Collaborating Authors


Optimising Rolling Stock Planning including Maintenance with Constraint Programming and Quantum Annealing Artificial Intelligence

We developed and compared Constraint Programming (CP) and Quantum Annealing (QA) approaches for rolling stock optimisation considering necessary maintenance tasks. To deal with such problems in CP we investigated specialised pruning rules and implemented them in a global constraint. For the QA approach, we developed quadratic unconstrained binary optimisation (QUBO) models. For testing, we use data sets based on real data from Deutsche Bahn and run the QA approach on real quantum computers from D-Wave. Classical computers are used to run the CP approach as well as tabu search for the QUBO models. We find that both approaches tend at the current development stage of the physical quantum annealers to produce comparable results, with the caveat that QUBO does not always guarantee that the maintenance constraints hold, which we fix by adjusting the QUBO model in preprocessing, based on how close the trains are to a maintenance threshold distance.

Minimax Estimation of Partially-Observed Vector AutoRegressions Machine Learning

To understand the behavior of large dynamical systems like transportation networks, one must often rely on measurements transmitted by a set of sensors, for instance individual vehicles. Such measurements are likely to be incomplete and imprecise, which makes it hard to recover the underlying signal of interest.Hoping to quantify this phenomenon, we study the properties of a partially-observed state-space model. In our setting, the latent state $X$ follows a high-dimensional Vector AutoRegressive process $X_t = \theta X_{t-1} + \varepsilon_t$. Meanwhile, the observations $Y$ are given by a noise-corrupted random sample from the state $Y_t = \Pi_t X_t + \eta_t$. Several random sampling mechanisms are studied, allowing us to investigate the effect of spatial and temporal correlations in the distribution of the sampling matrices $\Pi_t$.We first prove a lower bound on the minimax estimation error for the transition matrix $\theta$. We then describe a sparse estimator based on the Dantzig selector and upper bound its non-asymptotic error, showing that it achieves the optimal convergence rate for most of our sampling mechanisms. Numerical experiments on simulated time series validate our theoretical findings, while an application to open railway data highlights the relevance of this model for public transport traffic analysis.

Business analytics meets artificial intelligence: Assessing the demand effects of discounts on Swiss train tickets Machine Learning

We assess the demand effects of discounts on train tickets issued by the Swiss Federal Railways, the so-called `supersaver tickets', based on machine learning, a subfield of artificial intelligence. Considering a survey-based sample of buyers of supersaver tickets, we investigate which customer- or trip-related characteristics (including the discount rate) predict buying behavior, namely: booking a trip otherwise not realized by train, buying a first- rather than second-class ticket, or rescheduling a trip (e.g.\ away from rush hours) when being offered a supersaver ticket. Predictive machine learning suggests that customer's age, demand-related information for a specific connection (like departure time and utilization), and the discount level permit forecasting buying behavior to a certain extent. Furthermore, we use causal machine learning to assess the impact of the discount rate on rescheduling a trip, which seems relevant in the light of capacity constraints at rush hours. Assuming that (i) the discount rate is quasi-random conditional on our rich set of characteristics and (ii) the buying decision increases weakly monotonically in the discount rate, we identify the discount rate's effect among `always buyers', who would have traveled even without a discount, based on our survey that asks about customer behavior in the absence of discounts. We find that on average, increasing the discount rate by one percentage point increases the share of rescheduled trips by 0.16 percentage points among always buyers. Investigating effect heterogeneity across observables suggests that the effects are higher for leisure travelers and during peak hours when controlling several other characteristics.

Lilee Systems to launch first autonomous buses for public transportation in Taiwan


Lilee Systems has received the first permit for self-driving bus commercial services on two designated bus lines in Tainan, Taiwan. The self-driving fleet, subsidized by the Ministry of Transportation, will generate new revenues to the city's public transit systems by providing two regular bus services in the science park and between the high-speed railway station and the nearby university, exhibition center and large outlet mall. This milestone of the innovative autonomous rapid transit system has been achieved through partnership with Kasion Green Energy, Taiwan's sole distributor of BYD vehicles, and Tainan Bus, one of the largest bus operators servicing over 23-million passengers per year. Selected by the Tainan City Government and Taiwan's Ministry of Transportation, Lilee Systems, Kasion Green Energy and Tainan Bus have signed a memorandum of cooperation in creating a new smart transportation model that realizes true driverless driving of urban buses. The commercial services will begin on September 2021 using the BYD K6 bus fleet.

White Paper Machine Learning in Certified Systems Artificial Intelligence

Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submitted to certification constraints. But what are the actual challenges? Can they be overcome by selecting appropriate ML techniques, or by adopting new engineering or certification practices? These are some of the questions addressed by the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exup\'ery de Toulouse (IRT), as part of the DEEL Project.

A new interpretable unsupervised anomaly detection method based on residual explanation Artificial Intelligence

Despite the superior performance in modeling complex patterns to address challenging problems, the black-box nature of Deep Learning (DL) methods impose limitations to their application in real-world critical domains. The lack of a smooth manner for enabling human reasoning about the black-box decisions hinder any preventive action to unexpected events, in which may lead to catastrophic consequences. To tackle the unclearness from black-box models, interpretability became a fundamental requirement in DL-based systems, leveraging trust and knowledge by providing ways to understand the model's behavior. Although a current hot topic, further advances are still needed to overcome the existing limitations of the current interpretability methods in unsupervised DL-based models for Anomaly Detection (AD). Autoencoders (AE) are the core of unsupervised DL-based for AD applications, achieving best-in-class performance. However, due to their hybrid aspect to obtain the results (by requiring additional calculations out of network), only agnostic interpretable methods can be applied to AE-based AD. These agnostic methods are computationally expensive to process a large number of parameters. In this paper we present the RXP (Residual eXPlainer), a new interpretability method to deal with the limitations for AE-based AD in large-scale systems. It stands out for its implementation simplicity, low computational cost and deterministic behavior, in which explanations are obtained through the deviation analysis of reconstructed input features. In an experiment using data from a real heavy-haul railway line, the proposed method achieved superior performance compared to SHAP, demonstrating its potential to support decision making in large scale critical systems.

Graph Neural Network for Traffic Forecasting: A Survey Artificial Intelligence

Traffic forecasting is important for the success of intelligent transportation systems. Deep learning models, including convolution neural networks and recurrent neural networks, have been extensively applied in traffic forecasting problems to model spatial and temporal dependencies. In recent years, to model the graph structures in transportation systems as well as contextual information, graph neural networks have been introduced and have achieved state-of-the-art performance in a series of traffic forecasting problems. In this survey, we review the rapidly growing body of research using different graph neural networks, e.g. graph convolutional and graph attention networks, in various traffic forecasting problems, e.g. road traffic flow and speed forecasting, passenger flow forecasting in urban rail transit systems, and demand forecasting in ride-hailing platforms. We also present a comprehensive list of open data and source resources for each problem and identify future research directions. To the best of our knowledge, this paper is the first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems. We have also created a public GitHub repository where the latest papers, open data, and source resources will be updated.

Improved Sensitivity of Base Layer on the Performance of Rigid Pavement Artificial Intelligence

The performance of rigid pavement is greatly affected by the properties of base/subbase as well as subgrade layer. However, the performance predicted by the AASHTOWare Pavement ME design shows low sensitivity to the properties of base and subgrade layers. To improve the sensitivity and better reflect the influence of unbound layers a new set of improved models i.e., resilient modulus (MR) and modulus of subgrade reaction (k-value) are adopted in this study. An Artificial Neural Network (ANN) model is developed to predict the modified k-value based on finite element (FE) analysis. The training and validation datasets in the ANN model consist of 27000 simulation cases with different combinations of pavement layer thickness, layer modulus and slab-base interface bond ratio. To examine the sensitivity of modified MR and k-values on pavement response, eight pavement sections data are collected from the Long-Term Pavement performance (LTPP) database and modeled by using the FE software ISLAB2000. The computational results indicate that the modified MR values have higher sensitivity to water content in base layer on critical stress and deflection response of rigid pavements compared to the results using the Pavement ME design model. It is also observed that the k-values using ANN model has the capability of predicting critical pavement response at any partially bonded conditions whereas the Pavement ME design model can only calculate at two extreme bonding conditions (i.e., fully bonding and no bonding).

Smart Mobility Ontology: Current Trends and Future Directions Artificial Intelligence

Ontology, as a discipline of philosophy, explains the nature of existence and has its roots in Aristotle and Plato studies on "metaphysics" (Welty and Guarino, 2001). However, the word ontology originated from two Greek words: ontos (being) and logos (word), and conceived for the first time during the Sixteen century by German philosophers (Welty and Guarino, 2001). From then till the mid-twentieth, ontology evolved mainly as a branch of philosophy. However, with the advent of Artificial Intelligence since the 1950s, researchers perceived the necessity of ontology to describe a new world of intelligent systems (Welty and Guarino, 2001). Moreover, with the development of the World Wide Web in the 1990s, ontology development got to be common among different domain specialists to define and share the concepts and entities in their fields on the Internet (Noy et al., 2001). During the last three decades, ontology development studies have evolved and shifted from theoretical issues of ontology to practical implications of the use of ontology in real-world, large-scale applications (Noy et al., 2001). Nowadays, ontology development focuses mainly on defining machine interpretable concepts and their relationships in a domain. However, ontology development also pursues other goals, such as providing a common conceptualization of the domain on which different experts agree, (Métral and Cutting-Decelle, 2011) and enable them to reuse the domain knowledge (Noy et al., 2001). It also enables researchers to easily analyze the domain knowledge and eloquently express the domain assumptions.

A Data-Driven Analytical Framework of Estimating Multimodal Travel Demand Patterns using Mobile Device Location Data Artificial Intelligence

ABSTRACT While benefiting people's daily life in so many ways, smartphones and their location-based services are generating massive mobile device location data that has great potential to help us understand travel demand patterns and make transportation planning for the future. While recent studies have analyzed human travel behavior using such new data sources, limited research has been done to extract multimodal travel demand patterns out of them. This paper presents a datadriven analytical framework to bridge the gap. To be able to successfully detect travel modes using the passively collected location information, we conduct a smartphone-based GPS survey to collect ground truth observations. Then a jointly trained single-layer model and deep neural network for travel mode imputation is developed. Being "wide" and "deep" at the same time, this model combines the advantages of both types of models. The framework also incorporates the multimodal transportation network in order to evaluate the closeness of trip routes to the nearby rail, metro, highway and bus lines and therefore enhance the imputation accuracy. To showcase the applications of the introduced framework in answering real-world planning needs, a separate mobile device location data is processed through trip end identification and attribute generation, in a way that the travel mode imputation can be directly applied. The estimated multimodal travel demand patterns are then validated against typical household travel surveys in the same Washington D.C. and Baltimore Metropolitan Regions. BACKGROUND Thanks to the rapidly evolving smartphone industry and mobile computing technology, mobile device location data has never been so readily available before. According to the Pew Research Center, the United States has around 223 million smartphone users in 2017 (Mobile Fact Sheet). More than three-quarters of Americans (77%) now own a smartphone, with lower-income Americans and senior citizens above the age of 50 exhibiting a sharp uptick in ownership over the past years. These devices are generating a massive amount of location data continuously through the widespread use of location-based service (LBS) via Wi-Fi hotspots, cellular towers, Global Positioning System (GPS)-based technologies, and GPSenabled applications on these smartphone devices. This ubiquitous LBS data provides an opportunity to innovatively and accurately observe individuals' travel behavior and model the overall travel demand patterns for a region, a state, and even an entire country.