Traffic forecasting is an important research area in Intelligent Transportation Systems that is focused on anticipating traffic in order to mitigate congestion. In this work we propose a deep neural network that simultaneously extracts the spatial features of traffic, using graph convolution, and its temporal features by means of Long Short Term Memory (LSTM) cells to make both short-term and long-term predictions. The model is trained and tested using sparse trajectory (GPS) data coming from the ride-hailing service of DiDi in the cities of Xi'an and Chengdu in China. Besides, presenting the deep neural network, we also propose a data-reduction technique based on temporal correlation to select the most relevant road links to be used as input. Combining the suggested approaches, our model obtains better results compared to high-performance algorithms for traffic forecasting, such as LSTM or the algorithms presented in the TRANSFOR19 forecasting competition. The model is capable of maintaining its performance over different time-horizons from 5 minutes to up to 4 hours with multi-step predictions.

Despite the broad range of Machine Learning (ML) algorithms, there are no clear baselines to find the best method and its configuration given a Short-Term Traffic Forecasting (STTF) problem. In ML, this is known as the Model Selection Problem (MSP). Although Automatic Algorithm Selection (AAS) has proved success dealing with MSP in other areas, it has hardly been explored in STTF. This paper deepens into the benefits of AAS in this field. To this end, we have used Auto-WEKA, a well-known AAS method, and compared it to the general approach (which consists of selecting the best of a set of algorithms) over a multi-class imbalanced classification STTF problem. Experimental results show AAS as a promising methodology in this area and allow important conclusions to be drawn on how to improve the performance of ASS methods when dealing with STTF.

No abstract

Traffic Forecasting is a well-known strategy that supports road users and decision-makers to plan their movements on the roads and to improve the management of traffic, respectively. Current data availability and growing computational capacities have increased the use of Machine Learning methods to tackle Traffic Forecasting, which is mostly modelled as a supervised regression problem. Despite the broad range of Machine Learning algorithms, there are no baselines to determine what are the most suitable methods and their hyper-parameters configurations to approach the different Traffic Forecasting regression problems reported in the literature. In Machine Learning, this is known as the Model Selection Problem, and although Automated Machine Learning methods has proved successful dealing with this problem in other areas, it has hardly been explored in Traffic Forecasting. In this work, we go deeply into the benefits of Automated Machine Learning in the aforementioned field. To this end, we use Auto-WEKA, a well-known AutoML method, on a subset of families of Traffic Forecasting regression problems characterised by having loop detectors, as traffic data source, and scales of predictions focused on the point and the road segment levels within freeway and urban environments. The experiments include data from the Caltrans Performance Measurement System and the Madrid City Council. The results show that AutoML methods can provide competitive results for TF with low human intervention.

One contemporary policy to deal with traffic congestion is the design and implementation of forecasting methods that allow users to plan ahead of time and decision makers to improve traffic management. Current data availability and growing computational capacities have increased the use of machine learning (ML) to address traffic prediction, which is mostly modeled as a supervised regression problem. Although some studies have presented taxonomies to sort the literature in this field, they are mostly oriented to classify the ML methods applied and a little effort has been directed to categorize the traffic forecasting problems approached by them. As far as we know, there is no comprehensive taxonomy that classifies these problems from the point of view of both traffic and ML. In this paper, we propose a taxonomy to categorize the aforementioned problems from both traffic and a supervised regression learning perspective. The taxonomy aims at unifying and consolidating categorization criteria related to traffic and it introduces new criteria to classify the problems in terms of how they are modeled from a supervised regression approach. The traffic forecasting literature, from 2000 to 2019, is categorized using this taxonomy to illustrate its descriptive power. From this categorization, different remarks are discussed regarding the current gaps and trends in the addressed traffic forecasting area.

Background and purpose: Induced travel demand (ITD) is a phenomenon where road construction increases vehicles' kilometers traveled. It has been approached with econometric models that use elasticities as measure to estimate how much travel demand can be induced by new roads. However, there is a lack of "white-box" models with causal hypotheses that explain the structural complexity underlying this phenomenon. We propose a system dynamics model based on a feedback mechanism to explain structurally ITD. Methodology: A system dynamics methodology was selected to model and simulate ITD. First, a causal loop diagram is proposed to describe the ITD structure in terms of feedback loops. Then a stock-flows diagram is formulated to allow computer simulation. Finally, simulations are run to show the quantitative temporal evolution of the model built. Results: The simulation results show how new roads in the short term induce more kilometers traveled by vehicles already in use; meanwhile, in the medium-term, new traffic is generated. These new car drivers appear when better flow conditions coming from new roads increase attractiveness of car use. More cars added to vehicles already in use produce new traffic congestion, and high travel speeds provided by roads built are absorbed by ITD effects. Conclusion: We concluded that approaching ITD with a systemic perspective allows for identifying leverage points that contribute to design comprehensive policies aimed to cope with ITD. In this sense, the model supports decision-making processes in urban contexts wherein it is still necessary for road construction to guarantee connectivity, such as the case of developing countries.

Connected vehicles are revolutionizing the way in which transport and mobility are conceived. The main technology behind are the socalled Vehicular Ad-Hoc Networks (VANETs), which are communication networks that connect vehicles and facilitate various services. Usually, these services require a centralized architecture where the main server collects and disseminates information from/to vehicles. In this paper, we focus on improving the downlink information dissemination in VANETs with this centralized architecture. With this aim, we model the problem as a Vertex Covering optimization problem and we propose four new nature-inspired methods to solve it: Bat Algorithm (), Firefly Algorithm, Particle Swarm Optimization, and Cuckoo Search. The new methods are tested over data from a real scenario. Results show that these metaheuristics, especially Bat Algorithm, Firefly Algorithm and Particle Swarm Optimization, can be considered as powerful solvers for improving information dissemination in VANETs.

In the last few years, the Internet of Things, and other enabling technologies, have been progressively used for digitizing Food Supply Chains (FSC). These and other digitalization-enabling technologies are generating a massive amount of data with enormous potential to manage supply chains more efficiently and sustainably. Nevertheless, the intricate patterns and complexity embedded in large volumes of data present a challenge for systematic human expert analysis. In such a data-driven context, Computational Intelligence (CI) has achieved significant momentum to analyze, mine, and extract the underlying data information, or solve complex optimization problems, striking a balance between productive efficiency and sustainability of food supply systems. Although some recent studies have sorted the CI literature in this field, they are mainly oriented towards a single family of CI methods (a group of methods that share common characteristics) and review their application in specific FSC stages. As such, there is a gap in identifying and classifying FSC problems from a broader perspective, encompassing the various families of CI methods that can be applied in different stages (from production to retailing) and identifying the problems that arise in these stages from a CI perspective. This paper presents a new and comprehensive taxonomy of FSC problems (associated with agriculture, fish farming, and livestock) from a CI approach; that is, it defines FSC problems (from production to retail) and categorizes them based on how they can be modeled from a CI point of view. Furthermore, we review the CI approaches that are more commonly used in each stage of the FSC and in their corresponding categories of problems. We also introduce a set of guidelines to help FSC researchers and practitioners to decide on suitable families of methods when addressing any particular problems they might encounter. Finally, based on the proposed taxonomy, we identify and discuss challenges and research opportunities that the community should explore to enhance the contributions that CI can bring to the digitization of the FSC.