Driving a vehicle is considered a demanding task in a complex dynamic environment. For instance, driving a vehicle on urban roads, where motorized vehicles meet vulnerable road users (VRUs) creates a multifaceted environment with difficult trade-offs and interactions. Additionally, in-vehicle technology developments are being introduced to ease drivers with the driving task. However, these developments are changing “traditional” driving increasing drivers’ response in terms of information processing, thus making the driving task more demanding in some respects. Therefore, the aim of the present research is to further investigate drivers’ speed choice under varying traffic management regulations and in-vehicle warning systems. / <p>QC 20131114</p> / New Speed Limits in Built-Up Areas / COOPERS

The full spatial covariance matrix of the multiple input multiple-output (MIMO) channel is an important quantity in channel modeling, communication system signal processing, and performance analysis, and therefore this matrix forms the heart of the research outlined in this dissertation. The work begins with an investigation of a generalized framework for computing the full MIMO spatial covariance based on the power angular spectrum (PAS) of the multipath field and the transmit and receive antenna element radiation patterns. For the case of uniform linear arrays and when the PAS clusters satisfy uniform, truncated Gaussian, or truncated Laplacian distributions, a series expansion is used to allow analytic evaluation of the required integrals in the formulation. The study also demonstrates the validity of some simplifying assumptions used to reduce the complexity of the covariance computation by applying the technique to ray tracing data as well as considers an analysis of the convergence properties of the series when computed using a finite number of terms. The insights and tools obtained from this covariance analysis are then used to develop a general approach for constructing MIMO transmit and receive beamforming vectors based on the full spatial covariance. While transmit and receive beamforming for the MIMO channel is a well-studied topic, when the transmit precoding is based on channel covariance information, developing near-optimal transmit and receive beamformers when the receiver is constrained to use linear processing remains an unsolved problem. This iterative beamforming algorithm presented here can accommodate different types of available channel information and receiver capabilities as well as either a sum power constraint or a per-antenna power constraint. While the latter is more realistic, construction of the optimal transmit precoder is less understood for this constraint. Simulation results based on measured channels demonstrate that the approach generates beamformer solutions whose performance rivals that achieved for an optimal nonlinear receiver architecture.

Spatial diversity is an effective technique to combat the effects of severe fading in wireless environments. Recently, cooperative communications has emerged as an attractive communications paradigm that can introduce a new form of spatial diversity which is known as cooperative diversity, that can enhance system reliability without sacrificing the scarce bandwidth resource or consuming more transmit power. It enables single-antenna terminals in a wireless relay network to share their antennas to form a virtual antenna array on the basis of their distributed locations. As such, the same diversity gains as in multi-input multi-output systems can be achieved without requiring multiple-antenna terminals. In this thesis, a new approach to cooperative communications via distributed extended orthogonal space-time block coding (D-EO-STBC) based on limited partial feedback is proposed for cooperative relay networks with three and four relay nodes and then generalized for an arbitrary number of relay nodes. This scheme can achieve full cooperative diversity and full transmission rate in addition to array gain, and it has certain properties that make it alluring for practical systems such as orthogonality, flexibility, low computational complexity and decoding delay, and high robustness to node failure. Versions of the closed-loop D-EO-STBC scheme based on cooperative orthogonal frequency division multiplexing type transmission are also proposed for both flat and frequency-selective fading channels which can overcome imperfect synchronization in the network. As such, this proposed technique can effectively cope with the effects of fading and timing errors. Moreover, to increase the end-to-end data rate, this scheme is extended for two-way relay networks through a three-time slot framework. On the other hand, to substantially reduce the feedback channel overhead, limited feedback approaches based on parameter quantization are proposed. In particular, an optimal one-bit partial feedback approach is proposed for the generalized D-O-STBC scheme to maximize the array gain. To further enhance the end-to-end bit error rate performance of the cooperative relay system, a relay selection scheme based on D-EO-STBC is then proposed. Finally, to highlight the utility of the proposed D-EO-STBC scheme, an application to cognitive radio is studied.

Since the introduction of motor vehicles, the number of fatalities and accidents has been a concern for society.The number of fatalities on roads is amongst the most common causes of mortality worldwide (WHO, 2015).Even in industrialized countries the number of fatalities remains unacceptable. Therefore, in the last decades, anumber of approaches have emerged to support and boost traffic safety towards a system free from fatalities andserious impairment outcomes. ‘Sustainable Safety’ and ‘Vision Zero’ are well-known examples aiming to avoidfatalities within the traffic system and reduce injury severity when a traffic accident is inevitable. However, thenumber of fatalities and seriously injured accidents are still relatively high. More specifically, vulnerable roadusers remain involved in fatal and serious accidents even in industrialized countries. Therefore, further advancesin traffic safety studies are needed. This thesis aims at evaluating the impact of road characteristics, traffic rulesand information provision towards a safer traffic system. The thesis is composed of five scientific papers whichsummarizes the main contributions of this work. / <p>QC 20161109</p>

Les systèmes de communications par satellite sont utilisés dans le contexte de la radiodiffusion, de la navigation, du sauvetage et du secours aux sinistrés, car ils permettent de fournir des services sur une large zone de couverture. Cependant, cette zone de couverture est limitée par l'effet de masquage provoqué par des obstacles qui bloquent la liaison directe entre le satellite et un utilisateur terrestre. L'effet de masquage devient plus sévère en cas de satellites à faibles angles d'élévation ou lorsque l'utilisateur est à l'intérieur. Pour résoudre ce problème, les Systèmes Coopératifs Hybride Satellite-Terrestre (HSTCS) ont été proposés. Dans un système HSTCS, l'utilisateur mobile peut profiter de la diversité spatiale en recevant des signaux à la fois du satellite et des relais terrestres. Les gap-fillers fixes ou mobiles sont utilisés pour relayer le signal satellite. La plupart des systèmes de diffusion par satellite utilisent les gap-fillers fixes alors que les gap-fillers mobiles sont nécessaires en cas de communications d'urgence lorsque l'infrastructure fixe n'est pas disponible. Dans les scénarios d'urgence (incendie, tremblement de terre, inondations, explosion) l'infrastructure terrestre existante est endommagée, donc les HSTCSs sont appropriés pour mettre à jour des informations qui permettent aux sauveteurs d'intervenir efficacement et en toute sécurité. En particulier, une mise en œuvre rapide et souple est nécessaire, ce qui pourrait être fourni par le déploiement de gap-fillers mobiles (véhicule ou portable). Plusieurs scénarios coopératifs et techniques de transmission ont déjà été proposés et étudiés. Cependant, la plupart des méthodes proposées ne fournissent qu'une analyse de performance fondée sur la simulation alors que les expressions analytiques de la probabilité de coupure et de la Probabilité d'Erreur Symbole (SEP) n'ont pas encore été établies. Cette thèse se focalise sur l'analyse de performances des systèmes HSTCS. La probabilité de coupure et SEP du système utilisant le schéma de transmission Selective Decode-and-Forward (SDF), avec ou sans sélection de relais, est évaluée dans le cas des modulations MPSK et MQAM. Cette expression analytique permet de concevoir le système HSTCS. Ces résultats sont applicables aux cas des relais fixes ou mobiles. La seconde partie de cette thèse est consacrée à des problèmes de synchronisation (décalage en temps et en fréquence ainsi que l'étalement Doppler). La mobilité des utilisateurs crée l'étalement Doppler qui détruit l'orthogonalité des sous-porteuses dans les signaux de type Orthogonal Frequency Division Multiplexing (OFDM). Cette perte d'orthogonalité engendre de l'interférence entre sous-porteuses (ICI) et donc une dégradation des performances du système en termes de SEP. Dans ce cas, on présente les conditions dans lesquelles cette dégradation peut être compensée par une augmentation du Rapport Signal sur Bruit (SNR) du côté de l'émetteur. Le résultat dépend du schéma de modulation et aussi de la vitesse des utilisateurs. / Satellite communication systems are used in the context of broadcasting, navigation, rescue, and disaster relief since they allow the provision of services over a wide coverage area. However, this coverage area is limited by the masking effect caused by obstacles that block the Line-Of-Sight (LOS) link between the satellite and a terrestrial user. The masking effect becomes more severe in case of low satellite elevation angles or when the user is indoor. To address this issue, Hybrid Satellite-Terrestrial Cooperative Systems (HSTCSs) have been proposed. In an HSTCS, the mobile user can exploit the diversity advantages by receiving signals from both satellite and terrestrial components. Fixed or mobile gap-fillers are used to relay the satellite signal. Most of satellites broadcasting systems have been implemented using fixed gap-fillers while mobile gap-fillers are needed in emergency cases when the fixed infrastructure is not available. In emergency scenarios (e.g., fire, earthquake, flood and explosion), the existing terrestrial infrastructure has been destroyed. So, an HSTCS is appropriate for transmitting the information between the rescuers and the central office. This allows the rescuers to operate efficiently. In particular, a fast and flexible implementation is needed and this could be provided by deploying mobile gap fillers (vehicle or mobile handheld). Recently, the topic of HSTCSs has gain interest in the research community. Several cooperative scenarios and transmission techniques have been proposed and studied. However, most of existing approaches only provide a performance analysis based on simulation results and the analytical expression of the exact Symbol Error Probability (SEP) is generally not provided. This dissertation focuses on the performance analysis of HSTCSs. The exact closed-form outage probability and SEP of Selective Decode-and-Forward (SDF) transmission scheme with and without relay selection are derived for both M-ary phase shift keying (MPSK) and M-ary quadrature amplitude modulation (MQAM) schemes. This analytical SEP helps in designing and dimensioning HSTCSs. Our results are applicable to both fixed and mobile relaying techniques. Another part of the dissertation is dedicated to synchronization issues (time, frequency shifting/spreading). The mobility of users induces a Doppler spread in the Orthogonal Frequency Division Multiplexing (OFDM) signal that destroys the orthogonality of subcarriers. The loss of orthogonality produces Inter-subCarrier Interference (ICI) and hence a degradation of the system performance in terms of SEP. In this case, we present the conditions in which this degradation can be compensated for by an increase in the Signal to Noise Ratio (SNR) at the transmitter side. The result depends on both the modulation scheme and the speed of the mobile users.

Le problème d’exploration est un sujet fondamental de la robotique mobileautonome qui traite la réalisation de la catographie complète (mapping) d’un environnementprécédemment inconnu. Il y a plusieurs scénarios où l’achèvement de l’exploration d’unezone est une composante principale de la mission à accomplir. Par exemple: l’explorationplanétaire, la reconnaissance, la recherche et le sauvetage, l’agriculture, le nettoyage des lieuxdangereux, comme champs de mines et des zones radioactives. D’autre part, la communicationsans fil joue un rôle important dans les stratégies multi-robot collaboratives. Malheureusement,la supposition ou l’exigence de communication stable, ou encore, la connectivité continue,peuvent être compromises dans des scénarios réels. Dans cette thèse, deux nouvellesapproches abordent le problème d’exploration multi-robot d’environnements, en considérantune communication restreinte. D’abord, une stratégie multi-objectif auto-adaptative est proposéepour diriger la sélection de tâches en tennant compte de la performance d’explorationet du niveau de connectivité. Deuxièmement, deux rôles – l’explorateur et le relais de communication– sont considérés pour améliorer la stratégie de sélection de tâche précédente. Basésur le modèle de communication, une nouvelle approche de placement de robot relais pour desmissions d’exploration multi-robot est présentée en détail. Comparé avec d’autres approchesde l’état de l’art, les deux approches proposées dans cette thèse sont capables de diminuer ladurée de périodes de déconnexion sans dégradation considérable sur temps d’exploration. / The exploration problem is a fundamental subject in autonomous mobilerobotics that deals with achieving the complete coverage of a previously unknown environment.There are several scenarios where completing exploration of a zone is a main part of themission, e.g. planetary exploration, reconnaissance, search and rescue, agriculture, cleaning,or dangerous places as mined lands and radioactive zones. Wireless communication plays animportant role in collaborative multi-robot strategies. Unfortunately, the assumption or requirementof stable communication and end-to-end connectivity may be easily compromised inreal scenarios. In this thesis, two novel approaches to tackle the problem of multi-robot explorationof communication constrained environments are proposed. At first, an auto-adaptivemulti-objective strategy is followed in order to support the selection of tasks regarding bothexploration performance and connectivity level. Secondly, two roles –explorer and communicationrelay– are considered in order to improve the benefits of the previous task selectionstrategy. Based on the communication model, a novel polynomial-time relay placement approachfor multi-robot exploration missions is introduced in detail. Compared with others,the proposed approaches are capable of decreasing the last of disconnection periods withouta noticeable degradation of the completion exploration time.

Dans les communications coopératives, deux ou plusieurs terminaux de transmissionsont combinés pour accroître la diversité et/ou la puissance des signaux arrivant à un récepteur. Récemment, l'analyse tensorielle s'est avérée une approche efficace pour l'estimation de canaux dans les systèmes coopératifs. Cependant, parmi les quelques travaux consacrés à cette tâche, l'utilisation de la décomposition tensorielle PARAFAC pour modéliser les signaux reçus ne permet pas l'estimation conjointe des symboles et des canaux de communication. Afin d'éviter l'utilisation de séquences de symboles pilotes, l'objectif de cette thèse est de fournir de nouvelles approches tensorielles, en termes de systèmes de transmission et de récepteurs semi-aveugles, pour des systèmes de communication MIMO avec relai mono-directionnels, à deux sauts. Deux systèmes de transmission sont proposés en utilisant un codage spatio-temporel du type Khatri-Rao et deux stratégies de traitement Amplify-and-Forward (AF) au relai. Pour ces systèmes, appelés PT2-AF et NP-AF, les signaux reçus au niveau de la destination satisfont respectivement des modèles tensoriels du type PARATUCK2 et nested PARAFAC. En exploitant les propriétés d'unicité de ces modèles tensoriels établies dans la thèse, plusieurs récepteurs semi-aveugles sont dérivés. Certains de ces récepteurs sont du type ALS, tandis que d'autres sont des solutions non itératives basées sur des factorisations de produits de Khatri-Rao. Des résultats de simulation sont présentés pour illustrer les performances des récepteurs proposés qui sont comparés à des estimateurs supervisés. / In cooperative communication systems, two or more transmitting terminals arecombined to increase the diversity and/or the power of the signals arriving at aparticular receiver. Recently, the so-called tensor analysis has been an efficient approach for channel estimation in systems with cooperative diversity. However, among the few works devoted to this task, the utilization of the PARAFAC tensor decomposition for modeling the received signals did not allow the development of techniques for joint symbol and channel estimation. Aiming to avoid the use of pilot-based sequences, the objective of this thesis is to provide new tensor-based strategies, including transmission systems and semi-blind receivers, for one-way two-hop relaying systems. Based on a Khatri-Rao space-time coding at the source and two different Amplify-and-Forward (AF) relaying strategies, two transmission systems are proposed. For these systems, named PT2-AF and NP-AF, the received signals at the destination node follow respectively a PARATUCK2 and a nested PARAFAC tensor model. Exploiting uniqueness properties of these tensor models which are established in the thesis, several semi-blind receivers are derived. Some of these receivers are of iterative form using an ALS algorithm, whereas some other ones are close-form solutions associated with Khatri-Rao factorizations. Some simulation results are finally presented to illustrate the performance of the proposed receivers which are compared to some state-of-the-art supervised techniques.

Embodied Conversational Agents (ECA) form part of a range of virtual characters whose intended purpose include engaging in natural conversations with human users. While works in literature are ripe with descriptions of attempts at producing viable ECA architectures, few authors have addressed the role of episodic memory models in conversational agents. This form of memory, which provides a sense of autobiographic record-keeping in humans, has only recently been peripherally integrated into dialog management tools for ECAs. In our work, we propose to take a closer look at the shared characteristics of episodic memory models in recent examples from the field. Additionally, we propose several enhancements to these existing models through a unified episodic memory model for ECA's. As part of our research into episodic memory models, we present a process for determining the prevalent contexts in the conversations obtained from the aforementioned interactions. The process presented demonstrates the use of statistical and machine learning services, as well as Natural Language Processing techniques to extract relevant snippets from conversations. Finally, mechanisms to store, retrieve, and recall episodes from previous conversations are discussed. A primary contribution of this research is in the context of contemporary memory models for conversational agents and cognitive architectures. To the best of our knowledge, this is the first attempt at providing a comparative summary of existing works. As implementations of ECAs become more complex and encompass more realistic conversation engines, we expect that episodic memory models will continue to evolve and further enhance the naturalness of conversations.

Les besoins croissants en puissance de calcul sont généralement satisfaits en fédérant de plus en plus d’ordinateurs (ou noeuds) pour former des infrastructures distribuées. La tendance actuelle est d’utiliser la virtualisation système dans ces infrastructures, afin de découpler les logiciels des noeuds sous-jacents en les encapsulant dans des machines virtuelles. Pour gérer efficacement ces infrastructures virtualisées, de nouveaux gestionnaires logiciels ont été mis en place. Ces gestionnaires sont pour la plupart hautement centralisés (les tâches de gestion sont effectuées par un nombre restreint de nœuds dédiés). Cela limite leur capacité à passer à l’échelle, autrement dit à gérer de manière réactive des infrastructures de grande taille, qui sont de plus en plus courantes. Au cours de cette thèse, nous nous sommes intéressés aux façons d’améliorer cet aspect ; l’une d’entre elles consiste à décentraliser le traitement des tâches de gestion, lorsque cela s’avère judicieux. Notre réflexion s’est concentrée plus particulièrement sur l’ordonnancement dynamique des machines virtuelles, pour donner naissance à la proposition DVMS (Distributed Virtual Machine Scheduler). Nous avons mis en œuvre un prototype, que nous avons validé au travers de simulations (notamment via l’outil SimGrid), et d’expériences sur le banc de test Grid’5000. Nous avons pu constater que DVMS se montrait particulièrement réactif pour gérer des infrastructures virtualisées constituées de dizaines de milliers de machines virtuelles réparties sur des milliers de nœuds. Nous nous sommes ensuite penchés sur les perspectives d’extension et d’amélioration de DVMS. L’objectif est de disposer à terme d’un gestionnaire décentralisé complet, objectif qui devrait être atteint au travers de l’initiative Discovery qui fait suite à ces travaux. / The increasing need in computing power has been satisfied by federating more and more computers (called nodes) to build the so-called distributed infrastructures. Over the past few years, system virtualization has been introduced in these infrastructures (the software is decoupled from the hardware by packaging it in virtual machines), which has lead to the development of software managers in charge of operating these virtualized infrastructures. Most of these managers are highly centralized (management tasks are performed by a restricted set of dedicated nodes). As established, this restricts the scalability of managers, in other words their ability to be reactive to manage large-scale infrastructures, that are more and more common. During this Ph.D., we studied how to mitigate these concerns ; one solution is to decentralize the processing of management tasks, when appropriate. Our work focused in particular on the dynamic scheduling of virtual machines, resulting in the DVMS (Distributed Virtual Machine Scheduler) proposal. We implemented a prototype, that was validated by means of simulations (especially with the SimGrid tool) and with experiments on the Grid’5000 test bed. We observed that DVMS was very reactive to schedule tens of thousands of virtual machines distributed over thousands of nodes. We then took an interest in the perspectives to improve and extend DVMS. The final goal is to build a full decentralized manager. This goal should be reached by the Discovery initiative,that will leverage this work.

Τα συστήματα που έχουν πολλαπλές κεραίες σε πομπό και δέκτη (ΜΙΜΟ) έχουν την δυνατότητα να επιτύχουν υψηλούς ρυθμούς δεδομένων και αυξημένη αξιοπιστία χωρίς να απαιτείται επιπλέον εύρος ζώνης ή ισχύς μετάδοσης. Η βασική αρχή στην οποία βασίζονται είναι ότι το σήμα που εκπέμπεται από τον πομπό διέρχεται από περισσότερα του ενός ανεξάρτητα κανάλια. Ο δέκτης εκμεταλλευόμενος τις πολλαπλές λήψεις του ίδιου σήματος μπορεί να βελτιώσει την απόδοσή του. Η εισαγωγή πολλαπλών κεραιών σε κάποια συστήματα δεν είναι δυνατό να συμβεί συνήθως λόγω του χώρου που απαιτείται. Παρόλα αυτά, σε αυτό το περιβάλλον επικοινωνίας υπάρχουν συνήθως πολλαπλοί χρήστες που μπορούν να συνεργαστούν και να δημιουργήσουν ένα κατανεμημένο σύστημα ΜΙΜΟ, που αναφέρεται στην βιβλιογραφία ως συνεργατικό (cooperative). Στα συστήματα MIMO έχουν προταθεί τεχνικές προσανατολισμένης επικοινωνίας (beamforming) με σκοπό την ακύρωση των παρεμβολών και του θορύβου στο δέκτη. Οι τεχνικές αυτές απαιτούν την γνώση της κατάστασης του καναλιού αφού πραγματοποιούν διάσπαση της μήτρας των συντελεστών του καναλιού κατά παράγοντες ώστε να εξάγουν τα διανύσματα βάρους με τα οποία θα πολλαπλασιάσουν τις ακολουθίες των συμβόλων που λαμβάνει ο δέκτης ή /και των συμβόλων που μεταδίδει ο πομπός. Συγκεκριμένα, μελετήθηκε η περίπτωση της τεχνικής προσανατολισμένης επικοινωνίας που στηρίζεται στην μέθοδο SVD η οποία πολλαπλασιάζει το διάνυσμα των προς μετάδοση συμβόλων στον πομπό και το διάνυσμα των ληφθέντων συμβόλων στο δέκτη με τα κατάλληλα ιδιάζοντα διανύσματα, επιτυγχάνοντας προσανατολισμένη επικοινωνία λήψης και εκπομπής (transmit και receive beamforming). Όπως αναφέρθηκε, η συγκεκριμένη μέθοδος απαιτεί την γνώση της κατάστασης του καναλιού σε πομπό και σε δέκτη. Για αυτό το σκοπό αρχικά θα μελετηθεί η επίδραση της εκτίμησης του καναλιού στην επίδοση της μεθόδου η οποία διεξάγεται από ένα εκτιμητή μέγιστης πιθανοφάνειας από ακολουθίες συμβόλων εκμάθησης που έχει μεταδώσει ο πομπός. Στην συνέχεια θα εξεταστεί η περίπτωση που τα κανάλια μπορούν να περιγραφούν από ένα μοντέλο πολλαπλών μονοπατιών. Ένα τέτοιο μοντέλο είναι δυνατό να εκτιμηθεί από δείγματα της κρουστικής απόκρισης του καναλιού, βελτιώνοντας περαιτέρω την επίδοση του συστήματος. Επίσης, παρέχει και την δυνατότητα της πρόβλεψης των μεταγενέστερων καταστάσεων του καναλιού, μειώνοντας αρκετά τον αριθμό των συμβόλων εκμάθησης που απαιτούνται. Η εκτίμηση των παραμέτρων του μοντέλου του καναλιού θα γίνει με την βοήθεια της μεθόδου ESPRIT. Τελικά, θα ενσωματωθεί η εκτίμηση του μοντέλου και στην τεχνική προσανατολισμένης επικοινωνίας και θα μελετηθεί η επίδοσή της. Στην συνέχεια θα εφαρμόσουμε την προηγούμενη διάταξη στην περίπτωση των συνεργατικών συστημάτων. Θα εφαρμοστεί λοιπόν, σε ένα τέτοιο σύστημα η τεχνική με την εκτίμηση του μοντέλου του καναλιού και θα αναλυθεί η επίδοσή του για τα δύο πιο γνωστά πρωτόκολλα επικοινωνίας μεταξύ του κόμβου-πηγής και των κόμβων-συνεργατών, το ενίσχυσης και προώθησης και το αποκωδικοποίησης και προώθησης. / The systems that have multiple transmit and receive antennas (MIMO) can achieve high data rates and increased reliability without the need for additional bandwidth or transmission power. The aforementioned is based on the transmission of the signal of the transmitter via multiple independent channels. The receiver can use the multiple versions of the same signal to improve its performance. The introduction of multiple antennas in some systems it is not possible due to the lack of space. On contrast, in a multi-user environment there are users of a single antenna that can cooperate to construct a distributed MIMO system, which are called in the bibliography as a cooperative system. A number of beamforming schemes have already proposed in MIMO systems with the view of interference and noise cancellation. These schemes compute the singular value decomposition of the channel matrix and use the singular vectors to extract the weight vectors that are used to multiply the sequences of symbols that transmitter transmits and the symbols that receiver receives. This scheme achieves transmit and receive beamforming and transmitter and receiver must have full channel state information (CSI). The next step is to examine the performance of this method under channel estimation errors. The estimation of the channel is carried out with a maximum likelihood estimator from training sequences that were transmitted from the transmitter. After that, we examine the case in which the channel taps can be modeled by a multipath model. The parameters of a model of this kind can be computed from noise corrupted samples with sub-space methods. In this thesis we use the ESPRIT method for the estimation of these parameters. After the estimation of the model’s parameters we can use the model to predict future values of channel taps, decreasing with this way the number of the training symbols that are needed. Then, we will use this method in the system with the beamforming scheme and we will evaluate its performance. Finally, the complete infrastructure will be applied to a cooperative system and its performance will be tested for the two most popular cooperation protocols, the amplify and forward protocol and the decode and forward protocol.