Group-guided individual functional parcellation of the hippocampus and application to normal aging

Aging is closely associated with cognitive decline affecting attention, memory and executive functions. The hippocampus is the core brain area for human memory, learning, and cognition processing. To delineate the individual functional patterns of hippocampus is pivotal to reveal the neural basis of aging. In this study, we developed a group‐guided individual parcellation approach based on semisupervised affinity propagation clustering using the resting‐state functional magnetic resonance imaging to identify individual functional subregions of hippocampus and to identify the functional patterns of each subregion during aging. A three‐way group parcellation was yielded and was taken as prior information to guide individual parcellation of hippocampus into head, body, and tail in each subject. The superiority of individual parcellation of hippocampus is validated by higher intraregional functional similarities by compared to group‐level parcellation results. The individual variations of hippocampus were associated with coactivation patterns of three typical functions of hippocampus. Moreover, the individual functional connectivities of hippocampus subregions with predefined target regions could better predict age than group‐level functional connectivities. Our study provides a novel framework for individual brain functional parcellations, which may facilitate the future individual researches for brain cognitions and brain disorders and directing accurate neuromodulation.

RRH Clustering Using Affinity Propagation Algorithm with Adaptive Thresholding and Greedy Merging in Cloud Radio Access Network

Affinity propagation (AP) clustering with low complexity and high performance is suitable for radio remote head (RRH) clustering for real-time joint transmission in the cloud radio access network. The existing AP algorithms for joint transmission have the limitation of high computational complexities owing to re-sweeping preferences (diagonal components of the similarity matrix) to determine the optimal number of clusters as system parameters such as network topology. To overcome this limitation, we propose a new approach in which preferences are fixed, where the threshold changes in response to the variations in system parameters. In AP clustering, each diagonal value of a final converged matrix is mapped to the position (x,y coordinates) of a corresponding RRH to form two-dimensional image. Furthermore, an environment-adaptive threshold value is determined by adopting Otsu's method, which uses the gray-scale histogram of the image to make a statistical decision. Additionally, a simple greedy merging algorithm is proposed to resolve the problem of inter-cluster interference owing to the adjacent RRHs selected as exemplars (cluster centers). For a realistic performance assessment, both grid and uniform network topologies are considered, including exterior interference and various transmitting power levels of an RRH. It is demonstrated that with similar normalized execution times, the proposed algorithm provides better spectral and energy efficiencies than those of the existing algorithms.

Power Control and Clustering-Based Interference Management for UAV-Assisted Networks

Unmanned Aerial Vehicle (UAV) has been widely used in various applications of wireless network. A system of UAVs has the function of collecting data, offloading traffic for ground Base Stations (BSs) and illuminating coverage holes. However, inter-UAV interference is easily introduced because of the huge number of LoS paths in the air-to-ground channel. In this paper, we propose an interference management framework for UAV-assisted networks, consisting of two main modules: power control and UAV clustering. The power control is executed first to adjust the power levels of UAVs. We model the problem of power control for UAV networks as a non-cooperative game which is proved to be an exact potential game and the Nash equilibrium is reached. Next, to further improve system user rate, coordinated multi-point (CoMP) technique is implemented. The cooperative UAV sets are established to serve users and thus transforming the interfering links into useful links. Affinity propagation is applied to build clusters of UAVs based on the interference strength. Simulation results show that the proposed algorithm integrating power control with CoMP can effectively reduce the interference and improve system sum-rate, compared to Non-CoMP scenario. The law of cluster formation is also obtained where the average cluster size and the number of clusters are affected by inter-UAV distance.

Community Detection in Social Networks Using Affinity Propagation with Adaptive Similarity Matrix

Community detection problem is a projection of data clustering where the network's topological properties are only considered for measuring similarities among nodes. Also, finding communities' kernel nodes and expanding a community from kernel will certainly help us to find optimal communities. Among the existing community detection approaches, the affinity propagation (AP)-based method has been showing promising results and does not require any predefined information such as the number of clusters (communities). AP is an exemplar-based clustering method that defines the negative real-valued similarity measure sim(i, k) between data point i and exemplar k as the probability of k being the exemplar of data point i. According to our intuition, the value of sim(i, k) should not be identical to sim(k, i). In this study, a new version of AP using an adaptive similarity matrix, namely affinity propagation with adaptive similarity (APAS) matrix, is proposed, which could efficiently show the leadership probabilities between data points. APAS can adaptively transform the symmetric similarity matrix into an asymmetric one. It outperforms AP method in terms of accuracy. Extensive experiments conducted on artificial and real-world networks demonstrate the effectiveness of our approach.

An Affinity Propagation-Based Self-Adaptive Clustering Method for Wireless Sensor Networks

A wireless sensor network (WSN) is an essential component of the Internet of Things (IoTs) for information exchange and communication between ubiquitous smart objects. Clustering techniques are widely applied to improve network performance during the routing phase for WSN. However, existing clustering methods still have some drawbacks such as uneven distribution of cluster heads (CH) and unbalanced energy consumption. Recently, much attention has been paid to intelligent clustering methods based on machine learning to solve the above issues. In this paper, an affinity propagation-based self-adaptive (APSA) clustering method is presented. The advantage of K-medoids, which is a traditional machine learning algorithm, is combined with the affinity propagation (AP) method to achieve more reasonable clustering performance. AP is firstly utilized to determine the number of CHs and to search for the optimal initial cluster centers for K-medoids. Then the modified K-medoids is utilized to form the topology of the network by iteration. The presented method effectively avoids the weakness of the traditional K-medoids in aspects of the homogeneous clustering and convergence rate. Simulation results show that the proposed algorithm outperforms some latest work such as the unequal cluster-based routing scheme for multi-level heterogeneous WSN (UCR-H), the low-energy adaptive clustering hierarchy using affinity propagation (LEACH-AP) algorithm, and the energy degree distance unequal clustering (EDDUCA) algorithm.

Exploring Multidimensional Spatiotemporal Point Patterns Based on an Improved Affinity Propagation Algorithm

Affinity propagation (AP) is a clustering algorithm for point data used in image recognition that can be used to solve various problems, such as initial class representative point selection, large-scale sparse matrix calculations, and large-scale data with fewer parameter settings. However, the AP clustering algorithm does not consider spatiotemporal information and multiple thematic attributes simultaneously, which leads to poor performance in discovering patterns from massive spatiotemporal points (e.g., trajectory points). To resolve this issue, a multidimensional spatiotemporal affinity propagation (MDST-AP) algorithm is proposed in this study. First, the similarity of spatial and nonspatial attributes is measured in Gaussian kernel space instead of Euclidean space, which helps address the multidimensional linear inseparability problem. Then, the Davies-Bouldin (DB) index is applied to optimize the parameter value of the MDST-AP algorithm, which is applied to analyze road congestion in Beijing via taxi trajectories. Experiments on different datasets and algorithms indicated that the MDST-AP algorithm can process multidimensional spatiotemporal data points faster and more effectively.

Affinity propagation: An exemplar-based tool for clustering in psychological research

Affinity propagation is a message-passing-based clustering procedure that has received widespread attention in domains such as biological science, physics, and computer science. However, its implementation in psychology and related areas of social science is comparatively scant. In this paper, we describe the basic principles of affinity propagation, its relationship to other clustering problems, and the types of data for which it can be used for cluster analysis. More importantly, we identify the strengths and weaknesses of affinity propagation as a clustering tool in general and highlight potential opportunities for its use in psychological research. Numerical examples are provided to illustrate the method.

Combining affinity propagation clustering and mutual information network to investigate key genes in fibroid

The aim of the present study was to investigate key genes in fibroids based on the multiple affinity propogation-Krzanowski and Lai (mAP-KL) method, which included the maxT multiple hypothesis, Krzanowski and Lai (KL) cluster quality index, affinity propagation (AP) clustering algorithm and mutual information network (MIN) constructed by the context likelihood of relatedness (CLR) algorithm. In order to achieve this goal, mAP-KL was initially implemented to investigate exemplars in fibroid, and the maxT function was employed to rank the genes of training and test sets, and the top 200 genes were obtained for further study. In addition, the KL cluster index was applied to determine the quantity of clusters and the AP clustering algorithm was conducted to identify the clusters and their exemplars. Subsequently, the support vector machine (SVM) model was selected to evaluate the classification performance of mAP-KL. Finally, topological properties (degree, closeness, betweenness and transitivity) of exemplars in MIN constructed according to the CLR algorithm were assessed to investigate key genes in fibroid. The SVM model validated that the classification between normal controls and fibroid patients by mAP-KL had a good performance. A total of 9 clusters and exemplars were identified based on mAP-KL, which were comprised of CALCOCO2, COL4A2, COPS8, SNCG, PA2G4, C17orf70, MARK3, BTNL3 and TBC1D13. By accessing the topological analysis for exemplars in MIN, SNCG and COL4A2 were identified as the two most significant genes of four types of methods, and they were denoted as key genes in the progress of fibroid. In conclusion, two key genes (SNCG and COL4A2) and 9 exemplars were successfully investigated, and these may be potential biomarkers for the detection and treatment of fibroid.

Node Detection and Internode Length Estimation of Tomato Seedlings Based on Image Analysis and Machine Learning

Seedling vigor in tomatoes determines the quality and growth of fruits and total plant productivity. It is well known that the salient effects of environmental stresses appear on the internode length; the length between adjoining main stem node (henceforth called node). In this study, we develop a method for internode length estimation using image processing technology. The proposed method consists of three steps: node detection, node order estimation, and internode length estimation. This method has two main advantages: (i) as it uses machine learning approaches for node detection, it does not require adjustment of threshold values even though seedlings are imaged under varying timings and lighting conditions with complex backgrounds; and (ii) as it uses affinity propagation for node order estimation, it can be applied to seedlings with different numbers of nodes without prior provision of the node number as a parameter. Our node detection results show that the proposed method can detect 72% of the 358 nodes in time-series imaging of three seedlings (recall = 0.72, precision = 0.78). In particular, the application of a general object recognition approach, Bag of Visual Words (BoVWs), enabled the elimination of many false positives on leaves occurring in the image segmentation based on pixel color, significantly improving the precision. The internode length estimation results had a relative error of below 15.4%. These results demonstrate that our method has the ability to evaluate the vigor of tomato seedlings quickly and accurately.

A Mixed Approach to Similarity Metric Selection in Affinity Propagation-Based WiFi Fingerprinting Indoor Positioning

The weighted k-nearest neighbors (WkNN) algorithm is by far the most popular choice in the design of fingerprinting indoor positioning systems based on WiFi received signal strength (RSS). WkNN estimates the position of a target device by selecting k reference points (RPs) based on the similarity of their fingerprints with the measured RSS values. The position of the target device is then obtained as a weighted sum of the positions of the k RPs. Two-step WkNN positioning algorithms were recently proposed, in which RPs are divided into clusters using the affinity propagation clustering algorithm, and one representative for each cluster is selected. Only cluster representatives are then considered during the position estimation, leading to a significant computational complexity reduction compared to traditional, flat WkNN. Flat and two-step WkNN share the issue of properly selecting the similarity metric so as to guarantee good positioning accuracy: in two-step WkNN, in particular, the metric impacts three different steps in the position estimation, that is cluster formation, cluster selection and RP selection and weighting. So far, however, the only similarity metric considered in the literature was the one proposed in the original formulation of the affinity propagation algorithm. This paper fills this gap by comparing different metrics and, based on this comparison, proposes a novel mixed approach in which different metrics are adopted in the different steps of the position estimation procedure. The analysis is supported by an extensive experimental campaign carried out in a multi-floor 3D indoor positioning testbed. The impact of similarity metrics and their combinations on the structure and size of the resulting clusters, 3D positioning accuracy and computational complexity are investigated. Results show that the adoption of metrics different from the one proposed in the original affinity propagation algorithm and, in particular, the combination of different metrics can significantly improve the positioning accuracy while preserving the efficiency in computational complexity typical of two-step algorithms.

Identification of functional networks in resting state fMRI data using adaptive sparse representation and affinity propagation clustering

Human brain functional system has been viewed as a complex network. To accurately characterize this brain network, it is important to estimate the functional connectivity between separate brain regions (i.e., association matrix). One common approach to evaluating the connectivity is the pairwise Pearson correlation. However, this bivariate method completely ignores the influence of other regions when computing the pairwise association. Another intractable issue existed in many approaches to further analyzing the network structure is the requirement of applying a threshold to the association matrix. To address these issues, we develop a novel scheme to investigate the brain functional networks. Specifically, we first establish a global functional connection network by using the Adaptive Sparse Representation (ASR), adaptively integrating the sparsity of ℓ₁-norm and the grouping effect of ℓ₂-norm for linear representation and then identify connectivity patterns with Affinity Propagation (AP) clustering algorithm. Results on both simulated and real data indicate that the proposed scheme is superior to the Pearson correlation in connectivity quality and clustering quality. Our findings suggest that the proposed scheme is an accurate and useful technique to delineate functional network structure for functionally parsimonious and correlated fMRI data with a large number of brain regions.

Accelerated learning-based interactive image segmentation using pairwise constraints

Algorithms for fully automatic segmentation of images are often not sufficiently generic with suitable accuracy, and fully manual segmentation is not practical in many settings. There is a need for semiautomatic algorithms, which are capable of interacting with the user and taking into account the collected feedback. Typically, such methods have simply incorporated user feedback directly. Here, we employ active learning of optimal queries to guide user interaction. Our work in this paper is based on constrained spectral clustering that iteratively incorporates user feedback by propagating it through the calculated affinities. The original framework does not scale well to large data sets, and hence is not straightforward to apply to interactive image segmentation. In order to address this issue, we adopt advanced numerical methods for eigen-decomposition implemented over a subsampling scheme. Our key innovation, however, is an active learning strategy that chooses pairwise queries to present to the user in order to increase the rate of learning from the feedback. Performance evaluation is carried out on the Berkeley segmentation and Graz-02 image data sets, confirming that convergence to high accuracy levels is realizable in relatively few iterations.

Segmentation of high angular resolution diffusion MRI using sparse riemannian manifold clustering

We address the problem of segmenting high angular resolution diffusion imaging (HARDI) data into multiple regions (or fiber tracts) with distinct diffusion properties. We use the orientation distribution function (ODF) to model diffusion and cast the ODF segmentation problem as a clustering problem in the space of ODFs. Our approach integrates tools from sparse representation theory and Riemannian geometry into a graph theoretic segmentation framework. By exploiting the Riemannian properties of the space of ODFs, we learn a sparse representation for each ODF and infer the segmentation by applying spectral clustering to a similarity matrix built from these representations. In cases where regions with similar (resp. distinct) diffusion properties belong to different (resp. same) fiber tracts, we obtain the segmentation by incorporating spatial and user-specified pairwise relationships into the formulation. Experiments on synthetic data evaluate the sensitivity of our method to image noise and to the concentration parameters, and show its superior performance compared to alternative methods when analyzing complex fiber configurations. Experiments on phantom and real data demonstrate the accuracy of the proposed method in segmenting simulated fibers and white matter fiber tracts of clinical importance.

Segmentation based denoising of PET images: an iterative approach via regional means and affinity propagation

Delineation and noise removal play a significant role in clinical quantification of PET images. Conventionally, these two tasks are considered independent, however, denoising can improve the performance of boundary delineation by enhancing SNR while preserving the structural continuity of local regions. On the other hand, we postulate that segmentation can help denoising process by constraining the smoothing criteria locally. Herein, we present a novel iterative approach for simultaneous PET image denoising and segmentation. The proposed algorithm uses generalized Anscombe transformation priori to non-local means based noise removal scheme and affinity propagation based delineation. For nonlocal means denoising, we propose a new regional means approach where we automatically and efficiently extract the appropriate subset of the image voxels by incorporating the class information from affinity propagation based segmentation. PET images after denoising are further utilized for refinement of the segmentation in an iterative manner. Qualitative and quantitative results demonstrate that the proposed framework successfully removes the noise from PET images while preserving the structures, and improves the segmentation accuracy.

Classification of neocortical interneurons using affinity propagation

In spite of over a century of research on cortical circuits, it is still unknown how many classes of cortical neurons exist. In fact, neuronal classification is a difficult problem because it is unclear how to designate a neuronal cell class and what are the best characteristics to define them. Recently, unsupervised classifications using cluster analysis based on morphological, physiological, or molecular characteristics, have provided quantitative and unbiased identification of distinct neuronal subtypes, when applied to selected datasets. However, better and more robust classification methods are needed for increasingly complex and larger datasets. Here, we explored the use of affinity propagation, a recently developed unsupervised classification algorithm imported from machine learning, which gives a representative example or exemplar for each cluster. As a case study, we applied affinity propagation to a test dataset of 337 interneurons belonging to four subtypes, previously identified based on morphological and physiological characteristics. We found that affinity propagation correctly classified most of the neurons in a blind, non-supervised manner. Affinity propagation outperformed Ward's method, a current standard clustering approach, in classifying the neurons into 4 subtypes. Affinity propagation could therefore be used in future studies to validly classify neurons, as a first step to help reverse engineer neural circuits.

Representative landscapes in the forested area of Canada

Canada is a large nation with forested ecosystems that occupy over 60% of the national land base, and knowledge of the patterns of Canada's land cover is important to proper environmental management of this vast resource. To this end, a circa 2000 Landsat-derived land cover map of the forested ecosystems of Canada has created a new window into understanding the composition and configuration of land cover patterns in forested Canada. Strategies for summarizing such large expanses of land cover are increasingly important, as land managers work to study and preserve distinctive areas, as well as to identify representative examples of current land-cover and land-use assemblages. Meanwhile, the development of extremely efficient clustering algorithms has become increasingly important in the world of computer science, in which billions of pieces of information on the internet are continually sifted for meaning for a vast variety of applications. One recently developed clustering algorithm quickly groups large numbers of items of any type in a given data set while simultaneously selecting a representative-or "exemplar"-from each cluster. In this context, the availability of both advanced data processing methods and a nationally available set of landscape metrics presents an opportunity to identify sets of representative landscapes to better understand landscape pattern, variation, and distribution across the forested area of Canada. In this research, we first identify and provide context for a small, interpretable set of exemplar landscapes that objectively represent land cover in each of Canada's ten forested ecozones. Then, we demonstrate how this approach can be used to identify flagship and satellite long-term study areas inside and outside protected areas in the province of Ontario. These applications aid our understanding of Canada's forest while augmenting its management toolbox, and may signal a broad range of applications for this versatile approach.