arXiv subjects

Raja Jurdak

Publications and source records attributed to Raja Jurdak.

116 records · Page 7Linked to original sources

arXiv2015

Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets

The prediction of periodical time-series remains challenging due to various types of data distortions and misalignments. Here, we propose a novel model called Temporal embedding-enhanced convolutional neural Network (TeNet) to learn repeatedly-occurring-yet-hidden structural elements in periodical time-series, called abstract snippets, for predicting future changes. Our model uses convolutional neural networks and embeds a time-series with its potential neighbors in the temporal domain for aligning it to the dominant patterns in the dataset. The model is robust to distortions and misalignments in the temporal domain and demonstrates strong prediction power for periodical time-series. We conduct extensive experiments and discover that the proposed model shows significant and consistent advantages over existing methods on a variety of data modalities ranging from human mobility to household power consumption records. Empirical results indicate that the model is robust to various factors such as number of samples, variance of data, numerical ranges of data etc. The experiments also verify that the intuition behind the model can be generalized to multiple data types and applications and promises significant improvement in prediction performances across the datasets studied.

cs.LG↗

arXiv2014

Bounded Quadrant System: Error-bounded Trajectory Compression on the Go

Long-term location tracking, where trajectory compression is commonly used, has gained high interest for many applications in transport, ecology, and wearable computing. However, state-of-the-art compression methods involve high space-time complexity or achieve unsatisfactory compression rate, leading to rapid exhaustion of memory, computation, storage and energy resources. We propose a novel online algorithm for error-bounded trajectory compression called the Bounded Quadrant System (BQS), which compresses trajectories with extremely small costs in space and time using convex-hulls. In this algorithm, we build a virtual coordinate system centered at a start point, and establish a rectangular bounding box as well as two bounding lines in each of its quadrants. In each quadrant, the points to be assessed are bounded by the convex-hull formed by the box and lines. Various compression error-bounds are therefore derived to quickly draw compression decisions without expensive error computations. In addition, we also propose a light version of the BQS version that achieves $\mathcal{O}(1)$ complexity in both time and space for processing each point to suit the most constrained computation environments. Furthermore, we briefly demonstrate how this algorithm can be naturally extended to the 3-D case. Using empirical GPS traces from flying foxes, cars and simulation, we demonstrate the effectiveness of our algorithm in significantly reducing the time and space complexity of trajectory compression, while greatly improving the compression rates of the state-of-the-art algorithms (up to 47%). We then show that with this algorithm, the operational time of the target resource-constrained hardware platform can be prolonged by up to 41%.

cs.DS↗

arXiv2014

Multi-scale Population and Mobility Estimation with Geo-tagged Tweets

Recent outbreaks of Ebola and Dengue viruses have again elevated the significance of the capability to quickly predict disease spread in an emergent situation. However, existing approaches usually rely heavily on the time-consuming census processes, or the privacy-sensitive call logs, leading to their unresponsive nature when facing the abruptly changing dynamics in the event of an outbreak. In this paper we study the feasibility of using large-scale Twitter data as a proxy of human mobility to model and predict disease spread. We report that for Australia, Twitter users' distribution correlates well the census-based population distribution, and that the Twitter users' travel patterns appear to loosely follow the gravity law at multiple scales of geographic distances, i.e. national level, state level and metropolitan level. The radiation model is also evaluated on this dataset though it has shown inferior fitness as a result of Australia's sparse population and large landmass. The outcomes of the study form the cornerstones for future work towards a model-based, responsive prediction method from Twitter data for disease spread.

cs.SI↗

arXiv2014

In-Network Distributed Solar Current Prediction

Long-term sensor network deployments demand careful power management. While managing power requires understanding the amount of energy harvestable from the local environment, current solar prediction methods rely only on recent local history, which makes them susceptible to high variability. In this paper, we present a model and algorithms for distributed solar current prediction, based on multiple linear regression to predict future solar current based on local, in-situ climatic and solar measurements. These algorithms leverage spatial information from neighbors and adapt to the changing local conditions not captured by global climatic information. We implement these algorithms on our Fleck platform and run a 7-week-long experiment validating our work. In analyzing our results from this experiment, we determined that computing our model requires an increased energy expenditure of 4.5mJ over simpler models (on the order of 10^{-7}% of the harvested energy) to gain a prediction improvement of 39.7%.

cs.DC↗

arXiv2014

Optimal Lévy-flight foraging in a finite landscape

We present a simple model to study Lévy-flight foraging in a finite landscape with countable targets. In our approach, foraging is a step-based exploratory random search process with a power-law step-size distribution $P(l) \propto l^{-μ}$. We find that, when the termination is regulated by a finite number of steps $N$, the optimum value of $μ$ that maximises the foraging efficiency can vary substantially in the interval $μ\in (1,3)$, depending on the landscape features (landscape size and number of targets). We further demonstrate that subjective returning can be another significant factor that affects the foraging efficiency in such context. Our results suggest that Lévy-flight foraging may arise through an interaction between the environmental context and the termination of exploitation, and particularly that the number of steps can play an important role in this scenario which is overlooked by most previous work. Our study not only provides a new perspective on Lévy-flight foraging, but also opens new avenues for investigating the interaction between foraging dynamics and environment as well as offers a realistic framework for analysing animal movement patterns from empirical data.

cond-mat.stat-mech↗

arXiv2014

Guiding Ebola Patients to Suitable Health Facilities: An SMS-based Approach

We propose to utilize mobile phone technology as a vehicle for people to report their symptoms and to receive immediate feedback about the health services readily available, and for predicting spatial disease outbreak risk. Once symptoms are extracted from the patients text message, they undergo complex classification, pattern matching and prediction to recommend the nearest suitable health service. The added benefit of this approach is that it enables health care facilities to anticipate arrival of new potential Ebola cases.

cs.CY↗

arXiv2014

Genetic Programming for Smart Phone Personalisation

Personalisation in smart phones requires adaptability to dynamic context based on user mobility, application usage and sensor inputs. Current personalisation approaches, which rely on static logic that is developed a priori, do not provide sufficient adaptability to dynamic and unexpected context. This paper proposes genetic programming (GP), which can evolve program logic in realtime, as an online learning method to deal with the highly dynamic context in smart phone personalisation. We introduce the concept of collaborative smart phone personalisation through the GP Island Model, in order to exploit shared context among co-located phone users and reduce convergence time. We implement these concepts on real smartphones to demonstrate the capability of personalisation through GP and to explore the benefits of the Island Model. Our empirical evaluations on two example applications confirm that the Island Model can reduce convergence time by up to two-thirds over standalone GP personalisation.

cs.NE↗

arXiv2014

The Impact of Cost and Network Topology on Urban Mobility: A Study of Public Bicycle Usage in 2 U.S. Cities

Understanding the drivers of urban mobility is vital for epidemiology, urban planning, and communication networks. Human movements have so far been studied by observing people's positions in a given space and time, though most recent models only implicitly account for expected costs and returns for movements. This paper explores the explicit impact of cost and network topology on mobility dynamics, using data from 2 city-wide public bicycle share systems in the USA. User mobility is characterized through the distribution of trip durations, while network topology is characterized through the pairwise distances between stations and the popularity of stations and routes. Despite significant differences in station density and physical layout between the 2 cities, trip durations follow remarkably similar distributions that exhibit cost sensitive trends around pricing point boundaries, particularly with long-term users of the system. Based on the results, recommendations for dynamic pricing and incentive schemes are provided to positively influence mobility patterns and guide improved planning and management of public bicycle systems to increase uptake.

cs.SI↗