My research focuses on developing innovative ways to control Heating, Ventilation, and Air Conditioning (HVAC) and schedule occupancy flows in smart buildings to reduce our ecological footprint (and energy bills). We look at the potential for integrating building operations with room booking and meeting scheduling. Specifically, we improve on the effectiveness of energy-aware room-booking and occupancy scheduling approaches, by allowing the scheduling decisions to rely on an explicit model of the building's occupancy-based HVAC control. From computational standpoint, this is a challenging topic as HVAC models are inherently non-linear non-convex, and occupancy scheduling models additionally introduce discrete variables capturing the time slot and location at which each activity is scheduled. The mechanism needs to tradeoff minimizing energy cost against addressing occupancy thermal comfort and control feasibility in a highly dynamic and uncertain system.

The problem of unsupervised anomaly detection arises in awide variety of practical applications. While one-class sup-port vector machines have demonstrated their effectiveness asan anomaly detection technique, their ability to model largedatasets is limited due to their memory and time complexityfor training. To address this issue for supervised learning ofkernel machines, there has been growing interest in randomprojection methods as an alternative to the computationallyexpensive problems of kernel matrix construction and sup-port vector optimisation. In this paper we leverage the theoryof nonlinear random projections and propose the RandomisedOne-class SVM (R1SVM), which is an efficient and scalableanomaly detection technique that can be trained on large-scale datasets. Our empirical analysis on several real-life andsynthetic datasets shows that our randomised 1SVM algo-rithm achieves comparable or better accuracy to deep autoen-coder and traditional kernelised approaches for anomaly de-tection, while being approximately 100 times faster in train-ing and testing

Evacuation planning is a critical aspect of disaster preparedness and response to minimize the number of people exposed to a threat. Controlled evacuations aim at managing the flow of evacuees as efficiently as possible and have been shown to produce significant benefits compared to self-evacuations. However, existing approaches do not capture the delays introduced by diverging and crossing evacuation routes, although evidence from actual evacuations highlights that these can lead to significant congestion. This paper introduces the concept of convergent evacuation plans to tackle this issue. It presents a MIP model to obtain optimal convergent evacuation plans which, unfortunately, does not scale to realistic instances. The paper then proposes a two-stage approach that separates the route design and the evacuation scheduling. Experimental results on a real case study show that the two-stage approach produces better primal bounds than the MIP model and is two orders of magnitude faster; It also produces dual bounds stronger than the linear relaxation of the MIP model. Finally, simulations of the evacuation demonstrate that convergent evacuation plans outperform existing approaches for realistic driver behaviors.

Effective forecasting of future prevalent topics plays animportant role in social network business development.It involves two challenging aspects: predicting whethera topic will become prevalent, and when. This cannotbe directly handled by the existing algorithms in topicmodeling, item recommendation and action forecasting.The classic forecasting framework based on time seriesmodels may be able to predict a hot topic when a seriesof periodical changes to user-addressed frequency in asystematic way. However, the frequency of topics discussedby users often changes irregularly in social networks.In this paper, a generic probabilistic frameworkis proposed for hot topic prediction, and machine learningmethods are explored to predict hot topic patterns.Two effective models, PreWHether and PreWHen, areintroduced to predict whether and when a topic will becomeprevalent. In the PreWHether model, we simulatethe constructed features of previously observed frequencychanges for better prediction. In the PreWHen model,distributions of time intervals associated with the emergenceto prevalence of a topic are modeled. Extensiveexperiments on real datasets demonstrate that ourmethod outperforms the baselines and generates moreeffective predictions.

We introduce a novel method for the continuous online prediction of particulate matter in the air (more specifically, PM10 and PM2.5) given sparse sensor information. A nonparametric model is developed using Gaussian Processes, which eschews the need for an explicit formulation of internal -- and usually very complex -- dependencies between meteorological variables. Instead, it uses historical data to extrapolate pollutant values both spatially (in areas with no sensor information) and temporally (the near future). Each prediction also contains a respective variance, indicating its uncertainty level and thus allowing a probabilistic treatment of results. A novel training methodology (Structural Cross-Validation) is presented, which preserves the spatio-temporal structure of available data during the hyperparameter optimization process. Tests were conducted using a real-time feed from a sensor network in an area of roughly 50x80 km, alongside comparisons with other techniques for air pollution prediction. The promising results motivated the development of a smartphone applicative and a website, currently in use to increase the efficiency of air quality monitoring and control in the area.

We address the problem of power system restoration after a significant blackout. Prior work focus on optimization methods for finding high-quality restoration plans. Optimal solutions consist in a sequence of grid repairs and corresponding steady states. However, such approaches lack formal guarantees on the transient stability of restoration actions, a key property to avoid additional grid damage and cascading failures. In this paper, we show how to integrate transient stability in the optimization procedure by capturing the rotor dynamics of power generators. Our approach reasons about the differential equations describing the dynamics and their underlying transient states. The key contribution lies in modeling and solving optimization problems that return stable generators dispatch minimizing the difference with respect to steady states solutions. Computational efficiency is increased using preprocessing procedures along with traditional reduction techniques. Experimental results on existing benchmarks confirm the feasibility of the new approach.

In emergency medical systems, arriving at the incident locationa few seconds early can save a human life. Thus, this paper is motivated by the need to reduce the response time– time taken to arrive at the incident location after receivingthe emergency call — of Emergency Response Vehicles, ERVs(ex: ambulances, fire rescue vehicles) for as many requests as possible. We expect to achieve this primarily by positioning the ”right” number of ERVs at the ”right” places and at the ”right” times. Given the exponentially large action space(with respect to number of ERVs and their placement) and the stochasticity in location and timing of emergency incidents,this problem is computationally challenging. To that end, ourcontributions building on existing data-driven approaches are three fold:1. Based on real world evaluation metrics, we provide a riskbased optimization criterion to learn from past incident data. Instead of minimizing expected response time, we minimize the largest value of response time such that the risk of finding requests that have a higher value is bounded(ex: Only 10% of requests should have a response time greater than 8 minutes).2. We develop a mixed integer linear optimization formulation to learn and compute an allocation from a set of inputrequests while considering the risk criterion.3. To allow for ”live” reallocation of ambulances, we provide a decomposition method based on Lagrangian Relaxation to significantly reduce the run-time of the optimization formulation.Finally, we provide an exhaustive evaluation on real-world datasets from two asian cities that demonstrates the improvement provided by our approach over current practice and the best known approach from literature.

Causal structure discovery methods are investigated recently but none of them has taken possible time-varying structure into consideration. This paper uses a notion of causal time-varying dynamic Bayesian network (CTV-DBN) and define a causal boundary to govern cross-time information sharing. CTV-DBN is constructed by using asymmetric kernels to address sample scarcity and to adhere to causal principles; while maintaining good variance and bias trade-off. Upon satisfying causal Markov assumption, causal inference can be made based on manipulation rule. We explore trajectory data collected from taxis in Beijing which exhibit heterogeneous patterns, data sparseness and distribution skewness. Experiments show that by using casual structures and trajectory clustering, we can analyse the spatio-temporal behavior of the trajectory data.

We describe a multi-modal cargo routing (MMCR) domain for modelling military logistics planning problems. These are transport optimisation problems that feature timing constraints, concurrency, capacitated resources, and action costs. We have developed a PDDL domain model, and have released a collection of problem instances along with a software tool to aid in the design and generation of new problem instances. Small instances of this domain stretch the capabilities of existing automated planning procedures, and larger realistic instances are beyond the capabilities of existing automated planning systems. We anticipate that scalable solution procedures for this domain will follow in the footsteps of systems, such as OPTIC and TIMIPLAN, which combine heuristic search concepts with mathematical programming optimisation tools.

The Atari 2600 games supported in the Arcade Learning Environment (Bellemare et al. 2013) all feature aknown initial (RAM) state and actions that have deterministic effects. Classical planners, however, cannot be used for selecting actions for two reasons: first, nocompact PDDL-model of the games is given, and more importantly, the action effects and goals are not known a priori. Moreover, in these games there is usually no set of goals to be achieved but rewards to be collected. These features do not preclude the use of classical algorithms like breadth-first search or Dijkstra’s algorithm, but these methods are not effective over large state spaces. We thus turn to a different class of classical planning algorithms introduced recently that perform a structured exploration of the state space; namely, like breadth-first search and Dijkstra’s algorithm they are“blind” and hence do not require prior knowledge of state transitions, costs (rewards) or goals, and yet, like heuristic search algorithms, they have been shown to be effective for solving problems over huge state spaces.The simplest such algorithm, called Iterated Width or IW, consists of a sequence of calls IW(1), IW(2), . . . ,IW(k) where IW(i) is a breadth-first search in which a state is pruned when it is not the first state in the search to make true some subset of i atoms. The empirical results over 54 games suggest that the performance of IW with the k parameter fixed to 1, i.e., IW(1), is at the level of the state of the art represented by UCT. A simple best-first variation of IW that combines exploration and exploitation proves to be very competitive as well.