Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 622
-
ItemAn automated matrix profile for mining consecutive repeats in time series(Springer Nature, 2018-01-01)A key application of wearable sensors is remote patient monitoring, which facilitates clinicians to observe patients non-invasively, by examining the time series of sensor readings. For analysis of such time series, a recently proposed technique is Matrix Profile (MP). While being effective for certain time series mining tasks, MP depends on a key input parameter, the length of subsequences for which to search. We demonstrate that MP’s dependency on this input parameter impacts its effectiveness for finding patterns of interest. We focus on finding consecutive repeating patterns (CRPs), which represent human activities and exercises whilst tracked using wearable sensors. We demonstrate that MP cannot detect CRPs effectively and extend it by adding a locality preserving index. Our method automates the use of MP, and reduces the need for data labeling by experts. We demonstrate our algorithm’s effectiveness in detecting regions of CRPs through a number of real and synthetic datasets.
-
ItemNo Preview AvailableDesigning an App for Pregnancy Care for a Culturally and Linguistically Diverse Community(The Association for Computing Machinery, 2017)We report a study to design and evaluate an app to support pregnancy information provided to women through an Australian health service. As part of a larger project to provide prenatal resources for culturally and linguistically diverse groups, this study focused on the design and reception of an app with the local Vietnamese community and health professionals of a particular hospital. Our study had three stages: an initial design workshop with the hospital; prototype design and development; prototype-based interviews with health professionals and focus groups with Vietnamese women. We explore how an app of this sort must be designed for a range of different use scenarios, considering its use by consumers with a multiplicity of differing viewpoints about its nature and purpose in relation to pregnancy care.
-
ItemCooperating to compete: The mutuality of cooperation and competition in boardgame play(Association for Computing Machinery (ACM), 2018-04-20)This paper examines the complex relationship between competition and cooperation in boardgame play. We understand boardgaming as distributed cognition, where people work together in a shared activity to accomplish the game. Although players typically compete against each other, this competition is only possible through ongoing cooperation to negotiate, enact and maintain the rules of play. In this paper, we report on a study of people playing modern boardgames. We analyse how knowledge of the game's state is distributed amongst the players and the game components, and examine the different forms of cooperation and collaboration that occur during play. Further, we show how players use the material elements of the game to support articulation work and to improve their awareness and understanding of the game's state. Our goal is to examine the coordinative practices that the players use during play and explicate the ways in which these enable competition.
-
ItemNo Preview Available"I love all the bits": The Materiality of Boardgames(ASSOC COMPUTING MACHINERY, 2016-01-01)This paper presents findings from a study of boardgamers which stress the importance of the materiality of modern boardgames. It demonstrates that materiality is one of four significant factors in the player experience of tabletop gaming and describes four domains of materiality in boardgaming settings. Further, building on understanding of non-use in HCI, it presents boardgames as a unique situation of parallel use, in which users simultaneously engage with a single game in both digital and material, non-digital environments.
-
ItemSummarizing Significant Changes in Network Traffic Using Contrast Pattern Mining(Association for Computing Machinery, 2017)Extracting knowledge from the massive volumes of network traffic is an important challenge in network and security management. In particular, network managers require concise reports about significant changes in their network traffic. While most existing techniques focus on summarizing a single traffic dataset, the problem of finding significant differences between multiple datasets is an open challenge. In this paper, we focus on finding important differences between network traffic datasets, and preparing a summarized and interpretable report for security managers. We propose the use of contrast pattern mining, which finds patterns whose support differs significantly from one dataset to another. We show that contrast patterns are highly effective at extracting meaningful changes in traffic data. We also propose several evaluation metrics that reflect the interpretability of patterns for security managers. Our experimental results show that with the proposed unsupervised approach, the vast majority of extracted patterns are pure, i.e., most changes are either attack traffic or normal traffic, but not a mixture of both.
-
ItemJob Insecurity in Academic Research Employment: An Agent-Based Model(MIT Press, 2016-01-01)This paper presents an agent-based model of fixed-term academic employment in a competitive research funding environment based on UK academia. The goal of the model is to investigate the effects of job insecurity on research productivity. Agents may be either established academics who may apply for grants, or postdoctoral researchers who are unable to apply for grants and experience hardship when reaching the end of their fixed-term contracts. Model results show that in general adding fixed-term postdocs to the system produces less total research output than adding half as many permanent academics. An in-depth sensitivity analysis is performed across postdoc scenarios, and indicates that promoting more postdocs into permanent positions produces significant increases in research output.
-
ItemAnomalous Behavior Detection in Crowded Scenes Using Clustering and Spatio-Temporal Features(Springer, 2016)important problem in real-life applications. Detection of anomalous behaviors such as people standing statically and loitering around a place are the focus of this paper. In order to detect anomalous events and objects, ViBe was used for background modeling and object detection at first. Then, a Kalman filter and Hungarian cost algorithm were implemented for tracking and generating trajectories of people. Next, spatio-temporal features were extracted and represented. Finally, hyperspherical clustering was used for anomaly detection in an unsupervised manner. We investigate three different approaches to extracting and representing spatio-temporal features, and we demonstrate the effectiveness of our proposed feature representation on a standard benchmark dataset and a real-life video surveillance environment.
-
ItemCrowd Activity Change Point Detection in Videos via Graph Stream Mining(IEEE, 2018)In recent years, there has been a growing interest in detecting anomalous behavioral patterns in video. In this work, we address this task by proposing a novel activity change point detection method to identify crowd movement anomalies for video surveillance. In our proposed novel framework, a hyperspherical clustering algorithm is utilized for the automatic identification of interesting regions, then the density of pedestrian flows between every pair of interesting regions over consecutive time intervals is monitored and represented as a sequence of adjacency matrices where the direction and density of flows are captured through a directed graph. Finally, we use graph edit distance as well as a cumulative sum test to detect change points in the graph sequence. We conduct experiments on four real-world video datasets: Dublin, New Orleans, Abbey Road and MCG Datasets. We observe that our proposed approach achieves a high F-measure, i.e., in the range [0.7, 1], for these datasets. The evaluation reveals that our proposed method can successfully detect the change points in all datasets at both global and local levels. Our results also demonstrate the efficiency and effectiveness of our proposed algorithm for change point detection and segmentation tasks.
-
ItemLearning Free-Form Deformations for 3D Object Reconstruction(Springer, 2018)Representing 3D shape in deep learning frameworks in an accurate, efficient and compact manner still remains an open challenge. Most existing work addresses this issue by employing voxel-based representations. While these approaches benefit greatly from advances in computer vision by generalizing 2D convolutions to the 3D setting, they also have several considerable drawbacks. The computational complexity of voxel-encodings grows cubically with the resolution thus limiting such representations to low-resolution 3D reconstruction. In an attempt to solve this problem, point cloud representations have been proposed. Although point clouds are more efficient than voxel representations as they only cover surfaces rather than volumes, they do not encode detailed geometric information about relationships between points. In this paper we propose a method to learn free-form deformations (FFD) for the task of 3D reconstruction from a single image. By learning to deform points sampled from a high-quality mesh, our trained model can be used to produce arbitrarily dense point clouds or meshes with fine-grained geometry. We evaluate our proposed framework on synthetic data and achieve state-of-the-art results on surface and volumetric metrics. We make our implementation publicly available (Tensorflow implementation available at github.com/jackd/template_ffd.).
-
ItemAdversarially Parameterized Optimization for 3D Human Pose Estimation(IEEE, 2017)We propose Adversarially Parameterized Optimization, a framework for learning low-dimensional feasible parameterizations of human poses and inferring 3D poses from 2D input. We train a Generative Adversarial Network to `imagine' feasible poses, and search this imagination space for a solution that is consistent with observations. The framework requires no scene/observation correspondences and enforces known geometric invariances without dataset augmentation. The algorithm can be configured at run time to take advantage of known values such as intrinsic/extrinsic camera parameters or target height when available without additional training. We demonstrate the framework by inferring 3D human poses from projected joint positions for both single frames and sequences. We show competitive results with extremely simple shallow network architectures and make the code publicly available.