Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Unobtrusive Activity Recognition in Resource-Constrained Environments
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Computer Science.ORCID iD: 0000-0002-8752-2375
2018 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Diskret Aktivitetsigenkänning i Resursbegränsade Miljöer (Swedish)
Abstract [en]

This thesis discusses activity recognition from a perspective of unobtrusiveness, where devices are worn or placed in the environment without being stigmatising or in the way. The research focuses on performing unobtrusive activity recognition when computational and sensing resources are scarce. This includes investigating unobtrusive ways to gather data, as well as adapting data modelling and classification to small, resource-constrained, devices.

The work presents different aspects of data collection and data modelling when only using unobtrusive sensing. This is achieved by considering how different sensor placements affects prediction performance and how activity models can be created when using a single sensor, or when using a number of simple binary sensors, to perform movement analysis, recognise everyday activities, and perform stress detection. The work also investigates how classification can be performed on resource-constrained devices, resulting in a novel computation-efficient classifier and an efficient hand-made classification model. The work finally sets unobtrusive activity recognition into real-life contexts where it can be used for interventions to reduce stress, sedentary behaviour and symptoms of dementia.

The results indicate that activities can be recognised unobtrusively and that classification can be performed even on resource-constrained devices. This allows for monitoring a user’s activities over extensive periods, which could be used for creating highly personal digital interventions and in-time advice that help users make positive behaviour changes. Such digital health interventions based on unobtrusive activity recognition for resource-constrained environments are important for addressing societal challenges of today, such as sedentary behaviour, stress, obesity, and chronic diseases. The final conclusion is that unobtrusive activity recognition is a cornerstone necessary for bringing many digital health interventions into a wider use.

Abstract [sv]

Denna avhandling diskuterar aktivitetsigenkänning ur ett diskret perspektiv, där enheter bärs eller placeras i miljön utan att vara stigmatiserande eller i vägen. Forskningen fokuserar på att utföra diskret aktivitetsigenkänning när beräknings- och sensor-resurser är knappa. Detta inkluderar att undersöka diskreta sätt att samla in data, samt att anpassa datamodellering och klassificering till små, resursbegränsade enheter.

Arbetet presenterar olika aspekter av datainsamling och datamodellering när man bara använder diskreta sensorer. Detta uppnås genom att överväga hur olika sensorplaceringar påverkar prediktionsprestanda och hur aktivitetsmodeller kan skapas vid användning av en enda sensor eller vid användning av ett antal enkla binära sensorer, för att utföra rörelsesanalys, känna igen vardagliga aktiviteter och utföra stressdetektering. Arbetet undersöker också hur klassificering kan utföras på resursbegränsade enheter, vilket resulterar i en ny beräkningseffektiv klassificeringsalgoritm och en effektiv handgjord klassificeringsmodell. Slutligen sätter arbetet in diskret aktivitetsigenkänning i verkliga sammanhang där det kan användas för interventioner för att minska stress, stillasittande  beteende och symptom på demens.

Resultaten visar att diskret aktivitetsigenkänning är möjligt och att klassificeringen kan utföras även på resursbegränsade enheter. Detta möjliggör övervakning av användarens aktiviteter under längre  perioder, vilket kan användas för att skapa personliga digitala interventioner och tidsanpassad rådgivning som hjälper användarna att göra positiva beteendeförändringar. Sådana digitala hälsointerventioner baserade på diskret aktivitetsigenkänning i resursbegränsade miljöer är viktiga för att ta itu med dagens samhällsutmaningar, såsom stillasittande beteende, stress, fetma och kroniska sjukdomar. En slutsats av arbetet är att diskret aktivitetsigenkänning är en hörnsten som är nödvändig för att få en större användning av digitala hälsointerventioner.

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2018.
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
National Category
Computer Sciences Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
URN: urn:nbn:se:ltu:diva-71073ISBN: 978-91-7790-232-4 (print)ISBN: 978-91-7790-233-1 (electronic)OAI: oai:DiVA.org:ltu-71073DiVA, id: diva2:1256017
Public defence
2018-12-11, C305, Luleå Tekniska Universitet, 97187 Luleå, Luleå, 09:00 (English)
Opponent
Supervisors
Available from: 2018-10-16 Created: 2018-10-15 Last updated: 2018-12-28Bibliographically approved
List of papers
1. Analyzing Body Movements within the Laban Effort Framework using a Single Accelerometer
Open this publication in new window or tab >>Analyzing Body Movements within the Laban Effort Framework using a Single Accelerometer
Show others...
2014 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 14, no 3, p. 5725-41Article in journal (Refereed) Published
Abstract [en]

This article presents a study on analyzing body movements by using a single accelerometer sensor. The investigated categories of body movements belong to the Laban Effort Framework: Strong - Light, Free – Bound and Sudden - Sustained. All body movements were represented by a set of activities used for data collection. The calculated accuracy of detecting the body movements was based on collecting data from a single wireless tri-axial accelerometer sensor. Ten healthy subjects collected data from three body locations (chest, wrist and thigh) simultaneously in order to analyze the locations comparatively. The data was then processed and analyzed using Machine Learning techniques. The wrist placement was found to be the best single location to record data for detecting (Strong – Light) body movements using the Random Forest classifier. The wrist placement was also the best location for classifying (Bound – Free) body movements using the SVM classifier. However, the data collected from the chest placement yielded the best results for detecting (Sudden – Sustained) body movements using the Random Forest classifier. The study shows that the choice of the accelerometer placement should depend on the targeted type of movement. In addition, the choice of the classifier when processing data should also depend on the chosen location and the target movement.

National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-14175 (URN)10.3390/s140305725 (DOI)000336783300101 ()24662408 (PubMedID)d869bee7-d398-4f28-a6fc-b928a102737c (Local ID)d869bee7-d398-4f28-a6fc-b928a102737c (Archive number)d869bee7-d398-4f28-a6fc-b928a102737c (OAI)
Note
Validerad; 2014; 20140311 (basel)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-10-15Bibliographically approved
2. Designing ICT for Health and Wellbeing
Open this publication in new window or tab >>Designing ICT for Health and Wellbeing
2014 (English)In: Ambient Assisted Living and Daily Activities: 6th International Work-Conference, IWAAL 2014, Belfast, UK, December 2-5, 2014. Proceedings, Encyclopedia of Global Archaeology/Springer Verlag, 2014, p. 244-251Conference paper, Published paper (Refereed)
Abstract [en]

We are developing a monitoring and coaching app for health and wellbeing based on (1) an allostatic model of adaption combined with (2) behavioural change theory and (3) user-oriented design. The (1) allostatic model comes from stress research and was introduced to explain how human health and wellbeing can be maintained. It suggests that human health and wellbeing is a complex multidimensional phenomenon that needs to be understood holistically. We have used this model to incorporate the dimensions of human health and wellbeing that are key for stress reduction: physical and social activity and sleep. The allostatic model can allow us to understand human health and wellbeing but it does not tell us how to support the behavioural changes needed in order to reach a healthy state of allostasis. For this we rely on (2) theory of behavioural change. This article describes how we have integrated (1-3) into the system design and reports from an initial workshop with users.

Place, publisher, year, edition, pages
Encyclopedia of Global Archaeology/Springer Verlag, 2014
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 8868
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-29758 (URN)10.1007/978-3-319-13105-4_36 (DOI)354d4c74-753a-490d-9a16-6184f8cb11a1 (Local ID)978-3-319-13104-7 (ISBN)978-3-319-13105-4 (ISBN)354d4c74-753a-490d-9a16-6184f8cb11a1 (Archive number)354d4c74-753a-490d-9a16-6184f8cb11a1 (OAI)
Conference
International Work-Conference : 02/12/2014 - 05/12/2014
Note
Validerad; 2015; Nivå 1; 20141218 (qwazi)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2018-10-15Bibliographically approved
3. Classifier Optimized for Resource-constrained Pervasive Systems and Energy-efficiency
Open this publication in new window or tab >>Classifier Optimized for Resource-constrained Pervasive Systems and Energy-efficiency
Show others...
2017 (English)In: International Journal of Computational Intelligence Systems, ISSN 1875-6891, E-ISSN 1875-6883, Vol. 10, no 1, p. 1272-1279Article in journal (Refereed) Published
Abstract [en]

Computational intelligence is often used in smart environment applications in order to determine a user’scontext. Many computational intelligence algorithms are complex and resource-consuming which can beproblematic for implementation devices such as FPGA:s, ASIC:s and low-level microcontrollers. Thesetypes of devices are, however, highly useful in pervasive and mobile computing due to their small size,energy-efficiency and ability to provide fast real-time responses. In this paper, we propose a classi-fier, CORPSE, specifically targeted for implementation in FPGA:s, ASIC:s or low-level microcontrollers.CORPSE has a small memory footprint, is computationally inexpensive, and is suitable for parallel processing.The classifier was evaluated on eight different datasets of various types. Our results show thatCORPSE, despite its simplistic design, has comparable performance to some common machine learningalgorithms. This makes the classifier a viable choice for use in pervasive systems that have limitedresources, requires energy-efficiency, or have the need for fast real-time responses.

Place, publisher, year, edition, pages
Atlantis Press, 2017
Keywords
Cellular Automata, FPGA, Energy-efficient
National Category
Computer Sciences Other Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Pervasive Mobile Computing; Industrial Electronics
Identifiers
urn:nbn:se:ltu:diva-65869 (URN)10.2991/ijcis.10.1.86 (DOI)000415593600032 ()
Conference
10th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI), San Bartolome de Tirajana, Spain, Nov 29-Dec 2, 2016
Note

Konferensartikel i tidskrift

Available from: 2017-09-28 Created: 2017-09-28 Last updated: 2018-10-15Bibliographically approved
4. Utilizing a Wristband Sensor to Measure the Stress Level for People with Dementia
Open this publication in new window or tab >>Utilizing a Wristband Sensor to Measure the Stress Level for People with Dementia
Show others...
2016 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 16, no 12, article id 1989Article in journal (Refereed) Published
Abstract [en]

Stress is a common problem that affects most people with dementia and their caregivers. Stress symptoms for people with dementia are often measured by answering a checklist of questions by the clinical staff who work closely with the person with the dementia. This process requires a lot of effort with continuous observation of the person with dementia over the long term. This article investigates the effectiveness of using a straightforward method, based on a single wristband sensor to classify events of "Stressed" and "Not stressed" for people with dementia. The presented system calculates the stress level as an integer value from zero to five, providing clinical information of behavioral patterns to the clinical staff. Thirty staff members participated in this experiment, together with six residents suffering from dementia, from two nursing homes. The residents were equipped with the wristband sensor during the day, and the staff were writing observation notes during the experiment to serve as ground truth. Experimental evaluation showed relationships between staff observations and sensor analysis, while stress level thresholds adjusted to each individual can serve different scenarios.

National Category
Nursing Media and Communication Technology
Research subject
Nursing; Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-60730 (URN)10.3390/s16121989 (DOI)000391303000009 ()27886155 (PubMedID)2-s2.0-84997328010 (Scopus ID)
Note

Validerad; 2016; Nivå 2; 2016-11-28 (andbra)

Available from: 2016-11-28 Created: 2016-11-28 Last updated: 2018-10-15Bibliographically approved
5. A Domain Knowledge-based Solution for HumanActivity Recognition: the UJA Dataset Analysis
Open this publication in new window or tab >>A Domain Knowledge-based Solution for HumanActivity Recognition: the UJA Dataset Analysis
2018 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Detecting activities of daily living (ADL) allows for rich inference about user behavior,2 which can be of use in, for example, elderly care, battling chronic diseases, and psychological3 conditions. This paper proposes a domain knowledge-based solution for detecting 24 different4 ADLs in the UJA dataset. The solution is inspired by a Finite State Machine and performs activity5 recognition unobtrusively using binary sensor data only. Each day in the dataset is segmented into:6 morning, day, evening in order to facilitate the inference from the sensors. The model performs the7 ADL recognition in two steps. The first step is to detect the sequence of activities in a given event8 stream of binary sensors, and the second step is to assign a starting and ending times for each of9 detected activities. Our proposed model achieved an accuracy of 81.3% using only a very small10 amount of operations, making it an interesting approach for resource-constrained devices that are11 common in smart environments. It should be noted, however, that the model can end up in faulty12 states which could cause a series of misclassifications before the model is returned to the true state.

National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:ltu:diva-71071 (URN)
Conference
12th International Conference on Ubiquitous Computing and Ambient ‪Intelligence UCAmI 2018, (IWAAL & AmIHEALTH included)
Available from: 2018-10-02 Created: 2018-10-02 Last updated: 2019-09-06
6. Low-Power Classification using FPGA - An Approach based on Cellular Automata and Hyperdimensional Computing
Open this publication in new window or tab >>Low-Power Classification using FPGA - An Approach based on Cellular Automata and Hyperdimensional Computing
(English)Manuscript (preprint) (Other academic)
National Category
Computer Sciences
Identifiers
urn:nbn:se:ltu:diva-71168 (URN)
Available from: 2018-10-10 Created: 2018-10-10 Last updated: 2018-10-15

Open Access in DiVA

fulltext(2255 kB)212 downloads
File information
File name FULLTEXT01.pdfFile size 2255 kBChecksum SHA-512
3bab790a4b06285fa4580ac58f68b3433a701522bfb90508b01607f3aff38270753af44dd344b791c5a5ac901c96db911dfe4222dd90435300807120d7f17799
Type fulltextMimetype application/pdf

Authority records BETA

Karvonen, Niklas

Search in DiVA

By author/editor
Karvonen, Niklas
By organisation
Computer Science
Computer SciencesMedia and Communication Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 212 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 992 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf