In the realm of autonomous vehicles, ensuring safety through advanced anomaly detection is crucial. This thesis integrates Reservoir Computing with temporal-aware data analysis to enhance driver behavior assessment and traffic flow prediction. Our approach combines Reservoir Computing with autoencoder-based feature extraction to analyze driving metrics from vehicle sensors, capturing complex temporal patterns efficiently. Additionally, we extend our analysis to forecast traffic flow dynamics within road networks using the same framework. We evaluate our model using the PEMS-BAY and METRA-LA datasets, encompassing diverse traffic scenarios, along with a GPS dataset of 10,000 taxis, providing real-world driving dynamics. Through a support vector machine (SVM) algorithm, we categorize drivers based on their performance, offering insights for tailored anomaly detection strategies. This research advances anomaly detection for autonomous vehicles, promoting safer driving experiences and the evolution of vehicle safety technologies. By integrating Reservoir Computing with temporal-aware data analysis, this thesis contributes to both driver behavior assessment and traffic flow prediction, addressing critical aspects of autonomous vehicle systems. / Master of Science / Our cities are constantly growing, and traffic congestion is a major challenge. This project explores how innovative technology can help us predict traffic patterns and develop smarter management strategies. Inspired by the rigorous safety systems being developed for self-driving cars, we'll delve into the world of machine learning. By combining advanced techniques for identifying unusual traffic patterns with tools that analyze data over time, we'll gain a deeper understanding of traffic flow and driver behavior. We'll utilize data collected by car sensors, such as speed and turning patterns, to not only predict traffic jams but also see how drivers react in different situations. However, our project has a broader scope than just traffic flow. We aim to leverage this framework to understand driver behavior in general, with a particular focus on its implications for self-driving vehicles. Through meticulous data analysis and sophisticated algorithms, we can categorize drivers based on their performance. This valuable information can be used to develop improved methods for detecting risky situations, ultimately leading to safer roads and smoother traffic flow for everyone. To ensure the effectiveness of our approach, we'll rigorously test it using real-world data from GPS data from taxi fleets and nationally recognized traffic datasets. By harnessing the power of machine learning and tools that can adapt to changing data patterns, this project has the potential to revolutionize traffic management in cities. This paves the way for a future with safer roads, less congestion, and a more positive experience for everyone who lives in and travels through our bustling urban centers.

Traffic flow predictions are an important part of an Intelligent Transportation System as the ability to forecast accurately the traffic conditions in a transportation system allows for proactive rather than reactive traffic control. Providing accurate real-time traffic predictions is a challenging problem because of the nonlinear and stochastic features of traffic flow. An increasingly widespread deployment of traffic sensors in a growing transportation system produces greater volume of traffic flow data. This results in problems concerning fast, reliable and scalable traffic predictions.The thesis explores the feasibility of increasing the scalability of real-time traffic predictions by partitioning the transportation system into smaller subsections. This is done by using data collected by Trafikverket from traffic sensors in Stockholm and Gothenburg to construct a traffic sensor graph of the transportation system. In addition, three graph partitioning algorithms are designed to divide the traffic sensor graph according to vehicle travel time. Finally, the produced transportation system partitions are used to train multi-layered long shortterm memory recurrent neural networks for traffic density predictions. Four different types of models are produced and evaluated based on root mean squared error, training time and prediction time, i.e. transportation system model, partitioned transportation models, single sensor models, and overlapping partition models.Results of the thesis show that partitioning a transportation system is a viable solution to produce traffic prediction models as the average prediction accuracy for each traffic sensor across the different types of prediction models are comparable. This solution tackles scalability issues that are caused by increased deployment of traffic sensors to the transportation system. This is done by reducing the number of traffic sensors each prediction model is responsible for which results in less complex models with less amount of input data. A more decentralized and effective solution can be achieved since the models can be distributed to the edge of the transportation system, i.e. near the physical location of the traffic sensors, reducing prediction and response time of the models. / Prognoser för trafikflödet är en viktig del av ett intelligent transportsystem, eftersom möjligheten att prognostisera exakt trafiken i ett transportsystem möjliggör proaktiv snarare än reaktiv trafikstyrning. Att tillhandahålla noggrann trafikprognosen i realtid är ett utmanande problem på grund av de olinjära och stokastiska egenskaperna hos trafikflödet. En alltmer utbredd använding av trafiksensorer i ett växande transportsystem ger större volym av trafikflödesdata. Detta leder till problem med snabba, pålitliga och skalbara trafikprognoser.Avhandlingen undersöker möjligheten att öka skalbarheten hos realtidsprognoser genom att dela transportsystemet i mindre underavsnitt. Detta görs genom att använda data som samlats in av Trafikverket från trafiksensorer i Stockholm och Göteborg för att konstruera en trafiksensor graf för transportsystemet. Dessutom är tre grafpartitioneringsalgoritmer utformade för att dela upp trafiksensor grafen enligt fordonets körtid. Slutligen används de producerade transportsystempartitionerna för att träna multi-layered long short memory neurala nät för förspänning av trafiktäthet. Fyra olika typer av modeller producerades och utvärderades baserat på rotvärdes kvadratfel, träningstid och prediktionstid, d.v.s. transportsystemmodell, partitionerade transportmodeller, enkla sensormodeller och överlappande partitionsmodeller.Resultat av avhandlingen visar att partitionering av ett transportsystem är en genomförbar lösning för att producera trafikprognosmodeller, eftersom den genomsnittliga prognoser noggrannheten för varje trafiksensor över de olika typerna av prediktionsmodeller är jämförbar. Denna lösning tar itu med skalbarhetsproblem som orsakas av ökad användning av trafiksensorer till transportsystemet. Detta görs genom att minska antal trafiksensorer varje trafikprognosmodell är ansvarig för. Det resulterar i mindre komplexa modeller med mindre mängd inmatningsdata. En mer decentraliserad och effektiv lösning kan uppnås eftersom modellerna kan distribueras till transportsystemets kant, d.v.s. nära trafiksensorns fysiska läge, vilket minskar prognosoch responstid för modellerna.

The advancement in computational intelligence and computational power and the explosionof traffic data continues to drive the development and use of Intelligent TransportSystem and smart mobility applications. As one of the fundamental components of IntelligentTransport Systems, traffic flow prediction research has been advancing from theclassical statistical and time-series based techniques to data–driven methods mainly employingdata mining and machine learning algorithms. However, significant number oftraffic flow prediction studies have overlooked the impact of road network topology ontraffic flow. Thus, the main objective of this research is to show that traffic flow predictionproblems are not only affected by temporal trends of flow history, but also by roadnetwork topology by developing prediction methods in the spatio-temporal.In this study, time–series operators and data mining techniques are used by definingfive partially overlapping relative temporal offsets to capture temporal trends in sequencesof non-overlapping history windows defined on stream of historical record of traffic flowdata. To develop prediction models, two sets of modeling approaches based on LinearRegression and Support Vector Machine for Regression are proposed. In the modelingprocess, an orthogonal linear transformation of input data using Principal ComponentAnalysis is employed to avoid any potential problem of multicollinearity and dimensionalitycurse. Moreover, to incorporate the impact of road network topology in thetraffic flow of individual road segments, shortest path network–distance based distancedecay function is used to compute weights of neighboring road segment based on theprinciple of First Law of Geography. Accordingly, (a) Linear Regression on IndividualSensors (LR-IS), (b) Joint Linear Regression on Set of Sensors (JLR), (c) Joint LinearRegression on Set of Sensors with PCA (JLR-PCA) and (d) Spatially Weighted Regressionon Set of Sensors (SWR) models are proposed. To achieve robust non-linear learning,Support Vector Machine for Regression (SVMR) based models are also proposed.Thus, (a) SVMR for Individual Sensors (SVMR-IS), (b) Joint SVMR for Set of Sensors(JSVMR), (c) Joint SVMR for Set of Sensors with PCA (JSVMR-PCA) and (d) SpatiallyWeighted SVMR (SWSVMR) models are proposed. All the models are evaluatedusing the data sets from 2010 IEEE ICDM international contest acquired from TrafficSimulation Framework (TSF) developed based on the NagelSchreckenberg model.Taking the competition’s best solutions as a benchmark, even though different setsof validation data might have been used, based on k–fold cross validation method, withthe exception of SVMR-IS, all the proposed models in this study provide higher predictionaccuracy in terms of RMSE. The models that incorporated all neighboring sensorsdata into the learning process indicate the existence of potential interdependence amonginterconnected roads segments. The spatially weighted model in SVMR (SWSVMR) revealedthat road network topology has clear impact on traffic flow shown by the varyingand improved prediction accuracy of road segments that have more neighbors in a closeproximity. However, the linear regression based models have shown slightly low coefficientof determination indicating to the use of non-linear learning methods. The resultsof this study also imply that the approaches adopted for feature construction in this studyare effective, and the spatial weighting scheme designed is realistic. Hence, road networktopology is an intrinsic characteristic of traffic flow so that prediction models should takeit into consideration.

La modélisation du choix d'itinéraire est un sujet de recherche bien étudié avec des implications, par exemple, pour la planification urbaine et l'analyse des flux d'équilibre du trafic. En raison de l'ampleur des effets que ces problèmes peuvent avoir sur les communautés, il n'est pas surprenant que plusieurs domaines de recherche aient tenté de résoudre le même problème. Les défis viennent cependant de la taille des réseaux eux-mêmes, car les grandes villes peuvent avoir des dizaines de milliers de segments de routes reliés par des dizaines de milliers d'intersections. Ainsi, les approches discutées dans cette thèse se concentreront sur la comparaison des performances entre des modèles de deux domaines différents, l'économétrie et l'apprentissage par renforcement inverse (IRL). Tout d'abord, nous fournissons des informations sur le sujet pour que des chercheurs d'un domaine puissent se familiariser avec l'autre domaine. Dans un deuxième temps, nous décrivons les algorithmes utilisés avec une notation commune, ce qui facilite la compréhension entre les domaines. Enfin, nous comparons les performances des modèles sur des ensembles de données du monde réel, à savoir un ensemble de données couvrant des choix d’itinéraire de cyclistes collectés dans un réseau avec 42 000 liens. Nous rapportons nos résultats pour les deux modèles de l'économétrie que nous discutons, mais nous n'avons pas pu générer les mêmes résultats pour les deux modèles IRL. Cela était principalement dû aux instabilités numériques que nous avons rencontrées avec le code que nous avions modifié pour fonctionner avec nos données. Nous proposons une discussion de ces difficultés parallèlement à la communication de nos résultats. / Route choice modeling is a well-studied topic of research with implications, for example, for city planning and traffic equilibrium flow analysis. Due to the scale of effects these problems can have on communities, it is no surprise that diverse fields have attempted solutions to the same problem. The challenges, however, come with the size of networks themselves, as large cities may have tens of thousands of road segments connected by tens of thousands of intersections. Thus, the approaches discussed in this thesis will be focusing on the performance comparison between models from two different fields, econometrics and inverse reinforcement learning (IRL). First, we provide background on the topic to introduce researchers from one field to become acquainted with the other. Secondly, we describe the algorithms used with a common notation to facilitate this building of understanding between the fields. Lastly, we aim to compare the performance of the models on real-world datasets, namely covering bike route choices collected in a network of 42,000 links. We report our results for the two models from econometrics that we discuss, but were unable to generate the same results for the two IRL models. This was primarily due to numerical instabilities we encountered with the code we had modified to work with our data. We provide a discussion of these difficulties alongside the reporting of our results.