Quantifying Uncertainty in Real Time Performance Measurement for Highway Winter Maintenance Operations – Phase 2, RB03-013, 2014

Winter weather in Iowa is often unpredictable and can have an adverse impact on traffic flow. The Iowa Department of Transportation (Iowa DOT) attempts to lessen the impact of winter weather events on traffic speeds with various proactive maintenance operations. In order to assess the performance of these maintenance operations, it would be beneficial to develop a model for expected speed reduction based on weather variables and normal maintenance schedules. Such a model would allow the Iowa DOT to identify situations in which speed reductions were much greater than or less than would be expected for a given set of storm conditions, and make modifications to improve efficiency and effectiveness. The objective of this work was to predict speed changes relative to baseline speed under normal conditions, based on nominal maintenance schedules and winter weather covariates (snow type, temperature, and wind speed), as measured by roadside weather stations. This allows for an assessment of the impact of winter weather covariates on traffic speed changes, and estimation of the effect of regular maintenance passes. The researchers chose events from Adair County, Iowa and fit a linear model incorporating the covariates mentioned previously. A Bayesian analysis was conducted to estimate the values of the parameters of this model. Specifically, the analysis produces a distribution for the parameter value that represents the impact of maintenance on traffic speeds. The effect of maintenance is not a constant, but rather a value that the researchers have some uncertainty about and this distribution represents what they know about the effects of maintenance. Similarly, examinations of the distributions for the effects of winter weather covariates are possible. Plots of observed and expected traffic speed changes allow a visual assessment of the model fit. Future work involves expanding this model to incorporate many events at multiple locations. This would allow for assessment of the impact of winter weather maintenance across various situations, and eventually identify locations and times in which maintenance could be improved.

HIGH PERFORMANCE, LOW COST SUBSPACE DECOMPOSITION AND POLYNOMIAL ROOTING FOR REAL TIME DIRECTION OF ARRIVAL ESTIMATION: ANALYSIS AND IMPLEMENTATION

This thesis develops high performance real-time signal processing modules for direction of arrival (DOA) estimation for localization systems. It proposes highly parallel algorithms for performing subspace decomposition and polynomial rooting, which are otherwise traditionally implemented using sequential algorithms. The proposed algorithms address the emerging need for real-time localization for a wide range of applications. As the antenna array size increases, the complexity of signal processing algorithms increases, making it increasingly difficult to satisfy the real-time constraints. This thesis addresses real-time implementation by proposing parallel algorithms, that maintain considerable improvement over traditional algorithms, especially for systems with larger number of antenna array elements. Singular value decomposition (SVD) and polynomial rooting are two computationally complex steps and act as the bottleneck to achieving real-time performance. The proposed algorithms are suitable for implementation on field programmable gated arrays (FPGAs), single instruction multiple data (SIMD) hardware or application specific integrated chips (ASICs), which offer large number of processing elements that can be exploited for parallel processing. The designs proposed in this thesis are modular, easily expandable and easy to implement. Firstly, this thesis proposes a fast converging SVD algorithm. The proposed method reduces the number of iterations it takes to converge to correct singular values, thus achieving closer to real-time performance. A general algorithm and a modular system design are provided making it easy for designers to replicate and extend the design to larger matrix sizes. Moreover, the method is highly parallel, which can be exploited in various hardware platforms mentioned earlier. A fixed point implementation of proposed SVD algorithm is presented. The FPGA design is pipelined to the maximum extent to increase the maximum achievable frequency of operation. The system was developed with the objective of achieving high throughput. Various modern cores available in FPGAs were used to maximize the performance and details of these modules are presented in detail. Finally, a parallel polynomial rooting technique based on Newton’s method applicable exclusively to root-MUSIC polynomials is proposed. Unique characteristics of root-MUSIC polynomial’s complex dynamics were exploited to derive this polynomial rooting method. The technique exhibits parallelism and converges to the desired root within fixed number of iterations, making this suitable for polynomial rooting of large degree polynomials. We believe this is the first time that complex dynamics of root-MUSIC polynomial were analyzed to propose an algorithm. In all, the thesis addresses two major bottlenecks in a direction of arrival estimation system, by providing simple, high throughput, parallel algorithms.

Real-time detection of pneumothorax using electrical impedance tomogyaphy

Objectives: Pneumothorax is a frequent complication during mechanical ventilation. Electrical impedance tomography (EIT) is a noninvasive tool that allows real-time imaging of regional ventilation. The purpose of this study was to 1) identify characteristic changes in the EIT signals associated with pneumothoraces; 2) develop and fine-tune an algorithm for their automatic detection; and 3) prospectively evaluate this algorithm for its sensitivity and specificity in detecting pneumothoraces in real time. Design: Prospective controlled laboratory animal investigation. Setting: Experimental Pulmonology Laboratory of the University of Sao Paulo. Subjects: Thirty-nine anesthetized mechanically ventilated supine pigs (31.0 +/- 3.2 kg, mean +/- SD). Interventions. In a first group of 18 animals monitored by EIT, we either injected progressive amounts of air (from 20 to 500 mL) through chest tubes or applied large positive end-expiratory pressure (PEEP) increments to simulate extreme lung overdistension. This first data set was used to calibrate an EIT-based pneumothorax detection algorithm. Subsequently, we evaluated the real-time performance of the detection algorithm in 21 additional animals (with normal or preinjured lungs), submitted to multiple ventilatory interventions or traumatic punctures of the lung. Measurements and Main Results: Primary EIT relative images were acquired online (50 images/sec) and processed according to a few imaging-analysis routines running automatically and in parallel. Pneumothoraces as small as 20 mL could be detected with a sensitivity of 100% and specificity 95% and could be easily distinguished from parenchymal overdistension induced by PEEP or recruiting maneuvers, Their location was correctly identified in all cases, with a total delay of only three respiratory cycles. Conclusions. We created an EIT-based algorithm capable of detecting early signs of pneumothoraces in high-risk situations, which also identifies its location. It requires that the pneumothorax occurs or enlarges at least minimally during the monitoring period. Such detection was operator-free and in quasi real-time, opening opportunities for improving patient safety during mechanical ventilation.

Supporting intra-task parallelism in real-time multiprocessor systems

Os sistemas de tempo real modernos geram, cada vez mais, cargas computacionais pesadas e dinâmicas, começando-se a tornar pouco expectável que sejam implementados em sistemas uniprocessador. Na verdade, a mudança de sistemas com um único processador para sistemas multi- processador pode ser vista, tanto no domínio geral, como no de sistemas embebidos, como uma forma eficiente, em termos energéticos, de melhorar a performance das aplicações. Simultaneamente, a proliferação das plataformas multi-processador transformaram a programação paralela num tópico de elevado interesse, levando o paralelismo dinâmico a ganhar rapidamente popularidade como um modelo de programação. A ideia, por detrás deste modelo, é encorajar os programadores a exporem todas as oportunidades de paralelismo através da simples indicação de potenciais regiões paralelas dentro das aplicações. Todas estas anotações são encaradas pelo sistema unicamente como sugestões, podendo estas serem ignoradas e substituídas, por construtores sequenciais equivalentes, pela própria linguagem. Assim, o modo como a computação é na realidade subdividida, e mapeada nos vários processadores, é da responsabilidade do compilador e do sistema computacional subjacente. Ao retirar este fardo do programador, a complexidade da programação é consideravelmente reduzida, o que normalmente se traduz num aumento de produtividade. Todavia, se o mecanismo de escalonamento subjacente não for simples e rápido, de modo a manter o overhead geral em níveis reduzidos, os benefícios da geração de um paralelismo com uma granularidade tão fina serão meramente hipotéticos. Nesta perspetiva de escalonamento, os algoritmos que empregam uma política de workstealing são cada vez mais populares, com uma eficiência comprovada em termos de tempo, espaço e necessidades de comunicação. Contudo, estes algoritmos não contemplam restrições temporais, nem outra qualquer forma de atribuição de prioridades às tarefas, o que impossibilita que sejam diretamente aplicados a sistemas de tempo real. Além disso, são tradicionalmente implementados no runtime da linguagem, criando assim um sistema de escalonamento com dois níveis, onde a previsibilidade, essencial a um sistema de tempo real, não pode ser assegurada. Nesta tese, é descrita a forma como a abordagem de work-stealing pode ser resenhada para cumprir os requisitos de tempo real, mantendo, ao mesmo tempo, os seus princípios fundamentais que tão bons resultados têm demonstrado. Muito resumidamente, a única fila de gestão de processos convencional (deque) é substituída por uma fila de deques, ordenada de forma crescente por prioridade das tarefas. De seguida, aplicamos por cima o conhecido algoritmo de escalonamento dinâmico G-EDF, misturamos as regras de ambos, e assim nasce a nossa proposta: o algoritmo de escalonamento RTWS. Tirando partido da modularidade oferecida pelo escalonador do Linux, o RTWS é adicionado como uma nova classe de escalonamento, de forma a avaliar na prática se o algoritmo proposto é viável, ou seja, se garante a eficiência e escalonabilidade desejadas. Modificar o núcleo do Linux é uma tarefa complicada, devido à complexidade das suas funções internas e às fortes interdependências entre os vários subsistemas. Não obstante, um dos objetivos desta tese era ter a certeza que o RTWS é mais do que um conceito interessante. Assim, uma parte significativa deste documento é dedicada à discussão sobre a implementação do RTWS e à exposição de situações problemáticas, muitas delas não consideradas em teoria, como é o caso do desfasamento entre vários mecanismo de sincronização. Os resultados experimentais mostram que o RTWS, em comparação com outro trabalho prático de escalonamento dinâmico de tarefas com restrições temporais, reduz significativamente o overhead de escalonamento através de um controlo de migrações, e mudanças de contexto, eficiente e escalável (pelo menos até 8 CPUs), ao mesmo tempo que alcança um bom balanceamento dinâmico da carga do sistema, até mesmo de uma forma não custosa. Contudo, durante a avaliação realizada foi detetada uma falha na implementação do RTWS, pela forma como facilmente desiste de roubar trabalho, o que origina períodos de inatividade, no CPU em questão, quando a utilização geral do sistema é baixa. Embora o trabalho realizado se tenha focado em manter o custo de escalonamento baixo e em alcançar boa localidade dos dados, a escalonabilidade do sistema nunca foi negligenciada. Na verdade, o algoritmo de escalonamento proposto provou ser bastante robusto, não falhando qualquer meta temporal nas experiências realizadas. Portanto, podemos afirmar que alguma inversão de prioridades, causada pela sub-política de roubo BAS, não compromete os objetivos de escalonabilidade, e até ajuda a reduzir a contenção nas estruturas de dados. Mesmo assim, o RTWS também suporta uma sub-política de roubo determinística: PAS. A avaliação experimental, porém, não ajudou a ter uma noção clara do impacto de uma e de outra. No entanto, de uma maneira geral, podemos concluir que o RTWS é uma solução promissora para um escalonamento eficiente de tarefas paralelas com restrições temporais.

Dynamic global scheduling of parallel real-time tasks

High-level parallel languages offer a simple way for application programmers to specify parallelism in a form that easily scales with problem size, leaving the scheduling of the tasks onto processors to be performed at runtime. Therefore, if the underlying system cannot efficiently execute those applications on the available cores, the benefits will be lost. In this paper, we consider how to schedule highly heterogenous parallel applications that require real-time performance guarantees on multicore processors. The paper proposes a novel scheduling approach that combines the global Earliest Deadline First (EDF) scheduler with a priority-aware work-stealing load balancing scheme, which enables parallel realtime tasks to be executed on more than one processor at a given time instant. Experimental results demonstrate the better scalability and lower scheduling overhead of the proposed approach comparatively to an existing real-time deadline-oriented scheduling class for the Linux kernel.

Enhancing the real-time capabilities of the Linux Kernel

The mainline Linux Kernel is not designed forhard real-time systems; it only fits the requirements of soft realtimesystems. In recent years, a kernel developer communityhas been working on the PREEMPT-RT patch. This patch(that aims to get a fully preemptible kernel) adds some realtimecapabilities to the Linux kernel. However, in terms ofscheduling policies, the real-time scheduling class of Linux islimited to the First-In-First-Out (SCHED_FIFO) and Round-Robin (SCHED_RR) scheduling policies. These scheduling policiesare however quite limited in terms of realtime performance.Therefore, in this paper, we report one importantcontribution for adding more advanced real-time capabilitiesto the Linux Kernel. Specifically, we describe modificationsto the (PREEMPT-RT patched) Linux kernel to supportreal-time slot-based task-splitting scheduling algorithms. Ourpreliminary evaluation shows that our implementation exhibitsa real-time performance that is superior to the schedulingpolicies provided by the current version of PREMPT-RT. Thisis a significant add-on to a widely adopted operating system.

Real-time crowd density estimation using images

This paper presents a technique for real-time crowd density estimation based on textures of crowd images. In this technique, the current image from a sequence of input images is classified into a crowd density class. Then, the classification is corrected by a low-pass filter based on the crowd density classification of the last n images of the input sequence. The technique obtained 73.89% of correct classification in a real-time application on a sequence of 9892 crowd images. Distributed processing was used in order to obtain real-time performance. © Springer-Verlag Berlin Heidelberg 2005.

A new generation of real-time systems in the JET tokamak

Recently a new recipe for developing and deploying real-time systems has become increasingly adopted in the JET tokamak. Powered by the advent of x86 multi-core technology and the reliability of the JET’s well established Real-Time Data Network (RTDN) to handle all real-time I/O, an official Linux vanilla kernel has been demonstrated to be able to provide realtime performance to user-space applications that are required to meet stringent timing constraints. In particular, a careful rearrangement of the Interrupt ReQuests’ (IRQs) affinities together with the kernel’s CPU isolation mechanism allows to obtain either soft or hard real-time behavior depending on the synchronization mechanism adopted. Finally, the Multithreaded Application Real-Time executor (MARTe) framework is used for building applications particularly optimised for exploring multicore architectures. In the past year, four new systems based on this philosophy have been installed and are now part of the JET’s routine operation. The focus of the present work is on the configuration and interconnection of the ingredients that enable these new systems’ real-time capability and on the impact that JET’s distributed real-time architecture has on system engineering requirements, such as algorithm testing and plant commissioning. Details are given about the common real-time configuration and development path of these systems, followed by a brief description of each system together with results regarding their real-time performance. A cycle time jitter analysis of a user-space MARTe based application synchronising over a network is also presented. The goal is to compare its deterministic performance while running on a vanilla and on a Messaging Real time Grid (MRG) Linux kernel.

Low-cost real-time gesture recognition

A major impediment to developing real-time computer vision systems has been the computational power and level of skill required to process video streams in real-time. This has meant that many researchers have either analysed video streams off-line or used expensive dedicated hardware acceleration techniques. Recent software and hardware developments have greatly eased the development burden of realtime image analysis leading to the development of portable systems using cheap PC hardware and software exploiting the Multimedia Extension (MMX) instruction set of the Intel Pentium chip. This paper describes the implementation of a computationally efficient computer vision system for recognizing hand gestures using efficient coding and MMX-acceleration to achieve real-time performance on low cost hardware.

Digital signal processing implementation for near real-time wavelet transformation system for binary images

Communication has become an essential function in our civilization. With the increasing demand for communication channels, it is now necessary to find ways to optimize the use of their bandwidth. One way to achieve this is by transforming the information before it is transmitted. This transformation can be performed by several techniques. One of the newest of these techniques is the use of wavelets. Wavelet transformation refers to the act of breaking down a signal into components called details and trends by using small waveforms that have a zero average in the time domain. After this transformation the data can be compressed by discarding the details, transmitting the trends. In the receiving end, the trends are used to reconstruct the image. In this work, the wavelet used for the transformation of an image will be selected from a library of available bases. The accuracy of the reconstruction, after the details are discarded, is dependent on the wavelets chosen from the wavelet basis library. The system developed in this thesis takes a 2-D image and decomposes it using a wavelet bank. A digital signal processor is used to achieve near real-time performance in this transformation task. A contribution of this thesis project is the development of DSP-based test bed for the future development of new real-time wavelet transformation algorithms.

Video anomaly detection in real-time on a Power-Aware Heterogeneous Platform

FPGAs and GPUs are often used when real-time performance in video processing is required. An accelerated processor is chosen based on task-specific priorities (power consumption, processing time and detection accuracy), and this decision is normally made once at design time. All three characteristics are important, particularly in battery-powered systems. Here we propose a method for moving selection of processing platform from a single design-time choice to a continuous run time one.We implement Histogram of Oriented Gradients (HOG) detectors for cars and people and Mixture of Gaussians (MoG) motion detectors running across FPGA, GPU and CPU in a heterogeneous system. We use this to detect illegally parked vehicles in urban scenes. Power, time and accuracy information for each detector is characterised. An anomaly measure is assigned to each detected object based on its trajectory and location, when compared to learned contextual movement patterns. This drives processor and implementation selection, so that scenes with high behavioural anomalies are processed with faster but more power hungry implementations, but routine or static time periods are processed with power-optimised, less accurate, slower versions. Real-time performance is evaluated on video datasets including i-LIDS. Compared to power-optimised static selection, automatic dynamic implementation mapping is 10% more accurate but draws 12W extra power in our testbed desktop system.

A C80 DSP-based active vision system for real-time tracking

[EN]Active Vision Systems can be considered as dynamical systems which close the loop around artificial visual perception, controlling camera parameters, motion and also controlling processing to simplify, accelerate and do more robust visual perception. Research and Development in Active Vision Systems [Aloi87], [Bajc88] is a main area of interest in Computer Vision, mainly by its potential application in different scenarios where real-time performance is needed such as robot navigation, surveillance, visual inspection, among many others. Several systems have been developed during last years using robotic-heads for this purpose...

Development of a Real-Time Hierarchical 3D Path Planning Algorithm for Unmanned Aerial Vehicles

Unmanned aerial vehicles (UAVs) frequently operate in partially or entirely unknown environments. As the vehicle traverses the environment and detects new obstacles, rapid path replanning is essential to avoid collisions. This thesis presents a new algorithm called Hierarchical D* Lite (HD*), which combines the incremental algorithm D* Lite with a novel hierarchical path planning approach to replan paths sufficiently fast for real-time operation. Unlike current hierarchical planning algorithms, HD* does not require map corrections before planning a new path. Directional cost scale factors, path smoothing, and Catmull-Rom splines are used to ensure the resulting paths are feasible. HD* sacrifices optimality for real-time performance. Its computation time and path quality are dependent on the map size, obstacle density, sensor range, and any restrictions on planning time. For the most complex scenarios tested, HD* found paths within 10% of optimal in under 35 milliseconds.

Real time fault injection using enhanced OCD -- a performance analysis

Fault injection is frequently used for the verification and validation of dependable systems. When targeting real time microprocessor based systems the process becomes significantly more complex. This paper proposes two complementary solutions to improve real time fault injection campaign execution, both in terms of performance and capabilities. The methodology is based on the use of the on-chip debug mechanisms present in modern electronic devices. The main objective is the injection of faults in microprocessor memory elements with minimum delay and intrusiveness. Different configurations were implemented and compared in terms of performance gain and logic overhead.

The performance of semi-quantitative differential PCR is similar to that of real-time PCR for the detection of the MYCN gene in neuroblastomas

Amplification of the MYCN gene in neuroblastomas is a potent biological marker of highly aggressive tumors, which are invariably fatal unless sound clinical management is applied. To determine the usefulness of semi-quantitative differential PCR (SQ-PCR) for accurate quantification of MYCN gene copy number, we evaluated the analytical performance of this method by comparing the results obtained with it for 101 tumor samples of neuroblastoma to that obtained by absolute and relative real-time PCR. Similar results were obtained for 100 (99%) samples, no significant difference was detected between the median log10 MYCN copy number (1.53 by SQ-PCR versus 1.55 by absolute real-time PCR), and the results of the two assays correlated closely (r = 0.8, Pearson correlation; P < 0.001). In the comparison of SQ-PCR and relative real-time PCR, SQ-PCR versus relative real-time PCR concordant results were found in 100 (99%) samples, no significant difference was found in median log10 MYCN copy number (1.53 by SQ-PCR versus 1.27 by relative real-time PCR), and the results of the two assays correlated closely (r = 0.8, Pearson correlation; P < 0.001). These findings indicate that the performance of SQ-PCR was comparable to that of real-time PCR for the amplification and quantification of MYCN copy number. Thus, SQ-PCR can be reliably used as an alternative assay in laboratories without facilities for real-time PCR.