Sensor-based Human Activity Recognition: Overcoming Issues in a Real - - PowerPoint PPT Presentation

▶
sensor based human activity recognition overcoming issues
SMART_READER_LITE
LIVE PREVIEW

Sensor-based Human Activity Recognition: Overcoming Issues in a Real - - PowerPoint PPT Presentation

Jan 22, 2023 143 likes •729 views

Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler PhD Thesis Defense Timo Sztyler 1 09.05.2019 09.05.2019 Content P H D THESIS DEFENSE 1. Motivation 2. What is Activity Recognition? 3.

slide-1
SLIDE 1

Timo Sztyler PhD Thesis Defense

Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

1

Timo Sztyler

09.05.2019

slide-2
SLIDE 2

09.05.2019 2 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Content

  • 1. Motivation
  • 2. What is Activity Recognition?
  • 3. Activity Recognition with Wearable Devices
  • 4. Activity Recognition within Smart Environments
  • 5. Conclusion and Future Work

PHD THESIS DEFENSE

Timo Sztyler

slide-3
SLIDE 3

MOTIVATION

3 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

slide-4
SLIDE 4

09.05.2019 4 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Motivation (Why?)

PHD THESIS DEFENSE

Timo Sztyler

Insufficient physical activities but also the absence of needed help can lead to difficult-to-treat long-term effects. The consequences are ... … loss of self-confidence … change in behavior to prevent issues … physical but also a psychological decline in health … premature death

slide-5
SLIDE 5

09.05.2019 5 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Motivation (How?)

PHD THESIS DEFENSE

Timo Sztyler

Human Activity Recognition has been deeply investigated in the last decade. many pervasive health care systems have been proposed knowledge about the performed activities is a fundamental requirement sensor miniaturization and wireless communications have paved the way Our goal is to overcome this shortcomings and limitations! effectiveness out of the lab is still limited effective in controlled environments

slide-6
SLIDE 6

09.05.2019 6 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition

PHD THESIS DEFENSE

Timo Sztyler

Interpreting sensor data or signals to determine the activity which initially triggered them Sensor types External sensors Wearable sensors motion, proximity, environmental, video, and physiological carried by the user and are mostly used to recognize simpler activities like motions or postures intelligent- or smart-homes are typical examples of external sensing and recognize fairly complex activities like taking medicine

slide-7
SLIDE 7

09.05.2019 7 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition

PHD THESIS DEFENSE

Timo Sztyler

Physical Activities Activities of Daily Living (ADL) refers to people's daily self-care activities As this suggests, the HAR research area is fragmented … refers to walking, standing, sitting, running, … usually recognized by sensors that are attached to certain body parts (wearable sensors) usually recognized by sensors that are attached to preselected objects or locations (external sensors)

slide-8
SLIDE 8

09.05.2019 8 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition

PHD THESIS DEFENSE

Timo Sztyler

… to recognize the daily routine Recognizing activities enables … … to learn the user's behavior … to optimize the course of the day … to verify predefined patterns like medical instructions State-of-the-art human activity recognition systems are far from being able to achieve this

slide-9
SLIDE 9

09.05.2019 9 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition

PHD THESIS DEFENSE

Timo Sztyler

Activity Recognition

  • n-body

position position aware cross- subject person- alization avoid labeled datasets handle diversity

  • nline

recogniti

  • n

person- alization

slide-10
SLIDE 10

ACTIVITY RECOGNITION WITH WEARABLE DEVICES

10 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

slide-11
SLIDE 11

11 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition with Wearable Devices

PHD THESIS DEFENSE

Timo Sztyler

Especially accelerometers were investigated for recognizing physical activities (mainly under laboratory conditions) the user decides where to carry a wearable device The step out of the lab leads to new unaddressed problems: elderly or patients might not be able to collect data movement patterns of a person could change We aim to develop robust activity recognition methods that generate high quality results in a real world setting.

09.05.2019

slide-12
SLIDE 12

12 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions

PHD THESIS DEFENSE

Timo Sztyler

Given a cross-subjects based activity recognition model, how can we adapt the model efficiently to the movement patterns of the user? Is it possible to recognize automatically the on-body position of a wearable device by the device itself? RQ1.1 RQ1.2 How does the information about the wearable device

  • n-body position influence the physical activity

recognition performance? RQ1.3 Which technique can be used to build cross- subjects based activity recognition systems? RQ1.4

09.05.2019

slide-13
SLIDE 13

13 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions (Catchwords)

PHD THESIS DEFENSE

Timo Sztyler

… recognizing the on-body position … RQ1.1 RQ1.2 … position-aware physical activity recognition …

09.05.2019

slide-14
SLIDE 14
  • 15 subjects (8 males / 7 females)
  • seven wearable devices / body positions
  • chest, forearm, head, shin, thigh, upper arm,

waist

  • acceleration, GPS, gyroscope, light, magnetic

field, and sound level

  • climbing stairs up/down, jumping, lying,

standing, sitting, running, walking

  • each subject performed each activity ≈10 minutes

Data Collection

To address the mentioned problem it was necessary to create a new data set

14 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-15
SLIDE 15

Data Collection

  • common objects and clothes to attach the devices
  • subjects walked through downtown or jogged in a forest.
  • each movement was recorded by a video camera
  • We recorded for each position and axes 1065 minutes

We focused on realistic conditions

complete, realistic, and transparent data set

15 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-16
SLIDE 16

Feature Extraction

Methods Time Correlation coefficient (Pearson), entropy (Shannon), gravity (roll, pitch), mean, mean absolute deviation, interquartile range (type R-5), kurtosis, median, standard deviation, variance Frequency Energy (Fourier, Parseval), entropy (Fourier, Shannon), DC mean (Fourier)

  • time and frequency-based features
  • gravity-based features (low-pass filter)
  • derive device orientation (roll, pitch)

So far, there is no agreed set of features … … but splitting the recorded data into small overlapping segments has been shown to be the best setting.

16 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-17
SLIDE 17

Position Detection

Scenario: Single User lying, standing, and sitting lead to misclassification static vs. dynamic activities gravity provides useful information but … Stratified sampling and 10-fold cross validation … it is no indicator of the device position Broad set of classifiers

17 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

Insights Setting

slide-18
SLIDE 18

Position Detection

  • RF outperforms the other

classifier (89%)

  • The training phase of RF was one
  • f the fastest
  • k-NN (75%), ANN (77%), and

SVM (78%) achieved reasonable results

(parameter optimization was performed) 0,00 0,02 0,04 0,06 0,08 0,10 Classifier (PF-Rate) NB kNN ANN SVM DT RF

To compare the results we also evaluated further classifiers

0,35 0,45 0,55 0,65 0,75 0,85 0,95 Classifier (F-Measure) NB kNN ANN SVM DT RF

18 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-19
SLIDE 19

Physical Activity Recognition

Feasibility: Used the results of the previous experiment (including all mistakes) Again, we evaluated two approaches …

  • position-independent activity recognition
  • position-aware activity recognition

Set of individual classifiers for each position and subject 1) First decide if static or dynamic 2) Apply activity-level depended classifier (different feature sets) 3) Apply position-depended classifier

19 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-20
SLIDE 20

Physical Activity Recognition

0,02 0,03 0,04 0,05 0,06 Classifiers

FP-Rate

NB kNN SVM ANN DT RF 0,55 0,60 0,65 0,70 0,75 0,80 0,85 Classifiers

F-measure

NB kNN SVM ANN DT RF

To compare the results we also evaluated further classifiers

  • RF achieved the highest

recognition rate (84%)

  • All classifier performed worse in

a position-independent scenario RF performed the best in all settings.

  • k-NN (70%) and SVM (71%)

performed almost equal but worse than ANN (75%) and DT (76%)

20 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-21
SLIDE 21

21 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions (catchwords)

PHD THESIS DEFENSE

Timo Sztyler

… personalization of activity recognition models… RQ1.3 … cross-subjects based activity recognition … RQ1.4

09.05.2019

slide-22
SLIDE 22

Online Random Forest

Considering online mode, the main differences are … bagging (generation of subsamples) growing of the individual trees replace sample with replacement with Poisson(1) Select thresholds and features randomly (Extreme Randomized Forest) Training Sample Prediction k=Poisson (1) k=Poisson (1) . . . Tree #1 Tree #n . . . k-times

22 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-23
SLIDE 23

Active Learning Smoothing classification result Ask User aggregate uncertain recognitions Online Learning update update Body Sensor Network Labeled data set for base model New labeled data set Updatable Model

Personalization: Online and Active Learning

23 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-24
SLIDE 24

Personalization: Online and Active Learning

Smoothing classification result Online Learning update Updatable Model

Smoothing adjusts the classification result of a single window if it is surrounded by another activity adjusted window is used to update the model focuses on minor classification errors

i i+1 i+2 i-1 i-2

24 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-25
SLIDE 25

Personalization: Online and Active Learning

Active Learning classification result Ask User aggregate uncertain recognitions Online Learning update

New labeled data set

Updatable Model

User-Feedback queries the user regarding uncertain classification results infeasible to ask for a specific window (1 sec) focuses on major classification errors specified a duration of uncertainty query result is a new data set

25 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-26
SLIDE 26

Personalization (Results)

Personalization is a continuous process … especially dynamic activities improve significantly most improvement in the first two time intervals first iteration +4%, five iterations +8% number of windows with a low confidence value decrease with each iteration

26 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-27
SLIDE 27

Parameter

Considering different confidence thresholds … Considering a different number of trees… turning point  t=0.5 10 questions  +8% 10 trees vs. 100 trees a smaller forest is more feasible concerning wearable devices

27 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

slide-28
SLIDE 28

Main Contributions

28 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

  • A new real world dataset for on-body position detection

and position-aware physical activity recognition

  • We show that our on-body position recognition method

consistently improves the recognition of physical activities in a real world setting.

  • We show that using labeled data of different people of the

same gender and with a similar level of fitness and statue is feasible for cross-subjects activity recognition for people that are unable to collect required data.

  • We present a physical activity recognition approach that

personalize cross-subjects based recognition models by querying the user with a reasonable number of questions.

slide-29
SLIDE 29

ACTIVITY RECOGNITION WITHIN SMART ENVIRONMENTS

29 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

slide-30
SLIDE 30

30 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Activity Recognition within Smart Environments

PHD THESIS DEFENSE

Timo Sztyler 09.05.2019

… it says nothing about the actual situation While the physical activity is a valuable information … Sensors that are attached to items, furniture, or walls should overcome this problem. Critical activities (Activities of Daily Living) are not recognized An ADLs is more diverse than a physical activity.

slide-31
SLIDE 31

State of the Art and Open Issues

Most ADL recognition systems rely on … acquire expensive labeled data set … supervised-based approaches: enumerating all possible actions of an ADL … knowledge-based approaches: not flexible

31 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

  • ften user/environment-specific

questionable if such models could cover different environments and modes of execution

slide-32
SLIDE 32

32 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions

PHD THESIS DEFENSE

Timo Sztyler

Given a generic model of a smart environment, how can it be adapted to a certain environment and user at run-time? Which method can be used to overcome the requirement of a large expensive labeled dataset of Activities of Daily Living? RQ2.1 RQ2.2 Which type of recognition method is suitable for handling the diversity and complexity of Activities of Daily Living? RQ2.3 How can external sensor events be exploited to recognize Activities of Daily Living in almost real- time? RQ2.4

09.05.2019

slide-33
SLIDE 33

33 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions (catchwords)

PHD THESIS DEFENSE

Timo Sztyler

… avoid large expensive labeled dataset … RQ2.1 RQ2.2 … method for handling the diversity of ADLs …

09.05.2019

slide-34
SLIDE 34

Scenario

Recognizing activities of daily living in a smart-home to support healthcare, home automation, a more independent life, … We rely on unobtrusive sensors …

34 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-35
SLIDE 35

Our approach …

… overcomes drawbacks of supervised-based approaches … relies on semantic relations (activities↔ events) … recognizes interleaved activities derived from ontological reasoning inferred by a probabilistic model not user/environment-specific, no expensive data set, …

35 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-36
SLIDE 36

System overview 1. 2. 3.

Semantic correlation reasoner Semantic integration layer Statistical analysis of events Markov Logic Network (MLN) / MAP Inference

MLN knowledge base Event(se1,et1,t1) semantic correlations

Recognized activity instances

36 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-37
SLIDE 37
  • 1. Semantic Correlation Reasoner

Why do we use Ontology (OWL2)? to derive semantic correlations (event type ↔ activity class)

stove silverware_drawer freezer Hot meal 0.5 0.33 0.5 Cold meal 0.0 0.33 0.5 Tea 0.5 0.33 0.0

prepare interact {turn on stove} is a predictive sensor event type for {Prepare hot meal} and {Prepare tea} OWL2 Reasoner infers

PPM Matrix

37 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

Ontology

slide-38
SLIDE 38

Issues of this approach

Our goal is to refine and improve semantic correlations thanks to collaborative active learning!

09.05.2019

PHD THESIS DEFENSE

38 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

Semantic correlations are computed based on an ontology written by knowledge engineers (humans) it is very likely that the ontology is incomplete it is hence questionable if it can cover different environments/mode of execution

slide-39
SLIDE 39
  • 2. Statistical Analysis of Events

Input: PPM matrix and temporally ordered events infers most probable activity class for each event allows to define activity boundaries (activity instance candidate) activity instance candidate Events Temporal extension

  • f MLN (MLNNC )

Knowledge Base

Our ontology is translated into the MLNNC model

39 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-40
SLIDE 40
  • 3. MLN / MAP Inference

Hidden predicates Observed predicates

Event 1: opens freezer (1:00pm) Event 2: turns on stove (1:02pm)

hot meal? cold meal? tea?

ADL

Sensor Event Stove

Hot meal

belong to ADL  0.5: hot meal  0.5: cold meal  0.0: tea Sensor Event Freezer

&

 0.5: hot meal  0.0: cold meal  0.5: tea

40 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-41
SLIDE 41

Data Sets

We consider two well-known data sets …

  • 1. CASAS (controlled environment)
  • 2. SmartFABER (uncontrolled environment)
  • Interleaved ADLs of twenty-one subjects
  • Sensors: movement, water, interaction, door, phone
  • Activities: fill medications dispenser, watch DVD, water plants,

answer the phone, clean, choose outfit, …

  • An elderly woman diagnosed with Mild Cognitive Impairment
  • Sensors: magnetic, motion, presence, temperature
  • Activities: taking medicines, cooking, …

41 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-42
SLIDE 42

CASAS (1/2)

0,6 0,65 0,7 0,75 0,8 0,85 0,9 ac1 ac2 ac3 ac4 ac5 ac6 ac7 ac8 MLNNC (Dataset) MLNNC (Ontology) HMM (related work)

  • Our approach outperforms HMM
  • ntological reasoning is effective

0,5 1 1,5 2 2,5 3 Delta-Start Delta-Dur

F-Measure Minutes

Candidate Refined

  • Refinement improves boundary precision

42 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-43
SLIDE 43

SmartFABER (2/2)

0,6 0,65 0,7 0,75 0,8 0,85 0,9 ac9 ac10 ac11 MLNNC (Dataset) MLNNC (Ontology) Supervised / SmartFarber 5 10 15 20 25 Delta-Start Delta-Dur

Minutes F-Measure

Candidate Refined

  • unsupervised and supervised-based

results are comparable

  • results were penalized by a poor

choice of sensors

43 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-44
SLIDE 44

44 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting

Research Questions (catchwords)

PHD THESIS DEFENSE

Timo Sztyler

… personalize model to a user and environment … RQ2.3 … recognizing ADLs in almost real-time … RQ2.4

09.05.2019

slide-45
SLIDE 45

Architecture (Extension)

  • 3. Collaborative

Feedback Aggregation

Home

Continuous stream of Sensor Events

  • 1. Probabilistic and

Ontological Activity Recognition

  • 2. Query decision

(entropy-based)

45 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-46
SLIDE 46
  • 2. Query decision

Continuous Stream of Sensor Events Online rule-based segmentation Query decision (entropy-based) Semantic correlations Segment Sensor events Query Feedback

  • 3. Collaborative

Feedback Aggregation ...

46 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-47
SLIDE 47

Online rule-based segmentation

47 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

We consider five aspects … Object interaction Change of context Consistency likelihood Time leap Change of location We introduced two metrics … Purity of a segment Number of generated segments (DS)

0,8 0,85 0,9 0,95 CASAS SmartFABER

Purity (higher is better)

Naive Our Approach 10 20 30 CASAS SmartFABER

DS (lower is better)

Naive Our Approach

slide-48
SLIDE 48
  • 3. Collaborative Feedback Aggregation

48 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

Labeled segments are transmitted to a cloud service by the participating homes it stores feedback items: correspondence between sensor event types and activities Periodically, a personalized update is transmitted to each home it contains reliable feedback items provided by similar environments

slide-49
SLIDE 49

Semantic Correlation Updater

49 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

Each home receives periodically a set of personalized feedback items predictiveness is used to provide a semantic correlation to those event types for which the original ontology did not provide a starting correlation estimated similarity is used to scale semantic correlations of an event type which were originally computed by the ontology

slide-50
SLIDE 50

Recognition results (F1 score)

50 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-51
SLIDE 51

Entropy threshold vs. number of queries

51 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019

PHD THESIS DEFENSE

slide-52
SLIDE 52

Main Contributions

52 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

An unsupervised ADL recognition method that overcomes the main drawbacks of supervised- and specification- based approaches. A novel online segmentation algorithm that combines probabilistic and symbolic reasoning to divide on the fly a continuous stream of sensor events into high quality segments. A new active learning approach to Activity of Daily Living recognition that addresses the main problems of current statistical and knowledge-based methods …

slide-53
SLIDE 53

Summary - Activity Recognition

53 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

Motion Sensors Physiological Sensors Proximity Sensors Environmental Sensors

Physical Activities (Emotional) Conditions (Usage of) Objects Location / Weather

Activities of Daily Living

Machine Learning (e.g. Trees, Networks) Probabilistic Model (e.g. Markov Logic)

Analyzing the Daily Routine

Process Mining (e.g. Conformance Checking)

slide-54
SLIDE 54

Publications

54 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

  • T. Sztyler and H. Stuckenschmidt, “On-body localization of wearable devices: An

investigation of position-aware activity recognition,” in 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE Computer Society, 2016, pp. 1–9, doi: 10.1109/PERCOM.2016.7456521.

  • D. Riboni, T. Sztyler, G. Civitarese, and H. Stuckenschmidt, “Unsupervised

recognition of interleaved activities of daily living through ontological and probabilistic reasoning,” in Proceedings of the ACM International Joint Conference

  • n Pervasive and Ubiquitous Computing. ACM, 2016, pp. 1–12, doi:

10.1145/2971648.2971691.

  • T. Sztyler, H. Stuckenschmidt, and W. Petrich, “Position-aware activity recognition

with wearable devices,” Pervasive and Mobile Computing, vol. 38, no. Part 2, pp. 281–295, 2017, doi: 10.1016/j.pmcj.2017.01.008.

  • T. Sztyler and H. Stuckenschmidt, “Online personalization of cross-subjects based

activity recognition models on wearable devices,” in 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE Computer Society, 2017, pp. 180–189, doi: 10.1109/PERCOM.2017.7917864.

slide-55
SLIDE 55

Publications

55 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

  • T. Sztyler, “Towards real world activity recognition from wearable devices,” in 2017

IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE Computer Society, 2017, pp. 97–98, doi: 10.1109/PERCOMW.2017.7917535.

  • T. Sztyler, G. Civitarese, and H. Stuckenschmidt, “Modeling and reasoning with

Problog: An application in recognizing complex activities,” in 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE Computer Society, 2018, pp. 781–786, doi: 10.1109/PERCOMW.2018.8480299.

  • C. Krupitzer, T. Sztyler, J. Edinger, M. Breitbach, H. Stuckenschmidt, and C. Becker,

“Hips do lie! A position-aware mobile fall detection system,” in 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE Computer Society, 2018, pp. 95–104, doi: 10.1109/PERCOM.2018.8444583.

  • G. Civitarese, C. Bettini, T. Sztyler, D. Riboni, and H. Stuckenschmidt, “NECTAR:

Knowledge-based collaborative active learning for activity recognition,” in 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE Computer Society, 2018, pp. 125–134, doi: 10.1109/PERCOM.2018.8444590.

slide-56
SLIDE 56

Publications

56 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler

PHD THESIS DEFENSE

09.05.2019

  • T. Sztyler, J. Carmona, J. Völker, and H. Stuckenschmidt, “Self-Tracking Reloaded:

Applying Process Mining to Personalized Health Care from Labeled Sensor Data”, Springer-Verlag Berlin Heidelberg, 2016, vol. 9930, pp. 160–180, doi: 10.1007/978-3-662-53401-4.

  • T. Sztyler, J. Völker, J. Carmona, O. Meier, and H. Stuckenschmidt, “Discovery of

personal processes from labeled sensor data - An application of process mining to personalized health care, ” in Proceedings of the International Workshop on Algorithms & Theories for the Analysis of Event Data, ATAED. CEUR-WS.org, 2015,

  • pp. 31–46. ISSN 1613-0073
  • C. Civitarese, G. Bettini, T. Sztyler, D. Riboni, and H. Stuckenschmidt, “newNECTAR:

Collaborative active learning for knowledge-based probabilistic activity recognition”, Pervasive and Mobile Computing (2019), vol. 56, pp. 88–105, doi: j.pmcj.2019.04.006

  • and more ….
slide-57
SLIDE 57

Thank you for your attention :) …and especially “thank you” to all my friends and co-authors!

PHD THESIS DEFENSE

57 Sensor-based Human Activity Recognition: Overcoming Issues in a Real World Setting Timo Sztyler 09.05.2019