Anomaly Detection in Noisy Images

Finding rare events in multidimensional data is an important detection problem that has applications in many fields, such as risk estimation in insurance industry, finance, flood prediction, medical diagnosis, quality assurance, security, or safety in transportation. The occurrence of such anomalies is so infrequent that there is usually not enough training data to learn an accurate statistical model of the anomaly class. In some cases, such events may have never been observed, so the only information that is available is a set of normal samples and an assumed pairwise similarity function. Such metric may only be known up to a certain number of unspecified parameters, which would either need to be learned from training data, or fixed by a domain expert. Sometimes, the anomalous condition may be formulated algebraically, such as a measure exceeding a predefined threshold, but nuisance variables may complicate the estimation of such a measure. Change detection methods used in time series analysis are not easily extendable to the multidimensional case, where discontinuities are not localized to a single point. On the other hand, in higher dimensions, data exhibits more complex interdependencies, and there is redundancy that could be exploited to adaptively model the normal data. In the first part of this dissertation, we review the theoretical framework for anomaly detection in images and previous anomaly detection work done in the context of crack detection and detection of anomalous components in railway tracks. In the second part, we propose new anomaly detection algorithms. The fact that curvilinear discontinuities in images are sparse with respect to the frame of shearlets, allows us to pose this anomaly detection problem as basis pursuit optimization. Therefore, we pose the problem of detecting curvilinear anomalies in noisy textured images as a blind source separation problem under sparsity constraints, and propose an iterative shrinkage algorithm to solve it. Taking advantage of the parallel nature of this algorithm, we describe how this method can be accelerated using graphical processing units (GPU). Then, we propose a new method for finding defective components on railway tracks using cameras mounted on a train. We describe how to extract features and use a combination of classifiers to solve this problem. Then, we scale anomaly detection to bigger datasets with complex interdependencies. We show that the anomaly detection problem naturally fits in the multitask learning framework. The first task consists of learning a compact representation of the good samples, while the second task consists of learning the anomaly detector. Using deep convolutional neural networks, we show that it is possible to train a deep model with a limited number of anomalous examples. In sequential detection problems, the presence of time-variant nuisance parameters affect the detection performance. In the last part of this dissertation, we present a method for adaptively estimating the threshold of sequential detectors using Extreme Value Theory on a Bayesian framework. Finally, conclusions on the results obtained are provided, followed by a discussion of possible future work.

Arquitetura para o desenvolvimento de unidades de medição fasorial sincronizada no monitoramento a nível de distribuição

This work presents a low cost architecture for development of synchronized phasor measurement units (PMU). The device is intended to be connected in the low voltage grid, which allows the monitoring of transmission and distribution networks. Developments of this project include a complete PMU, with instrumentation module for use in low voltage network, GPS module to provide the sync signal and time stamp for the measures, processing unit with the acquisition system, phasor estimation and formatting data according to the standard and finally, communication module for data transmission. For the development and evaluation of the performance of this PMU, it was developed a set of applications in LabVIEW environment with specific features that let analyze the behavior of the measures and identify the sources of error of the PMU, as well as to apply all the tests proposed by the standard. The first application, useful for the development of instrumentation, consists of a function generator integrated with an oscilloscope, which allows the generation and acquisition of signals synchronously, in addition to the handling of samples. The second and main, is the test platform, with capabality of generating all tests provided by the synchronized phasor measurement standard IEEE C37.118.1, allowing store data or make the analysis of the measurements in real time. Finally, a third application was developed to evaluate the results of the tests and generate calibration curves to adjust the PMU. The results include all the tests proposed by synchrophasors standard and an additional test that evaluates the impact of noise. Moreover, through two prototypes connected to the electrical installation of consumers in same distribution circuit, it was obtained monitoring records that allowed the identification of loads in consumer and power quality analysis, beyond the event detection at the distribution and transmission levels.

Calibration and simulations of SIXS-P's response to energetic particles

The Solar Intensity X-ray and particle Spectrometer (SIXS) on board BepiColombo's Mercury Planetary Orbiter (MPO) will study solar energetic particles moving towards Mercury and solar X-rays on the dayside of Mercury. The SIXS instrument consists of two detector sub-systems; X-ray detector SIXS-X and particle detector SIXS-P. The SIXS-P subdetector will detect solar energetic electrons and protons in a broad energy range using a particle telescope approach with five outer Si detectors around a central CsI(Tl) scintillator. The measurements made by the SIXS instrument are necessary for other instruments on board the spacecraft. SIXS data will be used to study the Solar X-ray corona, solar flares, solar energetic particles, the Hermean magnetosphere, and solar eruptions. The SIXS-P detector was calibrated by comparing experimental measurement data from the instrument with Geant4 simulation data. Calibration curves were produced for the different side detectors and the core scintillator for electrons and protons, respectively. The side detector energy response was found to be linear for both electrons and protons. The core scintillator energy response to protons was found to be non-linear. The core scintillator calibration for electrons was omitted due to insufficient experimental data. The electron and proton acceptance of the SIXS-P detector was determined with Geant4 simulations. Electron and proton energy channels are clean in the main energy range of the instrument. At higher energies, protons and electrons produce non-ideal response in the energy channels. Due to the limited bandwidth of the spacecraft's telemetry, the particle measurements made by SIXS-P have to be pre-processed in the data processing unit of the SIXS instrument. A lookup table was created for the pre-processing of data with Geant4 simulations, and the ability of the lookup table to provide spectral information from a simulated electron event was analysed. The lookup table produces clean electron and proton channels and is able to separate protons and electrons. Based on a simulated solar energetic electron event, the incident electron spectrum cannot be determined from channel particle counts with a standard analysis method.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Improving drug discovery using a neural networks based parallel scoring function

Virtual Screening (VS) methods can considerably aid clinical research, predicting how ligands interact with drug targets. Most VS methods suppose a unique binding site for the target, but it has been demonstrated that diverse ligands interact with unrelated parts of the target and many VS methods do not take into account this relevant fact. This problem is circumvented by a novel VS methodology named BINDSURF that scans the whole protein surface to find new hotspots, where ligands might potentially interact with, and which is implemented in massively parallel Graphics Processing Units, allowing fast processing of large ligand databases. BINDSURF can thus be used in drug discovery, drug design, drug repurposing and therefore helps considerably in clinical research. However, the accuracy of most VS methods is constrained by limitations in the scoring function that describes biomolecular interactions, and even nowadays these uncertainties are not completely understood. In order to solve this problem, we propose a novel approach where neural networks are trained with databases of known active (drugs) and inactive compounds, and later used to improve VS predictions.

Adaptive Scalable SVD Unit for Fast Processing of Large LSE Problems

Singular Value Decomposition (SVD) is a key linear algebraic operation in many scientific and engineering applications. In particular, many computational intelligence systems rely on machine learning methods involving high dimensionality datasets that have to be fast processed for real-time adaptability. In this paper we describe a practical FPGA (Field Programmable Gate Array) implementation of a SVD processor for accelerating the solution of large LSE problems. The design approach has been comprehensive, from the algorithmic refinement to the numerical analysis to the customization for an efficient hardware realization. The processing scheme rests on an adaptive vector rotation evaluator for error regularization that enhances convergence speed with no penalty on the solution accuracy. The proposed architecture, which follows a data transfer scheme, is scalable and based on the interconnection of simple rotations units, which allows for a trade-off between occupied area and processing acceleration in the final implementation. This permits the SVD processor to be implemented both on low-cost and highend FPGAs, according to the final application requirements.

Memorability as a measure of processing: a unit analysis of prose and list learning.

The percentage of subjects recalling each unit in a list or prose passage is considered as a dependent measure. When the same units are recalled in different tasks, processing is assumed to be the same; when different units are recalled, processing is assumed to be different. Two collections of memory tasks are presented, one for lists and one for prose. The relations found in these two collections are supported by an extensive reanalysis of the existing prose memory literature. The same set of words were learned by 13 different groups of subjects under 13 different conditions. Included were intentional free-recall tasks, incidental free recall following lexical decision, and incidental free recall following ratings of orthographic distinctiveness and emotionality. Although the nine free-recall tasks varied widely with regard to the amount of recall, the relative probability of recall for the words was very similar among the tasks. Imagery encoding and recognition produced relative probabilities of recall that were different from each other and from the free-recall tasks. Similar results were obtained with a prose passage. A story was learned by 13 different groups of subjects under 13 different conditions. Eight free-recall tasks, which varied with respect to incidental or intentional learning, retention interval, and the age of the subjects, produced similar relative probabilities of recall, whereas recognition and prompted recall produced relative probabilities of recall that were different from each other and from the free-recall tasks. A review of the prose literature was undertaken to test the generality of these results. Analysis of variance is the most common statistical procedure in this literature. If the relative probability of recall of units varied across conditions, a units by condition interaction would be expected. For the 12 studies that manipulated retention interval, an average of 21% of the variance was accounted for by the main effect of retention interval, 17% by the main effect of units, and only 2% by the retention interval by units interaction. Similarly, for the 12 studies that varied the age of the subjects, 6% of the variance was accounted for by the main effect of age, 32% by the main effect of units, and only 1% by the interaction of age by units.(ABSTRACT TRUNCATED AT 400 WORDS)

Initial cord blood unit volume affects mononuclear cell and CD34+ cell-processing efficiency in a non-linear fashion

Umbilical cord blood (UCB) is a source of hematopoietic stem cells that initially was used exclusively for the hematopoietic reconstitution of pediatric patients. It is now suggested for use for adults as well, a fact that increases the pressure to obtain units with high cellularity. Therefore, the optimization of UCB processing is a priority.

The documentation of clinical psychotropic drug trials; [a workbook and user's guide to understanding and interpreting the data processing and output of the Biometric Laboratory Information Processing System (BLIPS), George Washington University, and the Early Clinical Drug Evaluation Unit (ECDEU), NIMH.

On cover of v. 2: Early clinical drug evaluation units, analyses.

Direct support and general support maintenance repair parts and special tools lists (including depot maintenance repair parts and special tools) for temperature control unit, photographic processing FH-19A (NSN 6740-420-5148).

"15 August 1980."

Planned unit development : processing guide -- April 1970-

Loose-leaf for updating.

Soundcipher : a music and sound library for processing

SoundCipher is a software library written in the Java language that adds important music and sound features to the Processing environment that is widely used by media artists and otherwise has an orientation toward computational graphics. This article introduces the SoundCipher library and its features, describes its influences and design intentions, and positions it within the field of computer music programming tools. SoundCipher enables the rich history of algorithmic music techniques to be accessible within one of today’s most popular media art platforms. It also provides an accessible means for learning to create algorithmic music and sound programs.

Development of a high-speed sensing and detection system for automatic removal of packages with leaky seals from a high-speed food processing and packaging line

Contamination of packaged foods due to micro-organisms entering through air leaks can cause serious public health issues and cost companies large amounts of money due to product recalls, consumer impact and subsequent loss of market share. The main source of contamination is leaks in packaging which allow air, moisture and microorganisms to enter the package. In the food processing and packaging industry worldwide, there is an increasing demand for cost effective state of the art inspection technologies that are capable of reliably detecting leaky seals and delivering products at six-sigma. The new technology will develop non-destructive testing technology using digital imaging and sensing combined with a differential vacuum technique to assess seal integrity of food packages on a high-speed production line. The cost of leaky packages in Australian food industries is estimated close to AUD $35 Million per year. Contamination of packaged foods due to micro-organisms entering through air leaks can cause serious public health issues and cost companies large sums of money due to product recalls, compensation claims and loss of market share. The main source of contamination is leaks in packaging which allow air, moisture and micro-organisms to enter the package. Flexible plastic packages are widely used, and are the least expensive form of retaining the quality of the product. These packets can be used to seal, and therefore maximise, the shelf life of both dry and moist products. The seals of food packages need to be airtight so that the food content is not contaminated due to contact with microorganisms that enter as a result of air leakage. Airtight seals also extend the shelf life of packaged foods, and manufacturers attempt to prevent food products with leaky seals being sold to consumers. There are many current NDT (non-destructive testing) methods of testing the seal of flexible packages best suited to random sampling, and for laboratory purposes. The three most commonly used methods are vacuum/pressure decay, bubble test, and helium leak detection. Although these methods can detect very fine leaks, they are limited by their high processing time and are not viable in a production line. Two nondestructive in-line packaging inspection machines are currently available and are discussed in the literature review. The detailed design and development of the High-Speed Sensing and Detection System (HSDS) is the fundamental requirement of this project and the future prototype and production unit. Successful laboratory testing was completed and a methodical design procedure was needed for a successful concept. The Mechanical tests confirmed the vacuum hypothesis and seal integrity with good consistent results. Electrically, the testing also provided solid results to enable the researcher to move the project forward with a certain amount of confidence. The laboratory design testing allowed the researcher to confirm theoretical assumptions before moving into the detailed design phase. Discussion on the development of the alternative concepts in both mechanical and electrical disciplines enables the researcher to make an informed decision. Each major mechanical and electrical component is detailed through the research and design process. The design procedure methodically works through the various major functions both from a mechanical and electrical perspective. It opens up alternative ideas for the major components that although are sometimes not practical in this application, show that the researcher has exhausted all engineering and functionality thoughts. Further concepts were then designed and developed for the entire HSDS unit based on previous practice and theory. In the future, it would be envisaged that both the Prototype and Production version of the HSDS would utilise standard industry available components, manufactured and distributed locally. Future research and testing of the prototype unit could result in a successful trial unit being incorporated in a working food processing production environment. Recommendations and future works are discussed, along with options in other food processing and packaging disciplines, and other areas in the non-food processing industry.

Distributed data acquisition unit with microsecond-accurate wireless clock synchronisation

This paper describes the implementation of the first portable, embedded data acquisition unit (BabelFuse) that is able to acquire and timestamp generic sensor data and trigger General Purpose I/O (GPIO) events against a microsecond-accurate wirelessly-distributed ‘global’ clock. A significant issue encountered when fusing data received from multiple sensors is the accuracy of the timestamp associated with each piece of data. This is particularly important in applications such as Simultaneous Localisation and Mapping (SLAM) where vehicle velocity forms an important part of the mapping algorithms; on fast-moving vehicles, even millisecond inconsistencies in data timestamping can produce errors which need to be compensated for. The timestamping problem is compounded in a robot swarm environment especially if non-deterministic communication hardware (such as IEEE-802.11-based wireless) and inaccurate clock synchronisation protocols are used. The issue of differing timebases makes correlation of data difficult and prevents the units from reliably performing synchronised operations or manoeuvres. By utilising hardware-assisted timestamping, clock synchronisation protocols based on industry standards and firmware designed to minimise indeterminism, an embedded data acquisition unit capable of microsecond-level clock synchronisation is presented.