A Distributed Robotic Vision Service

Robotic vision is limited by line of sight and onboard camera capabilities. Robots can acquire video or images from remote cameras, but processing additional data has a computational burden. This paper applies the Distributed Robotic Vision Service, DRVS, to robot path planning using data outside line-of-sight of the robot. DRVS implements a distributed visual object detection service to distributes the computation to remote camera nodes with processing capabilities. Robots request task-specific object detection from DRVS by specifying a geographic region of interest and object type. The remote camera nodes perform the visual processing and send the high-level object information to the robot. Additionally, DRVS relieves robots of sensor discovery by dynamically distributing object detection requests to remote camera nodes. Tested over two different indoor path planning tasks DRVS showed dramatic reduction in mobile robot compute load and wireless network utilization.

Reputation model based on rating data and application in recommender systems

This thesis introduced two novel reputation models to generate accurate item reputation scores using ratings data and the statistics of the dataset. It also presented an innovative method that incorporates reputation awareness in recommender systems by employing voting system methods to produce more accurate top-N item recommendations. Additionally, this thesis introduced a personalisation method for generating reputation scores based on users' interests, where a single item can have different reputation scores for different users. The personalised reputation scores are then used in the proposed reputation-aware recommender systems to enhance the recommendation quality.

Mining topical relevant patterns for multi-document summarization

Multi-document summarization addressing the problem of information overload has been widely utilized in the various real-world applications. Most of existing approaches adopt term-based representation for documents which limit the performance of multi-document summarization systems. In this paper, we proposed a novel pattern-based topic model (PBTMSum) for the task of the multi-document summarization. PBTMSum combining pattern mining techniques with LDA topic modelling could generate discriminative and semantic rich representations for topics and documents so that the most representative and non-redundant sentences can be selected to form a succinct and informative summary. Extensive experiments are conducted on the data of document understanding conference (DUC) 2007. The results prove the effectiveness and efficiency of our proposed approach.

Using a glow graph to represent data flow and dependency in event logs

The idea of extracting knowledge in process mining is a descendant of data mining. Both mining disciplines emphasise data flow and relations among elements in the data. Unfortunately, challenges have been encountered when working with the data flow and relations. One of the challenges is that the representation of the data flow between a pair of elements or tasks is insufficiently simplified and formulated, as it considers only a one-to-one data flow relation. In this paper, we discuss how the effectiveness of knowledge representation can be extended in both disciplines. To this end, we introduce a new representation of the data flow and dependency formulation using a flow graph. The flow graph solves the issue of the insufficiency of presenting other relation types, such as many-to-one and one-to-many relations. As an experiment, a new evaluation framework is applied to the Teleclaim process in order to show how this method can provide us with more precise results when compared with other representations.

A shallow water AUV for benthic and water column observations

Autonomous underwater vehicles (AUVs) are becoming commonplace in the study of inshore coastal marine habitats. Combined with shipboard systems, scientists are able to make in-situ measurements of water column and benthic properties. In CSIRO, autonomous gliders are used to collect water column data, while surface vessels are used to collect bathymetry information through the use of swath mapping, bottom grabs, and towed video systems. Although these methods have provided good data coverage for coastal and deep waters beyond 50m, there has been an increasing need for autonomous in-situ sampling in waters less than 50m deep. In addition, the collection of benthic and water column data has been conducted separately, requiring extensive post-processing to combine data streams. As such, a new AUV was developed for in-situ observations of both benthic habitat and water column properties in shallow waters. This paper provides an overview of the Starbug X AUV system, its operational characteristics including vision-based navigation and oceanographic sensor integration.

Combinatorial Design of Secure Lightweight Data Dispersal Schemes (Work in Progress)

Dispersing a data object into a set of data shares is an elemental stage in distributed communication and storage systems. In comparison to data replication, data dispersal with redundancy saves space and bandwidth. Moreover, dispersing a data object to distinct communication links or storage sites limits adversarial access to whole data and tolerates loss of a part of data shares. Existing data dispersal schemes have been proposed mostly based on various mathematical transformations on the data which induce high computation overhead. This paper presents a novel data dispersal scheme where each part of a data object is replicated, without encoding, into a subset of data shares according to combinatorial design theory. Particularly, data parts are mapped to points and data shares are mapped to lines of a projective plane. Data parts are then distributed to data shares using the point and line incidence relations in the plane so that certain subsets of data shares collectively possess all data parts. The presented scheme incorporates combinatorial design theory with inseparability transformation to achieve secure data dispersal at reduced computation, communication and storage costs. Rigorous formal analysis and experimental study demonstrate significant cost-benefits of the presented scheme in comparison to existing methods.

A cloud-based intelligent computing system for contextual exploration on personal sleep-tracking data using association rule mining

With the development of wearable and mobile computing technology, more and more people start using sleep-tracking tools to collect personal sleep data on a daily basis aiming at understanding and improving their sleep. While sleep quality is influenced by many factors in a person’s lifestyle context, such as exercise, diet and steps walked, existing tools simply visualize sleep data per se on a dashboard rather than analyse those data in combination with contextual factors. Hence many people find it difficult to make sense of their sleep data. In this paper, we present a cloud-based intelligent computing system named SleepExplorer that incorporates sleep domain knowledge and association rule mining for automated analysis on personal sleep data in light of contextual factors. Experiments show that the same contextual factors can play a distinct role in sleep of different people, and SleepExplorer could help users discover factors that are most relevant to their personal sleep.

Multi-GNSS precise point positioning with raw single-frequency and dual-frequency measurement models

The emergence of multiple satellite navigation systems, including BDS, Galileo, modernized GPS, and GLONASS, brings great opportunities and challenges for precise point positioning (PPP). We study the contributions of various GNSS combinations to PPP performance based on undifferenced or raw observations, in which the signal delays and ionospheric delays must be considered. A priori ionospheric knowledge, such as regional or global corrections, strengthens the estimation of ionospheric delay parameters. The undifferenced models are generally more suitable for single-, dual-, or multi-frequency data processing for single or combined GNSS constellations. Another advantage over ionospheric-free PPP models is that undifferenced models avoid noise amplification by linear combinations. Extensive performance evaluations are conducted with multi-GNSS data sets collected from 105 MGEX stations in July 2014. Dual-frequency PPP results from each single constellation show that the convergence time of undifferenced PPP solution is usually shorter than that of ionospheric-free PPP solutions, while the positioning accuracy of undifferenced PPP shows more improvement for the GLONASS system. In addition, the GLONASS undifferenced PPP results demonstrate performance advantages in high latitude areas, while this impact is less obvious in the GPS/GLONASS combined configuration. The results have also indicated that the BDS GEO satellites have negative impacts on the undifferenced PPP performance given the current “poor” orbit and clock knowledge of GEO satellites. More generally, the multi-GNSS undifferenced PPP results have shown improvements in the convergence time by more than 60 % in both the single- and dual-frequency PPP results, while the positioning accuracy after convergence indicates no significant improvements for the dual-frequency PPP solutions, but an improvement of about 25 % on average for the single-frequency PPP solutions.

Assessment of code bias variations of BDS triple-frequency signals and their impacts on ambiguity resolution for long baselines

Carrier phase ambiguity resolution over long baselines is challenging in BDS data processing. This is partially due to the variations of the hardware biases in BDS code signals and its dependence on elevation angles. We present an assessment of satellite-induced code bias variations in BDS triple-frequency signals and the ambiguity resolutions procedures involving both geometry-free and geometry-based models. First, since the elevation of a GEO satellite remains unchanged, we propose to model the single-differenced fractional cycle bias with widespread ground stations. Second, the effects of code bias variations induced by GEO, IGSO and MEO satellites on ambiguity resolution of extra-wide-lane, wide-lane and narrow-lane combinations are analyzed. Third, together with the IGSO and MEO code bias variations models, the effects of code bias variations on ambiguity resolution are examined using 30-day data collected over the baselines ranging from 500 to 2600 km in 2014. The results suggest that although the effect of code bias variations on the extra-wide-lane integer solution is almost ignorable due to its long wavelength, the wide-lane integer solutions are rather sensitive to the code bias variations. Wide-lane ambiguity resolution success rates are evidently improved when code bias variations are corrected. However, the improvement of narrow-lane ambiguity resolution is not obvious since it is based on geometry-based model and there is only an indirect impact on the narrow-lane ambiguity solutions.

RTK-based GNSS drifters for monitoring in estuaries and rivers: Field experimental results

This paper presents a novel RTK-based GNSS Lagrangian drifter system that is capable of monitoring water velocity, turbulence and dispersion coefficients of river and estuarine. The Lagrangian drifters use the dual-frequency real time kinematic (RTK) technique for both position and velocity estimations. The capsule is designed to meet the requirements such as minimizing height, diameter, minimizing the direct wind drag, positive buoyancy for satellite signal reception and stability, and waterproof housing for electronic components, such as GNSS receiver and computing board. The collected GNSS data are processed with post-processing RTK software. Several experiments have been carried out in two rivers in Brisbane and Sunshine Coast in Queensland. Results show that the high accuracy GNSS-drifters can be used to measure dispersion coefficient resulting from sub-tidal velocity fluctuations in shallow tidal water. In addition, the RTK-GNSS drifters respond well to vertical motion and thus could be applicable to flood monitoring.

Wide area kinematic positioning with BeiDou triple frequency signals

A key challenge of wide area kinematic positioning is to overcome the effects of the varying hardware biases in code signals of the BeiDou system. Based on three geometryfree/ionosphere-free combinations, the elevation-dependent code biases are modelled for all BeiDou satellites. Results from the data sets of 30-day for 5 baselines of 533 to 2545 km demonstrate that the wide-lane (WL) integer-fixing success rates of 98% to 100% can be achieved within 25 min. Under the condition of HDOP of less than 2, the overall RMS statistics show that ionospheric-free WL single-epoch solutions achieve 24 to 50 cm in the horizontal direction. Smoothing processing over the moving window of 20 min reduces the RMS values by a factor of about 2. Considering distance-independent nature, the above results show the potential that reliable and high precision positioning services could be provided in a wide area based on a sparsely distributed ground network.

Data-aware task scheduling for all-to-all comparison problems in heterogeneous distributed systems

Solving large-scale all-to-all comparison problems using distributed computing is increasingly significant for various applications. Previous efforts to implement distributed all-to-all comparison frameworks have treated the two phases of data distribution and comparison task scheduling separately. This leads to high storage demands as well as poor data locality for the comparison tasks, thus creating a need to redistribute the data at runtime. Furthermore, most previous methods have been developed for homogeneous computing environments, so their overall performance is degraded even further when they are used in heterogeneous distributed systems. To tackle these challenges, this paper presents a data-aware task scheduling approach for solving all-to-all comparison problems in heterogeneous distributed systems. The approach formulates the requirements for data distribution and comparison task scheduling simultaneously as a constrained optimization problem. Then, metaheuristic data pre-scheduling and dynamic task scheduling strategies are developed along with an algorithmic implementation to solve the problem. The approach provides perfect data locality for all comparison tasks, avoiding rearrangement of data at runtime. It achieves load balancing among heterogeneous computing nodes, thus enhancing the overall computation time. It also reduces data storage requirements across the network. The effectiveness of the approach is demonstrated through experimental studies.

Overview of the 2015 ALTA shared task: Identifying French cognates in English text

This paper presents an overview of the 6th ALTA shared task that ran in 2015. The task was to identify in English texts all the potential cognates from the perspective of the French language. In other words, identify all the words in the English text that would acceptably translate into a similar word in French. We present the motivations for the task, the description of the data and the results of the 4 participating teams. We discuss the results against a baseline and prior work.

Assessment of crop insect damage using unmanned aerial systems: A machine learning approach

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising technology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of the approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labeling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means. The outcome of this approach is a soft K-means algorithm similar to the EM algorithm for Gaussian mixture models. The results show the algorithm delivers decision boundaries that consistently classify the field into three clusters, one for each crop health level. The methodology presented in this paper represents a venue for further research towards automated crop damage assessments and biosecurity surveillance.

Extending visual perception with haptic exploration for improved scene understanding

Scene understanding has been investigated from a mainly visual information point of view. Recently depth has been provided an extra wealth of information, allowing more geometric knowledge to fuse into scene understanding. Yet to form a holistic view, especially in robotic applications, one can create even more data by interacting with the world. In fact humans, when growing up, seem to heavily investigate the world around them by haptic exploration. We show an application of haptic exploration on a humanoid robot in cooperation with a learning method for object segmentation. The actions performed consecutively improve the segmentation of objects in the scene.