Distributed shared memory (DSM) systems have been recognised as a compelling platform for parallel computing due to the programming advantages and scalability. DSM systems allow applications to access data in a logically shared address space by abstracting away the distinction of physical memory location. As the location of data is transparent, the sources of overhead caused by accessing the distant memories are difficult to analyse. This memory locality problem has been identified as crucial to DSM performance. Many researchers have investigated the problem using simulation as a tool for conducting experiments resulting in the progressive evolution of DSM systems. Nevertheless, both the diversity of architectural configurations and the rapid advance of DSM implementations impose constraints on simulation model designs in two issues: the limitation of the simulation framework on model extensibility and the lack of verification applicability during a simulation run causing the delay in verification process. This thesis studies simulation modelling techniques for memory locality analysis of various DSM systems implemented on top of a cluster of symmetric multiprocessors. The thesis presents a simulation technique to promote model extensibility and proposes a technique for verification applicability, called a Specification-based Parameter Model Interaction (SPMI). The proposed techniques have been implemented in a new interpretation-driven simulation called DSiMCLUSTER on top of a discrete event simulation (DES) engine known as HASE. Experiments have been conducted to determine which factors are most influential on the degree of locality and to determine the possibility to maximise the stability of performance. DSiMCLUSTER has been validated against a SunFire 15K server and has achieved similarity of cache miss results, an average of +-6% with the worst case less than 15% of difference. These results confirm that the techniques used in developing the DSiMCLUSTER can contribute ways to achieve both (a) a highly extensible simulation framework to keep up with the ongoing innovation of the DSM architecture, and (b) the verification applicability resulting in an efficient framework for memory analysis experiments on DSM architecture.

De nombreuses applications de la vision par ordinateur requièrent la détection, la localisation et le suivi de régions ou d’objets d’intérêt dans une image ou une séquence d’images. De nombreux modèles d’attention visuelle, inspirés de la vision humaine, qui détectent de manière automatique les régions d’intérêt dans une image ou une vidéo, ont récemment été développés et utilisés avec succès dans différentes applications. Néanmoins, la plupart des approches existantes sont limitées à l’analyse de scènes statiques et très peu de méthodes exploitent la nature temporelle des séquences d’images.L'objectif principal de ce travail de thèse est donc l'étude de modèles d'attention visuelle pour l'analyse de scènes dynamiques complexes. Une carte de saliance est habituellement obtenue par la fusion d'une carte statitque (saliance spatiale dans une image) d'une part, et d'une carte dynamique (salience temporelle entre une série d'image) d'autre part. Dans notre travail, nous modélisons les changements dynamiques par un opérateur de texture LBP-TOP (Local Binary Patterns) et nous utilisons l'information couleur pour l'aspect spatial.Les deux cartes de saliances sont calculées en utilisant une formulation discriminante inspirée du système visuel humain, et fuionnées de manière appropriée en une carte de saliance spatio-temporelle.De nombreuses expériences avec des bases de données publiques, montrent que notre approche obteint des résulats meilleurs ou comparables avec les approches de la littérature. / Visual saliency is an important research topic in the field of computer vision due to its numerouspossible applications. It helps to focus on regions of interest instead of processingthe whole image or video data. Detecting visual saliency in still images has been widelyaddressed in literature with several formulations. However, visual saliency detection invideos has attracted little attention, and is a more challenging task due to additional temporalinformation. Indeed, a video contains strong spatio-temporal correlation betweenthe regions of consecutive frames, and, furthermore, motion of foreground objects dramaticallychanges the importance of the objects in a scene. The main objective of thethesis is to develop a spatio-temporal saliency method that works well for complex dynamicscenes.A spatio-temporal saliency map is usually obtained by the fusion of a static saliency mapand a dynamic saliency map. In our work, we model the dynamic textures in a dynamicscene with Local Binary Patterns (LBP-TOP) to compute the dynamic saliency map, andwe use color features to compute the static saliency map. Both saliency maps are computedusing a bio-inspired mechanism of Human Visual System (HVS) with a discriminantformulation known as center surround saliency, and are fused in a proper way.The proposed models have been extensively evaluated with diverse publicly availabledatasets which contain several videos of dynamic scenes. The evaluation is performed intwo parts. First, the method in locating interesting foreground objects in complex scene.Secondly, we evaluate our model on the task of predicting human observers fixations.The proposed method is also compared against state-of-the art methods, and the resultsshow that the proposed approach achieves competitive results.In this thesis we also evaluate the performance of different fusion techniques, because fusionplays a critical role in the accuracy of the spatio-temporal saliency map. We evaluatethe performances of different fusion techniques on a large and diverse complex datasetand the results show that a fusion method must be selected depending on the characteristics,in terms of color and motion contrasts, of a sequence. Overall, fusion techniqueswhich take the best of each saliency map (static and dynamic) in the final spatio-temporalmap achieve best results.

Indian cities rely predominantly on buses for public transport. The issues of performance measurement and efficiency analyses for the bus company have been gaining significance due to severe operating conditions and financial constraints in which these bus companies provide the service. Performance is defined as the levels of success of the service with respect to different parameters such as quality of service, cost effectiveness and safety. Performance is measured in terms of operational efficiency and financial efficiency. Operational Efficiency of an organization is the ability to utilize its available resources to the maximum extent. Financial Efficiency is a measure of the organization’s ability to translate its financial resources into revenue. Public bus transportation plays a pivotal role in India in bringing about greater mobility both within and between urban and rural areas. Through increased mobility, road transport also contributes immensely to social and economic development of different regions of the country. Public transport is provided by surface road transport using buses by the State Road Transport Undertakings (SRTUs) and by private operators. In this thesis, scientific analysis of the performance of SRTUs is carried out at different levels considering physical and financial parameters through multivariate techniques, non-parametric techniques and qualitative techniques. A comprehensive study on all the SRTUs of Karnataka at depot, division level are done and determined which quantitative method is suited for depot level and division level studies. From quantitative and qualitative studies of SRTUs strategies are developed and recommendations are made to improve the performance of SRTUs. Further, in addition to Bangalore metropolitan transport corporation (BMTC) performance analyses, the routes are analyzed to reduce the dead kilometer. Major contributions from this work: 1. Both inter and intra city operations of the public transport corporation in the state of Karnataka have been exhaustively analysed using operational and financial parameters. 2. Large amount of data over a long period has been collated from State road transport units and a standard format has been developed for collecting both operational and financial parameters for SRTU’s. 3. A generic framework and plan for performance evaluation of SRTU’s has been developed using ratio and benchmarking analysis, and, non-parametric and multivariate techniques like DEA (constant return to scale (CRS) and variable return to scale (VRS)), DEA-principal component analysis (PCA), DEA- bootstrapping. These analyses have been carried out at different levels, like transport corporations level (KSRTC NEKRTC, NWKRTC, BMTC), division level (33 divisions), and Depot level (193 depots). 4. Non parametric and multivariate Models have been developed and validated using DEAP and GAMS software before embarking on the above detailed analyses. 5. Analytical hierarchy approach (AHP), which is multi criteria structured technique, has been adopted to evaluate and analyze performance of the SRTU’s, divisions and depots based on qualitative and quantitative data. 6. User and operator perception studies of different SRTU’s of Karnataka have been done to evaluate the performance of these corporations from qualitative techniques. 7. From these comprehensive non parametric techniques, the efficiency of the SRTU’s have been evaluated and found that KSRTC has been the best operating unit among the SRTU’s considered for the study. The same has been observed from the AHP as well as perception surveys carried out as part of this thesis. 8. Operation and financial performance including profitability studies of Mysore urban transportation (Mysore city transport division) has been carried out before and after implementation of intelligent transport system (ITS). 9. The dead kilometer minimization model was formulated, which is a mixed integer programming problem, to get the optimal solution considering the capacity of the depot and time period of operation for the chosen network. An optimization technique has been developed for solving the dead kilometer problem in the operations of BMTC buses for the Volvo division (division operates 794 schedules). The alternative depot locations have been identified to reduce the dead kilometer, leading to large amount of savings for the corporation. 10. From the detailed analyses using non parametric techniques, multivariate and multi-criteria techniques along with perception surveys, strategies and recommendations have been arrived at to improve performance of the public transport corporations. This thesis consists of nine chapters and they are as below; Chapter 1 provides a brief introduction of public bus transport systems in India, their problems and need for performance evaluation of SRTUs. The impacts study of Mysore ITS, dead kilometer minimization problem for BMTC along with evaluating the performance of SRTUs by quantitative and qualitative data. This chapter provides the objective of the work and scope of the work. The main objectives of this research are 1. To develop a generic framework and plan for evaluation by identifying the performance indicators and data sources for evaluation.