arXiv subjects

Una-May O'Reilly

Publications and source records attributed to Una-May O'Reilly.

44 records · Page 3Linked to original sources

arXiv2017

Distributed Stratified Locality Sensitive Hashing for Critical Event Prediction in the Cloud

The availability of massive healthcare data repositories calls for efficient tools for data-driven medicine. We introduce a distributed system for Stratified Locality Sensitive Hashing to perform fast similarity-based prediction on large medical waveform datasets. Our implementation, for an ICU use case, prioritizes latency over throughput and is targeted at a cloud environment. We demonstrate our system on Acute Hypotensive Episode prediction from Arterial Blood Pressure waveforms. On a dataset of $1.37$ million points, we show scaling up to $40$ processors and a $21\times$ speedup in number of comparisons to parallel exhaustive search at the price of a $10\%$ Matthews correlation coefficient (MCC) loss. Furthermore, if additional MCC loss can be tolerated, our system achieves speedups up to two orders of magnitude.

cs.LG↗

arXiv2014

Likely to stop? Predicting Stopout in Massive Open Online Courses

Understanding why students stopout will help in understanding how students learn in MOOCs. In this report, part of a 3 unit compendium, we describe how we build accurate predictive models of MOOC student stopout. We document a scalable, stopout prediction methodology, end to end, from raw source data to model analysis. We attempted to predict stopout for the Fall 2012 offering of 6.002x. This involved the meticulous and crowd-sourced engineering of over 25 predictive features extracted for thousands of students, the creation of temporal and non-temporal data representations for use in predictive modeling, the derivation of over 10 thousand models with a variety of state-of-the-art machine learning techniques and the analysis of feature importance by examining over 70000 models. We found that stop out prediction is a tractable problem. Our models achieved an AUC (receiver operating characteristic area-under-the-curve) as high as 0.95 (and generally 0.88) when predicting one week in advance. Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks' data, the models attained AUCs of 0.7.

cs.CY↗

arXiv2014

Towards Feature Engineering at Scale for Data from Massive Open Online Courses

We examine the process of engineering features for developing models that improve our understanding of learners' online behavior in MOOCs. Because feature engineering relies so heavily on human insight, we argue that extra effort should be made to engage the crowd for feature proposals and even their operationalization. We show two approaches where we have started to engage the crowd. We also show how features can be evaluated for their relevance in predictive accuracy. When we examined crowd-sourced features in the context of predicting stopout, not only were they nuanced, but they also considered more than one interaction mode between the learner and platform and how the learner was relatively performing. We were able to identify different influential features for stop out prediction that depended on whether a learner was in 1 of 4 cohorts defined by their level of engagement with the course discussion forum or wiki. This report is part of a compendium which considers different aspects of MOOC data science and stop out prediction.

cs.CY↗

arXiv2014

MOOCdb: Developing Standards and Systems to Support MOOC Data Science

We present a shared data model for enabling data science in Massive Open Online Courses (MOOCs). The model captures students interactions with the online platform. The data model is platform agnostic and is based on some basic core actions that students take on an online learning platform. Students usually interact with the platform in four different modes: Observing, Submitting, Collaborating and giving feedback. In observing mode students are simply browsing the online platform, watching videos, reading material, reading book or watching forums. In submitting mode, students submit information to the platform. This includes submissions towards quizzes, homeworks, or any assessment modules. In collaborating mode students interact with other students or instructors on forums, collaboratively editing wiki or chatting on google hangout or other hangout venues. With this basic definitions of activities, and a data model to store events pertaining to these activities, we then create a common terminology to map Coursera and edX data into this shared data model. This shared data model called MOOCdb becomes the foundation for a number of collaborative frameworks that enable progress in data science without the need to share the data.

cs.IR↗

arXiv2010

Computational Complexity Analysis of Simple Genetic Programming On Two Problems Modeling Isolated Program Semantics

Analyzing the computational complexity of evolutionary algorithms for binary search spaces has significantly increased their theoretical understanding. With this paper, we start the computational complexity analysis of genetic programming. We set up several simplified genetic programming algorithms and analyze them on two separable model problems, ORDER and MAJORITY, each of which captures an important facet of typical genetic programming problems. Both analyses give first rigorous insights on aspects of genetic programming design, highlighting in particular the impact of accepting or rejecting neutral moves and the importance of a local mutation operator.

cs.NE↗

arXiv2007

A Doubly Distributed Genetic Algorithm for Network Coding

We present a genetic algorithm which is distributed in two novel ways: along genotype and temporal axes. Our algorithm first distributes, for every member of the population, a subset of the genotype to each network node, rather than a subset of the population to each. This genotype distribution is shown to offer a significant gain in running time. Then, for efficient use of the computational resources in the network, our algorithm divides the candidate solutions into pipelined sets and thus the distribution is in the temporal domain, rather that in the spatial domain. This temporal distribution may lead to temporal inconsistency in selection and replacement, however our experiments yield better efficiency in terms of the time to convergence without incurring significant penalties.

cs.NE↗

arXiv2007

Genetic Representations for Evolutionary Minimization of Network Coding Resources

We demonstrate how a genetic algorithm solves the problem of minimizing the resources used for network coding, subject to a throughput constraint, in a multicast scenario. A genetic algorithm avoids the computational complexity that makes the problem NP-hard and, for our experiments, greatly improves on sub-optimal solutions of established methods. We compare two different genotype encodings, which tradeoff search space size with fitness landscape, as well as the associated genetic operators. Our finding favors a smaller encoding despite its fewer intermediate solutions and demonstrates the impact of the modularity enforced by genetic operators on the performance of the algorithm.

cs.NE↗

arXiv2007

Evolutionary Approaches to Minimizing Network Coding Resources

We wish to minimize the resources used for network coding while achieving the desired throughput in a multicast scenario. We employ evolutionary approaches, based on a genetic algorithm, that avoid the computational complexity that makes the problem NP-hard. Our experiments show great improvements over the sub-optimal solutions of prior methods. Our new algorithms improve over our previously proposed algorithm in three ways. First, whereas the previous algorithm can be applied only to acyclic networks, our new method works also with networks with cycles. Second, we enrich the set of components used in the genetic algorithm, which improves the performance. Third, we develop a novel distributed framework. Combining distributed random network coding with our distributed optimization yields a network coding protocol where the resources used for coding are optimized in the setup phase by running our evolutionary algorithm at each node of the network. We demonstrate the effectiveness of our approach by carrying out simulations on a number of different sets of network topologies.

cs.NI↗