This research investigated the effectiveness of in-vehicle information technologies on driver behavior in work zones. In-vehicle information devices can increase driver awareness to an oncoming change in traffic flow and provide specific guidelines for driving speed requirements, lane merging strategies, or unexpected changes in the roadway (e.g., detours and lane shifts). The overall conditional effects for vehicle speed are significant; that is, both the audio and visual groups out performed the control group within the simulated work zone. Participants in audio group did outperform the visual group, not significantly though. The overall conditional effects for total time in violation are significant; that is, both the audio and visual groups out performed the control group. The test session results for Total Time in Violation were statistically significant, F(2, 57) = 7.17, p ≤ .01. The strength of relationship between the warning messages and the Total Time in Violation with regular road signage, as assessed by η2 , was strong, the warning message factor accounting for 20% of the variance of the dependent variable.

In this thesis, we analyze the audio signal of a guitar to extract musical data in real-time. Specifically, the pitch and octave of notes and chords are displayed over time. Previous work has shown that non-negative matrix factorization is an effective method for classifying the pitches of simultaneous notes. We explore the effect of window size, hop length, and other parameters to maximize the resolution and accuracy of the output.Other groups have required prerecorded note samples to build a library of note templates to search for. We automate this step and compute the library at run-time, tuning it specifically for the input guitar. The program we present generates a musical visualization of the results in addition to suggestions for fingerings of chords in the form of a fretboard display and tablature notation. This program is built as an applet and is accessible from the web browser.

Infant apnea is a widespread condition in which infants fail to effectively breathe, and can lead to death. Clinical solutions exist for continuous monitoring of respirations in a hospital setting and requiring constant skin contact. This thesis investigates the construction of a proof of concept device that performs in-home monitoring without skin contact and with commonly available off-the-shelf components. The device constructed used a directional microphone to detect breathing sounds, an omnidirectional microphone to detect ambient noise as a baseline to help isolate the breathing sounds, and LabVIEW software deployed on an inexpensive laptop computer to quantify incidents of apparent lapses in breathing meeting the clinical definition of apnea. Testing results indicate that these components are effective in capturing these events in pre-term infants as well as adults, which provides promising evidence that a low-cost system could be manufactured for home detection to assist in infant monitoring.

yes / The findings of a wildness study are presented where audio–visual stimuli (video footage), were assessed by experimental subjects under controlled conditions, in order to obtain reliable estimates of perceived tranquillity together with a number of other rated qualities including calmness and pleasantness. A wide range of mainly natural scenes totalling 46 were presented including footage from the Scottish Highlands and Dartmoor National Park. The findings clearly demonstrate that rated tranquillity relates closely to rated calmness and pleasantness and this agrees with earlier studies of soundscape categorisation. The effect of adding man-made sounds to the soundscape was shown to seriously degrade perceived tranquillity though ratings of wildness were not nearly as affected. Attempts to improve the level of tranquillity further by adding natural sounds were largely unsuccessful. It was considered important to determine if the previously employed Tranquillity Rating Prediction Tool (TRAPT) successfully validated for mainly urban open spaces could usefully predict tranquility in remote wildland areas. In fact results demonstrated the relatively close relationship between predicted and actually rated tranquillity in these remote areas which further extended the range of validity of the prediction tool. The findings of this study will challenge the notion that characterization of landscapes is purely a visual exercise and that soundscape quality needs to be considered as an integral part of this assessment process. For this reason the findings will be of interest to those responsible for managing and marketing protected areas such as National Parks, practitioners involved in carrying out landscape character assessments, cartographers and landscape architects involved in designing tranquil spaces across a range of scales. / Full text was made available 1st March 2016 at the end of the publisher's embargo.

No description available.

No description available.

Today streaming services are the most popular way to consume music, and with this the field of Music Information Retrieval (MIR) has exploded. Tangy market is a music investment platform and they want to use MIR techniques to estimate the value of not yet released songs. In this thesis we collaborate with them investigating how a song’s financial success can be predicted using machine learning models. Previous research has shown that well-known algorithms used for tasks such as image recognition and machine translation, also can be used for audio analysis and prediction. We show that a lot of previous work has been done regarding different aspects of audio analysis and prediction, but that most of that work has been related to genre classification and hit song prediction. The popularity prediction of audio is still quite new and this is where we will contribute by researching if low-level audio features can be used to predict streams. We are using an existing dataset with more than 100 000 songs containing low-level features, which we extend with streaming information. We are using the features in two shapes, summarized and full, and the dataset only contains the summarized digital representation of features. We use Librosa to extend the dataset to also have the digital representation of the full version for the audio features.  A previous study by Martín-Gutiérrez et al. [1] successfully used a combination of low-level and high level audio features as well as non musical features such as number of social media followers. The aim of this thesis is to explore five of the low-level features used in a previous study in [1] in order to assess the predictive power that these features have on their own. The five features we explore is; Chromagram, Mel Spectrogram, Tonnetz, Spectral Contrast, and MFCC. These features are selected for our research specifically because they were used in [1], and we want to investigate to what extent these low-level features contribute to the final predictions made by their model. Our conclusion is that neither of these features could be used for prediction with any accuracy, which indicates that other high-level and external features are of more importance. However, Chromagram and Mel Spectrogram in their full feature states show some potential but they will need to be researched more.

Diese Arbeit stellt grundlegende Konzepte und Tools vor, die bei der Arbeit mit Game Audio angewendet werden können. Sie soll dabei einen Überblick über das Thema Game Audio bieten und die Kernthemen sowohl in theoretischer als auch praktischer Form darstellen. So sollen die Grundlagen vermittelt werden, Game Audio zu implementieren. Die Arbeit richtet sich damit insbesondere an Einsteiger, die ggf. bereits erste Erfahrungen mit der Entwicklung von Spielen gemacht haben, jedoch bislang wenig Berührungspunkte mit dem Audiobereich von Games hatten. Den Hauptteil der Arbeit stellt der praktische Leitfaden dar. In diesem werden die wichtigsten Game Audio Themen besprochen. Dabei wird sowohl auf Game-spezifische und physikalische Grundprinzipien eingegangen als auch auf die praktische Umsetzung mit der jeweiligen Software. Begleitend dazu wurde ein Prototyp entwickelt, bei dem die Ausführungen des Leitfadens Anwendung fanden. Im Leitfaden wird u. a. geklärt, welche Tools es braucht, um Audio in Games zu implementieren und wie diese funktionieren. Repräsentativ wurde dafür die Game Engine Unity sowie die beiden dazu kompatiblen Audio-Middlewares FMOD und Wwise eingesetzt. Darüber hinaus wird die Verwendung von sogenannten Spatial Audio Plugins mit einbezogen und wie diese die Darstellung von 3D-Audio verbessern.:I Einleitung II Theoretische Grundlagen 1 Auditive Wahrnehmung 1.1 Schall 1.2 Menschliches Hörsystem 1.3 Räumliche Orientierung 2 Hörumgebung und Formate 3 Audio in digitalen Medien III Praktischer Leitfaden 1 Entwicklungsumgebung 1.1 Unity 1.2 FMOD 1.3 Wwise 1.4 Spatial Audio Plugins 1.5 Prototyp 2 Diegese 2.1 Theorie 2.2 Implementierung 3 Panning und HRTF 3.1 Theorie 3.2 Implementierung 4 Distance 4.1 Theorie 4.2 Implementierung 5 Occlusion, Obstruction und Exclusion 5.1 Theorie 5.2 Implementierung 6 Salienz 6.1 Theorie 6.2 Implementierung 7 Reverb 7.1 Theorie 7.2 Implementierung 8 Ambience 8.1 Theorie 8.2 Implementierung 9 Variabilität 9.1 Theorie 9.2 Implementierung 10 Dynamische Musik 10.1 Theorie 10.2 Implementierung IV Schlussbetrachtung 1 Diskussion 2 Zusammenfassung und Ausblick Literatur Internetquellen Abbildungsverzeichnis Tabellenverzeichnis

No description available.

No description available.