Unsupervised Patterns Research Articles

Seeking patterns in rms voltage variations at the sub-10-minute scale from multiple locations via unsupervised learning and patterns' post-processing

This paper addresses the issue of seeking sub-10-min patterns in fast rms voltage variations from time-limited measurement data at multiple locations worldwide. This is a rarely considered time scale in studies that could be important for the incorrect operation of end-user equipment. Moreover, measurements from multiple locations could be significant from the view of seeking pattern methods. To learn more about this time scale, we propose an unsupervised learning method that employs a Kernel Principal Component Analysis (KPCA) with a Cosine kernel to extract principal features from 10-min time series of voltage variations with a 1-s resolution followed by a k-means clustering to group the features. The scheme is applied to measurements from 57 low-voltage locations in 19 countries from 2009 to 2018. Fifteen initial clusters/patterns are then extracted and converted to ten new (general) patterns using a clusters' merging strategy with highly similar patterns employed in a new post-processing approach useful for multiple locations. Utilizing data from multiple locations in multiple countries ensures a level of generality of the patterns. It also allows comparing the locations. Next to the ten general patterns, some typical patterns are extracted separately for every location. A statistical indices analysis confirms that a complete picture of sub-10-min oscillations needs both statistical indices (quantifying level and variations) and the proposed framework (quantifying patterns). The extracted patterns could be used as a reference for testing/putting requirements on the grid-connected equipment and quantifying the grid's hosting capacity for different types of new distributed generations connected to the grid. The framework is scalable and computationally cheap, making it appropriate for seeking typical patterns in the big data domain. Applying the framework to the much less understood phenomenon will result in providing general knowledge in the field of power quality.

Clustering with multi-layered perceptron

Multi-layered perceptron (MLP) is a widely used neural network architecture for supervised learning. The feed-forward network maps unknown data to a label based on prior labeled training samples. The accuracy with which test data is classified correctly depends on the number of training samples. However, in unsupervised learning hidden grouping patterns in data are learnt through various exploratory analysis without any prior knowledge of labels. Clustering using MLP architecture requires defining a different type of loss function. In this paper, we theoretically analyse the effectiveness of a loss function previously reported for this purpose, where the input features are mapped to an output cluster node based on the degree of belongingness. Thus, similar samples are grouped together to form clusters using entropy based measures. Various evaluation techniques to inspect the quality of clusters and intra-cluster distances are used to validate the clustering results on real world data sets.

Supervised mutational signatures for obesity and other tissue-specific etiological factors in cancer.

Determining the etiologic basis of the mutations that are responsible for cancer is one of the fundamental challenges in modern cancer research. Different mutational processes induce different types of DNA mutations, providing 'mutational signatures' that have led to key insights into cancer etiology. The most widely used signatures for assessing genomic data are based on unsupervised patterns that are then retrospectively correlated with certain features of cancer. We show here that supervised machine-learning techniques can identify signatures, called SuperSigs, that are more predictive than those currently available. Surprisingly, we found that aging yields different SuperSigs in different tissues, and the same is true for environmental exposures. We were able to discover SuperSigs associated with obesity, the most important lifestyle factor contributing to cancer in Western populations.

Data Cube Clustering with Improved DBSCAN based on Fuzzy Logic and Genetic Algorithm

Multi-dimensional data, such as data cube, are constructed based on aggregating data in data warehouses and it requires to analyze with high flexibility. Also, clustering, which is an unsupervised pattern recognition analysis, has significant challenges to perform on data cube. In this paper, two new drafts of density-based clustering methods are designed to recognize unsupervised patterns of the data cube. In the first draft, DBSCAN clustering is hybridized by genetic algorithm and called the Improved DBSCAN (IDBSCAN). The motivation of designing the IDBSCAN optimizes the DBSCAN’s parameters by a meta-heuristic algorithm such as GA. The second draft, which is called the Soft Improved DBSCAN (SIDBSCAN), is designed based on fuzzy tuning parameters of the GA in the IDBSCAN. The fuzzy tuning parameters are performed with two fuzzy groups rules of Mamdani (SIDBSCAN-Mamdani) and Sugeno (SIDBSCAN-Sugeno), separately. These ideas are proposed to present efficient and flexible unsupervised analysis for a data cube by utilizing a meta-heuristic algorithm to optimize DBSCAN’s parameters and increasing the efficiency of the idea by applying dynamic tuning parameters of the algorithm. To evaluate the efficiency, the SIDBSCAN-Mamdani and the SIDBSCAN-Sugeno are compared with the IDBSCAN and the DBSCAN. The experimental results, consisted of 20 times running, indicate that the proposed ideas achieved to their targets.

Computational discovery of pathway-level genetic vulnerabilities in non-small-cell lung cancer.

Motivation: Novel approaches are needed for discovery of targeted therapies for non-small-cell lung cancer (NSCLC) that are specific to certain patients. Whole genome RNAi screening of lung cancer cell lines provides an ideal source for determining candidate drug targets.Results: Unsupervised learning algorithms uncovered patterns of differential vulnerability across lung cancer cell lines to loss of functionally related genes. Such genetic vulnerabilities represent candidate targets for therapy and are found to be involved in splicing, translation and protein folding. In particular, many NSCLC cell lines were especially sensitive to the loss of components of the LSm2-8 protein complex or the CCT/TRiC chaperonin. Different vulnerabilities were also found for different cell line subgroups. Furthermore, the predicted vulnerability of a single adenocarcinoma cell line to loss of the Wnt pathway was experimentally validated with screening of small-molecule Wnt inhibitors against an extensive cell line panel.Availability and implementation: The clustering algorithm is implemented in Python and is freely available at https://bitbucket.org/youngjh/nsclc_paper.Contact: marcotte@icmb.utexas.edu or jon.young@utexas.eduSupplementary information: Supplementary data are available at Bioinformatics online.

ToxDB: pathway-level interpretation of drug-treatment data.

Motivation: Extensive drug treatment gene expression data have been generated in order to identify biomarkers that are predictive for toxicity or to classify compounds. However, such patterns are often highly variable across compounds and lack robustness. We and others have previously shown that supervised expression patterns based on pathway concepts rather than unsupervised patterns are more robust and can be used to assess toxicity for entire classes of drugs more reliably.Results: We have developed a database, ToxDB, for the analysis of the functional consequences of drug treatment at the pathway level. We have collected 2694 pathway concepts and computed numerical response scores of these pathways for 437 drugs and chemicals and 7464 different experimental conditions. ToxDB provides functionalities for exploring these pathway responses by offering tools for visualization and differential analysis allowing for comparisons of different treatment parameters and for linking this data with toxicity annotation and chemical information.Database URL: http://toxdb.molgen.mpg.de

What factors affect the visibility of Argentinean publications in humanities and social sciences in Scopus? Some evidence beyond the geographic realm of research

Argentinas patterns of publication in the humanities and social sciences were studied for the period 2003---2012, using the Scopus database and distinguishing the geographic realm of the research. The results indicate that topics of national scope have grown and gained international visibility. They can be broadly characterized as having Spanish as the language of publication, and a marked preference for single authorship; in contrast, the publication of global topics, not geographically limited, characteristically have English as the language of divulgation, and institutional collaboration is stronger and more consolidated. Citation is apparently not determined only by the geographic realm of research, but also by language of publication, co-authorship, and the profiles of the journals where published. These results could contribute to constructive reflection upon publishing policy. The existence of a community of journals that tolerates biased patterns may make researchers echo and perpetuate poor practices, constructing or adapting the channels of communication. Such results also prove useful as a point of reference when evaluation criteria are elaborated by scientific committees, as unsupervised promotion and evaluation patterns could become based on local or overly subjective precepts, disregarding the disciplinary practices of the international scientific community.

Using Unsupervised Patterns to Extract Gene Regulation Relationships for Network Construction

BackgroundThe gene expression is usually described in the literature as a transcription factor X that regulates the target gene Y. Previously, some studies discovered gene regulations by using information from the biomedical literature and most of them require effort of human annotators to build the training dataset. Moreover, the large amount of textual knowledge recorded in the biomedical literature grows very rapidly, and the creation of manual patterns from literatures becomes more difficult. There is an increasing need to automate the process of establishing patterns.Methodology/Principal FindingsIn this article, we describe an unsupervised pattern generation method called AutoPat. It is a gene expression mining system that can generate unsupervised patterns automatically from a given set of seed patterns. The high scalability and low maintenance cost of the unsupervised patterns could help our system to extract gene expression from PubMed abstracts more precisely and effectively.Conclusions/SignificanceExperiments on several regulators show reasonable precision and recall rates which validate AutoPat's practical applicability. The conducted regulation networks could also be built precisely and effectively. The system in this study is available at http://ikmbio.csie.ncku.edu.tw/AutoPat/.