• Publikationen
Show publication details

Bieber, Gerald; Haescher, Marian; Hanschmann, Paul; Matthies, Denys J.C.

Exploring Accelerometer-based Step Detection by using a Wheeled Walking Frame

2018

iWOAR 2018

International Workshop on Sensor-based Activity Recognition (iWOAR) <5, 2018, Rostock, Germany>

ACM International Conference Proceedings Series

Step detection with accelerometers is a very common feature that smart wearables already include. However, when using a wheeled walking frame / rollator, current algorithms may be of limited use, since a different type of motion is being excreted. In this paper, we uncover these limitations of current wearables by a pilot study. Furthermore, we investigated an accelerometer-based step detection for using a wheeled walking frame, when mounting an accelerometer to the frame and at the user’s wrist. Our findings include knowledge on signal propagation of each axis, knowledge on the required sensor quality and knowledge on the impact of different surfaces and floor types. In conclusion, we outline a new step detection algorithm based on accelerometer input data. Our algorithm can significantly empower future off-the-shelf wearables with the capability to sufficiently detect steps with elderly people using a wheeled walking frame. This can help to evaluate the state of health with regard to the human behavior and motor system and even to determine the progress of certain diseases.

978-1-4503-6487-4

Show publication details

Haescher, Marian; Matthies, Denys J.C.; Srinivasan, Karthik; Bieber, Gerald

Mobile Assisted Living: Smartwatch-based Fall Risk Assessment for Elderly People

2018

iWOAR 2018

International Workshop on Sensor-based Activity Recognition (iWOAR) <5, 2018, Rostock, Germany>

ACM International Conference Proceedings Series

We present a novel Smartwatch-based approach, to enable Mobile Assisted Living (MAL) for users with special needs. A major focus group for this approach are elderly people. We developed a tool for caregivers applicable in home environments, nursing care, and hospitals, to assess the vitality of their patients. Hereby, we particularly focus on the prediction of falls, because falls are a major reason for serious injuries and premature death among elderly. Therefore, we propose a multi parametric score based on standardized fall risk assessment tests, as well as on sleep quality, medication, patient history, motor skills, and environmental factors. The resulting total fall risk score reflects individual changes in behavior and vitality, which consequently enables for fall preventing interventions. Our system has been deployed and evaluated in a pilot study among 30 elderly patients over a period of four weeks.

978-1-4503-6487-4

Show publication details

Matthies, Denys J.C.; Urban, Bodo [Thesis Reviewer]; Schmidt, Albrecht [Thesis Reviewer]; Wolf, Katrin [Thesis Reviewer]

Reflexive Interaction - Extending Peripheral Interaction by Augmenting Humans

2018

Rostock, Univ., Diss., 2018

Technology is closer to the human than ever, it exists in various shapes and forms, is omnipresent, while continuously competing for the user's attention. With new opportunities constantly arising, such as mobile computing, we also face challenges, particularly when the user is on the go. Because of mobile devices often demand the user's full attention, control in mobile scenarios can be complicated, inadequate, awkward, risky, or not feasible at all. To overcome these problems, the concept of a Reflexive Interaction is presented, which can be seen as a specific manifestation of Peripheral Interaction. In contrast, a Reflexive Interaction is envisioned to be executed at a secondary task without involving substantial cognitive effort, while enabling the user tiny interactions, shorter than Microinteractions, without straining the user's main interaction channels occupied with the primary task. To underline the proposed concept, a series of research studies has been conducted that exploit the unique sensing and motor capabilities of the human body. For this, three body regions (head, body, and foot) have been selected, which all yield specific characteristics. For instance, the region of the head enables facial gesture control, while visual information is perceivable within our peripheral vision. On our body, quick tapping and hovering can be performed, while haptic, thermal, or electrical feedback can be applied on our skin in order to perceive different scales of notifications. The foot enables quick foot tapping gestures as well as the possibility to perceive vibrotactile feedback under the foot's sole. Moreover, in particular the foot, but also the face, generates unique information, which can be utilized to infer on the user's context, such as physical activity or emotional state. The consideration of context information is important in order to determine whether and how a Reflexive Interaction can be implemented.

Show publication details

Matthies, Denys J.C.; Daza Parra, Laura Milena; Urban, Bodo

Scaling Notifications Beyond Alerts: From Subtly Drawing Attention up to Forcing the User to Take Action

2018

UIST 2018 Adjunct

Research has been done in sophisticated notifications, still, devices today mainly stick to a binary level of information, while they are either attention drawing or silent. We propose scalable notifications, which adjust the intensity level reaching from subtle to obtrusive and even going beyond that level while forcing the user to take action. To illustrate the technical feasibility and validity of this concept, we developed three prototypes. The prototypes provided mechano-pressure, thermal, and electrical feedback, which were evaluated in different lab studies. Our first prototype provides subtle poking through to high and frequent pressure on the user’s spine, which significantly improves back posture. In a second scenario, the user is able to perceive the overuse of a drill by an increased temperature on the palm of a hand until the heat is intolerable, forcing the user to eventually put down the tool. The last application comprises of a speed control in a driving simulation, while electric muscle stimulation on the users’ legs, conveys information on changing the car’s speed by a perceived tingling until the system forces the foot to move involuntarily. In conclusion, all studies’ findings support the feasibility of our concept of a scalable notification system, including the system forcing an intervention.

978-1-4503-5949-8

Show publication details

Matthies, Denys J.C.; Haescher, Marian; Nanayakkara, Suranga; Bieber, Gerald

Step Detection for Rollator Users with Smartwatches

2018

SUI '18 Proceedings of the Symposium on Spatial User Interaction

ACM Symposium on Spatial User Interaction (SUI) <6, 2018, Berlin, Germany>

Smartwatches enable spatial user input, namely for the continuous tracking of physical activity and relevant health parameters. Additionally, smartwatches are experiencing greater social acceptability, even among the elderly. While step counting is an essential parameter to calculate the user’s spatial activity, current detection algorithms are insufficient for calculating steps when using a rollator, which is a common walking aid for elderly people. Through a pilot study conducted with eight different wrist-worn smart devices, an overall recognition of ~10% was achieved. This is because characteristic motions utilized by step counting algorithms are poorly reflected at the user’s wrist when pushing a rollator. This issue is also present among other spatial activities such as pushing a pram, a bike, and a shopping cart. This paper thus introduces an improved step counting algorithm for wrist-worn accelerometers. This new algorithm was first evaluated through a controlled study and achieved promising results with an overall recognition of ~85%. As a follow-up, a preliminary field study with randomly selected elderly people who used rollators resulted in similar detection rates of ~83%. To conclude, this research will expectantly contribute to greater step counting precision in smart wearable technology.

978-1-4503-5708-1

Show publication details

Matthies, Denys J.C.; Roumen, Thijs; Kuijper, Arjan; Urban, Bodo

CapSoles: Who Is Walking on What Kind of Floor?

2017

MobileHCI 2017

International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) <19, 2017, Vienna, Austria>

Foot interfaces, such as pressure-sensitive insoles, still yield unused potential such as for implicit interaction. In this paper, we introduce CapSoles, enabling smart insoles to implicitly identify who is walking on what kind of floor. Our insole prototype relies on capacitive sensing and is able to sense plantar pressure distribution underneath the foot, plus a capacitive ground coupling effect. By using machine-learning algorithms, we evaluated the identification of 13 users, while walking, with a confidence of ~95% after a recognition delay of ~1s. Once the user's gait is known, again we can discover irregularities in gait plus a varying ground coupling. While both effects in combination are usually unique for several ground surfaces, we demonstrate to distinguish six kinds of floors, which are sand, lawn, paving stone, carpet, linoleum, and tartan with an average accuracy of ~82%. Moreover, we demonstrate the unique effects of wet and electrostatically charged surfaces.

Show publication details

Matthies, Denys J.C.; Strecker, Bernhard Arthur; Urban, Bodo

EarFieldSensing: A Novel In-Ear Electric Field Sensing to Enrich Wearable Gesture Input through Facial Expressions

2017

CHI '17. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems

Conference on Human Factors in Computing Systems (CHI) <35, 2017, Denver, CO, USA>

EarFieldSensing (EarFS) is a novel input method for mobile and wearable computing using facial expressions. Facial muscle movements induce both electric field changes and physical deformations, which are detectable with electrodes placed inside the ear canal. The chosen ear-plug form factor is rather unobtrusive and allows for facial gesture recognition while utilizing the close proximity to the face. We collected 25 facial-related gestures and used them to compare the performance levels of several electric sensing technologies (EMG, CS, EFS, EarFS) with varying electrode setups. Our developed wearable fine-tuned electric field sensing employs differential amplification to effectively cancel out environmental noise while still being sensitive towards small facial-movement-related electric field changes and artifacts from ear canal deformations. By comparing a mobile with a stationary scenario, we found that EarFS continues to perform better in a mobile scenario. Quantitative results show EarFS to be capable of detecting a set of 5 facial gestures with a precision of 90% while sitting and 85.2% while walking. We provide detailed instructions to enable replication of our low-cost sensing device. Applying it to different positions of our body will also allow to sense a variety of other gestures and activities.

Show publication details

Daza Parra, Laura Milena; Matthies, Denys J.C. [Supervisor]; Urban, Bodo [Supervisor]

Going Beyond Scalable Notifcations - from Subtle Stimulus to Forced Response

2017

Rostock, Univ., Master Thesis, 2017

People's perception of their own body's appearance, capabilities and position are constantly updated through sensory cues that are naturally produced by their own actions. Alteration or enhancement of such cues has been carried out with multisensory feedback in multiple Human Computer Interaction (HCI) areas such as health, psychology, neuroscience and games. HCI applications use normally audible or visual alerts, such as LEDs, beeps, bells, among others. However haptic feedback (related to the sense of touch) uses normally other components to augment or replace such common alert methods. Such alerts, also called notifications, usually stick to a binary level of information, while they are either attention drawing or silent. This work proposes a concept that goes beyond scalable notifications, reaching from subtle to obtrusive and also forcing the user to take action. To illustrate the technical feasibility and validity of the concept, three prototypes were developed providing vibrotactile, thermal, and electrical feedback. Each prototype was evaluated in different lab settings suggesting that the concept is applicable in the given situations. It is shown the effect of different notification levels while completing a task and how going beyond an obtrusive level forces the user to execute a desired action such as correct their posture, stop using a tool or press down the gas pedal completely.

Show publication details

Strecker, Bernhard Arthur; Matthies, Denys J.C. [Advisor]; Thaller, Manfred [Advisor]

A Wearable Facial Expression Control Interface to Accomplish Microinteractions in Mobile Scenarios

2016

Köln, Univ., Master Thesis, 2016

In our modern society, computing technology has become ubiquitous. Starting with the advent of smartphones, wearable computing has become ever more commonplace and pervasive in recent years. Interaction does no longer only happen in confined environments. Having access to computer interfaces anytime and anywhere necessitates new interaction styles to fully benefit from the manifold technological and interactional possibilities computers offer. Since hands and eyes of users on the move are likely to be busy with other activities, alternative interaction strategies are worthwhile to consider. The human face is very communicative and consistently used for human-to-human interaction, but close to never used for human-computer-interaction. In this thesis, facial expression recognition with unobtrusive sensing technology is investigated. An overview over the concepts of wearable computing, peripheral computer interaction, and microinteractions is given. Since bulky hardware such as cameras cannot be used in mobile contexts without attracting attention and distracting the user, alternative technologies have been tested. Focus was laid on thoroughly testing seven different earplugs with mounted electrodes. A newly developed gesture set of 25 facial gestures was tested in conjunction with capacitive sensing, electric field sensing, and electromyography sensing technology. Facial muscle movements lead to electric and mechanical changes, which can be sensed inside the ear-canal. Classification accuracies above 90% for 5 gestures were achieved with both industrial grade capacitive sensing technology and a self-developed electric field sensing board. The theory behind each of the sensing technologies is explained depth throughout this thesis.

Show publication details

Bieber, Gerald; Kaulbars, Uwe; Trimpop, John; Haescher, Marian; Matthies, Denys J.C.

Abschlussbericht zum Vorhaben Smartwatches "FP 0375"

2016

Langanhaltende und intensive Vibrationseinwirkungen auf das Hand-Arm-System können zu schwerwiegenden Er-krankungen führen. Die Abschätzung einer Gefährdung hinsichtlich der Hand-Arm-Vibration (HAV) wird unter Be-rücksichtigung der Expositionsdauer sowie der Vibrationsintensität durchgeführt. Die subjektive Erfassung oder der Einsatz von Messgeräten zur Bestimmung der Expositionsdauer ist kostenintensiv, stört den Arbeitsablauf oder kann aufgrund des hohen Aufwandes nur sehr sporadisch und selten durchgeführt werden.Bedingt durch die Miniaturisierung in der Elektronik sind nun bezahlbare Smartwatches auf dem Markt, die eine Vielzahl von integrierten Sensoren enthalten. Obwohl die Smartwatches über leistungsfähige Beschleunigungs-, Drehraten- und Akustiksensoren sowie eine effiziente Verarbeitungseinheit verfügen, ist es bisher unklar, ob diese Systeme tatsächlich zur Bewertung der Hand-Arm-Vibration (HAV) eingesetzt werden können.In dem vorliegenden Projekt wurde gemeinsam mit dem Institut für Arbeitsschutz IFA, St. Augustin, und dem Fraun-hofer IGD, Rostock, eine Machbarkeitsuntersuchung durchgeführt, um nachzuweisen, ob mit Smartwatches eine Arbeitsgeräteidentifikation möglich ist. Hierbei wurden unter Laborbedingungen und in Feldversuchen Beschleuni-gungs- und Mikrofondaten während der Ausführung von Arbeiten mit vibrierenden Arbeitsgeräten erfasst und ana-lysiert. Dabei wurde untersucht, welche Verfahren zur Vibrationsmustererkennung geeignet und welche Erhebungs-parameter auszuwählen sind. Durch eine Klassifizierung der Messdaten wurde auf die genutzten Arbeitsgeräte so-wie die Expositionszeiträume geschlossen.Als Ergebnis der Untersuchung wurden die Möglichkeiten und Rahmenbedingungen für eine individuelle Bestim-mung der HA-Vibrationsdosis mit Smartwatches bestimmt und bewertet. Es konnte gezeigt werden, dass eine kon-tinuierliche Erfassung der HA-Vibrationsdosis mit Smartwatches möglich ist. Im Rahmen der Evaluation wurden Be-schleunigungsdaten mit 50 Hz sowie Sounddaten mit 8 kHz erfasst und in Fenster, zu je 1,28 Sekunden, unterteilt. Aus den Messdaten dieser Sensoren wurden 71 Merkmale selektiert und auf ihre Relevanz untersucht. Es zeigte sich, dass in Feldversuchen eine Untermenge von ca. 9 – 15 Merkmalen relevant sind. Bei dem Einsatz von vier unterschiedlichen Arbeitsgeräten wurden die Daten mit einem J48-Entscheidungsbaum klassifiziert, dieses führte zu einer Erkennungsrate der Arbeitsgeräte von ca. 72 Prozent. Für die A(8)-Bewertung wies hingegen die Smart-watch eine Überbewertung von ca. 11 Prozent auf.

Show publication details

Matthies, Denys J.C.; Bieber, Gerald; Kaulbars, Uwe

AGIS: Automated Tool Detection & Hand-Arm Vibration Estimation using an Unmodified Smartwatch

2016

iWOAR 2016

International Workshop on Sensor-based Activity Recognition (iWOAR) <3, 2016, Rostock, Germany>

Over the past three decades, it has been known that longlasting and intense hand-arm vibrations (HAV) can cause serious diseases, such as the Raynaud- / White Finger- Syndrome. In order to protect workers nowadays, the longterm use of tools such as a drill, grinder, rotary hammer etc. underlie strict legal regulations. However, users rarely comply with these regulations because it is quite hard to manually estimate vibration intensity throughout the day. Therefore, we propose a wearable system that automatically counts the daily HAV exposure doses due to the fact that we are able to determine the currently used tool. With the implementation of AGIS, we demonstrate the technical feasibility of using the integrated microphone and accelerometer from a commercial smartwatch. In contrast to prior works, our approach does not require a technical modification of the smartwatch nor an instrumentation of the environment or the tool. A pilot study shows our proofof- concept to be applicable in real workshop environments.

Show publication details

Matthies, Denys J.C. [Ed.]; Haescher, Marian [Ed.]; Bieber, Gerald [Ed.]; Urban, Bodo [Ed.]

iWOAR 2016

2016

ACM Press

International Workshop on Sensor-based Activity Recognition (iWOAR) <3, 2016, Rostock, Germany>

ACM International Conference Proceedings Series, 1183

Wearable sensors potentially enable for a better and unobtrusive recognition of human activity and the state of rest, sleep, stress and drive the ongoing trend of the quantified self-movement. As an enabling technology, powerful, while yet inexpensive MEMS-Chips (micro-electro-mechanical system) push the penetration of a broad variety of mobile devices. Thereby, these devices gain high interest, not only in terms of general customer products, but also as integrated systems in an industrial context, either way to enable continuous monitoring of complex life processes and workplace situations. Another challenge that research is facing concerns the limited human abilities of interaction in context of mobility and in situations, in which high attention is being demanded. New and alternative ways are needed to be found in order to take advantage of all human capabilities to enable safe and unobtrusive interaction. This conference-like workshop is initiated and organized by the Fraunhofer IGD in Rostock. It offers scientists, interested parties, and users in the area of sensor-based activity recognition and interaction the possibility to an exchange of experiences and a presentation of best-practice examples, as well as technical and scientific results. The workshop focuses on technologies for human activity recognition and interaction via inertial sensors (accelerometers, gyroscopes etc.) and their scientific applications.

978-1-4503-4245-2

Show publication details

Chua, Soon Hau; Perrault, Simon T.; Matthies, Denys J.C.; Zhao, Shengdong

Positioning Glass: Investigating Display Positions of Monocular Optical See-Through Head-Mounted Display

2016

Proceedings of the Fourth International Symposium on Chinese CHI

International Symposium of Chinese CHI (ChineseCHI) <4, 2016, San Jose, CA, USA>

The physical position of the display on a monocular OSTHMD in relative to our eye is an important factor of the performance and usability in dual-task scenarios. We investigated 9 different display positions in a modern dual-task scenario with 27 participants. The experiment-involved participants responding to 3 different types of notifications displayed on the HMD while performing a visually intensive primary task. We found that although the notifications at the middle and bottom center positions were noticed quicker, the top and the peripheral positions were more comfortable, unobtrusive, and preferred. In particular, middle-right strikes the best balance between performance and usability in the dual-task scenario we studied. Our findings and discussions demonstrated the need for further work and a more rigorous investigation in dual-task scenarios with characteristics dissimilar to ours.

Show publication details

Matthies, Denys J.C.; Haescher, Marian; Bieber, Gerald; Salomon, Ralf; Urban, Bodo

SeismoPen: Pulse Recognition via a Smart Pen

2016

Proceedings of the 9th International Conference on PErvasive Technologies Related to Assistive Environments

ACM International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) <9, 2016, Corfu, Greece>

We propose SeismoPen, an enhanced ballpoint pen, which is capable of calculating the patient's heart rate. This is enabled when being pressed the pen towards the patient's throat so it can sense and analyze the seismographic micro-eruption caused by the pulsing blood. We developed a suitable algorithm and tested three sensor setups in which we attached (1) a force-sensing resistor (FSR), (2) an accelerometer, and (3) a piezoelectric transducer to the pen's head. We also conducted a user study, which resulted in suggesting SeismoPen to be potentially more accepted by users, since it is less obtrusive than alternative measurement methods. In contrast to medical devices, this simple pen looks less perilous and potentially reduces the risk of triggering symptoms of a white coat hypertension.

Show publication details

Haescher, Marian; Trimpop, John; Matthies, Denys J.C.; Urban, Bodo

SeismoTracker: Upgrade Any Smart Wearable to Enable a Sensing of Heart Rate, Respiration Rate, and Microvibrations

2016

Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing

Conference on Human Factors in Computing Systems (CHI) <34, 2016, San Jose, CA, USA>

In this paper we present a method to enable any smart Wearable to sense vital data in resting states. These resting states (e.g. sleeping, sitting calmly, etc.) imply the presence of low-amplitude body-motions. Our approach relies on seismocardiography (SCG), which only requires a built-in accelerometer. Compared to commonly applied technologies, such as photoplethysmography (PPG), our approach is not only tracking heart rate (HR), but also respiration rate (RR), and microvibrations (MV) of the muscles, while being also computational inexpensive. In addition, we can calculate several other parameters, such as HR variability and RR variability. Our extracted vital parameters match with the vital data gathered from clinical state-of-the art technology. These data allow us to gain an impression on the user's activity, quality of sleep, arousal and stress level over the whole day, week, month, or year. Moreover, we can detect whether a device is actually worn or doffed, which is crucial when connecting such data with health services. We implemented our method on two current smartwatches: a Simvalley AW420 RX as well as on a LG G Watch R and recorded user data for several months. A web platform enables to keep track of one's data.

Show publication details

Klamet, Josephin; Matthies, Denys J.C.; Minge, Michael

WeaRelaxAble: A Wearable System to Enhance Stress Resistance using Various Kinds of Feedback Stimuli

2016

iWOAR 2016

International Workshop on Sensor-based Activity Recognition (iWOAR) <3, 2016, Rostock, Germany>

This paper introduces a wearable feedback device that aims at relaxing the user in stressful situations. The system, which is called WeaRelaxAble, provides various feedback modalities, such as vibration, ambient light, acoustic stimuli and heat in order to reduce the user's stress level. The development of WeaRelaxAble is based on two studies: At first, all five kinds of feedback and appropriate body positions for stimulation were evaluated with 15 participants. Based on the findings of this initial study, we built a wearable Arduino prototype to prove the feasibility of our concept. The experience while using the system was tested with 26 test subjects under laboratory conditions. We conclude with a concept design of a wrist-worn device that provides acoustic and visual feedback. As tactile stimulation, a shirt would provide vibration at the positions of the shoulders as well as heat at the loins. Users can explicitly activate the system at any time and in any combination of feedback modalities.

Show publication details

Meier, Anita; Matthies, Denys J.C.; Heidmann, Frank

A Brief Survey on Understanding the Interaction between Human and Technology at the Task of Pedestrian Navigation

2015

Proceedings of the International Summer School on Visual Computing 2015

International Summer School on Visual Computing <1, 2015, Rostock, Germany>

In this paper we present a brief summary of an online survey we conducted in 2014. 135 participants successfully completed this survey, whereby 46% of the subjects were females and 54% males. We found out, that nowadays many users fall back on using smartphones in order to orientate themselves in unknown environments. In terms of analog navigation methods, people still rely on street name signs and landmarks such as characteristic buildings. However, relying on current smartphone habits for navigation tasks, visual attention is usually heavily drawn, which can cause a reduced perception and potentially makes smartphone map navigation more dangerous.

Show publication details

Haescher, Marian; Matthies, Denys J.C.; Trimpop, John; Urban, Bodo

A Study on Measuring Heart- and Respiration-Rate via Wrist-Worn Accelerometer-based Seismocardiography (SCG) in Comparison to Commonly Applied Technologies

2015

iWOAR 2015 - 2nd international Workshop on Sensor-based Activity Recognition and Interaction

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

Since the human body is a living organism, it emits various life signs which can be traced with an action potential sensitive electromyography, but also with motion sensitive sensors such as typical inertial sensors. In this paper, we present a possibility to recognize the heart rate (HR), respiration rate (RR), and the muscular microvibrations (MV) by an accelerometer worn on the wrist. We compare our seismocardiography (SCG) / ballistocardiography (BCG) approach to commonly used measuring methods. In conclusion, our study confirmed that SCG/BCD with a wrist-worn accelerometer also provides accurate vital parameters. While the recognized RR deviated slightly from the ground truth (SD=16.61%), the detection of HR is nonsignificantly different (SD=1.63%) to the gold standard.

Show publication details

Haescher, Marian; Trimpop, John; Matthies, Denys J.C.; Bieber, Gerald; Urban, Bodo; Kirste, Thomas

aHead: Considering the Head Position in a Multi-sensory Setup of Wearables to Recognize Everyday Activities with Intelligent Sensor Fusions

2015

Human-Computer Interaction. Proceedings Part II

International Conference on Human-Computer Interaction (HCII) <17, 2015, Los Angeles, CA, USA>

In this paper we examine the feasibility of Human Activity Recognition (HAR) based on head mounted sensors, both as stand-alone sensors and as part of a wearable multi-sensory network. To prove the feasibility of such setting, an interactive online HAR-system has been implemented to enable for multi-sensory activity recognition while making use of a hierarchical sensor fusion. Our system incorporates 3 sensor positions distributed over the body, which are head (smart glasses), wrist (smartwatch), and hip (smartphone). We are able to reliably distinguish 7 daily activities, which are: resting, being active, walking, running, jumping, cycling and office work. The results of our field study with 14 participants clearly indicate that the head position is applicable for HAR. Moreover, we demonstrate an intelligent multi-sensory fusion concept that increases the recognition performance up to 86.13 % (recall). Furthermore, we found the head to possess very distinctive movement patterns regarding activities of daily living.

Show publication details

Haescher, Marian; Matthies, Denys J.C.; Urban, Bodo

Anomaly Detection with Smartwatches as an Opportunity for Implicit Interaction

2015

MobileHCI 2015

International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) <17, 2015, Copenhagen, Denmark>

In this paper we introduce application scenarios for implicit interaction with Smartwatches for the purpose of user assistance, to create awareness, and to enhance as well as simplify the interaction with Wearables. We envision three scenarios (1) the detection of sleep apnea, (2) the detection of epileptic seizures, and (3) a detection of accidents such as falling, car crashes etc., which are presented and discussed. Therefore, the recognition of all incidents described will be discussed under the meta-topic of anomaly detection.

Show publication details

Matthies, Denys J.C.; Perrault, Simon T.; Urban, Bodo; Zhao, Shengdong

Botential: Localizing On-Body Gestures by Measuring Electrical Signatures on the Human Skin

2015

MobileHCI 2015

International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) <17, 2015, Copenhagen, Denmark>

We present Botential, an on-body interaction method for a wearable input device that can identify the location of onbody tapping gestures, using the entire human body as an interactive surface to expand the usually limited interaction space in the context of mobility. When the sensor is being touched, Botential identifies a body part's unique electric signature, which depends on its physiological and anatomical compositions. This input method exhibits a number of advantages over previous approaches, which include: 1) utilizing the existing signal the human body already emits, to accomplish input with various body parts, 2) the ability to also sense soft and long touches, 3) an increased sensing range that covers the whole body, and 4) the ability to detect taps and hovering through clothes.

Show publication details

Haescher, Marian; Matthies, Denys J.C.; Bieber, Gerald; Urban, Bodo

CapWalk: A Capacitive Recognition of Walking-Based Activities as a Wearable Assistive Technology

2015

Proceedings of the 8th International Conference on PErvasive Technologies Related to Assistive Environments

ACM International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) <8, 2015, Corfu, Greece>

In this research project, we present an alternative approach to recognize various walking-based activities based on the technology of capacitive sensing. While accelerometry-based walking detections suffer from reduced accuracy at low speeds, the technology of capacitive sensing uses physical distance parameters, which makes it invariant to the duration of step performance. Determining accurate levels of walking activity is a crucial factor for people who perform walking with tiny step lengths such as elderlies or patients with pathologic conditions. In contrast to other gait analysis solutions, CapWalk is mobile and less affected by external influences such as bad lighting conditions, while it is also invariant to external acceleration artifacts. Our approach enables a reliable recognition of very slow walking speeds, in which accelerometer-based implementations can fail or provide high deviations. In CapWalk we present three different capacitive sensing prototypes (Leg Band, Chest Band, Insole) in the setup of loading mode to demonstrate recognition of sneaking, normal walking, fast walking, jogging, and walking while carrying weight. Our designs are wearable and could easily be integrated into wearable objects, such as shoes, pants or jackets. We envision such gathered information to be used to assist certain user groups such as diabetics, whose optimal insulin dose is depending on bread units and physical activity or elderlies whose personalized dosage of medication can be better determined based on their physical activity.

Show publication details

Meier, Anita; Matthies, Denys J.C.; Urban, Bodo; Wettach, Reto

Exploring Vibrotactile Feedback on the Body and Foot for the Purpose of Pedestrian Navigation

2015

iWOAR 2015 - 2nd international Workshop on Sensor-based Activity Recognition and Interaction

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

In this paper, we present an evaluation of vibrotactile onbody feedback for the purpose of pedestrian navigation. For this specific task, many researchers already provide different approaches such as vibrating belts, wristbands or shoes. Still, there are issues left that have to be considered, such as which body position is most suitable, what kind of vibration patterns are easy to interpret, and how applicable are vibrotactile feedback systems in real scenarios. To find answers, we reconstructed prototypes commonly found in literature and continued to further evaluate different foot-related designs. On the one hand, we learned that vibrotactile feedback at the foot reduces visual attention and thus also potentially reduces stress. However, on the other hand, we found that urban space can be very diverse, and ambiguous and therefore a vibrotactile system cannot completely replace common path finding systems for pedestrians. Rather, we envision such a system to be applied complementary as an assistive technology.

Show publication details

Matthies, Denys J.C. [Ed.]; Haescher, Marian [Ed.]; Aehnelt, Mario [Ed.]; Bieber, Gerald [Ed.]; Urban, Bodo [Ed.]

iWOAR 2015 - 2nd international Workshop on Sensor-based Activity Recognition and Interaction

2015

ACM Press

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

Wearable sensors potentially enable for a better and unobtrusive recognition of human activity and the state of rest, sleep, stress and drive the ongoing trend of the quantified self-movement. As an enabling technology, powerful, while yet inexpensive MEMS-Chips (micro-electro-mechanical system) push the penetration of a broad variety of mobile devices. Thereby, these devices gain high interest, not only in terms of general customer products, but also as integrated systems in an industrial context, either way to enable continuous monitoring of complex life processes and workplace situations. Another challenge that research is facing concerns the limited human abilities of interaction in context of mobility and in situations, in which high attention is being demanded. New and alternative ways are needed to be found in order to take advantage of all human capabilities to enable safe and unobtrusive interaction. This conference-like workshop is initiated and organized by the Fraunhofer IGD in Rostock. While we established the iWOAR workshop the 2nd time - in Rostock, North Germany - we aim to establish an annual tradition with the approach to bring together science and industry. It offers scientists, interested parties, and users in the area of sensor-based activity recognition and interaction the possibility to an exchange of experiences and a presentation of best-practice examples, as well as technical and scientific results. The workshop focuses on technologies for human activity recognition and interaction via inertial sensors (accelerometers, gyroscopes etc.) and their scientific applications.

978-1-4503-3454-9

Show publication details

Matthies, Denys J.C.; Haescher, Marian; Alm, Rebekka; Urban, Bodo

Properties of a Peripheral Head-Mounted Display (PHMD)

2015

HCI International 2015 - Posters' Extended Abstracts. Proceedings Part I

International Conference on Human-Computer Interaction (HCII) <17, 2015, Los Angeles, CA, USA>

In this paper we propose a definition for Peripheral Head-Mounted Display (PHMD) for Near Field Displays. This paper introduces a taxonomy for head-mounted displays that is based on the property of its functionality and the ability of our human eye to perceive peripheral information, instead of being technology-dependent. The aim of this paper is to help designers to understand the perception of the human eye, as well as to discuss the factors one needs to take into consideration when designing visual interfaces for PHMDs. We envision this term to help classifying devices such as Google Glass, which are often misclassified as a Head-Up Display (HUD) following NASA’s definition.

Show publication details

Trimpop, John; Haescher, Marian; Bieber, Gerald; Matthies, Denys J.C.; Lämmel, Friedrich; Burggraf, Paul

The Digital Health Companion: Personalized Health Support on Smartwatches via Recognition of Activity- and Vital-Data

2015

Proceedings of the International Summer School on Visual Computing 2015

International Summer School on Visual Computing <1, 2015, Rostock, Germany>

It has been shown that in various fields of social life, people tend to seek opportunities to measure their daily activities, bodily behaviors, and health related parameters. These kinds of activity tracking should be accomplished comfortably, unobtrusively and implicitly. Tracking behavior can be important for certain user groups, such as the growing population of elderlies. These people have a substantially higher risk of falling down, as they often live alone and thus have a greater need for other supporting services, as emergencies quickly occur. We would like to support these people, while providing a comfortable emergency detection and a monitoring of physical activities. Moreover, we believe such tracking applications to be beneficial for any user group, since we can perceive the trend of quantified self: knowing about one's own body characteristics, which is expressed in body movement. Simultaneously, we also perceive that a strong desire for a comprehensive monitoring of vital and health data is emerging. In this paper we describe the concept and implementation of the Digital Health Companion, a smart health support system that combines research developments of activity, vital data, and anomaly recognition with the functionality of contemporary smartwatches. The system's health monitoring includes an emergency detection and allows for the prevention of health risks in the short and long term through the recognition of body movement patterns.