Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

The frequency-dependent properties of Rayleigh-type surface waves can be utilized for imaging and characterizing the shallow subsurface. Most surface-wave analysis relies on the accurate calculation of phase velocities for the horizontally traveling fundamental-mode Rayleigh wave acquired by stepping out a pair of receivers at intervals based on calculated ground roll wavelengths. Interference by coherent source-generated noise inhibits the reliability of shear-wave velocities determined through inversion of the whole wave field. Among these nonplanar, nonfundamental-mode Rayleigh waves (noise) are body waves, scattered and nonsource-generated surface waves, and higher-mode surface waves. The degree to which each of these types of noise contaminates the dispersion curve and, ultimately, the inverted shear-wave velocity profile is dependent on frequency as well as distance from the source. Multichannel recording permits effective identification and isolation of noise according to distinctive traceto-trace coherency in arrival time and amplitude. An added advantage is the speed and redundancy of the measurement process. Decomposition of a multichannel record into a time variable-frequency format, similar to an uncorrelated Vibroseis record, permits analysis and display of each frequency component in a unique and continuous format. Coherent noise contamination can then be examined and its effects appraised in both frequency and offset space. Separation of frequency components permits real-time maximization of the S/N ratio during acquisition and subsequent processing steps. Linear separation of each ground roll frequency component allows calculation of phase velocities by simply measuring the linear slope of each frequency component. Breaks in coherent surface-wave arrivals, observable on the decomposed record, can be compensated for during acquisition and processing. Multichannel recording permits single-measurement surveying of a broad depth range, high levels of redundancy with a single field configuration, and the ability to adjust the offset, effectively reducing random or nonlinear noise introduced during recording. A multichannel shot gather decomposed into a sweptfrequency record allows the fast generation of an accurate dispersion curve. The accuracy of dispersion curves determined using this method is proven through field comparisons of the inverted shear-wave velocity (vs) profile with a downholevs profile.

/pdf/multichannel-analysis-of-surface-waves-yi4tcsl0li.pdf

Multichannel analysis of surface waves

The shear‐wave (S-wave) velocity of near‐surface materials (soil, rocks, pavement) and its effect on seismic‐wave propagation are of fundamental interest in many groundwater, engineering, and environmental studies. Rayleigh‐wave phase velocity of a layered‐earth model is a function of frequency and four groups of earth properties: P-wave velocity, S-wave velocity, density, and thickness of layers. Analysis of the Jacobian matrix provides a measure of dispersion‐curve sensitivity to earth properties. S-wave velocities are the dominant influence on a dispersion curve in a high‐frequency range (>5 Hz) followed by layer thickness. An iterative solution technique to the weighted equation proved very effective in the high‐frequency range when using the Levenberg‐Marquardt and singular‐value decomposition techniques. Convergence of the weighted solution is guaranteed through selection of the damping factor using the Levenberg‐Marquardt method. Synthetic examples demonstrated calculation efficiency and stability ...

/pdf/estimation-of-near-surface-shear-wave-velocity-by-inversion-29l31bs7zn.pdf

Estimation of near‐surface shear‐wave velocity by inversion of Rayleigh waves

Compare your culture to one of the cultures discussed in this unit. On a sheet of paper, list the cultures you are comparing and make one column titled “similarities,” and a second column titled “differences.” Now, list as many similarities and differences between the two as you can think of. Are there more similarities or differences between the two cultures you selected? Have you ever met anyone from this culture? How can you use this information to build greater respect between cultures?

Similarities and Differences

Detection of cracks on bridge decks is a vital task for maintaining the structural health and reliability of concrete bridges. Robotic imaging can be used to obtain bridge surface image sets for automated on-site analysis. We present a novel automated crack detection algorithm, the STRUM (spatially tuned robust multifeature) classifier, and demonstrate results on real bridge data using a state-of-the-art robotic bridge scanning system. By using machine learning classification, we eliminate the need for manually tuning threshold parameters. The algorithm uses robust curve fitting to spatially localize potential crack regions even in the presence of noise. Multiple visual features that are spatially tuned to these regions are computed. Feature computation includes examining the scale-space of the local feature in order to represent the information and the unknown salient scale of the crack. The classification results are obtained with real bridge data from hundreds of crack regions over two bridges. This comprehensive analysis shows a peak STRUM classifier performance of 95% compared with 69% accuracy from a more typical image-based approach. In order to create a composite global view of a large bridge span, an image sequence from the robot is aligned computationally to create a continuous mosaic. A crack density map for the bridge mosaic provides a computational description as well as a global view of the spatial patterns of bridge deck cracking. The bridges surveyed for data collection and testing include Long-Term Bridge Performance program's (LTBP) pilot project bridges at Haymarket, VA, USA, and Sacramento, CA, USA.

Automated Crack Detection on Concrete Bridges

As construction and remediation take place throughout New Jersey, the amount of construction and demolition debris increases, while the availability of landfill space decreases. A viable solution for disposing of these materials is to incorporate them into base and subbase applications. An extensive laboratory program was conducted on two types of construction and demolition debris: recycled concrete aggregate (RCA) and recycled asphalt pavement aggregate (RAP). These two materials were compared with dense-graded aggregate base coarse (DGABC), which currently is being used in roadway base applications in New Jersey. Both RCA and RAP were mixed at various percentages with the DGABC to evaluate whether an optimum mix blend could be formulated. The materials were evaluated under a traffic-type loading scheme that included resilient modulus and permanent deformation via cyclic triaxial testing. Laboratory tests indicated that the RAP, RCA, and DGABC blended materials all obtained higher resilient modulus values than the currently used DGABC. The permanent deformation results indicated that the RCA mixed samples obtained the lowest amount of permanent deformation when the material was cyclically loaded to 100,000 cycles. In contrast, the permanent deformation testing on RAP mixed samples resulted in the highest amount of permanent deformation at the same number of cycles. Existing models currently used for quarried base and subbase materials were used to predict the permanent deformation in the recycled materials. Laboratory test results indicated that these models could be used for predicting permanent deformation in unbound recycled materials.

Utilization of Construction and Demolition Debris Under Traffic-Type Loading in Base and Subbase Applications

https://deepblue.lib.umich.edu/bitstream/handle/2027.42/30325/0000727.pdf?sequence=1

Numerical simulation of the SASW test

This work was sponsored by the Federal Highway Administration in cooperation with the American Association of State Highway and Transportation Officials. It was conducted in the second Strategic Highway Research Program (SHRP 2), which is administered by the Transportation Research Board of the National Academies. The project was managed by Monica Starnes, Senior Program Officer for SHRP 2 Renewal.
The research reported herein was performed by the Center for Advanced Infrastructure and Transportation (CAIT) at Rutgers University (RU); the Center for Transportation Infrastructure Systems (CTIS) at The University of Texas at El Paso (UTEP); the Federal Institute for Materials Research and Testing (BAM), Germany; and Radar Systems International, Inc. (RSI). Rutgers University was the coordinator and contractor for this project. Dr. Nenad Gucunski, professor and chair of Civil and Environmental Engineering and director of CAIT’s Infrastructure Condition Monitoring Program at RU, was the principal investigator. The other authors of this report are Dr. Soheil Nazarian, professor of Civil Engineering and director of CTIS at UTEP; Dr. Deren Yuan, research associate at CTIS at UTEP; Dr. Herbert Wiggenhauser, head of Non-Destructive Testing (NDT) in Civil Engineering at BAM; Dr. Alexander Taffe, leader of Combination and Automation of NDT of Buildings at BAM; Dr. Parisa Shokouhi, Alexander von Humboldt Research Fellow, hosted by BAM; and Doria Kutrubes, president of RSI. Arezoo Imani and Touraj Tayebi, graduate research assistants at RU, helped conduct the validation testing, data analysis, and web manual content preparation. Hoda Azari, a graduate research assistant, and Dr. Manuel Celaya, a research engineer at UTEP, assisted in the validation study as well. Hooman Parvardeh, research assistant at RU, helped build the reference database and develop the framework for the web manual, while Erica Erlanger, a research staff member at RU, edited the manuscript. Their contributions are gratefully acknowledged.
The research team also gratefully acknowledges contributions of the participants from industry and academia in the validation testing. The participants include NDT Corporation; Germann Instruments; Olson Engineering; Dr. Ralf Arndt, National Research Council associate at FHWA Turner–Fairbank Highway Research Center; Ingegneria Dei Sistemi S.p.A. (IDS), Italy; 3D-RADAR, Norway; Dr. John Popovics, University of Illinois at Urbana-Champaign; Dr. Jinying Zhu, The University of Texas at Austin; Rutgers University—Center for Advanced Infrastructure and Transportation; and The University of Texas at El Paso—Center for Transportation Infrastructure Systems. The contributions of these participants were critical for the evaluation and grading of the performance of NDT technologies.

Nondestructive testing to identify concrete bridge deck deterioration

The usual inversion procedures for spectral analysis of surface waves (SASW) testing assume that only one Rayleigh mode is dominant, and thus fail to give reliable results for irregular soil profiles and some complex pavement systems. A new inversion algorithm is presented that is based on the numerical simulation of an actual SASW test, thus enabling the contributions of all types of waves and their modes to be taken into account. The algorithm also benefits from a nonlinear minimization technique in addition to the current linearized minimization to improve robustness of the inversion. Artificial irregular profiles, including a profile with a softer layer trapped between two stiffer layers, a profile with a stiffer layer sandwiched between two softer layers, and a profile with softer layers at larger depths, as well as two experimental pavement profiles have all been successfully inverted.

Nenad Gucunski

Papers

Automated Crack Detection on Concrete Bridges

Utilization of Construction and Demolition Debris Under Traffic-Type Loading in Base and Subbase Applications

Numerical simulation of the SASW test

Nondestructive testing to identify concrete bridge deck deterioration

Automated inversion procedure for spectral analysis of surface waves