Evolution of classifiers for pitch estimation of piano music using cartesian genetic programming

Pitch Estimation, also known as Fundamental Frequency (F0) estimation, has been a popular research topic for many years, and is still investigated nowadays. The goal of Pitch Estimation is to find the pitch or fundamental frequency of a digital recording of a speech or musical notes. It plays an important role, because it is the key to identify which notes are being played and at what time. Pitch Estimation of real instruments is a very hard task to address. Each instrument has its own physical characteristics, which reflects in different spectral characteristics. Furthermore, the recording conditions can vary from studio to studio and background noises must be considered. This dissertation presents a novel approach to the problem of Pitch Estimation, using Cartesian Genetic Programming (CGP).We take advantage of evolutionary algorithms, in particular CGP, to explore and evolve complex mathematical functions that act as classifiers. These classifiers are used to identify piano notes pitches in an audio signal. To help us with the codification of the problem, we built a highly flexible CGP Toolbox, generic enough to encode different kind of programs. The encoded evolutionary algorithm is the one known as 1 + , and we can choose the value for . The toolbox is very simple to use. Settings such as the mutation probability, number of runs and generations are configurable. The cartesian representation of CGP can take multiple forms and it is able to encode function parameters. It is prepared to handle with different type of fitness functions: minimization of f(x) and maximization of f(x) and has a useful system of callbacks. We trained 61 classifiers corresponding to 61 piano notes. A training set of audio signals was used for each of the classifiers: half were signals with the same pitch as the classifier (true positive signals) and the other half were signals with different pitches (true negative signals). F-measure was used for the fitness function. Signals with the same pitch of the classifier that were correctly identified by the classifier, count as a true positives. Signals with the same pitch of the classifier that were not correctly identified by the classifier, count as a false negatives. Signals with different pitch of the classifier that were not identified by the classifier, count as a true negatives. Signals with different pitch of the classifier that were identified by the classifier, count as a false positives. Our first approach was to evolve classifiers for identifying artifical signals, created by mathematical functions: sine, sawtooth and square waves. Our function set is basically composed by filtering operations on vectors and by arithmetic operations with constants and vectors. All the classifiers correctly identified true positive signals and did not identify true negative signals. We then moved to real audio recordings. For testing the classifiers, we picked different audio signals from the ones used during the training phase. For a first approach, the obtained results were very promising, but could be improved. We have made slight changes to our approach and the number of false positives reduced 33%, compared to the first approach. We then applied the evolved classifiers to polyphonic audio signals, and the results indicate that our approach is a good starting point for addressing the problem of Pitch Estimation.

The effect of a Computerised Decision Support System (CDSS) on compliance with the prehospital assessment process: results of an interrupted time-series study

BACKGROUND: Errors in the decision-making process are probably the main threat to patient safety in the prehospital setting. The reason can be the change of focus in prehospital care from the traditional "scoop and run" practice to a more complex assessment and this new focus imposes real demands on clinical judgment. The use of Clinical Guidelines (CG) is a common strategy for cognitively supporting the prehospital providers. However, there are studies that suggest that the compliance with CG in some cases is low in the prehospital setting. One possible way to increase compliance with guidelines could be to introduce guidelines in a Computerized Decision Support System (CDSS). There is limited evidence relating to the effect of CDSS in a prehospital setting. The present study aimed to evaluate the effect of CDSS on compliance with the basic assessment process described in the prehospital CG and the effect of On Scene Time (OST). METHODS: In this time-series study, data from prehospital medical records were collected on a weekly basis during the study period. Medical records were rated with the guidance of a rating protocol and data on OST were collected. The difference between baseline and the intervention period was assessed by a segmented regression. RESULTS: In this study, 371 patients were included. Compliance with the assessment process described in the prehospital CG was stable during the baseline period. Following the introduction of the CDSS, compliance rose significantly. The post-intervention slope was stable. The CDSS had no significant effect on OST. CONCLUSIONS: The use of CDSS in prehospital care has the ability to increase compliance with the assessment process of patients with a medical emergency. This study was unable to demonstrate any effects of OST.

Machine learning techniques for implicit interaction using mobile sensors

Interactions in mobile devices normally happen in an explicit manner, which means that they are initiated by the users. Yet, users are typically unaware that they also interact implicitly with their devices. For instance, our hand pose changes naturally when we type text messages. Whilst the touchscreen captures finger touches, hand movements during this interaction however are unused. If this implicit hand movement is observed, it can be used as additional information to support or to enhance the users’ text entry experience. This thesis investigates how implicit sensing can be used to improve existing, standard interaction technique qualities. In particular, this thesis looks into enhancing front-of-device interaction through back-of-device and hand movement implicit sensing. We propose the investigation through machine learning techniques. We look into problems on how sensor data via implicit sensing can be used to predict a certain aspect of an interaction. For instance, one of the questions that this thesis attempts to answer is whether hand movement during a touch targeting task correlates with the touch position. This is a complex relationship to understand but can be best explained through machine learning. Using machine learning as a tool, such correlation can be measured, quantified, understood and used to make predictions on future touch position. Furthermore, this thesis also evaluates the predictive power of the sensor data. We show this through a number of studies. In Chapter 5 we show that probabilistic modelling of sensor inputs and recorded touch locations can be used to predict the general area of future touches on touchscreen. In Chapter 7, using SVM classifiers, we show that data from implicit sensing from general mobile interactions is user-specific. This can be used to identify users implicitly. In Chapter 6, we also show that touch interaction errors can be detected from sensor data. In our experiment, we show that there are sufficient distinguishable patterns between normal interaction signals and signals that are strongly correlated with interaction error. In all studies, we show that performance gain can be achieved by combining sensor inputs.

La concentración de calcio iónico se asocia a la presencia de fibrilación auricular post operatoria en pacientes llevados a revascularización miocardica

Objetivo. Determinar en un grupo de pacientes llevados a revascularización miocárdica si existió asociación entre la presencia de niveles de calcio iónico inferiores a 1,1 en las 24 horas del post operatorio y la ocurrencia de fibrilación auricular post operatoria. Metodología. Estudio observacional, analítico de casos y controles, en donde de manera consecutiva se incluyeron 110 sujetos (57 en el grupo de casos con presencia de fibrilación auricular post operatoria y 54 en el grupo de controles sin evidencia de fibrilación auricular) estos sujetos fueron llevados a revascularización miocárdica en la Fundación Cardioinfantil en los años 2010 a 2015. Resultados. Hubo 13 casos de fibrilación auricular post operatoria en pacientes con niveles de calcio iónico inferiores a 1,1 mmol/l en las primeras 24 horas del post operatorio OR: 0,5, IC (0,2-1,2) p: 0,1. Sin determinarse asociación por limitaciones del estudio, sin embargo un 29% de los pacientes con fibrilación auricular tuvieron niveles de calcio inferiores a 1,1 mmol/l en las primeras 24 horas del post operatorio, este valor aumenta a 31% cuando se analizan por separado los valores de calcio obtenidos a las 12 horas. Conclusiones. Aunque no se logró determinar asociación entre la fibrilación auricular post operatoria y las concentraciones de calcio iónico, de manera exploratoria se pudo establecer que un 29% de los pacientes con fibrilación auricular tuvieron concentraciones de calcio iónico inferiores a 1,1 mmol/l, este valor aumenta a 31% cuando se analizan los niveles de calcio iónico por separado.

El dragón chino en Angola: la diplomacia cultural como una herramienta de construcción de identidad

El creciente interés de China por África ha modificado y estructurado una nueva política exterior, en donde el fortalecimiento de las relaciones políticas y económicas se ve ligado al uso de la diplomacia cultural como una herramienta de atracción. Teniendo en cuenta lo anterior, la presente investigación tiene por objetivo principal indagar cómo China construye una identidad a través de su diplomacia cultural en Angola, demostrando así, que este país utiliza sus costumbres, principios y normas para establecer una identidad de rol en la que se asume como una potencia que debe cooperar. No obstante, sus intereses van más allá de la cooperación al profundizar en relaciones de confianza que lo beneficien política y económicamente. Haciendo un uso del concepto de Imperialismo, la investigación mostrará las limitaciones y los vacíos de la noción de identidad para explicar acciones chinas en Angola, mostrando cómo se hacen uso de herramientas imperialistas para un beneficio propio.

Study of Rapid Alkalinization Factor (RALF)genes as plant susceptibility agents during plant-pathogen interaction in strawberry

Rapid Alkalinization Factor (RALF) are cysteins-rich peptides ubiquitous in plant kingdom. They play multiple roles as hormone signals and recently their involvement in host-pathogen crosstalk as negative regulator of immunity in Arabidopsis has also been recognized. In addition, RALF homologue peptides are secreted by different fungal pathogens as effectors during early stages of infections. The aim of this work was to characterize RALF genes as susceptibility factors during plant pathogen interaction in strawberry. For this, the genomic organization of the RALF gene families in the octoploid strawberry (Fragaria × ananassa) and the re-annotated genome of Fragaria vesca were described , identifying 13 member in F. vesca (FvRALF) and 50 members in F. x ananassa (FaRALF). The changes in expression of fruit FaRALF genes was investigated upon infection with C.acutatum and B. cinerea showing that, among RALF genes expressed in fruit, FaRALF3 was the only one upregulated by fungal infection in the ripe stage. A role of FaRALF3 as susceptibility gene was then assessed trough Agrobacterium-mediated transient FaRALF3 overexpression and silencing in fruits, revealing that FaRALF3 expression promotes fungal growth and hyphae penetration in host tissues. In silico analysis was used to identify distinct pathogen inducible elements upstream of the FaRALF3 gene. Agroinfiltration of strawberry fruit with deletion constructs of the FaRALF3 promoter identified a 5’ region required for FaRALF3 expression in fruit, but failed to identify a region responsible for fungal induced expression. Furthermore, FaRALF3 and strawberry receptor FERONIA (FaMRLK47) were heterologously expressed in E. coli in order to purify active proteins forms and study RALF-FERONIA interaction in strawberry. However, it was not possible to obtain pure and active proteins. Finally RNAi transgenic plants silenced for the FvRALF13 gene were genotypically and phenotypically characterized suggesting a role of FvRALF13 in flowering time regulation and reproductive organs development.

Advanced Mission Synthesis Algorithms for Vibration-based Accelerated Life-testing

In the field of vibration qualification testing, with the popular Random Control mode of shakers, the specimen is excited by random vibrations typically set in the form of a Power Spectral Density (PSD). The corresponding signals are stationary and Gaussian, i.e. featuring a normal distribution. Conversely, real-life excitations are frequently non-Gaussian, exhibiting high peaks and/or burst signals and/or deterministic harmonic components. The so-called kurtosis is a parameter often used to statistically describe the occurrence and significance of high peak values in a random process. Since the similarity between test input profiles and real-life excitations is fundamental for qualification test reliability, some methods of kurtosis-control can be implemented to synthesize realistic (non-Gaussian) input signals. Durability tests are performed to check the resistance of a component to vibration-based fatigue damage. A procedure to synthesize test excitations which starts from measured data and preserves both the damage potential and the characteristics of the reference signals is desirable. The Fatigue Damage Spectrum (FDS) is generally used to quantify the fatigue damage potential associated with the excitation. The signal synthesized for accelerated durability tests (i.e. with a limited duration) must feature the same FDS as the reference vibration computed for the component’s expected lifetime. Current standard procedures are efficient in synthesizing signals in the form of a PSD, but prove inaccurate if reference data are non-Gaussian. This work presents novel algorithms for the synthesis of accelerated durability test profiles with prescribed FDS and a non-Gaussian distribution. An experimental campaign is conducted to validate the algorithms, by testing their accuracy, robustness, and practical effectiveness. Moreover, an original procedure is proposed for the estimation of the fatigue damage potential, aiming to minimize the computational time. The research is thus supposed to improve both the effectiveness and the efficiency of excitation profile synthesis for accelerated durability tests.

Investigation of organic semiconductor/water interfaces for optobioelectronic devices

The thesis investigates the potential of photoactive organic semiconductors as a new class of materials for developing bioelectronic devices that can convert light into biological signals. The materials can be either small molecules or polymers. When these materials interact with aqueous biological fluids, they give rise to various electrochemical phenomena, including photofaradaic or photocapacitive processes, depending on whether photogenerated charges participate in redox processes or accumulate at an interface. The thesis starts by studying the behavior of the H2Pc/PTCDI molecular p/n thin-film heterojunction in contact with aqueous electrolyte. An equivalent circuit model is developed, explaining the measurements and predicting behavior in wireless mode. A systematic study on p-type polymeric thin-films is presented, comparing rr-P3HT with two low bandgap conjugated polymers: PBDB-T and PTB7. The results demonstrate that PTB7 has superior photocurrent performance due to more effective electron-transfer onto acceptor states in solution. Furthermore, the thesis addresses the issue of photovoltage generation for wireless photoelectrodes. An analytical model based on photoactivated charge-transfer across the organic-semiconductor/water interface is developed, explaining the large photovoltages observed for polymeric p-type semiconductor electrodes in water. Then, flash-precipitated nanoparticles made of the same three photoactive polymers are investigated, assessing the influence of fabrication parameters on the stability, structure, and energetics of the nanoparticles. Photocathodic current generation and consequent positive charge accumulation is also investigated. Additionally, newly developed porous P3HT thin-films are tested, showing that porosity increases both the photocurrent and the semiconductor/water interfacial capacity. Finally, the thesis demonstrates the biocompatibility of the materials in in-vitro experiments and shows safe levels of photoinduced intracellular ROS production with p-type polymeric thin-films and nanoparticles. The findings highlight the potential of photoactive organic semiconductors in the development of optobioelectronic devices, demonstrating their ability to convert light into biological signals and interface with biological fluids.

Applying machine learning: a multi-role perspective

Machine (and deep) learning technologies are more and more present in several fields. It is undeniable that many aspects of our society are empowered by such technologies: web searches, content filtering on social networks, recommendations on e-commerce websites, mobile applications, etc., in addition to academic research. Moreover, mobile devices and internet sites, e.g., social networks, support the collection and sharing of information in real time. The pervasive deployment of the aforementioned technological instruments, both hardware and software, has led to the production of huge amounts of data. Such data has become more and more unmanageable, posing challenges to conventional computing platforms, and paving the way to the development and widespread use of the machine and deep learning. Nevertheless, machine learning is not only a technology. Given a task, machine learning is a way of proceeding (a way of thinking), and as such can be approached from different perspectives (points of view). This, in particular, will be the focus of this research. The entire work concentrates on machine learning, starting from different sources of data, e.g., signals and images, applied to different domains, e.g., Sport Science and Social History, and analyzed from different perspectives: from a non-data scientist point of view through tools and platforms; setting a problem stage from scratch; implementing an effective application for classification tasks; improving user interface experience through Data Visualization and eXtended Reality. In essence, not only in a quantitative task, not only in a scientific environment, and not only from a data-scientist perspective, machine (and deep) learning can do the difference.

[In search of] Digital biomarkers for objective pain assessment

Pain is a highly complex phenomenon involving intricate neural systems, whose interactions with other physiological mechanisms are not fully understood. Standard pain assessment methods, relying on verbal communication, often fail to provide reliable and accurate information, which poses a critical challenge in the clinical context. In the era of ubiquitous and inexpensive physiological monitoring, coupled with the advancement of artificial intelligence, these new tools appear as the natural candidates to be tested to address such a challenge. This thesis aims to conduct experimental research to develop digital biomarkers for pain assessment. After providing an overview of the state-of-the-art regarding pain neurophysiology and assessment tools, methods for appropriately conditioning physiological signals and controlling confounding factors are presented. The thesis focuses on three different pain conditions: cancer pain, chronic low back pain, and pain experienced by patients undergoing neurorehabilitation. The approach presented in this thesis has shown promise, but further studies are needed to confirm and strengthen these results. Prior to developing any models, a preliminary signal quality check is essential, along with the inclusion of personal and health information in the models to limit their confounding effects. A multimodal approach is preferred for better performance, although unimodal analysis has revealed interesting aspects of the pain experience. This approach can enrich the routine clinical pain assessment procedure by enabling pain to be monitored when and where it is actually experienced, and without the involvement of explicit communication,. This would improve the characterization of the pain experience, aid in antalgic therapy personalization, and bring timely relief, with the ultimate goal of improving the quality of life of patients suffering from pain.

Signals transducers and activators of transcription (STAT)-induced STAT inhibitor-1 (SSI-1)/suppressor of cytokine signaling-1 (SOCS-1) suppresses tumor necrosis factor α-induced cell death in fibroblasts

Signal transducers and activators of transcription (STAT)-induced STAT inhibitor-1 [SSI-1; also known as suppressor of cytokine signaling-1 (SOCS-1)] was identified as a negative feedback regulator of Janus kinase-STAT signaling. We previously generated mice lacking the SSI-1 gene (SSI-1 −/−) and showed that thymocytes and splenocytes in SSI-1 −/− mice underwent accelerated apoptosis. In this paper, we show that murine embryonic fibroblasts lacking the SSI-1 gene are more sensitive than their littermate controls to tumor necrosis factor-α (TNF-α)-induced cell death. In addition, L929 cells forced to express SSI-1 (L929/SSI-1), but not SSI-3 or SOCS-5, are resistant to TNF-α-induced cell death. Furthermore L929/SSI-1 cells treated with TNF-α sustain the activation of p38 mitogen-activated protein (MAP) kinase. In contrast, SSI-1 −/− murine embryonic fibroblasts treated with TNF-α show hardly any activation of p38 MAP kinase. These findings suggest that SSI-1 suppresses TNF-α-induced cell death, which is mediated by p38 MAP kinase signaling.

Enhanced Glucose-induced Intracellular Signaling Promotes Insulin Hypersecretion: Pancreatic Beta-cell Functional Adaptations In A Model Of Genetic Obesity And Prediabetes.

Obesity is associated with insulin resistance and is known to be a risk factor for type-2 diabetes. In obese individuals, pancreatic beta-cells try to compensate for the increased insulin demand in order to maintain euglycemia. Most studies have reported that this adaptation is due to morphological changes. However, the involvement of beta-cell functional adaptations in this process needs to be clarified. For this purpose, we evaluated different key steps in the glucose-stimulated insulin secretion (GSIS) in intact islets from female ob/ob obese mice and lean controls. Obese mice showed increased body weight, insulin resistance, hyperinsulinemia, glucose intolerance and fed hyperglycemia. Islets from ob/ob mice exhibited increased glucose-induced mitochondrial activity, reflected by enhanced NAD(P)H production and mitochondrial membrane potential hyperpolarization. Perforated patch-clamp examination of beta-cells within intact islets revealed several alterations in the electrical activity such as increased firing frequency and higher sensitivity to low glucose concentrations. A higher intracellular Ca(2+) mobilization in response to glucose was also found in ob/ob islets. Additionally, they displayed a change in the oscillatory pattern and Ca(2+) signals at low glucose levels. Capacitance experiments in intact islets revealed increased exocytosis in individual ob/ob beta-cells. All these up-regulated processes led to increased GSIS. In contrast, we found a lack of beta-cell Ca(2+) signal coupling, which could be a manifestation of early defects that lead to beta-cell malfunction in the progression to diabetes. These findings indicate that beta-cell functional adaptations are an important process in the compensatory response to obesity.

Eye design and color signaling in a stomatopod crustacean Gonodactylus smithii

Many species of stomatopod crustaceans have multiple spectral classes of photoreceptors in their retinas. Behavioral evidence also indicates that stomatopods are capable of discriminating objects by their spectral differences alone, Most animals use only two to four different types of photoreceptors in their color vision systems, typically with broad sensitivity functions, but the stomatopods apparently include eight or more narrowband photoreceptor classes for color recognition. It is also known that stomatopods use several colored body regions in social interactions. To examine why stomatopods may be so 'concerned' with color, we measured the absorption spectra of visual pigments and intrarhabdomal filters, and the reflectance spectra from different parts of the bodies of several individuals of the gonodactyloid stomatopod species, Gonodactylus smithii. We then applied a model of multiple dichromatic channels for color encoding to examine whether the finely tuned color vision was specifically co-evolved with their complex color signals. Although the eye design of stomatopods seems suitable for detecting color signals of their own, the detection of color signals from other animals, such as reef fishes, can be enhanced as well. Color vision in G. smithii is therefore not exclusively adapted to detect its own color signals, but the spectral tuning of some photoreceptors (e.g. midband Rows 2 and 3) enhances the contrast of certain color signals to a large enough degree to make co-evolution between color vision and these rather specific color signals likely. Copyright (C) 2000 S. Karger AG, Basel.

Semiochemicals and social signaling in the wild European rabbit in Australia: I. Scent profiles of chin gland secretion from the field

The European rabbit (Oryctolagus cuniculus) uses the secretion of the chin gland in the maintenance of social status. Previous work has concentrated on secretion collected directly from the animal. In this study, the analysis was conducted by collecting scent marks made by free-ranging animals. Scent marks were found to be concentrated at the center of the area controlled by a social group, and at the boundaries between two adjacent social groups. Only the mark from dominant animals could be identified. Marks were also collected from the skin of rabbits, where they had been placed by the dominant individual. The mark found on the head of a subordinate animal may, in the future, be used to identify the dominant animal of the social group, who placed the mark.

PPAR gamma expression is increased in systemic lupus erythematosus patients and represses CD40/CD40L signaling pathway

Systemic lupus erythematosus (SLE) is a heterogeneous disease involving several immune cell types and pro-inflammatory signals, including the one triggered by binding of CD40L to the receptor CD40. Peroxisome-proliferator activated receptor gamma (PPAR gamma) is a transcription factor with anti-inflammatory properties. Here we investigated whether CD40 and PPAR gamma could exert opposite effects in the immune response and the possible implications for SLE. Increased PPAR gamma mRNA levels were detected by real-time PCR in patients with active SLE, compared to patients with inactive SLE PPAR gamma/GAPDH mRNA = 2.21 +/- 0.49 vs. 0.57 +/- 0.14, respectively (p < 0.05) or patients with infectious diseases and healthy subjects (p < 0.05). This finding was independent of the corticosteroid therapy. We further explored these observations in human THP1 and in SLE patient-derived macrophages, where activation of CD40 by CD40L promoted augmented PPAR gamma gene transcription compared to non-stimulated cells (PPAR gamma/GAPDH mRNA = 1.14 +/- 0.38 vs. 0.14 +/- 0.01, respectively; p < 0.05). This phenomenon occurred specifically upon CD40 activation, since lipopolysaccharide treatment did not induce a similar response. In addition, increased activity of PPAR gamma was also detected after CD40 activation, since higher PPAR gamma-dependent transcription of CD36 transcription was observed. Furthermore, CD40L-stimulated transcription of CD80 gene was elevated in cells treated with PPAR gamma-specific small interfering RNA (small interfering RNA, siRNA) compared to cells treated with CD40L alone (CD80/GAPDH mRNA = 0.11 +/- 0.04 vs. 0.05 +/- 0.02, respectively; p < 0.05), suggesting a regulatory role for PPAR gamma on the CD40/CD40L pathway. Altogether, our findings outline a novel mechanism through which PPAR gamma regulates the inflammatory signal initiated by activation of CD40, with important implications for the understanding of immunological mechanisms underlying SLE and the development of new treatment strategies. Lupus (2011) 20, 575-587.