Automated Software Testing in Machine Automation

The problem of software (SW) defaults is becoming more and more topical because of increasing amount of the SW and its complication. The majority of these defaults are founded during the test part that consumes about 40-50% of the development efforts. Test automation allows reducing the cost of this process and increasing testing effectiveness. In the middle of 1980 the first tools for automated testing appeared and the automated process was implemented in different kinds of SW testing. In short time, it became obviously, automated testing can cause many problems such as increasing product cost, decreasing reliability and even project fail. This thesis describes automated testing process, its concept, lists main problems, and gives an algorithm for automated test tools selection. Also this work presents an overview of the main automated test tools for embedded systems.

Kernel-Based Ranking. Methods for Learning and Performance Estimation

Machine learning provides tools for automated construction of predictive models in data intensive areas of engineering and science. The family of regularized kernel methods have in the recent years become one of the mainstream approaches to machine learning, due to a number of advantages the methods share. The approach provides theoretically well-founded solutions to the problems of under- and overfitting, allows learning from structured data, and has been empirically demonstrated to yield high predictive performance on a wide range of application domains. Historically, the problems of classification and regression have gained the majority of attention in the field. In this thesis we focus on another type of learning problem, that of learning to rank. In learning to rank, the aim is from a set of past observations to learn a ranking function that can order new objects according to how well they match some underlying criterion of goodness. As an important special case of the setting, we can recover the bipartite ranking problem, corresponding to maximizing the area under the ROC curve (AUC) in binary classification. Ranking applications appear in a large variety of settings, examples encountered in this thesis include document retrieval in web search, recommender systems, information extraction and automated parsing of natural language. We consider the pairwise approach to learning to rank, where ranking models are learned by minimizing the expected probability of ranking any two randomly drawn test examples incorrectly. The development of computationally efficient kernel methods, based on this approach, has in the past proven to be challenging. Moreover, it is not clear what techniques for estimating the predictive performance of learned models are the most reliable in the ranking setting, and how the techniques can be implemented efficiently. The contributions of this thesis are as follows. First, we develop RankRLS, a computationally efficient kernel method for learning to rank, that is based on minimizing a regularized pairwise least-squares loss. In addition to training methods, we introduce a variety of algorithms for tasks such as model selection, multi-output learning, and cross-validation, based on computational shortcuts from matrix algebra. Second, we improve the fastest known training method for the linear version of the RankSVM algorithm, which is one of the most well established methods for learning to rank. Third, we study the combination of the empirical kernel map and reduced set approximation, which allows the large-scale training of kernel machines using linear solvers, and propose computationally efficient solutions to cross-validation when using the approach. Next, we explore the problem of reliable cross-validation when using AUC as a performance criterion, through an extensive simulation study. We demonstrate that the proposed leave-pair-out cross-validation approach leads to more reliable performance estimation than commonly used alternative approaches. Finally, we present a case study on applying machine learning to information extraction from biomedical literature, which combines several of the approaches considered in the thesis. The thesis is divided into two parts. Part I provides the background for the research work and summarizes the most central results, Part II consists of the five original research articles that are the main contribution of this thesis.

Benefits of automated acclimatization during the pre-milking phase of lactating girolando cows

The aim of this paper was to evaluate the automated acclimatization effects during pre-milking of cows on thermal conditioning, physiology, milk production and cost-benefit of the automated adiabatic evaporative cooling system (AECS). The treatments 20; 30; 40 min and control consisted of exposure time of pre-milking cows to the automated AECS. Sixteen cows were used with an average daily milk yield of 19 kg, distributed in a 4 x 4 Latin square design. The Tukey's test (P<0.05) was used to compare the means. The environmental variables, dry bulb temperature (DBT, ºC) and relative humidity (RH, %), were recorded every minute, which allowed the determination of the system efficiency through the Temperature and Humidity Index (THI). The respiratory rate (RR), rectal temperature (RT) and temperature of the coat (TC) were measured before and after the acclimatization. The 40 min treatment kept the environmental variables and the comfort indexes within recommended limits. The physiological variables (RR, RT and TC) were lower in the 40 min treatment and reflected positively on milk production, which increased 3.66% compared to the control treatment. The system was profitable, having a 43 days return on investment and a monthly revenue increase of R$ 1,992.67.

Efficiency of distinct data mining algorithms for classifying stress level in piglets from their vocalization

Among the challenges of pig farming in today's competitive market, there is factor of the product traceability that ensures, among many points, animal welfare. Vocalization is a valuable tool to identify situations of stress in pigs, and it can be used in welfare records for traceability. The objective of this work was to identify stress in piglets using vocalization, calling this stress on three levels: no stress, moderate stress, and acute stress. An experiment was conducted on a commercial farm in the municipality of Holambra, São Paulo State , where vocalizations of twenty piglets were recorded during the castration procedure, and separated into two groups: without anesthesia and local anesthesia with lidocaine base. For the recording of acoustic signals, a unidirectional microphone was connected to a digital recorder, in which signals were digitized at a frequency of 44,100 Hz. For evaluation of sound signals, Praat® software was used, and different data mining algorithms were applied using Weka® software. The selection of attributes improved model accuracy, and the best attribute selection was used by applying Wrapper method, while the best classification algorithms were the k-NN and Naive Bayes. According to the results, it was possible to classify the level of stress in pigs through their vocalization.

Development of an automated bench top electronic penetrometer

The aim of this study was to develop a an automated bench top electronic penetrometer (ABEP) that allows performing tests with high rate of data acquisition (up to 19,600 Hz) and with variation of the displacement velocity and of the base area of cone penetration. The mechanical components of the ABEP are: a supporting structure, stepper motor, velocity reducer, double nut ball screw and six penetration probes. The electronic components of ABEP are: a "driver" to control rotation and displacement, power supply, three load cells, two software programs for running and storing data, and a data acquisition module. This penetrometer presented in compact size, portable and in 32 validation tests it proved easy to operate, and showed high resolution, high velocity in reliability in data collection. During the validation tests the equipment met the objectives, because the test results showed that the ABEP could use different sizes of cones, allowed work at different velocities, showed for velocity and displacement, were only 1.3% and 0.7%, respectively, at the highest velocity (30 mm s-1) and 1% and 0.9%, respectively for the lowest velocity (0.1 mm s-1).

Automated Purchase to Pay Process Value Modeling and Comparative Process Speeds

The importance of efficient supply chain management has increased due to globalization and the blurring of organizational boundaries. Various supply chain management technologies have been identified to drive organizational profitability and financial performance. Organizations have historically been concentrating heavily on the flow of goods and services, while less attention has been dedicated to the flow of money. While supply chains are becoming more transparent and automated, new opportunities for financial supply chain management have emerged through information technology solutions and comprehensive financial supply chain management strategies. This research concentrates on the end part of the purchasing process which is the handling of invoices. Efficient invoice processing can have an impact on organizations working capital management and thus provide companies with better readiness to face the challenges related to cash management. Leveraging a process mining solution the aim of this research was to examine the automated invoice handling process of four different organizations. The invoice data was collected from each organizations invoice processing system. The sample included all the invoices organizations had processed during the year 2012. The main objective was to find out whether e-invoices are faster to process in an automated invoice processing solution than scanned invoices (post entry into invoice processing solution). Other objectives included looking into the longest lead times between process steps and the impact of manual process steps on cycle time. Processing of invoices from maverick purchases was also examined. Based on the results of the research and previous literature on the subject, suggestions for improving the process were proposed. The results of the research indicate that scanned invoices were processed faster than e-invoices. This is mostly due to the more complex processing of e-invoices. It should be noted however that the manual tasks related to turning a paper invoice into electronic format through scanning are ignored in this research. The transitions with the longest lead times in the invoice handling process included both pre-automated steps as well as manual steps performed by humans. When the most common manual steps were examined in more detail, it was clear that these steps had a prolonging impact on the process. Regarding invoices from maverick purchases the evidence shows that these invoices were slower to process than invoices from purchases conducted through e-procurement systems and from preferred suppliers. Suggestions on how to improve the process included: increasing invoice matching, reducing of manual steps and leveraging of different value added services such as invoice validation service, mobile solutions and supply chain financing services. For companies that have already reaped all the process efficiencies the next step is to engage in collaborative financial supply chain management strategies that can benefit the whole supply chain.

Scalable algorithms for height field illumination

Global illumination algorithms are at the center of realistic image synthesis and account for non-trivial light transport and occlusion within scenes, such as indirect illumination, ambient occlusion, and environment lighting. Their computationally most difficult part is determining light source visibility at each visible scene point. Height fields, on the other hand, constitute an important special case of geometry and are mainly used to describe certain types of objects such as terrains and to map detailed geometry onto object surfaces. The geometry of an entire scene can also be approximated by treating the distance values of its camera projection as a screen-space height field. In order to shadow height fields from environment lights a horizon map is usually used to occlude incident light. We reduce the per-receiver time complexity of generating the horizon map on N N height fields from O(N) of the previous work to O(1) by using an algorithm that incrementally traverses the height field and reuses the information already gathered along the path of traversal. We also propose an accurate method to integrate the incident light within the limits given by the horizon map. Indirect illumination in height fields requires information about which other points are visible to each height field point. We present an algorithm to determine this intervisibility in a time complexity that matches the space complexity of the produced visibility information, which is in contrast to previous methods which scale in the height field size. As a result the amount of computation is reduced by two orders of magnitude in common use cases. Screen-space ambient obscurance methods approximate ambient obscurance from the depth bu er geometry and have been widely adopted by contemporary real-time applications. They work by sampling the screen-space geometry around each receiver point but have been previously limited to near- field effects because sampling a large radius quickly exceeds the render time budget. We present an algorithm that reduces the quadratic per-pixel complexity of previous methods to a linear complexity by line sweeping over the depth bu er and maintaining an internal representation of the processed geometry from which occluders can be efficiently queried. Another algorithm is presented to determine ambient obscurance from the entire depth bu er at each screen pixel. The algorithm scans the depth bu er in a quick pre-pass and locates important features in it, which are then used to evaluate the ambient obscurance integral accurately. We also propose an evaluation of the integral such that results within a few percent of the ray traced screen-space reference are obtained at real-time render times.

User-generated experiences: how automated platforms for content creation and sharing has transformed information access

Esitys KDK-käytettävyystyöryhmän järjestämässä seminaarissa: Miten käyttäjien toiveet haastavat metatietokäytäntöjämme? / How users' expectations challenge our metadata practices? 30.9.2014.

Efficient Optimization Algorithms for Nonlinear Data Analysis

Identification of low-dimensional structures and main sources of variation from multivariate data are fundamental tasks in data analysis. Many methods aimed at these tasks involve solution of an optimization problem. Thus, the objective of this thesis is to develop computationally efficient and theoretically justified methods for solving such problems. Most of the thesis is based on a statistical model, where ridges of the density estimated from the data are considered as relevant features. Finding ridges, that are generalized maxima, necessitates development of advanced optimization methods. An efficient and convergent trust region Newton method for projecting a point onto a ridge of the underlying density is developed for this purpose. The method is utilized in a differential equation-based approach for tracing ridges and computing projection coordinates along them. The density estimation is done nonparametrically by using Gaussian kernels. This allows application of ridge-based methods with only mild assumptions on the underlying structure of the data. The statistical model and the ridge finding methods are adapted to two different applications. The first one is extraction of curvilinear structures from noisy data mixed with background clutter. The second one is a novel nonlinear generalization of principal component analysis (PCA) and its extension to time series data. The methods have a wide range of potential applications, where most of the earlier approaches are inadequate. Examples include identification of faults from seismic data and identification of filaments from cosmological data. Applicability of the nonlinear PCA to climate analysis and reconstruction of periodic patterns from noisy time series data are also demonstrated. Other contributions of the thesis include development of an efficient semidefinite optimization method for embedding graphs into the Euclidean space. The method produces structure-preserving embeddings that maximize interpoint distances. It is primarily developed for dimensionality reduction, but has also potential applications in graph theory and various areas of physics, chemistry and engineering. Asymptotic behaviour of ridges and maxima of Gaussian kernel densities is also investigated when the kernel bandwidth approaches infinity. The results are applied to the nonlinear PCA and to finding significant maxima of such densities, which is a typical problem in visual object tracking.

Automated grading of left ventricular segmental wall motion by an artificial neural network using color kinesis images

The present study describes an auxiliary tool in the diagnosis of left ventricular (LV) segmental wall motion (WM) abnormalities based on color-coded echocardiographic WM images. An artificial neural network (ANN) was developed and validated for grading LV segmental WM using data from color kinesis (CK) images, a technique developed to display the timing and magnitude of global and regional WM in real time. We evaluated 21 normal subjects and 20 patients with LVWM abnormalities revealed by two-dimensional echocardiography. CK images were obtained in two sets of viewing planes. A method was developed to analyze CK images, providing quantitation of fractional area change in each of the 16 LV segments. Two experienced observers analyzed LVWM from two-dimensional images and scored them as: 1) normal, 2) mild hypokinesia, 3) moderate hypokinesia, 4) severe hypokinesia, 5) akinesia, and 6) dyskinesia. Based on expert analysis of 10 normal subjects and 10 patients, we trained a multilayer perceptron ANN using a back-propagation algorithm to provide automated grading of LVWM, and this ANN was then tested in the remaining subjects. Excellent concordance between expert and ANN analysis was shown by ROC curve analysis, with measured area under the curve of 0.975. An excellent correlation was also obtained for global LV segmental WM index by expert and ANN analysis (R² = 0.99). In conclusion, ANN showed high accuracy for automated semi-quantitative grading of WM based on CK images. This technique can be an important aid, improving diagnostic accuracy and reducing inter-observer variability in scoring segmental LVWM.

Cost-effective analysis of different algorithms for the diagnosis of hepatitis C virus infection

We compared the cost-benefit of two algorithms, recently proposed by the Centers for Disease Control and Prevention, USA, with the conventional one, the most appropriate for the diagnosis of hepatitis C virus (HCV) infection in the Brazilian population. Serum samples were obtained from 517 ELISA-positive or -inconclusive blood donors who had returned to Fundação Pró-Sangue/Hemocentro de São Paulo to confirm previous results. Algorithm A was based on signal-to-cut-off (s/co) ratio of ELISA anti-HCV samples that show s/co ratio ³95% concordance with immunoblot (IB) positivity. For algorithm B, reflex nucleic acid amplification testing by PCR was required for ELISA-positive or -inconclusive samples and IB for PCR-negative samples. For algorithm C, all positive or inconclusive ELISA samples were submitted to IB. We observed a similar rate of positive results with the three algorithms: 287, 287, and 285 for A, B, and C, respectively, and 283 were concordant with one another. Indeterminate results from algorithms A and C were elucidated by PCR (expanded algorithm) which detected two more positive samples. The estimated cost of algorithms A and B was US$21,299.39 and US$32,397.40, respectively, which were 43.5 and 14.0% more economic than C (US$37,673.79). The cost can vary according to the technique used. We conclude that both algorithms A and B are suitable for diagnosing HCV infection in the Brazilian population. Furthermore, algorithm A is the more practical and economical one since it requires supplemental tests for only 54% of the samples. Algorithm B provides early information about the presence of viremia.

Nutritional status and body composition after 6 months of patients switching from continuous ambulatorial peritoneal dialysis to automated peritoneal dialysis

Our objective was to determine if automated peritoneal dialysis (APD) leads to changes in nutritional parameters of patients treated by continuous ambulatory peritoneal dialysis (CAPD). Twenty-six patients (15 males; 50.5 ± 14.3 years) were evaluated during CAPD while training for APD and after 3 and 6 months of APD. Body fat was assessed by the sum of skinfold thickness and the other body compartments were assessed by bioelectrical impedance. During the 6-month follow-up, 12 patients gained more than 1 kg (GW group), 8 patients lost more than 1 kg (LW group), and 6 patients maintained body weight (MW group). Except for length on dialysis that was longer for the LW group compared with the GW group, no other differences were found between the groups at baseline. After 6 months on APD, the LW group had a reduction in body fat (24.5 ± 7.7 vs 22.1 ± 7.3 kg; P = 0.01), body cell mass (22.6 ± 6.2 vs 21.6 ± 5.8 kg, P = 0.02) and phase angle (5.4 ± 0.9 vs 5.1 ± 0.8 degrees, P = 0.004). In the GW group, body fat (25 ± 7.6 vs 27.2 ± 7.6 kg, P = 0.001) and body cell mass (20.1 ± 3.9 vs 20.8 ± 4.0 kg, P = 0.05) were increased. In the present study, different patterns of change in body composition were found. The length of previous dialysis treatment seems to be the most important factor in determining these nutritional modifications.