Ulf BlankeETH Zurich | ETH Zürich · Electronics Laboratory
Ulf Blanke
Dr. Ing.
About
64
Publications
28,807
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,542
Citations
Introduction
I have a Ph.D. in machine learning for human activity recognition.
Using a combination of machine learning, sensors, and open data, I contributed to medtech in the field of Parkinson Disease research and travel medicine research.
Later I focused on crowd behavior research, which led to the startup antavi to digitize the safety economy.
Additional affiliations
December 2012 - present
September 2011 - November 2012
October 2010 - August 2011
Education
September 2007 - December 2010
October 2001 - December 2006
Publications
Publications (64)
Automatic recognition of user context is essential for a variety of emerging applications, such as context-dependent content delivery, telemonitoring of medical patients, or quantified life-logging. Although not explicitly observable as, e.g., activities, an important aspect towards understanding user context lies in the affective state of mood.Whi...
Affordances from the urban space shape the way we interact with our environment, whether manifested as driving into the city centre for work or playing sports in designated arenas. Given today's abundance of crowd-generated digital traces on location-based social network (LBSN) platforms, an opportunity arises to grasp deeper semantic characterizat...
Human activity recognition is a core component of context-aware, ubiquitous computing systems. Traditionally, this task is accomplished by analyzing signals of wearable motion sensors. While such signals can effectively distinguish various low-level activities (e.g. walking or standing), two issues exist: First, high-level activities (e.g. watching...
Background
Current surveillance of travellers’ health captures only a small proportion of illness events. We aimed to evaluate the usability and feasibility of using an app to enable travellers to self-report illness.
Method
This pilot study assesses a novel mobile application called Infection Tracking in Travellers (ITIT) that records travel-rela...
Background
We used a mobile application to determine the incidence of health events and risk behaviours during travel by country and identify which health risks are significantly elevated during travel compared with at home.
Method
TOURIST2 is a prospective cohort study of 1000 adult travellers from Switzerland to Thailand, India, China, Tanzania,...
BACKGROUND Current surveillance of travellers' health captures only a small proportion of illness events. We aimed to evaluate the usability and feasibility of using an app to enable travellers to self-report illness. METHOD This pilot study assesses a novel mobile application called Infection Tracking in Travellers (ITIT) that records travel-relat...
Background
The adoption of mHealth technology in travel medicine is a relatively new and unexplored field. We have further developed a TRAVEL application (app) for real-time data monitoring during travel. In this manuscript we report on the feasibility using this new app in a large and diverse cohort of travellers to three continents.
Methods
We e...
Der technische Fortschritt schafft neue Gelegenheiten für Kriminalität. Man denke nur an Hacking, Datenbeschädigung, Trojanische Pferde und andere Schadsoftware im Internet. Auch im Alltag werden immer häufiger technische Hilfsmittel zu kriminellen Zwecken eingesetzt, wie beispielsweise Drohnen mit hochauflösenden Kameras, Miniwanzen und andere Sen...
Background:
Despite the continuing growth of international tourism, very little research has been done on the link between individual risk attitudes and health behaviours during travel. Our study uses a validated risk-taking questionnaire (DOSPERT) and data from a smartphone application to study the association between pre-travel risk attitudes an...
Background:
New research methods offer opportunities to investigate the influence of environment on health during travel. Our study uses data from a smartphone application to describe spatial and environmental patterns in health among travellers.
Methods:
A prospective cohort of travellers to Thailand used a smartphone application during their t...
Background:
Travel medicine research has remained relatively unchanged in the face of rapid expansion of international travel and is unlikely to meet health challenges beyond infectious diseases. Our aim was to identify the range of health outcomes during travel using real-time monitoring and daily reporting of health behaviours and outcomes and i...
Background
mHealth methodology such as smartphone applications offers new opportunities to capture the full range of health risks during travel in real time. Our study aims to widen the scope of travel health research in tropical and subtropical destinations by using a smartphone application to collect detailed information on health behaviours, cli...
Freezing of gait (FoG) is a motor impairment among patients with advanced Parkinson’s disease, associated with falls and negative impact on patient’s quality of life. Detecting such freezes allows real-time gait monitoring to reduce the risk of falls. We investigate the correlation between wrist movements and the freezing of the gait in Parkinson’s...
Human activity recognition is a core component of context-aware, ubiquitous computing systems. Traditionally, this task is accomplished by analysing signals of wearable motion sensors. While successful for low-level activities (e.g. walking or standing), high-level activities (e.g. watching movies or attending lectures) are difficult to distinguish...
We describe a platform for smart, city-wide crowd management based on participatory mobile phone sensing and location/situation specific information delivery. The platform supports quick and flexible deployments of end-to-end applications for specific events or spaces that include four key functionalities: (1) Mobile phone based delivery of event/s...
We investigate the correlation between wrist movement and freezing of the gait in Parkinsons disease. Detecting such freezes allows real-time monitoring to reduce the risk of falls in subjects with Parkinson’s. While most of research focuses on placing inertial sensors on lower limb, i.e., foot, ankle, thigh, lower back, we focus on the wrist as an...
People with Parkinson’s disease (PD) suffer from declining mobility capabilities, which cause a prevalent risk of falling. Commonly, short periods of motor blocks occur during walking, known as freezing of gait (FoG). To slow the progressive decline of motor abilities, people with PD usually undertake stationary motor-training exercises in the clin...
This editorial introduction describes the aims and scope of the ACM Transactions on Interactive Intelligent Systems special issue on Activity Recognition for Interaction. It explains why activity recognition is becoming crucial as part of the cycle of interaction between users and computing systems, and it shows how the five articles selected for t...
We describe a system that leverages users voluntarily having their smartphones scan the environment for discoverable Bluetooth devices to analyze crowd conditions in urban environments. Our method goes beyond mere counting of discoverable devices toward a set of more complex, robust features. We also show how to extend the analysis from crowd densi...
This paper targets the construction of pedestrian maps for city-scale events from GPS trajectories of visitors. Incom- plete data with a short lifetime, varying localisation accu- racy, and a high variation of walking behaviour render the extraction of a pedestrian map from crowd-sourced data a difficult task. Traditional network or map constructio...
Automatically recognizing people's daily activities is essential for a variety of applications, such as just-in-time content delivery or quantified self-tracking. Towards this, researchers often use customized wearable motion sensors tailored to recognize a small set of handpicked activities in controlled environments. In this paper, we design and...
In queues, persons - or objects (120) in general - move inside an area (110) to a target (112), such as to a counter. The queue has movement characteristics in terms of speed, waiting times and queue form. A computer-implemented approach obtains the characteristics by receiving a sequence (140) of image frames (141, 142, 143, 49) that represent the...
We discuss models and data of crowd disasters, crime, terrorism, war and disease spreading to show that conventional recipes, such as deterrence strategies, are often not effective and sufficient to contain them. Many common approaches do not provide a good picture of the actual system behavior, because they neglect feedback loops, instabilities an...
Patients with Parkinson’s disease often experience freezing of gait, which bears a high risk of falling, a prevalent cause for morbidity and mortality. In this work we present GaitAssist, a wearable system for freezing of gait support in daily life.
The system provides real-time auditory cueing after the onset of freezing episodes. Furthermore, Gai...
Large-scale festivals with a multitude of stages, food stands, and attractions require a complex perimeter design and program planning in order to manage the mobility of crowds as a controlled process. Errors in the planning phase can cause unexpected crowd dynamics and lead to stampedes with lethal consequences. We deployed an official app for Zu...
We investigate the use of WiFi Received Signal Strength Information (RSSI) at a mobile phone for the recognition of situations, activities and gestures. In particular, we propose a device-free and passive activity recognition system that does not require any device carried by the user and uses ambient signals. We discuss challenges and lessons lear...
Many patients with Parkinson's disease suffer from short periods during which they cannot continue walking, the so-called freezing of gait. Patients can learn to use rhythmic auditory sounds as support during these episodes. We developed GaitAssist, a personalized wearable system for freezing of gait support, that enables training in unsupervised e...
A computer implemented method, computer program product,and computer system for determining camera calibration data. The computer system receives geo-positional data of a moving object, wherein the geo-positional data is associated with an indicator (112). The computer system receives further a sequence of frames (140) from the at least one camera...
We discuss models and data of crowd disasters, crime, terrorism, war and disease spreading to show that conventional recipes, such as deterrence strategies, are often not effective and sufficient to contain them. Many common approaches do not provide a good picture of the actual system behavior, because they neglect feedback loops, instabilities an...
This book constitutes the thoroughly refereed post-conference proceedings of the 5th International Conference on Mobile Computing, Applications, and Services (MobiCASE 2013) held in Paris, France, in November 2013. The 13 full, 5 short and 9 poster papers were carefully reviewed and selected from 64 submissions, and are presented together with 3 pa...
Extracting semantic meaning of locations enables a large range of applications including automatic daily activity logging, assisted living for elderly, as well as the adaptation of phone user profiles according to user needs. Traditional location recognition approaches often rely on power-hungry sensor modalities such as GPS, network localization or...
Human activity recognition systems traditionally require a manual annotation of massive training data, which is laborious and non-scalable. An alternative approach is mining existing online crowd-sourced repositories for open-ended, free annotated training data. However, differences across data sources or in observed contexts prevent a crowd-source...
The growing ubiquity of sensors in mobile phones has opened many opportunities for personal daily activity sensing. Most context recognition systems require a cumbersome preparation by collecting and manually annotating training examples. Recently, mining online crowd-generated repositories for free annotated training data has been proposed to buil...
Besucher von grossanlässen sind sich oft der poten- ziellen gefahren nicht bewusst. Dennoch zeigen zahl- reiche ereignisse – wie die love Parade 2010 mit über einer Million Besuchern in Duisburg oder das hindu-Fest Maha Kumbh Mela in indien 2013 – wie schnell es zu Verletzten oder gar Toten kommen kann. Mit einer Smartphone-App, die den Besuchern n...
A computer implemented method, computer program product and computer system for sensor classification. The computer system receives from an unclassified sensor node a series of measurement data. The unclassified sensor node is unknown in an infrastructure knowledge base. The computer system logs the series of measurement data in a first database. A...
We explore the feasibility of utilizing large, crowd-generated online repositories to construct prior knowledge models for high-level activity recognition. Towards this, we mine the popular location-based social network, Foursquare, for geo-tagged activity reports. Although unstructured and noisy, we are able to extract, categorize and geographical...
Many people with Parkinson's disease suffer from freezing of gait, a debilitating temporary inability to pursue walking. Rehabilitation with wearable technology is promising. State of the art approaches face difficulties in providing the needed bio-feedback with a sufficient low-latency and high accuracy, as they rely solely on the crude analysis o...
We address a specific, particularly difficult class of activity recognition problems defined by (1) subtle, and hardly discriminative hand motions such as a short press or pull, (2) large, ill defined NULL class (any other hand motion a person may express during normal life), and (3) difficulty of collecting sufficient training data, that generaliz...
The last 20 years have seen an ever increasing research activity in the field of human activity recognition. With activity recognition having considerably matured so did the number of challenges in designing, implementing and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers t...
With the introduction of the Kinect as a gaming interfaces, its broad commercial accessibility and high quality depth sensor has attracted the attention not only from consumers but also from researchers in the robotics community. The active sensing technique of the Kinect produces robust depth maps for reliable human pose estimation. But for a broa...
Location is a key information for context-aware systems. While coarse-grained indoor location estimates may be ob- tained quite easily (e.g. based on WiFi or GSM), finer- grained estimates typically require additional infrastructure (e.g. ultrasound). This work explores an approach to esti- mate significant places, e.g., at the fridge, with no addi...
The introduction of the Microsoft Kinect Sensors has stirred significant interest in the robotics community. While originally developed as a gaming interface, a high quality depth sensor and affordable price have made it a popular choice for robotic perception. Its active sensing strategy is very well suited to produce robust and high-frame rate de...
Current systems for motion capturing based on inertial measurement incorporate several powerhungry sensor modalities to accurately estimate the sensor's orientation. To drive motion capturing towards longterm applications, we use a reduced sensor setting based on accelerometers and magnetometers only to estimate orientation. We analyze this setting...
Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity r...
We present an approach to model sleeping trends, using a light-weight setup to be deployed over longer time-spans and with a minimum of maintenance by the user. Instead of characterizing sleep with traditional signals such as EEG and EMG, we propose to use sensor data that is a lot weaker, but also less invasive and that can be deployed unobtrusive...
Choosing the right feature for motion based activity spotting is not a trivial task. Often, features derived by intuition or that proved to work well in previous work are used. While feature selection algorithms allow automatic decision, definition of features remains a manual task. We conduct a comparative study of features with very different ori...
pActivity Recognition has made significant progress in the past years. We strongly believe however that we could make far greater progress if we build more systematically on each other’s work. Comparing the activity recognition community with other more mature communities (e.g., those of computer vision and speech recognition) there appear to be tw...
Model-based activity recognition has been recently proposed as an alternative to signal-oriented recognition. Such model-based approaches seem attractive due to their ability to enable user-independent activity recognition and due to their improved robustness to signal-variation. The first goal of this paper is therefore to systematically analyze t...
This paper explores the possibility of using low-level activity spotting for daily routine recognition. Using occurrence statistics of low- level activities and simple classiers based on their statistics allows to train a discriminative classier for daily routine activities such as work- ing and commuting. Using a recently published data set we nd...
We present an approach for recognizing location transitions of persons in buildings, using inertial sensor data from mo-bile devices. By normalizing trajectories using principal com-ponent analysis (PCA), our approach is robust to changes in sensor placement and orientation. On a data set containing 10 location transitions and 7 different placement...
High-level and longer-term activity recognition has great potentials in areas such as medical diagnosis and human behavior
modeling. So far however, activity recognition research has mostly focused on low-level and short-term activities. This paper
therefore makes a first step towards recognition of high-level activities as they occur in daily life...
Questions
Question (1)
I am looking for historical data in 15-min bins for backtesting. So far I can only find per-day data. Other than that, what's your favorite data source?