July 29, 2019

3402 words 16 mins read

Paper Group ANR 56

Predicting Individual Physiologically Acceptable States for Discharge from a Pediatric Intensive Care Unit. Correlation Alignment by Riemannian Metric for Domain Adaptation. Semantic Photometric Bundle Adjustment on Natural Sequences. Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching. Contracting Nonlinear Observ …

Predicting Individual Physiologically Acceptable States for Discharge from a Pediatric Intensive Care Unit


Title	Predicting Individual Physiologically Acceptable States for Discharge from a Pediatric Intensive Care Unit
Authors	Cameron Carlin, Long Van Ho, David Ledbetter, Melissa Aczon, Randall Wetzel
Abstract	Objective: Predict patient-specific vitals deemed medically acceptable for discharge from a pediatric intensive care unit (ICU). Design: The means of each patient’s hr, sbp and dbp measurements between their medical and physical discharge from the ICU were computed as a proxy for their physiologically acceptable state space (PASS) for successful ICU discharge. These individual PASS values were compared via root mean squared error (rMSE) to population age-normal vitals, a polynomial regression through the PASS values of a Pediatric ICU (PICU) population and predictions from two recurrent neural network models designed to predict personalized PASS within the first twelve hours following ICU admission. Setting: PICU at Children’s Hospital Los Angeles (CHLA). Patients: 6,899 PICU episodes (5,464 patients) collected between 2009 and 2016. Interventions: None. Measurements: Each episode data contained 375 variables representing vitals, labs, interventions, and drugs. They also included a time indicator for PICU medical discharge and physical discharge. Main Results: The rMSEs between individual PASS values and population age-normals (hr: 25.9 bpm, sbp: 13.4 mmHg, dbp: 13.0 mmHg) were larger than the rMSEs corresponding to the polynomial regression (hr: 19.1 bpm, sbp: 12.3 mmHg, dbp: 10.8 mmHg). The rMSEs from the best performing RNN model were the lowest (hr: 16.4 bpm; sbp: 9.9 mmHg, dbp: 9.0 mmHg). Conclusion: PICU patients are a unique subset of the general population, and general age-normal vitals may not be suitable as target values indicating physiologic stability at discharge. Age-normal vitals that were specifically derived from the medical-to-physical discharge window of ICU patients may be more appropriate targets for ‘acceptable’ physiologic state for critical care patients. Going beyond simple age bins, an RNN model can provide more personalized target values.
Tasks
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06214v1
PDF	http://arxiv.org/pdf/1712.06214v1.pdf
PWC	https://paperswithcode.com/paper/predicting-individual-physiologically
Repo
Framework

Correlation Alignment by Riemannian Metric for Domain Adaptation


Title	Correlation Alignment by Riemannian Metric for Domain Adaptation
Authors	Pietro Morerio, Vittorio Murino
Abstract	Domain adaptation techniques address the problem of reducing the sensitivity of machine learning methods to the so-called domain shift, namely the difference between source (training) and target (test) data distributions. In particular, unsupervised domain adaptation assumes no labels are available in the target domain. To this end, aligning second order statistics (covariances) of target and source domains have proven to be an effective approach ti fill the gap between the domains. However, covariance matrices do not form a subspace of the Euclidean space, but live in a Riemannian manifold with non-positive curvature, making the usual Euclidean metric suboptimal to measure distances. In this paper, we extend the idea of training a neural network with a constraint on the covariances of the hidden layer features, by rigorously accounting for the curved structure of the manifold of symmetric positive definite matrices. The resulting loss function exploits a theoretically sound geodesic distance on such manifold. Results show indeed the suboptimal nature of the Euclidean distance. This makes us able to perform better than previous approaches on the standard Office dataset, a benchmark for domain adaptation techniques.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08180v1
PDF	http://arxiv.org/pdf/1705.08180v1.pdf
PWC	https://paperswithcode.com/paper/correlation-alignment-by-riemannian-metric
Repo
Framework

Semantic Photometric Bundle Adjustment on Natural Sequences


Title	Semantic Photometric Bundle Adjustment on Natural Sequences
Authors	Rui Zhu, Chaoyang Wang, Chen-Hsuan Lin, Ziyan Wang, Simon Lucey
Abstract	The problem of obtaining dense reconstruction of an object in a natural sequence of images has been long studied in computer vision. Classically this problem has been solved through the application of bundle adjustment (BA). More recently, excellent results have been attained through the application of photometric bundle adjustment (PBA) methods – which directly minimize the photometric error across frames. A fundamental drawback to BA & PBA, however, is: (i) their reliance on having to view all points on the object, and (ii) for the object surface to be well textured. To circumvent these limitations we propose semantic PBA which incorporates a 3D object prior, obtained through deep learning, within the photometric bundle adjustment problem. We demonstrate state of the art performance in comparison to leading methods for object reconstruction across numerous natural sequences.
Tasks	Object Reconstruction
Published	2017-11-30
URL	http://arxiv.org/abs/1712.00110v1
PDF	http://arxiv.org/pdf/1712.00110v1.pdf
PWC	https://paperswithcode.com/paper/semantic-photometric-bundle-adjustment-on
Repo
Framework

Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching


Title	Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching
Authors	Wenpeng Yin, Hinrich Schütze
Abstract	This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention in AS. The key to reach this observation lies in phrase detection, phrase representation, phrase alignment, and more importantly how to connect those aligned phrases of different matching degrees with the final classifier. Prior work (i) has limitations in phrase generation and representation, or (ii) conducts alignment at word and phrase levels by handcrafted features or (iii) utilizes a single framework of alignment without considering the characteristics of specific tasks, which limits the framework’s effectiveness across tasks. We propose an architecture based on Gated Recurrent Unit that supports (i) representation learning of phrases of arbitrary granularity and (ii) task-specific attentive pooling of phrase alignments between two sentences. Experimental results on TE and AS match our observation and show the effectiveness of our approach.
Tasks	Answer Selection, Natural Language Inference, Representation Learning
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02149v1
PDF	http://arxiv.org/pdf/1701.02149v1.pdf
PWC	https://paperswithcode.com/paper/task-specific-attentive-pooling-of-phrase
Repo
Framework

Contracting Nonlinear Observers: Convex Optimization and Learning from Data


Title	Contracting Nonlinear Observers: Convex Optimization and Learning from Data
Authors	Ian R. Manchester
Abstract	A new approach to design of nonlinear observers (state estimators) is proposed. The main idea is to (i) construct a convex set of dynamical systems which are contracting observers for a particular system, and (ii) optimize over this set for one which minimizes a bound on state-estimation error on a simulated noisy data set. We construct convex sets of continuous-time and discrete-time observers, as well as contracting sampled-data observers for continuous-time systems. Convex bounds for learning are constructed using Lagrangian relaxation. The utility of the proposed methods are verified using numerical simulation.
Tasks
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08135v1
PDF	http://arxiv.org/pdf/1711.08135v1.pdf
PWC	https://paperswithcode.com/paper/contracting-nonlinear-observers-convex
Repo
Framework

A Novel data Pre-processing method for multi-dimensional and non-uniform data


Title	A Novel data Pre-processing method for multi-dimensional and non-uniform data
Authors	Farhana Javed Zareen, Suraiya Jabin
Abstract	We are in the era of data analytics and data science which is on full bloom. There is abundance of all kinds of data for example biometrics based data, satellite images data, chip-seq data, social network data, sensor based data etc. from a variety of sources. This data abundance is the result of the fact that storage cost is getting cheaper day by day, so people as well as almost all business or scientific organizations are storing more and more data. Most of the real data is multi-dimensional, non-uniform, and big in size, such that it requires a unique pre-processing before analyzing it. In order to make data useful for any kind of analysis, pre-processing is a very important step. This paper presents a unique and novel pre-processing method for multi-dimensional and non-uniform data with the aim of making it uniform and reduced in size without losing much of its value. We have chosen biometric signature data to demonstrate the proposed method as it qualifies for the attributes of being multi-dimensional, non-uniform and big in size. Biometric signature data does not only captures the structural characteristics of a signature but also its behavioral characteristics that are captured using a dynamic signature capture device. These features like pen pressure, pen tilt angle, time taken to sign a document when collected in real-time turn out to be of varying dimensions. This feature data set along with the structural data needs to be pre-processed in order to use it to train a machine learning based model for signature verification purposes. We demonstrate the success of the proposed method over other methods using experimental results for biometric signature data but the same can be implemented for any other data with similar properties from a different domain.
Tasks
Published	2017-08-05
URL	http://arxiv.org/abs/1708.04664v1
PDF	http://arxiv.org/pdf/1708.04664v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-data-pre-processing-method-for-multi
Repo
Framework

Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities


Title	Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities
Authors	Rajesh Bordawekar, Bortik Bandyopadhyay, Oded Shmueli
Abstract	We propose Cognitive Databases, an approach for transparently enabling Artificial Intelligence (AI) capabilities in relational databases. A novel aspect of our design is to first view the structured data source as meaningful unstructured text, and then use the text to build an unsupervised neural network model using a Natural Language Processing (NLP) technique called word embedding. This model captures the hidden inter-/intra-column relationships between database tokens of different types. For each database token, the model includes a vector that encodes contextual semantic relationships. We seamlessly integrate the word embedding model into existing SQL query infrastructure and use it to enable a new class of SQL-based analytics queries called cognitive intelligence (CI) queries. CI queries use the model vectors to enable complex queries such as semantic matching, inductive reasoning queries such as analogies, predictive queries using entities not present in a database, and, more generally, using knowledge from external sources. We demonstrate unique capabilities of Cognitive Databases using an Apache Spark based prototype to execute inductive reasoning CI queries over a multi-modal database containing text and images. We believe our first-of-a-kind system exemplifies using AI functionality to endow relational databases with capabilities that were previously very hard to realize in practice.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07199v1
PDF	http://arxiv.org/pdf/1712.07199v1.pdf
PWC	https://paperswithcode.com/paper/cognitive-database-a-step-towards-endowing
Repo
Framework

Selective Harvesting over Networks


Title	Selective Harvesting over Networks
Authors	Fabricio Murai, Diogo Rennó, Bruno Ribeiro, Gisele L. Pappa, Don Towsley, Krista Gile
Abstract	Active search (AS) on graphs focuses on collecting certain labeled nodes (targets) given global knowledge of the network topology and its edge weights under a query budget. However, in most networks, nodes, topology and edge weights are all initially unknown. We introduce selective harvesting, a variant of AS where the next node to be queried must be chosen among the neighbors of the current queried node set; the available training data for deciding which node to query is restricted to the subgraph induced by the queried set (and their node attributes) and their neighbors (without any node or edge attributes). Therefore, selective harvesting is a sequential decision problem, where we must decide which node to query at each step. A classifier trained in this scenario suffers from a tunnel vision effect: without recourse to independent sampling, the urge to query promising nodes forces classifiers to gather increasingly biased training data, which we show significantly hurts the performance of AS methods and standard classifiers. We find that it is possible to collect a much larger set of targets by using multiple classifiers, not by combining their predictions as an ensemble, but switching between classifiers used at each step, as a way to ease the tunnel vision effect. We discover that switching classifiers collects more targets by (a) diversifying the training data and (b) broadening the choices of nodes that can be queried next. This highlights an exploration, exploitation, and diversification trade-off in our problem that goes beyond the exploration and exploitation duality found in classic sequential decision problems. From these observations we propose D3TS, a method based on multi-armed bandits for non-stationary stochastic processes that enforces classifier diversity, matching or exceeding the performance of competing methods on seven real network datasets in our evaluation.
Tasks	Multi-Armed Bandits
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05082v1
PDF	http://arxiv.org/pdf/1703.05082v1.pdf
PWC	https://paperswithcode.com/paper/selective-harvesting-over-networks
Repo
Framework

Visualizing the Consequences of Evidence in Bayesian Networks


Title	Visualizing the Consequences of Evidence in Bayesian Networks
Authors	Clifford Champion, Charles Elkan
Abstract	This paper addresses the challenge of viewing and navigating Bayesian networks as their structural size and complexity grow. Starting with a review of the state of the art of visualizing Bayesian networks, an area which has largely been passed over, we improve upon existing visualizations in three ways. First, we apply a disciplined approach to the graphic design of the basic elements of the Bayesian network. Second, we propose a technique for direct, visual comparison of posterior distributions resulting from alternative evidence sets. Third, we leverage a central mathematical tool in information theory, to assist the user in finding variables of interest in the network, and to reduce visual complexity where unimportant. We present our methods applied to two modestly large Bayesian networks constructed from real-world data sets. Results suggest the new techniques can be a useful tool for discovering information flow phenomena, and also for qualitative comparisons of different evidence configurations, especially in large probabilistic networks.
Tasks
Published	2017-07-04
URL	http://arxiv.org/abs/1707.00791v1
PDF	http://arxiv.org/pdf/1707.00791v1.pdf
PWC	https://paperswithcode.com/paper/visualizing-the-consequences-of-evidence-in
Repo
Framework

Probabilistic Matching: Causal Inference under Measurement Errors


Title	Probabilistic Matching: Causal Inference under Measurement Errors
Authors	Fani Tsapeli, Peter Tino, Mirco Musolesi
Abstract	The abundance of data produced daily from large variety of sources has boosted the need of novel approaches on causal inference analysis from observational data. Observational data often contain noisy or missing entries. Moreover, causal inference studies may require unobserved high-level information which needs to be inferred from other observed attributes. In such cases, inaccuracies of the applied inference methods will result in noisy outputs. In this study, we propose a novel approach for causal inference when one or more key variables are noisy. Our method utilizes the knowledge about the uncertainty of the real values of key variables in order to reduce the bias induced by noisy measurements. We evaluate our approach in comparison with existing methods both on simulated and real scenarios and we demonstrate that our method reduces the bias and avoids false causal inference conclusions in most cases.
Tasks	Causal Inference
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04334v1
PDF	http://arxiv.org/pdf/1703.04334v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-matching-causal-inference-under
Repo
Framework

CAD Priors for Accurate and Flexible Instance Reconstruction


Title	CAD Priors for Accurate and Flexible Instance Reconstruction
Authors	Tolga Birdal, Slobodan Ilic
Abstract	We present an efficient and automatic approach for accurate reconstruction of instances of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional scanning, where the background is assumed to be rather static, we aim at handling dynamic clutter where background drastically changes during the object scanning. Currently, it is tedious to solve this with available methods unless the object of interest is first segmented out from the rest of the scene. We address the problem by assuming the availability of a prior CAD model, roughly resembling the object to be reconstructed. This assumption almost always holds in applications such as industrial inspection or reverse engineering. With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity. This allows initial scan alignment to the CAD model space, which is then refined without the CAD constraint to fully recover a high fidelity 3D reconstruction, accurate up to the sensor noise level. We also contribute a novel object detection method, local implicit shape models (LISM) and give a fast verification scheme. We evaluate our method on multiple datasets, demonstrating the ability to accurately reconstruct objects from small sizes up to $125m^3$.
Tasks	3D Reconstruction, Object Detection
Published	2017-05-08
URL	http://arxiv.org/abs/1705.03111v2
PDF	http://arxiv.org/pdf/1705.03111v2.pdf
PWC	https://paperswithcode.com/paper/cad-priors-for-accurate-and-flexible-instance
Repo
Framework

Distributed Online Learning of Event Definitions


Title	Distributed Online Learning of Event Definitions
Authors	Nikos Katzouris, Alexander Artikis, Georgios Paliouras
Abstract	Logic-based event recognition systems infer occurrences of events in time using a set of event definitions in the form of first-order rules. The Event Calculus is a temporal logic that has been used as a basis in event recognition applications, providing among others, direct connections to machine learning, via Inductive Logic Programming (ILP). OLED is a recently proposed ILP system that learns event definitions in the form of Event Calculus theories, in a single pass over a data stream. In this work we present a version of OLED that allows for distributed, online learning. We evaluate our approach on a benchmark activity recognition dataset and show that we can significantly reduce training times, exchanging minimal information between processing nodes.
Tasks	Activity Recognition
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02175v1
PDF	http://arxiv.org/pdf/1705.02175v1.pdf
PWC	https://paperswithcode.com/paper/distributed-online-learning-of-event
Repo
Framework

Discovery of Shifting Patterns in Sequence Classification


Title	Discovery of Shifting Patterns in Sequence Classification
Authors	Xiaowei Jia, Ankush Khandelwal, Anuj Karpatne, Vipin Kumar
Abstract	In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren land after harvest or before planting. Besides, even within the same class, the discriminative patterns can appear in different periods of sequential data. Due to such property, these discriminative patterns are also referred to as shifting patterns. The shifting patterns in sequential data severely degrade the performance of traditional classification methods without sufficient training data. We propose a novel sequence classification method by automatically mining shifting patterns from multi-variate sequence. The method employs a multi-instance learning approach to detect shifting patterns while also modeling temporal relationships within each multi-instance bag by an LSTM model to further improve the classification performance. We extensively evaluate our method on two real-world applications - cropland mapping and affective state recognition. The experiments demonstrate the superiority of our proposed method in sequence classification performance and in detecting discriminative shifting patterns.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07203v1
PDF	http://arxiv.org/pdf/1712.07203v1.pdf
PWC	https://paperswithcode.com/paper/discovery-of-shifting-patterns-in-sequence
Repo
Framework

Forecasting day-ahead electricity prices in Europe: the importance of considering market integration


Title	Forecasting day-ahead electricity prices in Europe: the importance of considering market integration
Authors	Jesus Lago, Fjo De Ridder, Peter Vrancx, Bart De Schutter
Abstract	Motivated by the increasing integration among electricity markets, in this paper we propose two different methods to incorporate market integration in electricity price forecasting and to improve the predictive performance. First, we propose a deep neural network that considers features from connected markets to improve the predictive accuracy in a local market. To measure the importance of these features, we propose a novel feature selection algorithm that, by using Bayesian optimization and functional analysis of variance, evaluates the effect of the features on the algorithm performance. In addition, using market integration, we propose a second model that, by simultaneously predicting prices from two markets, improves the forecasting accuracy even further. As a case study, we consider the electricity market in Belgium and the improvements in forecasting accuracy when using various French electricity features. We show that the two proposed models lead to improvements that are statistically significant. Particularly, due to market integration, the predictive accuracy is improved from 15.7% to 12.5% sMAPE (symmetric mean absolute percentage error). In addition, we show that the proposed feature selection algorithm is able to perform a correct assessment, i.e. to discard the irrelevant features.
Tasks	Feature Selection
Published	2017-08-01
URL	http://arxiv.org/abs/1708.07061v3
PDF	http://arxiv.org/pdf/1708.07061v3.pdf
PWC	https://paperswithcode.com/paper/forecasting-day-ahead-electricity-prices-in
Repo
Framework

Dynamics Based Features For Graph Classification


Title	Dynamics Based Features For Graph Classification
Authors	Leonardo Gutierrez Gomez, Benjamin Chiem, Jean-Charles Delvenne
Abstract	Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks. Here, we propose a new feature based approach to network classification. We show how dynamics on a network can be useful to reveal patterns about the organization of the components of the underlying graph where the process takes place. We define generalized assortativities on networks and use them as generalized features across multiple time scales. These features turn out to be suitable signatures for discriminating between different classes of networks. Our method is evaluated empirically on established network benchmarks. We also introduce a new dataset of human brain networks (connectomes) and use it to evaluate our method. Results reveal that our dynamics based features are competitive and often outperform state of the art accuracies.
Tasks	Graph Classification
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10817v1
PDF	http://arxiv.org/pdf/1705.10817v1.pdf
PWC	https://paperswithcode.com/paper/dynamics-based-features-for-graph
Repo
Framework