Video-based Event Detection in Catheterization Laboratory

Catheterization Laboratory (Cath Lab) is a hospital examination room equipped with diagnostic imaging equipment to display the heart arteries and to detect and treat any abnormality or stenosis. This thesis addresses the urgent need to improve the efficiency of operating rooms in Cath Labs due to the increasing number of patients with...

Air–water properties of unsteady breaking bores part 1: Novel Eulerian and Lagrangian velocity measurements using intrusive and non-intrusive techniques

Transient motion, turbulence and bubble dynamics make any velocity quantification extremely difficult in unsteady gas–liquid flows. In the present study, novel Eulerian and Lagrangian techniques of velocimetry were developed, using both intrusive and non-intrusive measurements. The selected unsteady gas–liquid flow was a breaking bore,...

Human-in-the-Loop Rule Discovery for Micropost Event Detection

Platforms such as Twitter are increasingly being used for real-world event detection. Recent work often leverages event-related keywords for training machine learning based event detection models. These approaches make strong assumptions on the distribution of the relevant microposts containing the keyword – referred to as the expectation – and...

Cryoseismic Event Analysis on Distributed Strain Recordings Leveraging Statistical Learning Methods

In the summer of 2020, ETH researchers installed a 9 km long fiber-optic cable on the Rhonegletscher (Switzerland), covering the whole glacier extent from accumulation to ablation zone.<br/>The fiber was then interrogated with a DAS system, turning it into a distributed seismic antenna. The DAS system recorded continuously for one month on more...

AI supported noise analyses for structure design requirements definition

The artificial intelligence (AI) field has encountered a turning point mainly due to advancements in machine learning, which allows systems to learn, improve, and perform a specific task through data without being explicitly programmed. Machine learning can be utilized with machining processes to improve product quality levels and...

Towards validation and standardization of automatic gait event identification algorithms for use in paediatric pathological populations

Background: To analyse and interpret gait patterns in pathological paediatric populations, accurate determination of the timing of specific gait events (e.g. initial contract – IC, or toe-off – TO) is essential. As currently used clinical identification methods are generally subjective, time-consuming, or limited to steps with force platform...

One Step At a Time: Newly Proposed Gait Event Detection Using Position Benchmarked Against Existing Acceleration­-Based Methods

Gait event detection allows for insight into one’s gait pattern, an invaluable aid in rehabilitation. Current methods often rely on measured acceleration and rarely on position measurements [3]–[6]. In this paper we propose 4 novel gait detection methods based on the position of the Center of Mass (one approach being causal and thus suitable for...

Acoustic Perception in Intelligent Vehicles using a single microphone system

Passive acoustic sensing utilizes the ability of sound to travel beyond the line-of-sight to understand the surroundings. This provides an advantage over the currently used sensors in Intelligent Vehicles that can sense obstacles within their line-of-sight only. Recently, a localization based approach has been implemented to take advantage of...

Automatic high-resolution microseismic event detection via supervised machine learning

Microseismic methods are crucial for real-Time monitoring of the hydraulic fracturing dynamic status during the development of unconventional reservoirs. However, unlike the active-source seismic events, the microseismic events usually have low signal-To-noise ratio (SNR), which makes its data processing challenging. To overcome the noise...

Music in Use: Novel perspectives on content-based music Retrieval

Music consumption has skyrocketed in the past few years with advancements in internet and streaming technologies. This has resulted in the rapid development of the inter-disciplinary field of Music Information Retrieval (MIR), which develops automatic methods to efficiently and effectively access the wealth of musical content. In general,...

Detecting Socially Significant Music Events using Temporally Noisy Labels

In this paper, we focus on event detection over the timeline of a music track. Such technology is motivated by the need for innovative applications such as searching, non-linearaccess and recommendation. Event detection over the timeline requires time-code level labels in order to train machine learning dels. We use timed comments from...

Crowdsensing as a tool for up-to-date road asset distress detection

Contractors are moving from traditional maintenance to preventive maintenance. To apply preventive maintenance, up-to-date data is required which is unavailable. The goal is to research the applicability of crowdsensing to detect road pavement distresses, and to investigate how the positions of these detections can be used to gain information on...

Measuring performance and improvement of amateur runners

The main idea behind the project was to construct some sort of tool that could help runners, with a TomTom sports watch, in their training, by analysing the data that TomTom has available. Although, still far from reaching the desired goal, this project resulted in many useful insights. In order to construct such a tool training performance and...

Weak signal detection on twitter datasets: A non-accumulated approach for non-famous events

With the rise of social networking platforms, a great amount of data has been generated. Extracting information regarding interesting events from this large data pool has become an interesting direction of research. Multiple tools have been built for this challenge. Detecting the signals for a target event has thus become a crucial task and it...