Big data, nosql e machine learning: un'applicazione di prediction e recommendation basata sulle api di Amazon

In questa tesi sono stati introdotti e studiati i Big Data, dando particolare importanza al mondo NoSQL, approfondendo MongoDB, e al mondo del Machine Learning, approfondendo PredictionIO. Successivamente è stata sviluppata un'applicazione attraverso l'utilizzo di tecnologie web, nodejs, node-webkit e le tecnologie approfondite prima. L'applicazione utilizza l'interpolazione polinomiale per predirre il prezzo di un bene salvato nello storico presente su MongoDB. Attraverso PredictionIO, essa analizza il comportamento degli altri utenti consigliando dei prodotti per l'acquisto. Infine è stata effetuata un'analisi dei risultati dell'errore prodotto dall'interpolazione.

"Cloudy": un'applicazione di assistenza allo shopping basata sulle API di Marketcloud

In questo lavoro di tesi si è analizzato il problema di creare un sistema di assistenza allo shopping integrabile in applicazioni e-commerce web e mobile sviluppate con le tecnologie messe a disposizione da Marketcloud, ovvero un progetto che punta a fornire strumenti per la realizzazione, la manutenzione, la gestione, la diffusione e la pubblicizzazione di tali applicazioni limitando i costi e le problematiche di sviluppo a carico delle aziende che intendono fornire servizi di e-commerce. Dopo aver discusso gli aspetti principali del progetto Marketcloud, sono state analizzate le necessità delle aziende interessate allo sviluppo del sistema di assistenza in esame, così come le aspettative degli utenti (i clienti) finali, ed è stato discusso perché fosse necessario e preferibile, nel caso in esame, non utilizzare soluzioni già presenti sul mercato. Infine, è stata progettata ed implementata un’applicazione web che includesse tale sistema e che fosse immediatamente integrabile tra i servizi già sviluppati da Marketcloud, testandone risultati, prestazioni, problemi e possibili sviluppi futuri. Al termine del lavoro di implementazione, il sistema e l'applicazione garantiscono all'utente finale l'utilizzo di tre funzioni: ricerca per categoria, ricerca libera, recommendation di prodotti. Per gestire la ricerca libera, è stato implementato un sistema di filtri successivi, ed una rete neurale multi-livello dotata di un opportuno algoritmo di machine learning per poter apprendere dalle scelte degli utenti; per la recommendation di prodotti, è stato utilizzato un sistema di ranking (classificazione). Le prestazioni della rete neurale sono state oggetto di attenta analisi.

Progettazione e sviluppo di una SDK in swift 2.1 per la piattaforma "Marketcloud"

Lo scopo di questa tesi di laurea è di presentare e documentare i risultati della tesi svolta in contesto aziendale presso la start-up "Marketcloud". L’obiettivo è stato quello di progettare, sviluppare e documentare una SDK REST in linguaggio Swift 2.1 per interfacciare eventuali future applicazioni iOS con le API Marketcloud. Viene fornita una panoramica sulla start-up in questione, sul linguaggio Swift, sulle motivazioni dietro lo sviluppo dell’SDK e sulle varie fasi di progettazione e sviluppo di quest’ultima. Tutto il lavoro in questione è documentato e reperibile sul repository Github di riferimento all'indirizzo https://github.com/Marketcloud/marketcloud-swift-sdk.

Posttraumatic stress disorder and soluble cellular adhesion molecules at rest and in response to a trauma-specific interview in patients after myocardial infarction

Posttraumatic stress disorder (PTSD) and circulating cellular adhesion molecules (CAMs) predict cardiovascular risk. We hypothesized a positive relationship between PTSD caused by myocardial infarction (MI) and soluble CAMs. We enrolled 22 post-MI patients with interviewer-rated PTSD and 22 post-MI patients with no PTSD. At 32±6months after index MI, all patients were re-scheduled to undergo the Clinician-Administered PTSD Scale (CAPS) interview and had blood collected to assess soluble CAMs at rest and after the CAPS interview. Relative to patients with no PTSD, those with PTSD had significantly higher levels of soluble vascular cellular adhesion molecule (sVCAM)-1 and intercellular adhesion molecule (sICAM)-1 at rest and, controlling for resting CAM levels, significantly higher sVCAM-1 and sICAM-1 after the interview. Greater severity of PTSD predicted significantly higher resting levels of sVCAM-1 and soluble P-selectin in patients with PTSD. At follow-up, patients with persistent PTSD (n=15) and those who had remitted (n=7) did not significantly differ in CAM levels at rest and after the interview; however, both these groups had significantly higher sVCAM-1 and sICAM-1 at rest and also after the interview compared to patients with no PTSD. Elevated levels of circulating CAMs might help explain the psychophysiologic link of PTSD with cardiovascular risk.

Cardiogoniometric parameters for detection of coronary artery disease at rest as a function of stenosis localization and distribution

Cardiogoniometry (CGM), a spatiotemporal electrocardiologic 5-lead method with automated analysis, may be useful in primary healthcare for detecting coronary artery disease (CAD) at rest. Our aim was to systematically develop a stenosis-specific parameter set for global CAD detection. In 793 consecutively admitted patients with presumed non-acute CAD, CGM data were collected prior to elective coronary angiography and analyzed retrospectively. 658 patients fulfilled the inclusion criteria, 405 had CAD verified by coronary angiography; the 253 patients with normal coronary angiograms served as the non-CAD controls. Study patients--matched for age, BMI, and gender--were angiographically assigned to 8 stenosis-specific CAD categories or to the controls. One CGM parameter possessing significance (P < .05) and the best diagnostic accuracy was matched to one CAD category. The area under the ROC curve was .80 (global CAD versus controls). A set containing 8 stenosis-specific CGM parameters described variability of R vectors and R-T angles, spatial position and potential distribution of R/T vectors, and ST/T segment alterations. Our parameter set systematically combines CAD categories into an algorithm that detects CAD globally. Prospective validation in clinical studies is ongoing.

Flexibles WebMapping durch eigene Erweiterungen des Esri JavaScript API

Wie viele andere GIS-Dienstleister der Öffentlichen Verwaltung auch, ist die Abteilung Geoinformation und Vermessung des Kantons Luzern (geo) mit der wachsenden Nachfrage nach flexiblen Webmapping-Applikationen konfrontiert. Neben klassischen Stand-Alone-Anwendungen unterschiedlicher Komplexität werden zunehmend integrierte Lösungen aktuell. Drittanbieter-Applikationen sollen mit Mapping- und GIS-Funktionalitäten erweitert werden. Um den vielfältigen Ansprüchen gerecht zu werden, hat geo zu diesem Zweck einen Viewer (MapViewer LU 4.0) und ein eigenes API (geo.api LU) inklusive Print-Service entwickelt. Das API baut als Erweiterung auf dem bestehenden Esri JavaScript API auf. In der Präsentation werden Anforderungen, Lösungsansätze sowie die konkrete Umsetzung mittels Anwendungs-Demo vorgestellt.

IgE to recombinant allergens Api m 1, Ves v 1, and Ves v 5 distinguish double sensitization from crossreaction in venom allergy

Diagnostic tests in patients with Hymenoptera venom allergy are frequently positive to venoms of both honey bee and wasp (Vespula). Component-resolved analysis with recombinant species-specific major allergens (rSSMA) may help to distinguish true double sensitization from crossreactivity.

Non-invasive diagnosis of coronary artery disease using cardiogoniometry performed at rest

PRINCIPLES: Cardiogoniometry is a non-invasive technique for quantitative three-dimensional vectorial analysis of myocardial depolarization and repolarization. We describe a method of surface electrophysiological cardiac assessment using cardiogoniometry performed at rest to detect variables helpful in identifying coronary artery disease. METHODS: Cardiogoniometry was performed in 793 patients prior to diagnostic coronary angiography. Using 13 variables in men and 10 in women, values from 461 patients were retrospectively analyzed to obtain a diagnostic score that would identify patients having coronary artery disease. This score was then prospectively validated on 332 patients. RESULTS: Cardiogoniometry showed a prospective diagnostic sensitivity of 64%, and a specificity of 82%. ECG diagnostic sensitivity was significantly lower, with 53% and a similar specificity of 75%. CONCLUSIONS: Cardiogoniometry is a new, noninvasive, quantitative electrodiagnostic technique which is helpful in identifying patients with coronary artery disease. It can easily be performed at rest and delivers an accurate, automated diagnostic score.

INFLUENCE OF 24-HOUR SLEEP DEPRIVATION ON CARDIOVASCULAR AND NEURAL CONTROL AT REST AND DURING ACUTE STRESS IN HUMANS

Recent epidemiological studies report a consistent association between short sleep and incidence of hypertension, as well as short sleep and cardiovascular disease-related mortality. While the association between short sleep and hypertension appears to be stronger in women than men, the mechanisms underlying the relations between sleep deprivation, stress, risks of cardiovascular diseases, and sex remain unclear. We conducted two studies to investigate the underlying neural mechanisms of these relations. In study 1, we examined sympathetic neural and blood pressure responses to experimentally-induced sleep deprivation in men and women. We further investigated the influence of sleep deprivation on cardiovascular reactivity to acute stress. In study 2, we examined the neural and cardiovascular function throughout the ovarian cycle in sleep deprived women. Twenty-eight young healthy subjects (14men and 14 women) were tested twice in study 1, once after normal sleep (NS) and once after 24-h total sleep deprivation (TSD). We measured the blood pressure, heart rate (HR), muscle sympathetic nerve activity (MSNA) and forearm blood flow (FBF) during 10min baseline, 5min of mental stress (MS) and 2 min cold pressor test (CPT). We demonstrated that TSD increased resting arterial blood pressure to a similar extent in both men and women, but MSNA decreased only in men following TSD. This MSNA response was associated with altered baroreflex function in women and divergent testosterone responses to TSD between men and women. Regarding TSD and cardiovascular reactivity, TSD elicited augmented HR reactivity and delayed recovery during both MS and CPT in men and women, and responses between sexes were not statistically different. Fourteen young healthy women participated in study 2. Subjects were tested twice, once during their early follicular (EF) phase after TSD, once during their mid-luteal (ML) phase after TSD. Blood pressure, HR, MSNA, and FBF were recorded during 10min baseline, 5 min MS, and 2 min CPT. We observed an augmented resting supine blood pressure during EF compared to ML in sleep deprived women. In contrast, resting MSNA, as well as cardiovascular responses to stressors, were similar between EF and ML after TSD. In conclusion, we observed sex differences in MSNA responses to TSD that demonstrate reductions of MSNA in men, but not women. TSD elicited augmented HR reactivity and delayed HR recovery to acute stressors similarly in men and women. We also reported an augmented supine blood pressure during EF compared to ML in sleep deprived women. These novel findings provide new and valuable mechanistic insight regarding the complex and poorly understood relations among sleep deprivation, sex, stress, and risk of cardiovascular disease.

Using Dynamic Analysis for API Migration

When changing the API of a framework, we need to migrate its clients. This is best done automatically. In this paper, we focus on API migration where the mechanism for inversion of control changes. We propose to use dynamic analysis for such API migration since structural refactorings alone are often not sufficient. We consider JExample as a case-study. JExample extends JUnit with first-class dependencies and fixture injection. We investigate how dynamically collected information about test coverage and about instances under test can be used to detect dependency injection candidates.

A deviant EEG brain microstate in acute, neuroleptic-naive schizophrenics at rest

Momentary brain electric field configurations are manifestations of momentary global functional states of the brain. Field configurations tend to persist over some time in the sub-second range (“microstates”) and concentrate within few classes of configurations. Accordingly, brain field data can be reduced efficiently into sequences of re-occurring classes of brain microstates, not overlapping in time. Different configurations must have been caused by different active neural ensembles, and thus different microstates assumedly implement different functions. The question arises whether the aberrant schizophrenic mentation is associated with specific changes in the repertory of microstates. Continuous sequences of brain electric field maps (multichannel EEG resting data) from 9 neuroleptic-naive, first-episode, acute schizophrenics and from 18 matched controls were analyzed. The map series were assigned to four individual microstate classes; these were tested for differences between groups. One microstate class displayed significantly different field configurations and shorter durations in patients than controls; degree of shortening correlated with severity of paranoid symptomatology. The three other microstate classes showed no group differences related to psychopathology. Schizophrenic thinking apparently is not a continuous bias in brain functions, but consists of intermittent occurrences of inappropriate brain microstates that open access to inadequate processing strategies and context information

Effects of weight on blood pressure at rest and during exercise.

Body weight (BW) and blood pressure (BP) have a close relationship, which has been accounted for by hormonal changes. No previous study has evaluated the effect of wearing an external weight vest on BP to determine whether there is a simple mechanism between BW and BP. Seventeen healthy volunteers underwent weight reduction (WR) through caloric restriction. Before and after WR, BW, body fat percentage and BP at rest and during exercise were measured. Before and after WR, exercise testing was performed twice with the random allocation of a weight vest (10 kg) during one of the tests. Linear regression was used to detect independent associations between BP and the weight vest, BW and body fat percentage. BW decreased from 89.4 ± 15.4 kg to 79.1 ± 14.0 kg following WR (P<0.001). WR led to significant decreases in BP at rest (from 130.0/85.9 mm Hg to 112.5/77.8 mm Hg, P<0.001 for systolic and diastolic BPs) and during exercise. The weight vest significantly increased BP at rest (to 136.1/90.7 mm Hg before and 125.8/84.6 mm Hg after WR) and during exercise. Linear regression analysis identified an independent association between the weight vest and BP (P=0.006 for systolic BP and P=0.009 for diastolic BP at rest). This study demonstrates that wearing an external weight vest has immediate effects on BP at rest and during exercise independent of BW or body fat. More research is needed to understand the physiological mechanisms between weight and BP.

Abnormal expression of REST/NRSF and Myc in neural stem/progenitor cells causes cerebellar tumors by blocking neuronal differentiation.

Medulloblastoma, one of the most malignant brain tumors in children, is thought to arise from undifferentiated neural stem/progenitor cells (NSCs) present in the external granule layer of the cerebellum. However, the mechanism of tumorigenesis remains unknown for the majority of medulloblastomas. In this study, we found that many human medulloblastomas express significantly elevated levels of both myc oncogenes, regulators of neural progenitor proliferation, and REST/NRSF, a transcriptional repressor of neuronal differentiation genes. Previous studies have shown that neither c-Myc nor REST/NRSF alone could cause tumor formation. To determine whether c-Myc and REST/NRSF act together to cause medulloblastomas, we used a previously established cell line derived from external granule layer stem cells transduced with activated c-myc (NSC-M). These immortalized NSCs were able to differentiate into neurons in vitro. In contrast, when the cells were engineered to express a doxycycline-regulated REST/NRSF transgene (NSC-M-R), they no longer underwent terminal neuronal differentiation in vitro. When injected into intracranial locations in mice, the NSC-M cells did not form tumors either in the cerebellum or in the cerebral cortex. In contrast, the NSC-M-R cells did produce tumors in the cerebellum, the site of human medulloblastoma formation, but not when injected into the cerebral cortex. Furthermore, the NSC-M-R tumors were blocked from terminal neuronal differentiation. In addition, countering REST/NRSF function blocked the tumorigenic potential of NSC-M-R cells. To our knowledge, this is the first study in which abnormal expression of a sequence-specific DNA-binding transcriptional repressor has been shown to contribute directly to brain tumor formation. Our findings indicate that abnormal expression of REST/NRSF and Myc in NSCs causes cerebellum-specific tumors by blocking neuronal differentiation and thus maintaining the "stemness" of these cells. Furthermore, these results suggest that such a mechanism plays a role in the formation of human medulloblastoma.