Data Analysis Tasks Research Articles

Unsupervised feature learning for data classification

Data classification is a critical task for data analysis. However, recent methods aim to model this task as a classification or regression task, which needs ground truth for discriminative representation learning. This paper aims to learn a more efficient and effective feature for data analysis in an unsupervised learning manner. Our method consists of two main components: a customized autoencoder network (C-AENet) and a customized squeeze-and-excitation network (C-SENet). The C-AENet aims to reconstruct the feature using the fewer dimension, and C-SENet is to improve the representation by providing channel attention. Experiment on the Avila dataset shows that both modules are effective in data classification with fewer feature dimension.

Estimation and computations for Gaussian mixtures with uniform noise under separation constraints

In this paper we study a finite Gaussian mixture model with an additional uniform component that has the role to catch points in the tails of the data distribution. An adaptive constraint enforces a certain level of separation between the Gaussian mixture components and the uniform component representing noise and outliers in the tail of the distribution. The latter makes the proposed tool particularly useful for robust estimation and outlier identification. A constrained ML estimator is introduced for which existence and consistency is shown. One of the attractive features of the methodology is that the noise level is estimated from data. We also develop an EM-type algorithm with proven convergence. Based on numerical evidence we show how the methods developed in this paper are useful for several fundamental data analysis tasks: outlier identification, robust location-scale estimation, clustering, and density estimation.

Data-driven deep density estimation

Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples. Thus, it is used in tasks as diverse as analyzing population data, spatial locations in 2D sensor readings, or reconstructing scenes from 3D scans. In this paper, we introduce a learned, data-driven deep density estimation (DDE) to infer PDFs in an accurate and efficient manner, while being independent of domain dimensionality or sample size. Furthermore, we do not require access to the original PDF during estimation, neither in parametric form, nor as priors, or in the form of many samples. This is enabled by training an unstructured convolutional neural network on an infinite stream of synthetic PDFs, as unbound amounts of synthetic training data generalize better across a deck of natural PDFs than any natural finite training data will do. Thus, we hope that our publicly available DDE method will be beneficial in many areas of data analysis, where continuous models are to be estimated from discrete observations.

I2dash: Creation of Flexible, Interactive, and Web-based Dashboards for Visualization of Omics Data

Data visualization and interactive data exploration are important aspects of illustrating complex concepts and results from analyses of omics data. A suitable visualization has to be intuitive and accessible. Web-based dashboards have become popular tools for the arrangement, consolidation, and display of such visualizations. However, the combination of automated data processing pipelines handling omics data and dynamically generated, interactive dashboards is poorly solved. Here, we present i2dash, an R package intended to encapsulate functionality for the programmatic creation of customized dashboards. It supports interactive and responsive (linked) visualizations across a set of predefined graphical layouts. i2dash addresses the needs of data analysts/software developers for a tool that is compatible and attachable to any R-based analysis pipeline, thereby fostering the separation of data visualization on one hand and data analysis tasks on the other hand. In addition, the generic design of i2dash enables the development of modular extensions for specific needs. As a proof of principle, we provide an extension of i2dash optimized for single-cell RNA sequencing analysis, supporting the creation of dashboards for the visualization needs of such experiments. Equipped with these features, i2dash is suitable for extensive use in large-scale sequencing/bioinformatics facilities. Along this line, we provide i2dash as a containerized solution, enabling a straightforward large-scale deployment and sharing of dashboards using cloud services. i2dash is freely available via the R package archive CRAN (https://CRAN.R-project.org/package=i2dash).

Robust regression with compositional covariates

Many biological high-throughput datasets, such as targeted amplicon-based and metagenomic sequencing data, are compositional. A common exploratory data analysis task is to infer robust statistical associations between high-dimensional microbial compositions and habitat- or host-related covariates. To address this, a general robust statistical regression framework RobRegCC (Robust Regression with Compositional Covariates) is proposed, which extends the linear log-contrast model by a mean shift formulation for capturing outliers. RobRegCC includes sparsity-promoting convex and non-convex penalties for parsimonious model estimation, a data-driven robust initialization procedure, and a novel robust cross-validation model selection scheme. The procedure is implemented in the R package robregcc. Extensive simulation studies show the RobRegCC's ability to perform simultaneous sparse log-contrast regression and outlier detection over a wide range of settings. To demonstrate the seamless applicability of the workflow to real data, the gut microbiome dataset from HIV patients are analyzed and robust associations between a sparse set of microbial species and host immune response from soluble CD14 measurements are inferred.

Stock Price Forecast Based on CNN-BiLSTM-ECA Model

Financial data as a kind of multimedia data contains rich information, which has been widely used for data analysis task. However, how to predict the stock price is still a hot research problem for investors and researchers in financial field. Forecasting stock prices becomes an extremely challenging task due to high noise, nonlinearity, and volatility of the stock price time series data. In order to provide better prediction results of stock price, a new stock price prediction model named as CNN-BiLSTM-ECA is proposed, which combines Convolutional Neural Network (CNN), Bidirectional Long Short-term Memory (BiLSTM) network, and Attention Mechanism (AM). More specifically, CNN is utilized to extract the deep features of stock data for reducing the influence of high noise and nonlinearity. Then, BiLSTM network is employed to predict the stock price based on the extracted deep features. Meanwhile, a novel Efficient Channel Attention (ECA) module is introduced into the network model to further improve the sensitivity of the network to the important features and key information. Finally, extensive experiments are conducted on the three stock datasets such as Shanghai Composite Index, China Unicom, and CSI 300. Compared with the existing methods, the experimental results verify the effectiveness and feasibility of the proposed CNN-BILSTM-ECA network model, which can provide an important reference for investors to make decisions.

Assassin

The increasing complexity of data analysis tasks makes it dependent on human expertise and challenging for non-experts. One of the major challenges faced in data analysis is the selection of the proper algorithm for given tasks and data sets. Motivated by this, we develop Assassin, aiming at helping users without enough expertise to automatically select optimal algorithms for classification tasks. By embedding meta-learning techniques and reinforced policy, our system can automatically extract experiences from previous tasks and train a meta-classifier to implement algorithm recommendations. Then we apply genetic search to explore hyperparameter configuration for the selected algorithm. We demonstrate Assassin with classification tasks from OpenML. The system chooses an appropriate algorithm and optimal hyperparameter configuration for them to achieve a high-level performance target. The Assassin has a user-friendly interface that allows users to customize the parameters during the search process.

Visual Active Learning for Labeling: A Case for Soundscape Ecology Data

Labeling of samples is a recurrent and time-consuming task in data analysis and machine learning and yet generally overlooked in terms of visual analytics approaches to improve the process. As the number of tailored applications of learning models increases, it is crucial that more effective approaches to labeling are developed. In this paper, we report the development of a methodology and a framework to support labeling, with an application case as background. The methodology performs visual active learning and label propagation with 2D embeddings as layouts to achieve faster and interactive labeling of samples. The framework is realized through SoundscapeX, a tool to support labeling in soundscape ecology data. We have applied the framework to a set of audio recordings collected for a Long Term Ecological Research Project in the Cantareira-Mantiqueira Corridor (LTER CCM), localized in the transition between northeastern São Paulo state and southern Minas Gerais state in Brazil. We employed a pre-label data set of groups of animals to test the efficacy of the approach. The results showed the best accuracy at 94.58% in the prediction of labeling for birds and insects; and 91.09% for the prediction of the sound event as frogs and insects.

Generic server-aided secure multi-party computation in cloud computing

Cloud computing has become one of the most popular distributed computing paradigms in recent years. With its advantages of low cost, on-demand flexibility, and high data processing abilities, more and more enterprises have adopted the cloud computing paradigm to build up their IT infrastructure. By performing collaborative computation tasks (e.g., big data analysis tasks) with multiple datasets of different correlated enterprises in cloud computing, the generated valuable information will provide the enterprises with higher productivity and financial gains. However, due to the privacy concerns from the enterprises, how to efficiently enable them to achieve secure multi-party joint datasets analysis in cloud computing without leaking their own private dataset becomes a critical but challenging problem for the enterprises. In this paper, focusing on securely performing any collaborative computation task in cloud computing, we construct a generic server-aided secure multi-party computation protocol to tackle the problem. Our solution can provide security guarantee in the setting where at most n-1 client parties are malicious while the server is semi-honest and there is no collusion between the server and clients. The security and experimental performance analysis show that this work is currently the most efficient server-aided secure multi-party computation protocol with the same security guarantee compared with all the previous works to the best of our knowledge.

ENSURING THE QUALITY AND VOLUME OF GEOLOGICAL-TECHNOLOGICAL DATA FOR APPLICATION OF MACHINE LEARNING METHODS KNOWLEDGE-ORIENTED SYSTEM

The article considers the issues of complications arising during the technological processes of drilling related to geological, geophysical and external conditions, urbanization and detection of inconsistencies between the actual drilling conditions from the projected ones due to changes in climate and geological changes, which occur in the period from the end of the project and the actual start of development of the field. The interrelation of the factors that complicate the drilling process with the stages of design and organization of precedents, on the basis of which the technological processes of drilling are modeled, is analyzed. The phases of the cycle of reasoning based on knowledge with a projection on the information cycle of drilling process control are revealed. The architecture of automation of technological processes of drilling with reference to the pyramid of computer-integrated production is presented. The article shows the possibility of applying machine learning methods to data analysis tasks related to the drilling process. The use of a combined approach to adapt the data used for knowledge-based decision-making is proposed. The problem of insufficient precedent for training knowledge-oriented system of intellectual support of decision-making processes is considered and the provision of full-scale simulators with the necessary amount of data for modeling complications of high-risk drilling process is substantiated. The authors determine the level of the expected ratio between the main objects of the knowledge-oriented system of intelligent decision-making on the course of the technological process: the problems of machine learning on the one hand and oil and gas wells on the other.

Orthogonal Nonnegative Matrix Factorization using a novel deep Autoencoder Network

Orthogonal Nonnegative Matrix Factorization (ONMF) offers an important analytical vehicle for addressing many problems. Encouraged by record-breaking successes attained by neural computing models in solving an assortment of data analytics tasks, a rich collection of neural computing models has been proposed to perform ONMF with compelling performance. Such existing models can be broadly classified into the shallow-layered structure (SLS) based and deep-layered structure (DLS) based models. However, SLS models cannot capture complex relationships and hierarchical information latent in a matrix due to their simple network structures and DLS models rely on an iterative procedure to derive weights, leading to a less efficient solution process and cannot be reused to factorize new matrices. To overcome these shortcomings, this paper proposes a novel deep autoencoder network for ONMF, which is abbreviated as DAutoED-ONMF. Compared with SLS models, the newly proposed model is capable of generating solutions with good interpretability and solution uniqueness like original SLS models, yet the new model attains a superior learning capability thanks to its deep structure employed. In comparison with DLS models, the new model trains a reusable encoder network to directly factorize any given matrix with no need to repeatedly retrain the model for factorizing multiple matrices using a tailor-designed network training procedure. Proof of the procedure’s convergence is presented with an analysis of its computational complexity. The numerical experiments conducted on several publicly data sets convincingly demonstrate that the proposed DAutoED-ONMF model gains promising performance in terms of multiple metrics.

Two-Level Multimodal Fusion for Sentiment Analysis in Public Security

Large amounts of data are widely stored in cyberspace. Not only can they bring much convenience to people’s lives and work, but they can also assist the work in the information security field, such as microexpression recognition and sentiment analysis in the criminal investigation. Thus, it is of great significance to recognize and analyze the sentiment information, which is usually described by different modalities. Due to the correlation among different modalities data, multimodal can provide more comprehensive and robust information than unimodal in data analysis tasks. The complementary information from different modalities can be obtained by multimodal fusion methods. These approaches can process multimodal data through fusion algorithms and ensure the accuracy of the information used for subsequent classification or prediction tasks. In this study, a two-level multimodal fusion (TlMF) method with both data-level and decision-level fusion is proposed to achieve the sentiment analysis task. In the data-level fusion stage, a tensor fusion network is utilized to obtain the text-audio and text-video embeddings by fusing the text with audio and video features, respectively. During the decision-level fusion stage, the soft fusion method is adopted to fuse the classification or prediction results of the upstream classifiers, so that the final classification or prediction results can be as accurate as possible. The proposed method is tested on the CMU-MOSI, CMU-MOSEI, and IEMOCAP datasets, and the empirical results and ablation studies confirm the effectiveness of TlMF in capturing useful information from all the test modalities.

Visualizing large-scale high-dimensional data via hierarchical embedding of KNN graphs

Visualizing intrinsic structures of high-dimensional data is an essential task in data analysis. Over the past decades, a large number of methods have been proposed. Among all solutions, one promising way for enabling effective visual exploration is to construct a k-nearest neighbor (KNN) graph and visualize the graph in a low-dimensional space. Yet, state-of-the-art methods such as the LargeVis still suffer from two main problems when applied to large-scale data: (1) they may produce unappealing visualizations due to the non-convexity of the cost function; (2) visualizing the KNN graph is still time-consuming. In this work, we propose a novel visualization algorithm that leverages a multi-level representation to achieve a high-quality graph layout and employs a cluster-based approximation scheme to accelerate the KNN graph layout. Experiments on various large-scale datasets indicate that our approach achieves a speedup by a factor of five for KNN graph visualization compared to LargeVis and yields aesthetically pleasing visualization results.

Towards a Method to Predict the Evaluation Result in a Microlearning Context

This paper presents a method for predicting the evaluation results of learners interacting with a context-aware microlearning system. We use ASUM-DM to guide different data analytics tasks, including applying a genetic algorithm that selects the prediction’s highest weight features. Then, we apply Machine Learning models like Random Forest, Gradient Boosting Tree, Decision Tree, SVM, and Neural Networks to train data and evaluate the context’s effects, either success or failure of the learner’s evaluation. We are interested in finding the model of significant context-influence to the learner’s evaluation results. The Random Forest model provided an accuracy of 94%, which was calculated with the cross-validation technique. Thus, it is possible to conclude that the model can accurately predict the evaluation result and relate it to the learner context. The model result is a useful insight for sending notifications to the learners to improve the learning process. We want to provide recommendations about learner behavior and context and adapt the microlearning content in the future.

Optimal Axes for Data Value Estimation in Star Coordinates and Radial Axes Plots

AbstractRadial axes plots are projection methods that represent high‐dimensional data samples as points on a two‐dimensional plane. These techniques define mappings through a set of axis vectors, each associated with a data variable, which users can manipulate interactively to create different plots and analyze data from multiple points of view. However, updating the direction and length of an axis vector is far from trivial. Users must consider the data analysis task, domain knowledge, the directions in which values should increase, the relative importance of each variable, or the correlations between variables, among other factors. Another issue is the difficulty to approximate high‐dimensional data values in the two‐dimensional visualizations, which can hamper searching for data with particular characteristics, analyzing the most common data values in clusters, inspecting outliers, etc. In this paper we present and analyze several optimization approaches for enhancing radial axes plots regarding their ability to represent high‐dimensional data values. The techniques can be used not only to approximate data values with greater accuracy, but also to guide users when updating axis vectors or extending visualizations with new variables, since they can reveal poor choices of axis vectors. The optimal axes can also be included in nonlinear plots. In particular, we show how they can be used within RadViz to assess the quality of a variable ordering. The in‐depth analysis carried out is useful for visualization designers developing radial axes techniques, or planning to incorporate axes into other visualization methods.

Visualization in Astrophysics: Developing New Methods, Discovering Our Universe, and Educating the Earth

AbstractWe present a state‐of‐the‐art report on visualization in astrophysics. We survey representative papers from both astrophysics and visualization and provide a taxonomy of existing approaches based on data analysis tasks. The approaches are classified based on five categories: data wrangling, data exploration, feature identification, object reconstruction, as well as education and outreach. Our unique contribution is to combine the diverse viewpoints from both astronomers and visualization experts to identify challenges and opportunities for visualization in astrophysics. The main goal is to provide a reference point to bring modern data analysis and visualization techniques to the rich datasets in astrophysics.

An Overview of Deep Learning Algorithms and Their Applications in Neuropsychiatry.

Deep learning (DL) algorithms have achieved important successes in data analysis tasks, thanks to their capability of revealing complex patterns in data. With the advance of new sensors, data storage, and processing hardware, DL algorithms start dominating various fields including neuropsychiatry. There are many types of DL algorithms for different data types from survey data to functional magnetic resonance imaging scans. Because of limitations in diagnosing, estimating prognosis and treatment response of neuropsychiatric disorders; DL algorithms are becoming promising approaches. In this review, we aim to summarize the most common DL algorithms and their applications in neuropsychiatry and also provide an overview to guide the researchers in choosing the proper DL architecture for their research.

An IoT-Based Smart Building Solution for Indoor Environment Management and Occupants Prediction

Smart buildings use Internet of Things (IoT) sensors for monitoring indoor environmental parameters, such as temperature, humidity, luminosity, and air quality. Due to the huge amount of data generated by these sensors, data analytics and machine learning techniques are needed to extract useful and interesting insights, which provide the input for the building optimization in terms of energy-saving, occupants’ health and comfort. In this paper, we propose an IoT-based smart building (SB) solution for indoor environment management, which aims to provide the following main functionalities: monitoring of the room environmental parameters; detection of the number of occupants in the room; a cloud platform where virtual entities collect the data acquired by the sensors and virtual super entities perform data analysis tasks using machine learning algorithms; a control dashboard for the management and control of the building. With our prototype, we collected data for 10 days, and we built two prediction models: a classification model that predicts the number of occupants based on the monitored environmental parameters (average accuracy of 99.5%), and a regression model that predicts the total volatile organic compound (TVOC) values based on the environmental parameters and the number of occupants (Pearson correlation coefficient of 0.939).

A New Robust Subspace Recovery Algorithm (Student Abstract)

A common task in data analysis is to compute an approximate embedding of the data in a low dimensional subspace. This is used, for example, for dimensionality reduction. Robust Subspace Recovery computes the embedding by ignoring a fraction of the data considered as outliers. Its performance can be evaluated by how accurate the inliers (non-outliers) are represented. We propose a new algorithm that outperforms the current state of the art when the data is dominated by outliers. The main idea is to rank each point by evaluating the change in the global PCA error when that point is considered as an outlier. We show that this lookahead procedure can be implemented efficiently by centered rank-one modifications.

Inductive Graph Neural Networks for Spatiotemporal Kriging

Time series forecasting and spatiotemporal kriging are the two most important tasks in spatiotemporal data analysis. Recent research on graph neural networks has made substantial progress in time series forecasting, while little attention has been paid to the kriging problem---recovering signals for unsampled locations/sensors. Most existing scalable kriging methods (e.g., matrix/tensor completion) are transductive, and thus full retraining is required when we have a new sensor to interpolate. In this paper, we develop an Inductive Graph Neural Network Kriging (IGNNK) model to recover data for unsampled sensors on a network/graph structure. To generalize the effect of distance and reachability, we generate random subgraphs as samples and the corresponding adjacency matrix for each sample. By reconstructing all signals on each sample subgraph, IGNNK can effectively learn the spatial message passing mechanism. Empirical results on several real-world spatiotemporal datasets demonstrate the effectiveness of our model. In addition, we also find that the learned model can be successfully transferred to the same type of kriging tasks on an unseen dataset. Our results show that: 1) GNN is an efficient and effective tool for spatial kriging; 2) inductive GNNs can be trained using dynamic adjacency matrices; 3) a trained model can be transferred to new graph structures and 4) IGNNK can be used to generate virtual sensors.