clustering approach named Affinity Propagation (AP) has been devised to resolve these problems. Although AP seems to be very powerful it still has several issues that need to be improved. In this paper several improvement or development are discussed in , i.e. other four approaches: Adaptive Affinity Propagation, Partition Affinity Propagation, Soft Constraint Affinity propagation, and Fuzzy Statistic Affinity Propagation. and those approaches are be implemented and compared to look for the issues that AP really deal with and need to be improved. According to the testing results, Partition Affinity Propagation is the fastest one among four other approaches. On the other hand Adaptive Affinity Propagation is much more tolerant to errors, it can remove the oscillation when it occurs where the occupance of oscillation will bring the algorithm to fail to converge. Adaptive Affinity propagation is more stable than the other since it can deal with error which the other can not. And Fuzzy Statistic Affinity Propagation can produce smaller number of cluster compared to the other since it produces its own preferences using fuzzy iterative methods.

Quantitative classification and environmental interpretations for the structural differentiation of the plant communities in the dry valley of Jinshajiang River

The structural differentiation of plant communities are associated with species traits, and interspecific interactions in heterogeneous environment. The comprehensive analysis of spatial variation in species assemblages may help infer processes shaping ecological communities. Based on field investigation of 116 sites and 562 sampling points in the dry valley of Jinshajiang River, combined with vegetation classification by adaptive-affinity propagation, we used Moran’s Eigenvector Maps and variation partitioning to quantify the effects of spatial and environmental factors on the community structure. The results showed that: (1) the plant communities were divided into 30 groups by Adaptive-AP, and classified into 7 vegetation types, 23 formations. Savanna (30.0%) and warm deciduous broadleaved thicket (55.7%) were the main vegetation •研究报告• 408 生 物 多 样 性 Biodiversity Science 第 24 卷 types. (2) Mean annual temperature (MAT) and aridity index (k) are two dominant climate factors limiting the distribution of plant community types in the dry valley of Jinshajiang River. Savanna, succulent thicket and evergreen broadleaved thicket are dominant vegetation types in typical dry-hot valley. Warm deciduous broadleaved thicket and evergreen sclerophyllous forest are dominant in dry-warm valley. Warm needle-leaved forest and deciduous broadleaved forest are more adaptive to lower temperature. (3) The pure environmental fraction can explain 5.5% of the species composition variation, the pure broad-scale spatial fraction can explain 22.5% of the species composition variation, 6.6% can be explained by the fraction corresponding to broad-scale structured environment and the unexplainable part was 65.4%. Among all the factors, MAT and k indicated the critical difference among the community habitats, which has prominent impact on the change of community composition. The broad-scale spatial factors played an important role in shaping the community structure by geographic isolation.

An Affinity Propagation Clustering Algorithm for Mixed Numeric and Categorical Datasets

Clustering has been widely used in different fields of science, technology, social science, and so forth. In real world, numeric as well as categorical features are usually used to describe the data objects. Accordingly, many clustering methods can process datasets that are either numeric or categorical. Recently, algorithms that can handle the mixed data clustering problems have been developed. Affinity propagation (AP) algorithm is an exemplar-based clustering method which has demonstrated good performance on a wide variety of datasets. However, it has limitations on processing mixed datasets. In this paper, we propose a novel similarity measure for mixed type datasets and an adaptive AP clustering algorithm is proposed to cluster the mixed datasets. Several real world datasets are studied to evaluate the performance of the proposed algorithm. Comparisons with other clustering algorithms demonstrate that the proposed method works well not only on mixed datasets but also on pure numeric and categorical datasets.