Normalized Mutual Information Research Articles

Evaluating Template Generation Methods for Spatially Normalizing Down Syndrome Brain Magnetic Resonance Images

AbstractBackgroundMagnetic resonance (MR) image registration and segmentation algorithms commonly used in studies of neurodegeneration have a higher failure rate for Down syndrome (DS) populations due to anatomical and morphological differences. For example, the Desikan‐Killiany atlas used by FreeSurfer was defined using MR images from cognitively normal adults and patients with Alzheimer’s disease (AD). The aim of this work was to evaluate three template generation methods (or group‐wise image registration) for spatially matching DS MR images and generating a DS cohort‐specific template.Method138 scans of DS subjects from the NiAD consortium were employed. The three template generation methods evaluated were DARTEL, SHOOT, and SyGN. DARTEL and SHOOT are implemented in the SPM12 (v7771) software package and operate on tissue segmentation maps. SyGN is implemented in ANTs software and operates on MR images. The data processing pipeline is presented in Figure 1. Scan‐specific grey matter (GM) and white matter (WM) tissue probability maps were generated using SPM12’s Unified Segmentation method for DARTEL and SHOOT, and MR images were skull‐stripped for SyGN. To evaluate spatial matching, all MR images were warped to each template space using method‐specific deformation fields and an average MR image was generated specific to each template method. Structural similarity index measure (SSIM) and Normalized Mutual Information (NMI) metrics were calculated on a scan specific basis relative to the average MR image for each template method. Lower SSIM and NMI measures effectively reflect greater spatial variability across DS scans and therefore worse spatial matching performance.ResultThe DARTEL and SHOOT tissue map (GM and WM) templates and SyGN MR template are presented in Figure 2. Average MRs for each template method are presented in Figure 3. Consistent relationships were observed between the 3 template generation methods for the mean (SHOOT > SyGN > DARTEL) and standard deviation (SyGN < DARTEL < SHOOT) of SSIM and NMI (Figures 4 and 5, Table 1).ConclusionWith relatively high means and the lowest standard deviation, SyGN produced robust spatial matching across all scans. Future Down syndrome MRI and PET image processing will make use of the SyGN template.

An improved author-topic (AT) model with authorship credit allocation schemes

Authorship credit allocation schemes have attracted considerable research attention. However, no consensus about which one is the best has been attained until now, and limited evidence from practical tasks has been reported. Therefore, this study uses the author interest discovery task as a real-world task case to provide valuable insights into authorship credit allocation schemes and guidelines for further practical applications. For this purpose, a novel model, ATcredit, is proposed to strengthen the Author-Topic (AT) model with an authorship credit allocation scheme, and collapsed Gibbs sampling is used to approximate the posterior and estimate model parameters. Extensive experiments using the SynBio dataset reveal several interesting findings as follows. (a) Any scheme for allocating unequal authorship credits performs better than its equal-credit counterpart with our ATcredit model in terms of perplexity. (b) The fixed versions of four out of the six schemes work better than their flexible counterparts with our ATcredit model, regardless of the hyper-authorship strategy. (c) The variation coefficient of credit awards can serve as a criterion to decide whether the hyper-authorship strategy should be used. (d) When the number of authors in a scholarly article is less than three, the six authorship credit allocation schemes are similar to each other with our ATcredit model in terms of perplexity. (e) The harmonic counting scheme performs the best, followed by the arithmetic counting scheme, and the network-based counting scheme performs the worst with our ATcredit model in terms of perplexity. (f) The arithmetic counting scheme is similar to the harmonic counting scheme in terms of the normalised mutual information (NMI) of discovered interests, but the geometric counting scheme is different from the axiomatic and network-based counting schemes.

Examining unsupervised ensemble learning using spectroscopy data of organic compounds.

One solution to the challenge of choosing an appropriate clustering algorithm is to combine different clusterings into a single consensus clusteringresult, known as cluster ensemble (CE). This ensemble learning strategy can provide more robust and stable solutions across different domains and datasets. Unfortunately, not all clusterings in the ensemble contribute to the final data partition. Cluster ensemble selection (CES) aims at selecting a subset from a large library of clustering solutions to form a smaller cluster ensemble that performs as well as or better than the set of all available clustering solutions. In this paper, we investigate four CES methods for the categorization of structurally distinct organic compounds using high-dimensional IR and Raman spectroscopy data. Single quality selection (SQI) forms a subset of the ensemble by selecting the highest quality ensemble members. The Single Quality Selection (SQI) method is used with various quality indices to select subsets by including the highest quality ensemble members. The Bagging method, usually applied in supervised learning,ranksensemble members by calculating the normalized mutual information (NMI) between ensemble members and consensus solutions generated from a randomly sampled subset of the full ensemble. The hierarchical cluster and select method (HCAS-SQI) uses the diversity matrix of ensemble members to select a diverse set of ensemble members with the highest quality. Furthermore, a combining strategy can be used to combine subsets selected using multiple quality indices (HCAS-MQI) for the refinement of clustering solutions in the ensemble. The IR + Raman hybrid ensemble library is created by merging two complementary "views" of the organic compounds. This inherently more diverse library gives the best full ensemble consensus results. Overall, the Bagging method is recommended because it provides the most robust results that are better than or comparable to the full ensemble consensus solutions.

Hiding ourselves from community detection through genetic algorithms

Community structure plays an important role in social networks, which can reveal potential social relationships and deliver vast economic benefits to enterprises and organizations. Many efficient community detection algorithms have been proposed by researchers. However, effective community detection algorithms are accompanied by a growing problem of privacy disclosure. People have started to worry that their private information will be overexposed by community detection algorithms, so determining how to hide the community structure in the network to resist community detection algorithms has become an important issues. In view of this, we develop effective strategies to attack community detection algorithms through invisible disturbances to the network, namely, adding and removing a small number of connections, thus achieving privacy protection. In particular, a hiding strategy named “community hiding based on genetic algorithms using NMI (CGN)” is proposed in this paper. The algorithm uses normalized mutual information (NMI) as the fitness function and achieves an efficient global hiding effect by introducing a gene pool with prior information. We launched attacks based on CGN against four community detection algorithms on multiple real-world networks. By comparing with several state-of-the-art baseline algorithms, our CGN achieved the optimal results in NMI reduction. By visualizing the attack effect, it is proven that our CGN can achieve the community division error of nodes irrelevant to the connection changes by changing a very small number of connections, which fully reflects the concealment of community hiding. In addition, we further test the transferability and find that the modified network obtained by CGN on a specific community detection algorithm also shows extraordinary hiding effects when extended to other algorithms.

CLCLP: Overlapping Community Detection in Networks Using a Combination of Link Community and Label Propagation Algorithm

Overlapping Community Detection is a tremendous method for accepting a crucial shape and complicated network software. As of overlapping communities descriptions of real-world networks must subsist quantified for community identification, this research suggested a method for discovering overlapping communities termed the Combination of Link Community with Label Propagation (CLCLP) algorithm. CLCLP converts a node separation issue into a link division issue because of its simplicity and competency of the label propagation technique, an improved label propagation algorithm that prioritizes connections over nodes to perceive communities has been developed. The proposed CLCLP then employs post-processing to develop discovered overlapping communities by removing over-overlapping and inaccurate fragile secures partitions. When tested on a large scale of synthetic and real-world networks, the proposed CLCLP approach attains good precision (i.e., accuracy) and NMI (Normalized Mutual Information) in recognizing overlapping communities in networks

Sentiment lexicon for cross-domain adaptation with multi-domain dataset in Indian languages enhanced with BERT classification model

Many websites are attempting to offer a platform for users or customers to leave their reviews and comments about the products or services in their native languages. The cross-domain adaptation (CDA) analyses sentiment across domains. The sentiment lexicon falls short resulting in issues like feature mismatch, sparsity, polarity mismatch and polysemy. In this research, an augmented sentiment dictionary is developed in our native regional language (Tamil) that intends to construct the contextual links between terms in multi-domain datasets to reduce problems like polarity mismatch, feature mismatch, and polysemy. Data from the source domain and target domain both labeled and unlabeled are used in the proposed dictionary. To be more specific, the initial dictionary uses normalised pointwise mutual information (nPMI) to derive contextual weight, whereas the final dictionary uses the value of terms across all reviews to compute the accurate rank score. Here, a deep learning model called BERT is used for sentiment classification. For cross-domain adaptation, a modified multi-layer fuzzy-based convolutional neural network (M-FCNN) is deployed. This work aims to build a single dictionary using large number of vocabularies for classifying the reviews in Tamil for several target domains. This extendible dictionary enhances the accuracy of CDA greatly when compared to existing baseline techniques and easily handles a large number of terms in different domains.

Dynamic functional connectivity estimation for neurofeedback emotion regulation paradigm with simultaneous EEG-fMRI analysis.

Joint Analysis of EEG and fMRI datasets can bring new insight into brain mechanisms. In this paper, we employed the recently introduced Correlated Coupled Tensor Matrix Factorization (CCMTF) method for analysis of the emotion regulation paradigm based on EEG frontal asymmetry neurofeedback in the alpha frequency band with simultaneous fMRI. CCMTF method assumes that the co-variations of the common dimension (temporal dimension) between EEG and fMRI are correlated and not necessarily identical. The results of the CCMTF method suggested that EEG and fMRI had similar covariations during the transition of brain activities from resting states to task (view and upregulation) states and these covariations followed an increasing trend. The fMRI shared spatial component showed activations in the limbic system, DLPFC, OFC, and VLPC regions, which were consistent with the previous studies and were linked to EEG frequency patterns in the range of 1–15 Hz with a correlation value close to 0.75. The estimated regions from the CCMTF method were then used as the candidate nodes for dynamic functional connectivity (dFC) analysis, in which the changes in connectivity from view to upregulation states were examined. The results of the dFC analysis were compared with a Normalized Mutual information (NMI) based approach in two different frequency ranges (1–15 and 15–40 Hz) as the NMI method was applied to the vectors of dFC nodes of EEG and fMRI data. The results of the two methods illustrated that the relation between EEG and fMRI datasets was mostly in the frequency range of 1–15 Hz. These relations were both in the brain activations and the dFCs between the two modalities. This paper suggests that the CCMTF method is a capable approach for extracting the shared information between EEG and fMRI data and can reveal new information about brain functions and their connectivity without solving the EEG inverse problem or analyzing different frequency bands.

Exercise improves choroid plexus epithelial cells metabolism to prevent glial cell-associated neurodegeneration.

Recent studies have shown that physical activities can prevent aging-related neurodegeneration. Exercise improves the metabolic landscape of the body. However, the role of these differential metabolites in preventing neurovascular unit degeneration (NVU) is still unclear. Here, we performed single-cell analysis of brain tissue from young and old mice. Normalized mutual information (NMI) was used to measure heterogeneity between each pair of cells using the non-negative Matrix Factorization (NMF) method. Astrocytes and choroid plexus epithelial cells (CPC), two types of CNS glial cells, differed significantly in heterogeneity depending on their aging status and intercellular interactions. The MetaboAnalyst 5.0 database and the scMetabolism package were used to analyze and calculate the differential metabolic pathways associated with aging in the CPC. These mRNAs and corresponding proteins were involved in the metabolites (R)-3-Hydroxybutyric acid, 2-Hydroxyglutarate, 2-Ketobutyric acid, 3-Hydroxyanthranilic acid, Fumaric acid, L-Leucine, and Oxidized glutathione pathways in CPC. Our results showed that CPC age heterogeneity-associated proteins (ECHS1, GSTT1, HSD17B10, LDHA, and LDHB) might be directly targeted by the metabolite of oxidized glutathione (GSSG). Further molecular dynamics and free-energy simulations confirmed the insight into GSSG’s targeting function and free-energy barrier on these CPC age heterogeneity-associated proteins. By inhibiting these proteins in CPC, GSSG inhibits brain energy metabolism, whereas exercise improves the metabolic pathway activity of CPC in NVU by regulating GSSG homeostasis. In order to develop drugs targeting neurodegenerative diseases, further studies are needed to understand how physical exercise enhances NVU function and metabolism by modulating CPC-glial cell interactions.

Tensor Multi-Clustering Parallel Intelligent Computing Method Based on Tensor Chain Decomposition.

Adaptable methods for representing higher-order data with various features and high dimensionality have been demanded by the increasing usage of multi-sensor technologies and the emergence of large data sets. Arrays of multi-dimensional data, known as tensors, can be found in a variety of applications. Standard data that depicts things from a single point of view lacks the semantic richness, utility, and complexity of multi-dimensional data. Research into multi-clustering has taken off since traditional clustering methods are unable to handle large datasets. There are three main kinds of multi-clustering algorithms: Self-weighted Multiview Clustering (SwMC), Latent Multi-view Subspace Clustering (LMSC), and Multi-view Subspace Clustering with Intactness-Aware Similarity (MSC IAS) that are explored in this paper. To evaluate their performance, we do in-depth tests on seven real-world datasets. The three most important metrics Accuracy (ACC), normalized mutual information (NMI), and purity are grouped. Furthermore, traditional Principal Component Analysis (PCA) cannot uncover hidden components within multi-dimensional data. For this purpose, tensor decomposition algorithms have been presented that are flexible in terms of constraint selection and extract more broad latent components. In this examination, we also go through the various tensor decomposition methods, with an emphasis on the issues that classical PCA is designed to solve. Various tensor models are also tested for dimensionality reduction and supervised learning applications in the experiments presented here.

S2-PCM: Super-Resolution Structural Point Cloud Matching for High-Accuracy Video-SAR Image Registration

In this paper, the super-resolution structural point cloud matching (S2-PCM) framework is proposed for video synthetic aperture radar (SAR) inter-frame registration, which consists of a feature recurrence super-resolution network (FRSR-Net), structural point cloud extraction network (SPCE-Net) and robust point matching network (RPM-Net). FRSR-Net is implemented by integrating the feature recurrence structure and residual dense block (RDB) for super-resolution enhancement, SPCE-Net is implemented by training a U-Net with data augmentation, and RPM-Net is applied for robust point cloud matching. Experimental results show that compared with the classical SIFT-like algorithms, S2-PCM achieves higher registration accuracy for video-SAR images under diverse evaluation metrics, such as mutual information (MI), normalized mutual information (NMI), entropy correlation coefficient (ECC), structural similarity (SSIM), etc. The proposed FRSR-Net can significantly improve the quality of video-SAR images and point cloud extraction accuracy. Combining FRSR-Net with S2-PCM, we can obtain higher inter-frame registration accuracy, which is crucial for moving target detection and shadow tracking.

Image preprocessing to improve the accuracy and robustness of mutual-information-based automatic image registration in proton therapy

PurposeWe propose a method that potentially improves the outcome of mutual-information-based automatic image registration by using the contrast enhancement filter (CEF). MethodsSeventy-six pairs of two-dimensional X-ray images and digitally reconstructed radiographs for 20 head and neck and nine lung cancer patients were analyzed retrospectively. Automatic image registration was performed using the mutual-information-based algorithm in VeriSuite®. Images were preprocessed using the CEF in VeriSuite®. The correction vector for translation and rotation error was calculated and manual image registration was compared with automatic image registration, with and without CEF. In addition, the normalized mutual information (NMI) distribution between two-dimensional images was compared, with and without CEF. ResultsIn the correction vector comparison between manual and automatic image registration, the average differences in translation error were < 1 mm in most cases in the head and neck region. The average differences in rotation error were 0.71 and 0.16 degrees without and with CEF, respectively, in the head and neck region; they were 2.67 and 1.64 degrees, respectively, in the chest region. When used with oblique projection, the average rotation error was 0.39 degrees with CEF. CEF improved the NMI by 17.9 % in head and neck images and 18.2 % in chest images. ConclusionsCEF preprocessing improved the NMI and registration accuracy of mutual-information-based automatic image registration on the medical images. The proposed method achieved accuracy equivalent to that achieved by experienced therapists and it will significantly contribute to the standardization of image registration quality.

Functional brain abnormalities in major depressive disorder using a multiscale community detection approach

Major depressive disorder (MDD) is a serious disease associated with abnormal brain regions, however, the interconnection between specific brain regions related to depression has not been fully explored. To solve this problem, the paper proposes a novel multiscale community detection method to compare the differences in brain regions between normal controls (NC) and MDD patients. This study adopted the Brainnetome Atlas to divide the brain into 246 regions and extract the time series of each region. The Pearson correlation was used to measure the similarity among different brain regions to conduct the brain functional network and to perform multiscale community detection. The optimal brain community structure of each group was further explored based on the modularized Qcut algorithm, normalized mutual information (NMI), and variation of information (VI). The Jaccard index was then applied to compare the abnormalities of each brain region from different community environments between the brain function networks of NC and MDD patients. The experiments revealed several abnormal brain regions between NC and MDD, including the superior frontal gyrus, middle frontal gyrus, inferior frontal gyrus, orbital gyrus, superior temporal gyrus, middle temporal gyrus, inferior temporal gyrus, posterior superior temporal sulcus, inferior parietal gyrus, precuneus, postcentral gyrus, insular gyrus, cingulate gyrus, hippocampus and basal ganglia. Finally, a new subnetwork related to cognitive function was discovered, which was composed of the island gyrus and inferior frontal gyrus. All experiments indicated that the proposed method is useful in detecting functional brain abnormalities in MDD, and it can provide valuable insights into the diagnosis and treatment of MDD.

Uncorrelated feature selection via sparse latent representation and extended OLSDA

Modern unsupervised feature selection methods predominantly obtain the cluster structure and pseudo-labels information through spectral clustering. However, the pseudo-labels obtained by spectral clustering are usually mixed between positive and negative. Moreover, the Laplacian matrix in spectral clustering typically affects feature selection. Additionally, spectral clustering does not consider the interconnection information between data. To address these problems, this paper proposes uncorrelated feature selection via sparse latent representation and extended orthogonal least square discriminant analysis (OLSDA), which we term SLREO). Firstly, SLREO retains the interconnection between data by latent representation learning, and preserves the internal information between the data. In order to remove redundant interconnection information, an l2,1-norm constraint is applied to the residual matrix of potential representation learning. Secondly, SLREO obtains non-negative pseudo-labels through orthogonal least square discriminant analysis (OLSDA) of embedded non-negative manifold structure. It not only avoids the appearance of negative pseudo-labels, but also eliminates the effect of the Laplacian matrix on feature selection. The manifold information of the data is also preserved. Furthermore, the matrix of the learned latent representation and OLSDA is used as pseudo-labels information. It not only ensures that the generated pseudo-labels are non-negative, but also makes the pseudo-labels closer to the true class labels. Finally, in order to avoid trivial solutions, an uncorrelated constraint and l2,1-norm constraint are imposed on the feature transformation matrix. These constraints ensure row sparsity of the feature transformation matrix, select low-redundant and discriminative features, and improve the effect of feature selection. Experimental results show that the Clustering Accuracy (ACC) and Normalized Mutual Information (NMI) of SLREO are significantly improved, as compared with six other published algorithms, tested on 11 benchmark datasets.

The trade-off between topology and content in community detection: An adaptive encoder–decoder-based NMF approach

Community detection is an important research field of complex network analysis and focuses on the study of networks’ aggregation behaviours. Different from traditional methods that only consider network structural topology, many efforts have been put into combining network structural topology with node content attributes to achieve better community detection performance. However, it is critical to make an appropriate trade-off between structural topology and node content. In this paper, we propose an adaptive trade-off approach, called ANMF, which not only considers both structural topology and node content, but also provides a flexible parameter to balance their contribution. Compared with other related approaches, ANMF is a kind of non-negative matrix factorization (NMF)-based community detection method, but it imposes more constraints on the network reconstruction. More precisely, ANMF simultaneously employs a decoder that reconstructs a network from its community membership space and an encoder that transforms the network into the community membership space. Moreover, compared with the most related state-of-the-art effort adaptive semantic community detection (ASCD), which considers the topology part always has more contribution if there is a mismatch, ANMF considers the mismatch in two different situations, i.e., the topology part contributes more than the node content part and the node content part contributes more than the topology part. Based on the intensive evaluation on both real and artificial networks, ANMF provides higher normalized mutual information (NMI) values of 4.95%∼126.41% than the models without considering node content information on 13 out of 14 experimental networks. ANMF also presents higher NMI values of 7.38%∼201.01% than ASCD on 13 out of 14 experimental networks. Moreover, ANMF shows good convergence performance, and it can converge after 100 iterations on all of the networks. ANMF also provides stability alike to similar methods in terms of the average NMI standard deviation, which is 0.03 on all of the networks.

Seed Community Identification Framework for Community Detection over Social Media.

The social media podium offers a communal perspective platform for web marketing, advertisement, political campaign, etc. It structures like-minded end-users over the explicit group as a community. Community structure over social media is the collaborative group of globally spread users having similar interests regarding a communal topic, product or any other axis. In recent years, researchers have widely used clustering techniques of data mining to structure communities over social media. Still, due to a lack of network and implicit communal information, researchers cannot bind mutually robust and modular community structures. The collaborative features of social media are inherent with implicit and explicit end-users. The explicit nature of both active and passive users is easily extracted from the graphical structure of social media. On the other hand, the degree of information inclusion of implicit features depends upon end-users participation. The Implicit features of frequently active users are diversely available, while integrating passive and silent users’ implicit features over the community is tedious. This work proposed a social theory based influence maximization (STIM) framework for community detection over social media. It combines user-generated content with profile information, extracts passive social media users through influence maximization, and provides the user space for influencing inactive users. The STIM framework clusters identical nodes over the maximum influencing node axis based on their graphical parameters such as node degree, node similarity, node reachability, modularity, and node density. This framework also provides the structural, relational and mathematical concept for the functional grouping of like-minded people as a community over social media through social theory. Finally, an evaluation has been carried out over six real-time datasets. It analyses that convolution neural network over STIM structure more dense and modular communities via influence maximization. STIM acquired around 93% modularity and 94% Normalized Mutual Information (NMI), resulting in approximately 2.23% and 5.69% improvements in modularity and NMI, respectively, over the best-acquired result of the benchmark approach.

Nonlinear functional network connectivity in resting functional magnetic resonance imaging data.

In this work, we focus on explicitly nonlinear relationships in functional networks. We introduce a technique using normalized mutual information (NMI) that calculates the nonlinear relationship between different brain regions. We demonstrate our proposed approach using simulated data and then apply it to a dataset previously studied by Damaraju et al. This resting‐state fMRI data included 151 schizophrenia patients and 163 age‐ and gender‐matched healthy controls. We first decomposed these data using group independent component analysis (ICA) and yielded 47 functionally relevant intrinsic connectivity networks. Our analysis showed a modularized nonlinear relationship among brain functional networks that was particularly noticeable in the sensory and visual cortex. Interestingly, the modularity appears both meaningful and distinct from that revealed by the linear approach. Group analysis identified significant differences in explicitly nonlinear functional network connectivity (FNC) between schizophrenia patients and healthy controls, particularly in the visual cortex, with controls showing more nonlinearity (i.e., higher normalized mutual information between time courses with linear relationships removed) in most cases. Certain domains, including subcortical and auditory, showed relatively less nonlinear FNC (i.e., lower normalized mutual information), whereas links between the visual and other domains showed evidence of substantial nonlinear and modular properties. Overall, these results suggest that quantifying nonlinear dependencies of functional connectivity may provide a complementary and potentially important tool for studying brain function by exposing relevant variation that is typically ignored. Beyond this, we propose a method that captures both linear and nonlinear effects in a “boosted” approach. This method increases the sensitivity to group differences compared to the standard linear approach, at the cost of being unable to separate linear and nonlinear effects.

SimCTC: A Simple Contrast Learning Method of Text Clustering (Student Abstract)

This paper presents SimCTC, a simple contrastive learning (CL) framework that greatly advances the state-of-the-art text clustering models. In SimCTC, a pre-trained BERT model first maps the input sequence to the representation space, which is then followed by three different loss function heads: Clustering head, Instance-CL head and Cluster-CL head. Experimental results on multiple benchmark datasets demonstrate that SimCTC remarkably outperforms 6 competitive text clustering methods with 1%-6% improvement on Accuracy (ACC) and 1%-4% improvement on Normalized Mutual Information (NMI). Moreover, our results also show that the clustering performance can be further improved by setting an appropriate number of clusters in the cluster-level objective.

Knowledge Discovery in a Recommender System: The Matrix Factorization Approach

Two famous matrix factorization techniques, the Singular Value Decomposition (SVD) and the Nonnegative Matrix Factorization (NMF), are popularly used by recommender system applications. Recommender system data matrices have many missing entries, and to make them suitable for factorization, the missing entries need to be filled. For matrix completion, we use mean, median and mode as three different cases of imputation. The natural clusters produced after factorization are used to formulate simple out-of-sample extension algorithms and methods to generate recommendation for a new user. Two cluster evaluation measures, Normalized Mutual Information (NMI) and Purity are used to evaluate the quality of clusters.

A neighbour-similarity based community discovery algorithm

Discovery of communities in a network is a non-trivial task. Recently, many similarity functions have been introduced to cluster nodes of the same type, but tightness relationship between the nodes inside the clusters always remained as an issue. Another important issue is that for some difficult cases like selecting a community for a node that equally belongs to more than one community which may create an ambiguity in determining the node’s best-fit community remain unaddressed in many community discovery algorithms. A single wrong prediction about a node’s community may lead to an incorrect prediction for other nodes, resulting in a poor community structure. To address such issues, a Neighbour Based Community Detection(NBCD) algorithm based on two novel similarity measures using a similarity parameter α and a set of ground rules are proposed in this work. The similarity parameter α provides a choice for the user to select the tightness of the nodes within the communities. The NBCD algorithm is a two-step process: one is community detection and the next is node shifting. Extensive experiments are carried out on real-world benchmark data sets and artificial networks to assess the performance of the proposed algorithm. NBCD algorithm is compared with several recent and state-of-the-art community discovery algorithms. Normalized Mutual Information(NMI), Adjusted Mutual Information(AMI), Adjusted Rand Index(ARI), F-measure and Modularity are used as the performance measures. Experimental results prove that the proposed algorithm, NBCD, performs well with respect to all the performance measures and performs better than the other community detection algorithms considered.

Analysis of Gut Microbiome Structure Based on GMPR+Spectrum

The gut microbiome is related to many major human diseases, and it is of great significance to study the structure of the gut microbiome under different conditions. Multivariate statistics or pattern recognition methods were often used to identify different structural patterns in gut microbiome data. However, these methods have some limitations. Minimal hepatic encephalopathy (MHE) datasets were taken as an example. Due to the physical lack or insufficient sampling of the gut microbiome in the sequencing process, the microbiome data contains many zeros. Therefore, the geometric mean of pairwise ratios (GMPR) was used to normalize gut microbiome data, then Spectrum was used to analyze the structure of the gut microbiome, and lastly, the structure of core microflora was compared with Network analysis. GMPR calculates the Intraclass correlation coefficient (ICC), whose reproducibility was significantly better than other normalization methods. In addition, running-time, Normalized Mutual Information (NMI), Davies-Boulding Index (DBI), and Calinski-Harabasz index (CH) of GMPR+Spectrum were far superior to other clustering algorithms such as M3C, iClusterPlus. GMPR+Spectrum can not only perform better but also effectively identify the structural differences of intestinal microbiota in different patients and excavate the unique critical bacteria such as Akkermansia, and Lactobacillus in MHE patients, which may provide a new reference for the study of the gut microbiome in disease.