TECNALIA Publications Repository :: Browsing by Author "Oregi, Izaskun"

Browsing by Author "Oregi, Izaskun"

Now showing 1 - 20 of 24

Adversarial sample crafting for time series classification with elastic similarity measures
(Springer Verlag, 2018) Oregi, Izaskun; Del Ser, Javier; Perez, Aritz; Lozano, Jose A.; Quantum
Adversarial Machine Learning (AML) refers to the study of the robustness of classification models when processing data samples that have been intelligently manipulated to confuse them. Procedures aimed at furnishing such confusing samples exploit concrete vulnerabilities of the learning algorithm of the model at hand, by which perturbations can make a given data instance to be misclassified. In this context, the literature has so far gravitated on different AML strategies to modify data instances for diverse learning algorithms, in most cases for image classification. This work builds upon this background literature to address AML for distance based time series classifiers (e.g., nearest neighbors), in which attacks (i.e. modifications of the samples to be classified by the model) must be intelligently devised by taking into account the measure of similarity used to compare time series. In particular, we propose different attack strategies relying on guided perturbations of the input time series based on gradient information provided by a smoothed version of the distance based model to be attacked. Furthermore, we formulate the AML sample crafting process as an optimization problem driven by the Pareto trade-off between (1) a measure of distortion of the input sample with respect to its original version; and (2) the probability of the crafted sample to confuse the model. In this case, this formulated problem is efficiently tackled by using multi-objective heuristic solvers. Several experiments are discussed so as to assess whether the crafted adversarial time series succeed when confusing the distance based model under target.
Analyzing the behaviour of D'WAVE quantum annealer: Fine-tuning parameterization and tests with restrictive Hamiltonian formulations
(Institute of Electrical and Electronics Engineers Inc., 2022) Villar-Rodriguez, Esther; Osaba, Eneko; Oregi, Izaskun; Ishibuchi, Hisao; Kwoh, Chee-Keong; Tan, Ah-Hwee; Srinivasan, Dipti; Miao, Chunyan; Trivedi, Anupam; Crockett, Keeley; Quantum
Despite being considered as the next frontier in computation, Quantum Computing is still in an early stage of development. Indeed, current commercial quantum computers suffer from some critical restraints, such as noisy processes and a limited amount of qubits, among others, that affect the performance of quantum algorithms. Despite these limitations, researchers have devoted much effort to propose different frameworks for efficiently using these Noisy Intermediate-Scale Quantum (NISQ) devices. One of these procedures is D'WAVE Systems' quantum-annealer, which can be used to solve optimization problems by translating them into an energy minimization problem. In this context, this work is focused on providing useful insights and information into the behaviour of the quantum-annealer when addressing real-world combinatorial optimization problems. Our main motivation with this study is to open some quantum computing frontiers to non-expert stakeholders. To this end, we perform an extensive experimentation, in the form of a parameter sensitive analysis. This experimentation has been conducted using the Traveling Salesman Problem as benchmarking problem, and adopting two QUBOs: state-of-the-art and a heuristically generated. Our analysis has been performed on a single 7-noded instance, and it is based on more than 200 different parameter configurations, comprising more than 3700 unitary runs and 7 million of quantum reads. Thanks to this study, findings related to the energy distribution and most appropriate parameter settings have been obtained. Finally, an additional study has been performed, aiming to determine the efficiency of the heuristically built QUBO in further TSP instances.
Deep Echo State Networks for Short-Term Traffic Forecasting: Performance Comparison and Statistical Assessment
(Institute of Electrical and Electronics Engineers Inc., 2020-09-20) Del Ser, Javier; Laña, Ibai; Manibardo, Eric L.; Oregi, Izaskun; Osaba, Eneko; Lobo, Jesus L.; Bilbao, Miren Nekane; Vlahogianni, Eleni I.; IA; Quantum
In short-term traffic forecasting, the goal is to accurately predict future values of a traffic parameter of interest occurring shortly after the prediction is queried. The activity reported in this long-standing research field has been lately dominated by different Deep Learning approaches, yielding overly complex forecasting models that in general achieve accuracy gains of questionable practical utility. In this work we elaborate on the performance of Deep Echo State Networks for this particular task. The efficient learning algorithm and simpler parametric configuration of these alternative modeling approaches make them emerge as a competitive traffic forecasting method for real ITS applications deployed in devices and systems with stringently limited computational resources. An extensive comparison benchmark is designed with real traffic data captured over the city of Madrid (Spain), amounting to more than 130 Automatic Traffic Readers (ATRs) and several shallow learning, ensembles and Deep Learning models. Results from this comparison benchmark and the analysis of the statistical significance of the reported performance gaps are decisive: Deep Echo State Networks achieve more accurate traffic forecasts than the rest of considered modeling counterparts.
Detection of non-technical losses in smart meter data based on load curve profiling and time series analysis
(2017) Villar-Rodriguez, Esther; Del Ser, Javier; Oregi, Izaskun; Bilbao, Miren Nekane; Gil-Lopez, Sergio; Quantum; IA
The advent and progressive deployment of the so-called Smart Grid has unleashed a profitable portfolio of new possibilities for an efficient management of the low-voltage distribution network supported by the introduction of information and communication technologies to exploit its digitalization. Among all such possibilities this work focuses on the detection of anomalous energy consumption traces: disregarding whether they are due to malfunctioning metering equipment or fraudulent purposes, strong efforts are invested by utilities to detect such outlying events and address them to optimize the power distribution and avoid significant income costs. In this context this manuscript introduce a novel algorithmic approach for the identification of consumption outliers in Smart Grids that relies on concepts from probabilistic data mining and time series analysis. A key ingredient of the proposed technique is its ability to accommodate time irregularities – shifts and warps – in the consumption habits of the user by concentrating on the shape of the consumption rather than on its temporal properties. Simulation results over real data from a Spanish utility are presented and discussed, from where it is concluded that the proposed approach excels at detecting different outlier cases emulated on the aforementioned consumption traces.
Digital Quantum Simulation and Circuit Learning for the Generation of Coherent States
(2022-10-25) Liu, Ruilin; V. Romero, Sebastián; Oregi, Izaskun; Osaba, Eneko; Villar-Rodriguez, Esther; Ban, Yue; Tecnalia Research & Innovation; Quantum
Coherent states, known as displaced vacuum states, play an important role in quantum information processing, quantum machine learning, and quantum optics. In this article, two ways to digitally prepare coherent states in quantum circuits are introduced. First, we construct the displacement operator by decomposing it into Pauli matrices via ladder operators, i.e., creation and annihilation operators. The high fidelity of the digitally generated coherent states is verified compared with the Poissonian distribution in Fock space. Secondly, by using Variational Quantum Algorithms, we choose different ansatzes to generate coherent states. The quantum resources—such as numbers of quantum gates, layers and iterations—are analyzed for quantum circuit learning. The simulation results show that quantum circuit learning can provide high fidelity on learning coherent states by choosing appropriate ansatzes.
Digital-analog quantum computation with arbitrary two-body Hamiltonians
(2024-01) Garcia-De-Andoin, Mikel; Saiz, Álvaro; Pérez-Fernández, Pedro; Lamata, Lucas; Oregi, Izaskun; Sanz, Mikel; Quantum
Digital-analog quantum computing is a computational paradigm which employs an analog Hamiltonian resource together with single-qubit gates to reach universality. Here, we design a new scheme which employs an arbitrary two-body source Hamiltonian, extending the experimental applicability of this computational paradigm to most quantum platforms. We show that the simulation of an arbitrary two-body target Hamiltonian of n qubits requires O(n2) analog blocks with guaranteed positive times, providing a polynomial advantage compared to the previous scheme. Additionally, we propose a classical strategy which combines a Bayesian optimization with a gradient descent method, improving the performance by ∼55% for small systems measured in the Frobenius norm.
Exploiting the stimuli encoding scheme of evolving Spiking Neural Networks for stream learning
(2020-03) Lobo, Jesus L.; Oregi, Izaskun; Bifet, Albert; Del Ser, Javier; IA; Quantum
Stream data processing has lately gained momentum with the arrival of new Big Data scenarios and applications dealing with continuously produced information flows. Unfortunately, traditional machine learning algorithms are not prepared to tackle the specific challenges imposed by data stream processing, such as the need for learning incrementally, limited memory and processing time requirements, and adaptation to non-stationary data, among others. To face these paradigms, Spiking Neural Networks have emerged as one of the most promising stream learning techniques, with variants such as Evolving Spiking Neural Networks capable of efficiently addressing many of these challenges. Interestingly, these networks resort to a particular population encoding scheme – Gaussian Receptive Fields – to transform the incoming stimuli into temporal spikes. The study presented in this manuscript sheds light on the predictive potential of this encoding scheme, focusing on how it can be applied as a computationally lightweight, model-agnostic preprocessing step for data stream learning. We provide informed intuition to unveil under which circumstances the aforementioned population encoding method yields effective prediction gains in data stream classification with respect to the case where no preprocessing is performed. Results obtained for a variety of stream learning models and both synthetic and real stream datasets are discussed to empirically buttress the capability of Gaussian Receptive Fields to boost the predictive performance of stream learning methods, spanning further research towards extrapolating our findings to other machine learning problems.
Focusing on the hybrid quantum computing - Tabu search algorithm: New results on the Asymmetric Salesman Problem
(Association for Computing Machinery, Inc, 2021-07-07) Osaba, Eneko; Villar-Rodriguez, Esther; Oregi, Izaskun; Moreno-Fernandez-De-Leceta, Aitor; Quantum
Quantum Computing is an emerging paradigm which is gathering a lot of popularity in the current scientific and technological community. Widely conceived as the next frontier of computation, Quantum Computing is still at the dawn of its development. Thus, current solving systems suffer from significant limitations in terms of performance and capabilities. Some interesting approaches have been devised by researchers and practitioners in order to overcome these barriers, being quantum-classical hybrid algorithms one of the most often used solving schemes. The main goal of this paper is to extend the results and findings of the recently proposed hybrid Quantum Computing - Tabu Search Algorithm for partitioning problems. To do that, we focus our research on the adaptation of this method to the Asymmetric Traveling Salesman Problem. In overall, we have employed six well-known instances belonging to TSPLIB to assess the performance of Quantum Computing - Tabu Search Algorithm in comparison to QBSolv. Furthermore, as an additional contribution, this work also supposes the first solving of the Asymmetric Traveling Salesman Problem using a Quantum Computing based method. Aiming to boost whole community's research in QC, we have released the project's repository as open source code for further application and improvements.
Hybrid Quantum Computing - Tabu Search Algorithm for Partitioning Problems: Preliminary Study on the Traveling Salesman Problem
(Institute of Electrical and Electronics Engineers Inc., 2021) Osaba, Eneko; Villar-Rodriguez, Esther; Oregi, Izaskun; Moreno-Fernandez-de-Leceta, Aitor; Quantum
Quantum Computing is considered as the next frontier in computing, and it is attracting a lot of attention from the current scientific community. This kind of computation provides to researchers with a revolutionary paradigm for addressing complex optimization problems, offering a significant speed advantage and an efficient search ability. Anyway, Quantum Computing is still in an incipient stage of development. For this reason, present architectures show certain limitations, which have motivated the carrying out of this paper. In this paper, we introduce a novel solving scheme coined as hybrid Quantum Computing - Tabu Search Algorithm. Main pillars of operation of the proposed method are a greater control over the access to quantum resources, and a considerable reduction of nonprofitable accesses. To assess the quality of our method, we have used 7 different Traveling Salesman Problem instances as benchmarking set. The obtained outcomes support the preliminary conclusion that our algorithm is an approach which offers promising results for solving partitioning problems while it drastically reduces the access to quantum computing resources. We also contribute to the field of Transfer Optimization by developing an evolutionary multiform multitasking algorithm as initialization method.
Hybridizing differential evolution and novelty search for multimodal optimization problems
(Association for Computing Machinery, Inc, 2019-07-13) Martinez, Aritz D.; Fister, Iztok; Osaba, Eneko; Fister, Iztok; Oregi, Izaskun; Ser, Javier Del; IA; Quantum
Multimodal optimization has shown to be a complex paradigm underneath real-world problems arising in many practical applications, with particular prevalence in physics-related domains. Among them, a plethora of cases within the computational design of aerospace structures can be modeled as a multimodal optimization problem, such as aerodynamic optimization or airfoils and wings. This work aims at presenting a new research direction towards efficiently tackling this kind of optimization problems, which pursues the discovery of the multiple (at least locally optimal) solutions of a given optimization problem. Specifically, we propose to exploit the concept behind the so-called Novelty Search mechanism and embed it into the self-adaptive Differential Evolution algorithm so as to gain an increased level of controlled diversity during the search process. We assess the performance of the proposed solver over the well-known CEC'2013 suite of multimodal test functions. The obtained outcomes of the designed experimentation supports our claim that Novelty Search is a promising approach for heuristically addressed multimodal problems.
jMetalPy: A Python framework for multi-objective optimization with metaheuristics: A Python framework for multi-objective optimization with metaheuristics
(2019-12) Benítez-Hidalgo, Antonio; Nebro, Antonio J.; García-Nieto, José; Oregi, Izaskun; Del Ser, Javier; Quantum; IA
This paper describes jMetalPy, an object-oriented Python-based framework for multi-objective optimization with metaheuristic techniques. Building upon our experiences with the well-known jMetal framework, we have developed a new multi-objective optimization software platform aiming not only at replicating the former one in a different programming language, but also at taking advantage of the full feature set of Python, including its facilities for fast prototyping and the large amount of available libraries for data processing, data analysis, data visualization, and high-performance computing. As a result, jMetalPy provides an environment for solving multi-objective optimization problems focused not only on traditional metaheuristics, but also on techniques supporting preference articulation, constrained and dynamic problems, along with a rich set of features related to the automatic generation of statistical data from the results generated, as well as the real-time and interactive visualization of the Pareto front approximations produced by the algorithms. jMetalPy offers additionally support for parallel computing in multicore and cluster systems. We include some use cases to explore the main features of jMetalPy and to illustrate how to work with it.
Joint feature selection and parameter tuning for short-term traffic flow forecasting based on heuristically optimized multi-layer neural networks
(Springer Verlag, 2017) Laña, Ibai; Del Ser, Javier; Vélez, Manuel; Oregi, Izaskun; Del Ser, Javier; IA; Tecnalia Research & Innovation; Quantum
Short-term traffic flow forecasting is a vibrant research topic that has been growing in interest since the late 70’s. In the last decade this vibrant field has shifted its focus towards machine learning methods. These techniques often require fine-grained parameter tuning to obtain satisfactory performance scores, a process that usually relies on manual trial-and-error adjustment. This paper explores the use of Harmony Search optimization for tuning the parameters of neural network jointly with the selection of the input features from the dataset at hand. Results are discussed and compared to other tuning methods, from which it is concluded that neural predictors optimized via the proposed heuristic wrapper outperform those tuned by means of na¨ıve parametrized algorithms, thus allowing for longer-term predictions. These promising results unfold potential applications of this technique in multi-location neighbor-aware traffic prediction.
Methodology to Compare Meta-heuristic Algorithms to Solve Selective Harmonic Elimination-PWM and Optimal Pulse Pattern Formulations
(IEEE Computer Society, 2021-10-13) Ibanez-Hidalgo, Irati; Oregi, Izaskun; Gil-Lopez, Sergio; Perez-Basante, Angel; Sanchez-Ruiz, Alain; Pujana, Ainhoa; Zubizarreta, Asier; Ceballos, Salvador; POWER ELECTRONICS AND SYSTEM EQUIPMENT; Quantum; IA; DIGITAL ENERGY
Low switching frequency modulation techniques such as Selective Harmonic Elimination-Pulse Width Modulation (SHE-PWM) or Optimal Pulse Pattern (OPP) are commonly used in medium voltage-high power multilevel converters to improve their efficiency. These techniques require solving non-linear equations in order to calculate the firing angles. These equations can be solved by meta-heuristic optimization algorithms, which depend on a set of hyperparameters that must be properly adjusted to ensure their effectiveness. This paper presents a methodology to tune different meta-heuristic algorithms to fairly compare them and select the best algorithm to solve SHE-PWM/OPP formulation. The methodology is applied considering different meta-heuristic algorithms such as genetic algorithm, differential evolution, harmony search and simulated annealing. It has been validated in SHE-PWM and OPP techniques with different number of firing angles.
Nature-inspired approaches for distance metric learning in multivariate time series classification
(Institute of Electrical and Electronics Engineers Inc., 2017-07-05) Oregi, Izaskun; Del Ser, Javier; Perez, Aritz; Lozano, Jose A.; Quantum; IA
The applicability of time series data mining in many different fields has motivated the scientific community to focus on the development of new methods towards improving the performance of the classifiers over this particular class of data. In this context the related literature has extensively shown that dynamic time warping is the similarity measure of choice when univariate time series are considered. However, possible statistical coupling among different dimensions make the generalization of this metric to the multivariate case all but obvious. This has ignited the interest of the community in new distance definitions capable of capturing such inter-dimension dependences. In this paper we propose a simple dynamic time warping based distance that finds the best weighted combination between the dependent - where multivariate time series are treated as whole - and independent approaches - where multivariate time series are just a collection of unrelated univariate time series - of the time series to be classified. A benchmark of four heuristic wrappers, namely, simulated annealing, particle swarm optimization, estimation of distribution algorithms and genetic algorithms are used to evolve the set of weighting coefficients towards maximizing the cross-validated predictive score of the classifiers. In this context one of the most recurring classifiers is nearest neighbor. This classifier is couple with a distance that as afore mentioned, in most cases, have been dynamic time warping. The performance of the proposed approach is validated over datasets widely utilized in the related literature, from which it is concluded that the obtained performance gains can be enlarged by properly decoupling the influence of each dimension in the definition of the dependent dynamic time warping distance.
On-Line Dynamic Time Warping for Streaming Time Series
(Springer Verlag, 2017) Oregi, Izaskun; Pérez, Aritz; Del Ser, Javier; Lozano, José A.; Ceci, Michelangelo; Hollmen, Jaakko; Todorovski, Ljupco; Vens, Celine; Dzeroski, Saso; Quantum; IA
Dynamic Time Warping is a well-known measure of dissimilarity between time series. Due to its flexibility to deal with non-linear distortions along the time axis, this measure has been widely utilized in machine learning models for this particular kind of data. Nowadays, the proliferation of streaming data sources has ignited the interest and attention of the scientific community around on-line learning models. In this work, we naturally adapt Dynamic Time Warping to the on-line learning setting. Specifically, we propose a novel on-line measure of dissimilarity for streaming time series which combines a warp constraint and a weighted memory mechanism to simplify the time series alignment and adapt to non-stationary data intervals along time. Computer simulations are analyzed and discussed so as to shed light on the performance and complexity of the proposed measure.
On-line Elastic Similarity Measures for time series
(2019-04) Oregi, Izaskun; Pérez, Aritz; Del Ser, Javier; Lozano, Jose A.; Quantum; IA
The way similarity is measured among time series is of paramount importance in many data mining and machine learning tasks. For instance, Elastic Similarity Measures are widely used to determine whether two time series are similar to each other. Indeed, in off-line time series mining, these measures have been shown to be very effective due to their ability to handle time distortions and mitigate their effect on the resulting distance. In the on-line setting, where available data increase continuously over time and not necessary in a stationary manner, stream mining approaches are required to be fast with limited memory consumption and capable of adapting to different stationary intervals. In this sense, the computational complexity of Elastic Similarity Measures and their lack of flexibility to accommodate different stationary intervals, make these similarity measures incompatible with the requirements mentioned. To overcome these issues, this paper adapts the family of Elastic Similarity Measures – which includes Dynamic Time Warping, Edit Distance, Edit Distance for Real Sequences and Edit Distance with Real Penalty – to the on-line setting. The proposed adaptation is based on two main ideas: a forgetting mechanism and the incremental computation. The former makes the similarity consistent with streaming time series characteristics by giving more importance to recent observations, whereas the latter reduces the computational complexity by avoiding unnecessary computations. In order to assess the behavior of the proposed similarity measure in on-line settings, two different experiments have been carried out. The first aims at showing the efficiency of the proposed adaptation, to do so we calculate and compare the computation time for the elastic measures and their on-line adaptation. By analyzing the results drawn from a distance-based streaming machine learning model, the second experiment intends to show the effect of the forgetting mechanism on the resulting similarity value. The experimentation shows, for the aforementioned Elastic Similarity Measures, that the proposed adaptation meets the memory, computational complexity and flexibility constraints imposed by streaming data.
Optimization of Image Acquisition for Earth Observation Satellites via Quantum Computing
(Springer Science and Business Media Deutschland GmbH, 2023) Makarov, Antón; Taddei, Márcio M.; Osaba, Eneko; Franceschetto, Giacomo; Villar-Rodríguez, Esther; Oregi, Izaskun; Quaresma, Paulo; Gonçalves, Teresa; Camacho, David; Yin, Hujun; Julian, Vicente; Tallón-Ballesteros, Antonio J.; Quantum
Satellite image acquisition scheduling is a problem that is omnipresent in the earth observation field; its goal is to find the optimal subset of images to be taken during a given orbit pass under a set of constraints. This problem, which can be modeled via combinatorial optimization, has been dealt with many times by the artificial intelligence and operations research communities. However, despite its inherent interest, it has been scarcely studied through the quantum computing paradigm. Taking this situation as motivation, we present in this paper two QUBO formulations for the problem, using different approaches to handle the non-trivial constraints. We compare the formulations experimentally over 20 problem instances using three quantum annealers currently available from D-Wave, as well as one of its hybrid solvers. Fourteen of the tested instances have been obtained from the well-known SPOT5 benchmark, while the remaining six have been generated ad-hoc for this study. Our results show that the formulation and the ancilla handling technique is crucial to solve the problem successfully. Finally, we also provide practical guidelines on the size limits of problem instances that can be realistically solved on current quantum computers.
A Quantum Computing-Based System for Portfolio Optimization Using Future Asset Values and Automatic Reduction of the Investment Universe
(Springer Science and Business Media Deutschland GmbH, 2024) Osaba, Eneko; Gelabert, Guillaume; Villar-Rodriguez, Esther; Asla, Antón; Oregi, Izaskun; Yang, Xin-She; Sherratt, Simon; Dey, Nilanjan; Joshi, Amit; Quantum
One of the problems in quantitative finance that has received the most attention is the portfolio optimization problem. Regarding its solving, this problem has been approached using different techniques, with those related to quantum computing being especially prolific in recent years. In this study, we present a system called Quantum Computing-based System for Portfolio Optimization with Future Asset Values and Automatic Universe Reduction (Q4FuturePOP), which deals with the Portfolio Optimization Problem considering the following innovations: (i) the developed tool is modeled for working with future prediction of assets, instead of historical values; and (ii) Q4FuturePOP includes an automatic universe reduction module, which is conceived to intelligently reduce the complexity of the problem. We also introduce a brief discussion about the preliminary performance of the different modules that compose the prototypical version of Q4FuturePOP.
Quantum Optimization Methods for Satellite Mission Planning
(2024) Makarov, Anton; Perez-Herradon, Carlos; Franceschetto, Giacomo; Taddei, Marcio M.; Osaba, Eneko; Del Barrio Cabello, Paloma; Villar-Rodriguez, Esther; Oregi, Izaskun; Quantum
Satellite mission planning for Earth observation satellites is a combinatorial optimization problem that consists of selecting the optimal subset of imaging requests, subject to constraints, to be fulfilled during an orbit pass of a satellite. The ever-growing amount of satellites in orbit underscores the need to operate them efficiently, which requires solving many instances of the problem in short periods of time. However, current classical algorithms often fail to find the global optimum or take too long to execute. Here, we approach the problem from a quantum computing point of view, which offers a promising alternative that could lead to significant improvements in solution quality or execution speed in the future. To this end, we study a planning problem with a variety of intricate constraints and discuss methods to encode them for quantum computers. Additionally, we experimentally assess the performance of quantum annealing and the quantum approximate optimization algorithm on a realistic and diverse dataset. Our results identify key aspects like graph connectivity and constraint structure that influence the performance of the methods. We explore the limits of today's quantum algorithms and hardware, providing bounds on the problems that can be currently solved successfully and showing how the solution degrades as the complexity grows. This work aims to serve as a baseline for further research in the field and establish realistic expectations on current quantum optimization capabilities.
A Question of Trust: Statistical Characterization of Long-Term Traffic Estimations for their Improved Actionability
(Institute of Electrical and Electronics Engineers Inc., 2019-10) Lana, Ibai; Villar-Rodriguez, Esther; Etxegarai, Urtats; Oregi, Izaskun; Ser, Javier Del; IA; Quantum
Actionability is a key aspect of research advances achieved in diverse fields, as it determines whether new developments are useful in practice for expert users. Intelligent Transport Systems (ITS) are among such fields due to the highly applied set of knowledge areas lying at their core, with some of them subject to high user sensitiveness (e.g. autonomous driving, signaling or guiding systems, among others). In this context, certain ITS areas such as traffic forecasting have received so far little attention in regards to the actionability of the outcomes produced by data-based models. Indeed, most studies are devoted to performance assessment, thereby leaving the actionability and usability of traffic predictions as a rarely addressed matter. Likewise, long-term traffic estimation models have been very scarcely tackled in the literature, partly due to the lack of certainty of their estimations which, unless quantified and properly gauged for the application at hand, renders them far less useful than their short-term counterparts. It is well known that in general, uncertainty increases for a data-based model when the prediction horizon grows. It is precisely uncertainty what reduces most the usability of these models, which are designed to ultimately help taking traffic-related decisions. In this paper we propose a set of heuristic metrics that help reducing the uncertainty in long-term traffic estimations, yielding a more informed decision making process for a traffic manager. Our proposed methodology relies on the statistical analysis of the cluster space spanned by the available traffic data, and is intended to provide not only future traffic estimates, but also a set of quantitative measures reflecting their confidence. Results obtained with real traffic data will showcase the augmented information produced by our proposed methodology.

Browsing by Author "Oregi, Izaskun"

Results Per Page

Sort Options