Final Clustering Research Articles

Consensus graph learning-based self-supervised ensemble clustering

目的 随着实际应用场景中海量数据采集技术的发展和数据标注成本的不断增加，自监督学习成为海量数据分析的一个重要策略。然而，如何从海量数据中抽取有用的监督信息，并该监督信息下开展有效的学习仍然是制约该方向发展的研究难点。为此，提出了一个基于共识图学习的自监督集成聚类框架。方法 框架主要包括3个功能模块。首先，利用集成学习中多个基学习器构建共识图；其次，利用图神经网络分析共识图，捕获节点优化表示和节点的聚类结构，并从聚类中挑选高置信度的节点子集及对应的类标签生成监督信息；再次，在此标签监督下，联合其他无标注样本更新集成成员基学习器。交替迭代上述功能块，最终提高无监督聚类的性能。结果 为验证该框架的有效性，在标准数据集（包括图像和文本数据）上设计了一系列实验。实验结果表明，所提方法在性能上一致优于现有聚类方法。尤其是在MNIST-Test （modified national institute of standards and technology database）上，本文方法实现了97.78%的准确率，比已有最佳方法高出3.85%。结论 该方法旨在利用图表示学习提升自监督学习中监督信息捕获的能力，监督信息的有效获取进一步强化了集成学习中成员构建的能力，最终提升了无监督海量数据本质结构的挖掘性能。;Objective Clustering is focused on machine learning-related data segmentation for multiple datasets. Its applications are in relevant to such domains like image segmentation and anomaly detection. In addition，to simplify complex tasks optimize its performance，clustering is used in data preprocessing tasks of those are data sub-blocks segmentation， pseudo-labels generation，and abnormal points-removal. Self-supervised learning has become an essential technique for massive data analysis. However，it is challenged to extract effective supervision information and analyze the input data. Method A consensus graph learning based self-supervised ensemble clustering（CGL-SEC）framework is developed. It consists of three main modules：1）to construct the consensus graph based on several ensemble components（i. e. ，the basic clustering methods）. 2）to extract the supervision information by learning the consensus graph representation，and 3）its node clustering results，where the subset of nodes with the high-confidence are selected as labeled samples. To optimize the ensemble components and the corresponding consensus graph，t basic clustering methods are re-trained in related the option of samples-labeled and other samples-unlabeled. The final clustering results can be optimized iteratively until the learning process converges. Result A series of experiments are carried out on benchmarks，including both image and textual datasets. Especially，CGL-SEC is 3. 85% over baseline in terms of clustering evaluation metric on themodified national institute of standards and technology database（MNIST-Test）. First，to optimize data representation and cluster assignment at the same time，deep embedding clustering can be focused on data itself as the supervision information and auto-encoder with the reconstruction loss is pre-trained. The soft cluster assignment of features-embedded is then calculated，and the KL（Kullback-Leibler）divergence is minimized between the soft cluster assignment and the auxiliary target distribution. To improve the performance of the model further，following deep clustering network（DCN）can use hard clustering instead of soft allocation，and local constraints are applied by improved deep embedding clustering（IDEC）. The pseudo-label strategy is implemented as a self-supervised learning method that uses the prediction results of the neural network as the label to simulate the supervision information compared to using data itself as the supervision information. Deepcluster-based K-means clustering is used to generate pseudo-labels to guide the training of convolutional networks. However，the generated pseudo-labels have lower confidence and are prone to trivial solutions in the initial stage of network training. Deep embedding clustering with data augmentation（DEC-DA）and MixMatch-based prediction of data-enhanced samples are used as the supervision information of the original data，which improves the accuracy of the supervision information to a certain extent，but this method is difficult to extend to text and other fields. Deep adaptive clustering-based high-confidence pseudo-label subsets-selected are iteratively trained the network in the prediction results，but lowconfidence samples-involved data distribution information is ignored. Pseudo-semi-supervised clustering votes are used to select a subset of high-confidence pseudo-labels，and all samples are used to train semi-supervised neural network. Although the ensemble strategy can improve the confidence of the pseudo-label，the voting strategy is concerned of category representation only without the feature representation of the sample itself，which can reduce the clustering performance in some cases. The ensemble learning is regarded as a representative machine learning method that reflects the ability of group intelligence，whereas a learning method can improve the overall prediction performance via multiple base learners training and their coordinated prediction results. In pseudo-label-based clustering tasks，it can coordinate multiple base learners to obtain high-confidence pseudo-labels. However，the effectiveness of the supervision information acquisition is still to be resolved. The category information of the sample is considered for current pseudo-label-based ensemble clustering method only when the label is captured and some effective information are ignored like the feature representation of the sample itself and the clustering structure between samples. Conclusion Graph neural network is composed of content information of nodes and the structural information between nodes at the same time. To design a self-supervised ensemble clustering method based on consensus graph representation learning，it is required to make full use of sample features and relationships between samples in ensemble learning. To obtain higher confidence pseudo-labels as supervised information and improve the performance of self-supervised clustering，it is necessary to mine global and local information at the same time. We illustrate a learnable data ensemble representation through graph neural network. The confidence of pseudo-labels is improved，and the entire model is trained in self-supervision iteratively. To be summarized：1）Commonly-used consensus graph learning-integrated clustering framework is developed，which can use multi-level information like clusteringintegrated sample characteristics and category structure. 2）Self-supervision method is proposed，which uses graph neural network to mine the global and local information of the consensus graph，and high-confidence pseudo-labels are obtained as supervised information. 3）Experiments are demonstrated that the consensus graph learning ensemble clustering method has its potentials on image and text datasets.

Block Diagonal Representation Learning for Hyperspectral Band Selection

Hyperspectral band selection is viewed as an effective dimension reduction method. Recently, researchers present graph-based clustering for hyperspectral image (HSI) processing. However, most of them conduct clustering on a fixed data matrix so that it is sensitive to the quality of initial matrix. Moreover, these algorithms apply spectral clustering to obtain the final clustering result in increasing the time consumption. Based on these facts, we propose a block diagonal representation learning algorithm (BDRLA) in this paper. BDRLA generates a high-quality similarity matrix by approximating the initial affinity matrix. Meanwhile, motivated to the spectral bands distance similarity matrix has a clear diagonal structure, a block diagonal similarity matrix with ordered partition points based upon the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -norm is constructed. By doing so, the obtained similarity matrix is directly applied to subsequent processing without extracting the clustering indicators. Additionally, in order to estimate the importance of bands, dictionary learning is adopted to select the representative band in each cluster. Extensive experiment results on three public datasets indicate that the bands selected by the proposed method achieve satisfactory performance.

The Application of Clustering on Principal Components for Nutritional Epidemiology: A Workflow to Derive Dietary Patterns.

In the last decades, different multivariate techniques have been applied to multidimensional dietary datasets to identify meaningful patterns reflecting the dietary habits of populations. Among them, principal component analysis (PCA) and cluster analysis represent the two most used techniques, either applied separately or in parallel. Here, we propose a workflow to combine PCA, hierarchical clustering, and a K-means algorithm in a novel approach for dietary pattern derivation. Since the workflow presents certain subjective decisions that might affect the final clustering solution, we also provide some alternatives in relation to different dietary data used. For example, we used the dietary data of 855 women from Catania, Italy. Our approach-defined as clustering on principal components-could be useful to leverage the strengths of each method and to obtain a better cluster solution. In fact, it seemed to disentangle dietary data better than simple clustering algorithms. However, before choosing between the alternatives proposed, it is suggested to consider the nature of dietary data and the main questions raised by the research.

Consensus and complementary regularized non-negative matrix factorization for multi-view image clustering

Multi-view clustering (MVC) aims to classify objects using multi-view data. Many existing MVC methods explore the consensus agreement among views or enhance the complementary features from multiple views in order to improve the clustering quality. However, multi-view data, especially multi-view image data, contains much more complex and meaningful information, which not only describes intrinsic common properties of one object, but also implies rich unique features from different views. Both of them are important and useful for MVC. Though the widely-used non-negative matrix factorization (NMF) based MVC methods can address these two kinds of information, the qualities of learned representations are not well, which limits the clustering performance. To solve this problem, motivated by the ideas of feature selection and graph regularization, a novel NMF based unified representation learning framework is presented with the integration of two specifically designed graph regularization terms in order to obtain a high-quality representation for multi-view data: An unified NMF based optimization problem is formulated to learn the consensus and complementary representations simultaneously and an alternating optimization algorithm is designed to solve this non-convex optimization problem. Then, these learned representations are efficiently fused to create an integrated graph representation for the final clustering. Extensive experiments on six real image datasets demonstrate the superior performance of the proposed method compared with other eleven competitive MVC methods.

One step multi-view spectral clustering via joint adaptive graph learning and matrix factorization

Multi-view clustering based on graph learning has attracted extensive attention due to its simplicity and efficiency in recent years. However, there are still some issues in most of the existing graph-based multi-view clustering methods. First, most of those methods require post-processing such as K-means or spectral rotation to get the final discrete clustering result. Second, graph-based clustering methods perform clustering on a fixed input similarity graph, which could induce bad clustering results if the initial graph is with low quality. Third, these methods have high computation cost, which hinders them for dealing with large-scale data. In order to solve these problems, we propose a multi-view spectral clustering method via joint Adaptive Graph Learning and Matrix Factorization (AGLMF). In this method, to reduce computational cost, we adopt the anchor-based strategy to construct the input similarity graphs. Then, we use the l1-norm to learn a high quality similarity graph adaptively from original similarity graphs which can make the final graph more robust than original ones. In addition, AGLMF uses symmetric non-negative matrix factorization to learn the final clustering indicators which can show the final consistent clustering result directly. Finally, experimental results on multiple multi-view datasets validate the effectiveness of the proposed algorithm when compared with previous multi-view spectral clustering algorithms. The demo code of this work is publicly available at https://github.com/theywq/AGLMF.git.

Research on the optimisation of logistics parcel intelligent sorting and conveying chain combined with variable clustering mathematical method

Abstract The rapid development of China’s economy, especially the rapid rise of the logistics and distribution industry in recent years, coupled with the rise of e-commerce in recent years, has created a huge impact on the traditional logistics industry. Aiming at the sorting system of small and medium-sized logistics distribution centrer, this paper proposes an item allocation strategy based on customer demand in combination with practical application requirements and adopts the direct dynamic clustering algorithm based on hierarchical clustering. As a clustering index, all items in the distribution centre are clustered and the final clustering result is obtained. The results show that the maximum value of segmentation using the single connection method is 5.8, reflecting that the distribution distance is more advantageous; the maximum value of the segmentation method using the median method is 2.94, and the minimum value is 2.35, which reflects that the result of the algorithm is relatively uniform. A reasonable item allocation strategy has a certain positive effect and influence on the development of modern logistics and the service quality of the logistics industry.

An ensemble hierarchical clustering algorithm based on merits at cluster and partition levels

Ensemble clustering has emerged as a combination of several basic clustering algorithms to achieve high quality final clustering. However, this technique is challenging due to the complexities in primary clusters such as overlapping, vagueness, instability and uncertainty. Typically, ensemble clustering uses all the primary clusters into partitions for consensus, where the merits of a cluster or a partition can be considered to improve the quality of the consensus. In general, the robustness of a partition may be poorly measured, while having some high-quality clusters. Inspired by the evaluation of cluster and partition, this paper proposes an ensemble hierarchical clustering algorithm based on the cluster consensus selection approach. Here, the selection of a subset of primary clusters from partitions based on their merit level is emphasized. Merit level is defined using the development of Normalized Mutual Information measure. Clusters of basic clustering algorithms that satisfy the predefined threshold of this measure are selected to participate in the final consensus. In addition, the consensus of the selected primary clusters to create the final clusters is performed based on the clusters clustering technique. In this technique, the selected primary clusters are re-clustered to create hyper-clusters. Finally, the final clusters are formed by assigning instances to hyper-clusters with the highest similarity. Here, an innovative criterion based on merit and cluster size for defining similarity is presented. The performance of the proposed algorithm has been proven by extensive experiments on real-world datasets from the UCI repository compared to state-of-the-art algorithms such as CPDM, ENMI, IDEA, CFTLC and SSCEN.

Big Data Clustering Using Chemical Reaction Optimization Technique: A Computational Symmetry Paradigm for Location-Aware Decision Support in Geospatial Query Processing

The emergence of geospatial big data has opened up new avenues for identifying urban environments. Although both geographic information systems (GIS) and expert systems (ES) have been useful in resolving geographical decision issues, they are not without their own shortcomings. The combination of GIS and ES has gained popularity due to the necessity of boosting the effectiveness of these tools in resolving very difficult spatial decision-making problems. The clustering method generates the functional effects necessary to apply spatial analysis techniques. In a symmetric clustering system, two or more nodes run applications and monitor each other simultaneously. This system is more efficient than an asymmetric system since it utilizes all available hardware and does not maintain a node in a hot standby state. However, it is still a major issue to figure out how to expand and speed up clustering algorithms without sacrificing efficiency. The work presented in this paper introduces an optimized hierarchical distributed k-medoid symmetric clustering algorithm for big data spatial query processing. To increase the k-medoid method’s efficiency and create more precise clusters, a hybrid approach combining the k-medoid and Chemical Reaction Optimization (CRO) techniques is presented. CRO is used in this approach to broaden the scope of the optimal medoid and improve clustering by obtaining more accurate data. The suggested paradigm solves the current technique’s issue of predicting the accurate clusters’ number. The suggested approach includes two phases: in the first phase, the local clusters are built using Apache Spark’s parallelism paradigm based on their portion of the whole dataset. In the second phase, the local clusters are merged to create condensed and reliable final clusters. The suggested approach condenses the data provided during aggregation and creates the ideal clusters’ number automatically based on the dataset’s structures. The suggested approach is robust and delivers high-quality results for spatial query analysis, as shown by experimental results. The proposed model reduces average query latency by 23%.

Big data analysis using a parallel ensemble clustering architecture and an unsupervised feature selection approach

Ensemble clustering is known as a challenging research direction in data mining. The results of several individual clustering methods are combined to produce higher quality final clusters. This study introduces a parallel hierarchical clustering approach based on the divide-and-conquer strategy, which is an attempt to realize faster and more efficient ensemble clustering. Here, we propose a cluster consensus selection approach that selects a subset of meriting primary clusters to participate in the final consensus. Considering the sample-cluster and cluster–cluster similarity on the selected primary clusters, we form the final clusters based on the clusters clustering technique as a consensus function. In addition, the proposed scheme is equipped with an unsupervised feature selection approach to remove features that do not contribute significantly to clustering. Extensive evaluations have been performed on datasets of different dimensions from the University of California Irvine (UCI) machine learning repository. The simulation results guarantee the efficiency of the proposed scheme and improves the average performance between 6% and 24% compared to the state-of-the-art clustering methods.

VDPC: Variational density peak clustering algorithm

The widely applied density peak clustering (DPC) algorithm makes an intuitive cluster formation assumption that cluster centers are often surrounded by data points with lower local density and far away from other data points with higher local density. However, this assumption suffers from one limitation that it is often problematic when identifying clusters with lower density because they might be easily merged into other clusters with higher density. As a result, DPC may not be able to identify clusters with variational density. To address this issue, we propose a variational density peak clustering (VDPC) algorithm, which is designed to systematically and autonomously perform the clustering task on datasets with various types of density distributions. Specifically, we first propose a novel method to identify the representatives among all data points and construct initial clusters based on the identified representatives for further analysis of the clusters’ property. Furthermore, we divide all data points into different levels according to their local density and propose a unified clustering framework by combining the advantages of both DPC and DBSCAN. Thus, all the identified initial clusters spreading across different density levels are systematically processed to form the final clusters. To evaluate the effectiveness of the proposed VDPC algorithm, we conduct extensive experiments using 20 datasets including eight synthetic, six real-world, and six image datasets. The experimental results show that VDPC outperforms two classical algorithms (i.e., DPC and DBSCAN) and four state-of-the-art extended DPC algorithms.

Indonesian pharmacy retailer segmentation using recency frequency monetary-location model and ant K-means algorithm

&lt;span lang="EN-US"&gt;We proposed an approach of retailer segmentation using a hybrid swarm intelligence algorithm and recency frequency monetary (RFM)-location model to develop a tailored marketing strategy for a pharmacy industry distribution company. We used sales data and plug it into MATLAB to implement ant clustering algorithm and K-means, then the results were analyzed using RFM-location model to calculate each clusters’ customer lifetime value (CLV). The algorithm generated 13 clusters of retailers based on provided data with a total of 1,138 retailers. Then, using RFM-location, some clusters were combined due to identical characteristics, the final clusters amounted to 8 clusters with unique characteristics. The findings can inform the decision-making process of the company, especially in prioritizing retailer segments and developing a tailored marketing strategy. We used a hybrid algorithm by leveraging the advantage of swarm intelligence and the power of K-means to cluster the retailers, then we further added value to the generated clusters by analyzing it using RFM-location model and CLV. However, location as a variable may not be relevant in smaller countries or developed countries, because the shipping cost may not be a problem. &lt;/span&gt;

Optimasi Support Vector Mechine (SVM) Menggunakan K-Means dan K-Medoids untuk Klasterisasi Tema Tugas Akhir

The large amount of final project document data from study programs at the Sekolah Tinggi Manajemen Informatika dan Komputer (STMIK) Abulyatama can make a major contribution to the difficulty of the process of grouping a student's final project theme. The clustering process that has been carried out manually so far has been very ineffective and inefficient, so a data mining application is needed to manage the data, especially for clustering the data. The goal to be achieved from writing this thesis is to implement the Support Vector Machine with K-Means and K-Medoids to optimize the final assignment clustering. the results of the Optimization Support Vector Machine (SVM) analysis using K-Means and K-Medoids for Grouping Student Final Project Themes can be concluded in a number of ways, namely; with the K-Means Clustering method it can be seen that there are 23 data mining, 10 networks, 26 artificial intelligence, and 21 websites, and website 11 items.

Enhanced Firefly-K-Means Clustering with Adaptive Mutation and Central Limit Theorem for Automatic Clustering of High-Dimensional Datasets

Metaheuristic algorithms have been hybridized with the standard K-means to address the latter’s challenges in finding a solution to automatic clustering problems. However, the distance calculations required in the standard K-means phase of the hybrid clustering algorithms increase as the number of clusters increases, and the associated computational cost rises in proportion to the dataset dimensionality. The use of the standard K-means algorithm in the metaheuristic-based K-means hybrid algorithm for the automatic clustering of high-dimensional real-world datasets poses a great challenge to the clustering performance of the resultant hybrid algorithms in terms of computational cost. Reducing the computation time required in the K-means phase of the hybrid algorithm for the automatic clustering of high-dimensional datasets will inevitably reduce the algorithm’s complexity. In this paper, a preprocessing phase is introduced into the K-means phase of an improved firefly-based K-means hybrid algorithm using the concept of the central limit theorem to partition the high-dimensional dataset into subgroups of randomly formed subsets on which the K-means algorithm is applied to obtain representative cluster centers for the final clustering procedure. The enhanced firefly algorithm (FA) is hybridized with the CLT-based K-means algorithm to automatically determine the optimum number of cluster centroids and generate corresponding optimum initial cluster centroids for the K-means algorithm to achieve optimal global convergence. Twenty high-dimensional datasets from the UCI machine learning repository are used to investigate the performance of the proposed algorithm. The empirical results indicate that the hybrid FA-K-means clustering method demonstrates statistically significant superiority in the employed performance measures and reducing computation time cost for clustering high-dimensional dataset problems, compared to other advanced hybrid search variants.

Unsupervised neural networks as a support tool for pathology diagnosis in MALDI-MSI experiments: A case study on thyroid biopsies

Artificial intelligence is getting a foothold in medicine for disease screening and diagnosis. While typical machine learning methods require large labeled datasets for training and validation, their application is limited in clinical fields since ground truth information can hardly be obtained on a sizeable cohort of patients. Unsupervised neural networks – such as Self-Organizing Maps (SOMs) – represent an alternative approach to identifying hidden patterns in biomedical data. Here we investigate the feasibility of SOMs for the identification of malignant and non-malignant regions in liquid biopsies of thyroid nodules, on a patient-specific basis. MALDI-ToF (Matrix Assisted Laser Desorption Ionization - Time of Flight) mass spectrometry-imaging (MSI) was used to measure the spectral profile of bioptic samples. SOMs were then applied for the analysis of MALDI-MSI data of individual patients’ samples, also testing various pre-processing and agglomerative clustering methods to investigate their impact on SOMs’ discrimination efficacy. The final clustering was compared against the sample’s probability to be malignant, hyperplastic or related to Hashimoto thyroiditis as quantified by multinomial regression with LASSO. Our results show that SOMs are effective in separating the areas of a sample containing benign cells from those containing malignant cells. Moreover, they allow to overlap the different areas of cytological glass slides with the corresponding proteomic profile image, and inspect the specific weight of every cellular component in bioptic samples. We envision that this approach could represent an effective means to assist pathologists in diagnostic tasks, avoiding the need to manually annotate cytological images and the effort in creating labeled datasets.

DCE-IVI: Density-based clustering ensemble by selecting internal validity index

As each clustering algorithm cannot efficiently partition datasets with arbitrary shapes, the thought of clustering ensemble is proposed to consistently integrate clustering results to obtain better division. Most of ensemble research employs a single algorithm with different parameters to clustering. And this can be easily integrated, however it is hardly to divide complex datasets. Other available methods integrate different algorithms, it can divide datasets from different aspects, but fail to take outliers into account, which produces negative effects on the partition results. In order to solve these problems, we clustering datasets with three different density-based algorithms. The innovation of this paper is described as: (1) by setting dynamic thresholds, lower frequency evidence in the co-association matrix is gradually deleted to obtain multiple reconstructed matrices; (2) these reconstructed matrices are analyzed by hierarchical clustering to obtain basic clustering results; (3) an internal validity index is designed by the compactness within clusters and the correlation between clusters, which is used to select the final clustering result. By this innovation, the clustering effect is significantly improved. Finally, a series of experiments are designed, and the results verify the improvement and effectiveness of the proposed technique (DCE-IVI).

DWDP-Stream: A Dynamic Weight and Density Peaks Clustering Algorithm for Data Stream

Identifying clusters of arbitrary shapes and constantly processing the newly arrived data points are two critical challenges in the study of clustering. This paper proposes a dynamic weight and density peaks clustering algorithm to simultaneously solve these two key issues. An online–offline framework is used, creating and maintaining micro-clusters in the online phase, and treating the micro-clusters as pseudo-points to form the final cluster in the offline phase. In the online phase, when a new data point is merged into the corresponding micro-cluster, a dynamic weight method is proposed to update the weight of the micro-cluster according to the distance between the point and the center of the micro-cluster, so as to more accurately describe the information of the micro-cluster. In the offline phase, the density peak clustering algorithm is improved, natural neighbors are introduced to adaptively obtain the local density of the data point, and the allocation process is improved to reduce the probability of allocation errors. The algorithm is evaluated on different synthetic and real-world datasets using different quality metrics. The experimental results show that the proposed algorithm improves the clustering quality in both static and streaming environments.

Scalable one-stage multi-view subspace clustering with dictionary learning

The clustering of large numbers of heterogeneous features is a hot topic in multi-view communities. Most existing multi-view clustering (MvC) methods employ matrix factorization or anchor strategies to handle large-scale datasets. The former operates on the original data and is, therefore, sensitive to noise and feature redundancy, which is reflected in the final clustering performance. The latter requires post-processing steps to generate the clustering results, which may be suboptimal owing to the isolation steps. To address the above problems, we propose one-stage multi-view subspace clustering with dictionary learning (OSMvSC). Specifically, we integrate dictionary learning, representation coefficient matrix learning, and matrix factorization as a unified learning framework, which directly learns the dictionary and representation coefficient matrix to encode the original multi-view data, and obtains the clustering results with linear time complexity without any postprocessing step. By manipulating the class centroid with the nuclear norm, a more compact and discriminative class centroid representation can be obtained to further improve clustering performance. An effective optimization algorithm with guaranteed convergence is designed to solve the proposed method. Substantial experiments on various real-world multi-view datasets demonstrate the effectiveness and superiority of the proposed method. The source code is available at https://github.com/justcallmewilliam/OSMvSC.

Robust large-scale clustering based on correntropy.

With the explosive growth of data, how to efficiently cluster large-scale unlabeled data has become an important issue that needs to be solved urgently. Especially in the face of large-scale real-world data, which contains a large number of complex distributions of noises and outliers, the research on robust large-scale real-world data clustering algorithms has become one of the hottest topics. In response to this issue, a robust large-scale clustering algorithm based on correntropy (RLSCC) is proposed in this paper, specifically, k-means is firstly applied to generated pseudo-labels which reduce input data scale of subsequent spectral clustering, then anchor graphs instead of full sample graphs are introduced into spectral clustering to obtain final clustering results based on pseudo-labels which further improve the efficiency. Therefore, RLSCC inherits the advantages of the effectiveness of k-means and spectral clustering while greatly reducing the computational complexity. Furthermore, correntropy is developed to suppress the influence of noises and outlier the real-world data on the robustness of clustering. Finally, extensive experiments were carried out on real-world datasets and noise datasets and the results show that compared with other state-of-the-art algorithms, RLSCC can improve efficiency and robustness greatly while maintaining comparable or even higher clustering effectiveness.

In the Belly of the Night and Other Poems. En el vientre de la noche y otros poemas. Ndaani' Gueela' ne xhupa diidxaguie' by Irma Pineda

Reviewed by: In the Belly of the Night and Other Poems. En el vientre de la noche y otros poemas. Ndaani' Gueela' ne xhupa diidxaguie' by Irma Pineda Susan Smith Nash Irma Pineda In the Belly of the Night and Other Poems. En el vientre de la noche y otros poemas. Ndaani' Gueela' ne xhupa diidxaguie' Trans. Wendy Call with the author. Illus. Natalia Gurovich. Mexico City. Pluralia Edicionese Impresiones. 2021. 160 pages. TO PUBLISH POETRY written in endangered Indigenous languages not only preserves the language but also a way of knowing, which is often an alternative epistemology. The work of poet Irma Pineda is no exception. She writes in Isthmus Zapotec, from her rural small town in Oaxaca, Mexico, where the number of speakers is dwindling rapidly. She also writes in Spanish in what she considers to be "mirror poems" rather than denotative translations of each other. To accommodate both versions in a single English version, translator Wendy Call sat with the author, Pineda, who explained just how each poem is shaped, and the kinds of wordplay that each has, and why. In investigating the differences, core ideas about the world and systems of knowledge came to light. For example, in Spanish, en el vientre means "in the belly." However, Gueela does not mean belly or intestines at all but umbilical cord. Further, the umbilical cord is inextricably linked to the house where one was born, because, after birth, the umbilical cord is placed in a small pot, which is then buried under the house. The earth and the body have a unique connection that does not occur with the Spanish colonial impositional culture. The fact that the translator spent time to learn about the embedded beliefs and traditions, and to incorporate them into her English translation, and to explain the process in the preface, is a great contribution to an understanding of the Isthmus Zapotec culture and poetic output. The themes in the clusters of poems include the concept of the guenda, which is simultaneously spirit and animal. "Sun" reflects an animistic view of the world, where objects in the natural world can take on human traits and then shape-shift back. Similarly, the crocodile's eggs swim just as the observer's mind opens to the fecundity of all things and to unbreakable (albeit not always visible) connections. An animist perception of the world is also apparent in a poem from the first cluster of poems, "Red Belt," where the red ribbon wrapped around the narrator's pregnant belly both adorns and protects. The final cluster of poems, "From the Cord House to the Nine Handspans," incorporates Isthmus Zapotec traditions while reflecting on the deep love the narrator has for Sebastian in his journey through life, from the "[umbilical] cord house" where he was born to the "nine handspans" (the grave, nine handspans below the surface of the earth). Knowing that Pineda is writing from her home in Mexico City—and lives in a kind of self-imposed exile from the cluster of Isthmus Zapotec speakers she grew up with—adds another level of loss and nostalgia. Susan Smith Nash University of Oklahoma Copyright © 2022 World Literature Today and the Board of Regents of the University of Oklahoma

SAM-X: sorting algorithm for musculoskeletal x-ray radiography

ObjectiveTo develop a two-phased deep learning sorting algorithm for post-X-ray image acquisition in order to facilitate large musculoskeletal image datasets according to their anatomical entity.MethodsIn total, 42,608 unstructured and pseudonymized radiographs were retrieved from the PACS of a musculoskeletal tumor center. In phase 1, imaging data were sorted into 1000 clusters by a self-supervised model. A human-in-the-loop radiologist assigned weak, semantic labels to all clusters and clusters with the same label were merged. Three hundred thirty-two non-musculoskeletal clusters were discarded. In phase 2, the initial model was modified by “injecting” the identified labels into the self-supervised model to train a classifier. To provide statistical significance, data split and cross-validation were applied. The hold-out test set consisted of 50% external data. To gain insight into the model’s predictions, Grad-CAMs were calculated.ResultsThe self-supervised clustering resulted in a high normalized mutual information of 0.930. The expert radiologist identified 28 musculoskeletal clusters. The modified model achieved a classification accuracy of 96.2% and 96.6% for validation and hold-out test data for predicting the top class, respectively. When considering the top two predicted class labels, an accuracy of 99.7% and 99.6% was accomplished. Grad-CAMs as well as final cluster results underlined the robustness of the proposed method by showing that it focused on similar image regions a human would have considered for categorizing images.ConclusionFor efficient dataset building, we propose an accurate deep learning sorting algorithm for classifying radiographs according to their anatomical entity in the assessment of musculoskeletal diseases.Key Points• Classification of large radiograph datasets according to their anatomical entity.• Paramount importance of structuring vast amounts of retrospective data for modern deep learning applications.• Optimization of the radiological workflow and increase in efficiency as well as decrease of time-consuming tasks for radiologists through deep learning.