Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 64) Show all publications
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K. & Hallberg, J. (2018). Automatic annotation for human activity recognition in free living using a smartphone. Sensors, 18(7), Article ID 2203.
Open this publication in new window or tab >>Automatic annotation for human activity recognition in free living using a smartphone
Show others...
2018 (English)In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 18, no 7, article id 2203Article in journal (Refereed) Published
Abstract [en]

Data annotation is a time-consuming process posing major limitations to the development of Human Activity Recognition (HAR) systems. The availability of a large amount of labeled data is required for supervised Machine Learning (ML) approaches, especially in the case of online and personalized approaches requiring user specific datasets to be labeled. The availability of such datasets has the potential to help address common problems of smartphone-based HAR, such as inter-person variability. In this work, we present (i) an automatic labeling method facilitating the collection of labeled datasets in free-living conditions using the smartphone, and (ii) we investigate the robustness of common supervised classification approaches under instances of noisy data. We evaluated the results with a dataset consisting of 38 days of manually labeled data collected in free living. The comparison between the manually and the automatically labeled ground truth demonstrated that it was possible to obtain labels automatically with an 80–85% average precision rate. Results obtained also show how a supervised approach trained using automatically generated labels achieved an 84% f-score (using Neural Networks and Random Forests); however, results also demonstrated how the presence of label noise could lower the f-score up to 64–74% depending on the classification approach (Nearest Centroid and Multi-Class Support Vector Machine).

Place, publisher, year, edition, pages
MDPI, 2018
National Category
Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-70137 (URN)10.3390/s18072203 (DOI)29987218 (PubMedID)2-s2.0-85050029995 (Scopus ID)
Note

Validerad;2018;Nivå 2;2018-07-19 (inah)

Available from: 2018-07-19 Created: 2018-07-19 Last updated: 2018-08-08Bibliographically approved
Cleland, I., Donnelly, M., Nugent, C., Hallberg, J., Espinilla, M. & Garcia-Constantino, M. (2018). Collection of a Diverse, Realistic and Annotated Dataset for Wearable Activity Recognition. In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018: . Paper presented at 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 19-23 March 2018, Athens, Greece (pp. 555-560). IEEE, Article ID 8480322.
Open this publication in new window or tab >>Collection of a Diverse, Realistic and Annotated Dataset for Wearable Activity Recognition
Show others...
2018 (English)In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018, IEEE, 2018, p. 555-560, article id 8480322Conference paper, Published paper (Refereed)
Abstract [en]

This paper discusses the opportunities and challenges associated with the collection of a large scale, diverse dataset for Activity Recognition. The dataset was collected by 141 undergraduate students, in a controlled environment. Students collected triaxial accelerometer data from a wearable accelerometer whilst each carrying out 3 of the 18 investigated activities, categorized into 6 scenarios of daily living. This data was subsequently labelled, anonymized and uploaded to a shared repository. This paper presents an analysis of data quality, through outlier detection and assesses the suitability of the dataset for the creation and validation of Activity Recognition models. This is achieved through the application of a range of common data driven machine learning approaches. Finally, the paper describes challenges identified during the data collection process and discusses how these could be addressed. Issues surrounding data quality, in particular, identifying and addressing poor calibration of the data were identified. Results highlight the potential of harnessing these diverse data for Activity Recognition. Based on a comparison of six classification approaches, a Random Forest provided the best classification (F-measure: 0.88). In future data collection cycles, participants will be encouraged to collect a set of 'common' activities, to support generation of a larger homogeneous dataset. Future work will seek to refine the methodology further and to evaluate model on new unseen data.

Place, publisher, year, edition, pages
IEEE, 2018
National Category
Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-72319 (URN)10.1109/PERCOMW.2018.8480322 (DOI)2-s2.0-85056470379 (Scopus ID)978-1-5386-3227-7 (ISBN)
Conference
2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 19-23 March 2018, Athens, Greece
Available from: 2018-12-18 Created: 2018-12-18 Last updated: 2018-12-18Bibliographically approved
Kostenius, C., Hallberg, J. & Lindqvist, A.-K. (2018). Gamification of health education: Schoolchildren’s participation in the development of a serious game to promote health and learning. Health Education, 118(4), 354-368
Open this publication in new window or tab >>Gamification of health education: Schoolchildren’s participation in the development of a serious game to promote health and learning
2018 (English)In: Health Education, ISSN 0965-4283, E-ISSN 1758-714X, Vol. 118, no 4, p. 354-368Article in journal (Refereed) Published
Abstract [en]

Purpose

The use of modern technology has many challenges and risks. However, by collaborating with schoolchildren, ideas to effectively promote health and learning in school can be identified. This study aimed to examine how a participatory approach can deepen the understanding of how schoolchildren relate to and use gamification as a tool to promote physical activity and learning.

Design/methodology/approach

Inspired by the concept and process of empowerment and child participation, the methodological focus of this study was on consulting schoolchildren. During a 2-month period, 18 schoolchildren (10–12-years-old) participated in workshops to create game ideas that would motivate them to be physically active and learn in school.

Findings

The phenomenological analysis resulted in one main theme, ‘Playing games for fun to be the best I can be’. This consisted of four themes with two sub-themes each. The findings offer insights on how to increase physical activity and health education opportunities using serious games in school.

Originality/value

The knowledge gained provides gamification concepts and combinations of different technological applications to increase health and learning, as well as motivational aspects suggested by the schoolchildren. The findings are discussed with health promotion and health education in mind.

Place, publisher, year, edition, pages
Emerald Group Publishing Limited, 2018
National Category
Other Health Sciences Physiotherapy Media and Communication Technology
Research subject
Health Science; Physiotherapy; Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-68485 (URN)10.1108/HE-10-2017-0055 (DOI)2-s2.0-85047988587 (Scopus ID)
Note

Validerad;2018;Nivå 2;2018-06-01 (svasva)

Available from: 2018-04-24 Created: 2018-04-24 Last updated: 2018-09-14Bibliographically approved
Synnes, K., Lilja, M., Nyman, A., Espinilla, M., Cleland, I., Sanchez Comas, A. G., . . . Nugent, C. (2018). H2Al - The Human Health and Activity Laboratory. In: MDPI (Ed.), 12th International Conference on Ubiquitous Computing and Ambient ‪Intelligence (UCAmI 2018), Punta Cana, Dominican Republic, 4-7 December, 2018.: . Paper presented at International Conference on Ubiquitous Computing and Ambient ‪Intelligence. MDPI, 2, Article ID 1241.
Open this publication in new window or tab >>H2Al - The Human Health and Activity Laboratory
Show others...
2018 (English)In: 12th International Conference on Ubiquitous Computing and Ambient ‪Intelligence (UCAmI 2018), Punta Cana, Dominican Republic, 4-7 December, 2018. / [ed] MDPI, MDPI, 2018, Vol. 2, article id 1241Conference paper, Published paper (Refereed)
Abstract [en]

The Human Health and Activity Laboratory (H2Al) is a new research facility at Luleå University of Technology implemented during 2018 as a smart home environment in an educational training apartment for nurses and therapists at the Luleå campus. This paper presents the design and implementation of the lab together with a discussion on potential impact. The aim is to identify and overcome economical, technical and social barriers to achieve an envisioned good and equal health and welfare within and from home environments. The lab is equipped with multiple sensor and actuator systems in the environment, worn by persons and based on digital information. The systems will allow for advanced capture, filtering, analysis and visualization of research data such as A/V, EEG, ECG, EMG, GSR, respiration and location while being able to detect falls, sleep apnea and other critical health and wellbeing issues. The resulting studies will be aimed towards supporting and equipping future home environments and care facilities, spanning from temporary care to primary care at hospitals, with technologies for activity and critical health and wellness issue detection. The work will be conducted at an International level and within a European context, based on a collaboration with other smart labs, such that experiments can be replicated at multiple sites. This paper presents some initial lessons learnt including design, setup and configuration for comparison of sensor placements and configurations as well as analytical methods.

Place, publisher, year, edition, pages
MDPI, 2018
National Category
Computer and Information Sciences
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-72988 (URN)10.3390/proceedings2191241 (DOI)
Conference
International Conference on Ubiquitous Computing and Ambient ‪Intelligence
Projects
REMIND
Funder
The Kempe Foundations
Available from: 2019-02-21 Created: 2019-02-21 Last updated: 2019-09-06
Cruciani, F., Cleland, I., Nugent, C., McCullagh, P., Synnes, K. & Hallberg, J. (2018). Personalized Online Training for Physical Activity monitoring using weak labels. In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops): . Paper presented at 2nd International Workshop on Annotation of useR Data for UbiquitOUs Systems (ARDUOUS 2018), Athens, Greece, March 19-23, 2018 (pp. 567-572). IEEE
Open this publication in new window or tab >>Personalized Online Training for Physical Activity monitoring using weak labels
Show others...
2018 (English)In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), IEEE, 2018, p. 567-572Conference paper, Published paper (Refereed)
Abstract [en]

The use of smartphones for activity recognition is becoming common practice. Most approaches use a single pretrained classifier to recognize activities for all users. Research studies, however, have highlighted how a personalized trained classifier could provide better accuracy. Data labeling for ground truth generation, however, is a time-consuming process. The challenge is further exacerbated when opting for a personalized approach that requires user specific datasets to be labeled, making conventional supervised approaches unfeasible. In this work, we present early results on the investigation into a weakly supervised approach for online personalized activity recognition. This paper describes: (i) a heuristic to generate weak labels used for personalized training, (ii) a comparison of accuracy obtained using a weakly supervised classifier against a conventional ground truth trained classifier. Preliminary results show an overall accuracy of 87% of a fully supervised approach against a 74% with the proposed weakly supervised approach.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
data annotation, weakly supervised learning, smartphone activity recognition
National Category
Computer and Information Sciences Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-68146 (URN)10.1109/PERCOMW.2018.8480292 (DOI)2-s2.0-85050025511 (Scopus ID)978-1-5386-3227-7 (ISBN)
Conference
2nd International Workshop on Annotation of useR Data for UbiquitOUs Systems (ARDUOUS 2018), Athens, Greece, March 19-23, 2018
Available from: 2018-04-03 Created: 2018-04-03 Last updated: 2019-01-18Bibliographically approved
Kikhia, B., Stavropoulos, T. G., Meditskos, G., Kompatsiaris, I., Hallberg, J., Sävenstedt, S. & Melander, C. (2018). Utilizing ambient and wearable sensors to monitor sleep and stress for people with BPSD in nursing homes (ed.). Journal of Ambient Intelligence and Humanized Computing, 9(2), 261-273
Open this publication in new window or tab >>Utilizing ambient and wearable sensors to monitor sleep and stress for people with BPSD in nursing homes
Show others...
2018 (English)In: Journal of Ambient Intelligence and Humanized Computing, ISSN 1868-5137, E-ISSN 1868-5145, Vol. 9, no 2, p. 261-273Article in journal (Refereed) Published
Abstract [en]

Clinical assessment of behavioral and psychological symptoms of dementia (BPSD) in nursing homes is often based on staff member’s observations and the use of the Neuropsychiatric Inventory-Nursing Home version (NPI-NH) instrument. This requires continuous observation of the person with BPSD, and a lot of effort and manual input from the nursing home staff. This article presents the DemaWare@NH monitoring framework system, which complements traditional methods in measuring patterns of behavior, namely sleep and stress, for people with BPSD in nursing homes. The framework relies on ambient and wearable sensors for observing the users and analytics to assess their conditions. In our proof-of-concept scenario, four residents from two nursing homes were equipped with sleep and skin sensors, whose data is retrieved, processed and analyzed by the framework, detecting and highlighting behavioral problems, and providing relevant, accurate information to clinicians on sleep and stress patterns. The results indicate that structured information from sensors can ease and improve the understanding of behavioral patterns, and, as a consequence, the efficiency of care interventions, yielding a positive impact on the quality of the clinical assessment process for people with BPSD in nursing homes.

Place, publisher, year, edition, pages
Springer, 2018
National Category
Media and Communication Technology Nursing
Research subject
Pervasive Mobile Computing; Nursing
Identifiers
urn:nbn:se:ltu:diva-9225 (URN)10.1007/s12652-015-0331-6 (DOI)000429249200005 ()7c97293a-e058-4224-b5bb-882faec2867e (Local ID)7c97293a-e058-4224-b5bb-882faec2867e (Archive number)7c97293a-e058-4224-b5bb-882faec2867e (OAI)
Note

Validerad;2018;Nivå 2;2018-04-04 (rokbeg)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-04-26Bibliographically approved
Karvonen, N., Jimenez, L. L., Gomez Simon, M., Nilsson, J., Kikhia, B. & Hallberg, J. (2017). Classifier Optimized for Resource-constrained Pervasive Systems and Energy-efficiency. Paper presented at 10th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI), San Bartolome de Tirajana, Spain, Nov 29-Dec 2, 2016. International Journal of Computational Intelligence Systems, 10(1), 1272-1279
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
Hedemalm, E., Hallberg, J., Kor, A.-L., Andersson, K. & Pattinson, C. (2017). Promoting green transportation via persuasive games. In: International SEEDS Conference 2017: Sustainable Ecological Engineering Design for Society – 13th & 14th September 2017. Paper presented at International conference on Sustainable, Ecological Engineering Design for Society (SEEDS), Leeds, 13–14 September 2017.
Open this publication in new window or tab >>Promoting green transportation via persuasive games
Show others...
2017 (English)In: International SEEDS Conference 2017: Sustainable Ecological Engineering Design for Society – 13th & 14th September 2017, 2017Conference paper, Published paper (Refereed)
Abstract [en]

It is now widely accepted that human behaviour accounts for a large portion of total global emissions, and thus influences climate change to a large extent (IPCC, 2014). Changing human behaviour when it comes to mode of transportation is one component which could make a difference in the long term. In order to achieve behavioural change, we investigate the use of a persuasive multiplayer game. Transportation mode recognition is used within the game to provide bonuses and penalties to users based on their daily choices regarding transportation. Preliminary results from testers of the game indicate that using games may be successful in causing positive change in user behaviour.

National Category
Engineering and Technology Media and Communication Technology
Research subject
Pervasive Mobile Computing
Identifiers
urn:nbn:se:ltu:diva-64774 (URN)
Conference
International conference on Sustainable, Ecological Engineering Design for Society (SEEDS), Leeds, 13–14 September 2017
Available from: 2017-07-04 Created: 2017-07-04 Last updated: 2019-04-03
Karvonen, N., Kikhia, B., Jimenez, L. L., Gomez Simon, M. & Hallberg, J. (2016). A Computationally Inexpensive Classifier Merging Cellular Automata and MCP-Neurons. In: Carmelo R. García, Pino Caballero-Gil, Mike Burmester, Alexis Quesada-Arencibia (Ed.), Ubiquitous Computing and Ambient Intelligence: 10th International Conference, UCAmI 2016, San Bartolomé de Tirajana, Gran Canaria, Spain, November 29 – December 2, 2016, Part II. Paper presented at 10th International Conference, UCAmI 2016, San Bartolomé de Tirajana, Gran Canaria, Spain, November 29 – December 2, 2016 (pp. 368-379). Springer, 2
Open this publication in new window or tab >>A Computationally Inexpensive Classifier Merging Cellular Automata and MCP-Neurons
Show others...
2016 (English)In: Ubiquitous Computing and Ambient Intelligence: 10th International Conference, UCAmI 2016, San Bartolomé de Tirajana, Gran Canaria, Spain, November 29 – December 2, 2016, Part II / [ed] Carmelo R. García, Pino Caballero-Gil, Mike Burmester, Alexis Quesada-Arencibia, Springer, 2016, Vol. 2, p. 368-379Conference paper, Published paper (Refereed)
Abstract [en]

There is an increasing need for personalised and context-aware services in our everyday lives and we rely on mobile and wearable devices to provide such services. Context-aware applications often make use of machine-learning algorithms, but many of these are too complex or resource-consuming for implementation on some devices that are common in pervasive and mobile computing. The algorithm presented in this paper, named CAMP, has been developed to obtain a classifier that is suitable for resource-constrained devices such as FPGA:s, ASIC:s or microcontrollers. The algorithm uses a combination of the McCulloch-Pitts neuron model and Cellular Automata in order to produce a computationally inexpensive classifier with a small memory footprint. The algorithm consists of a sparse binary neural network where neurons are updated using a Cellular Automata rule as the activation function. Output of the classifier is depending on the selected rule and the interconnections between the neurons. Since solving the input-output mapping mathematically can not be performed using traditional optimization algorithms, the classifier is trained using a genetic algorithm. The results of the study show that CAMP, despite its minimalistic structure, has a comparable accuracy to that of more advanced algorithms for the datasets tested containing few classes, while performing poorly on the datasets with a higher amount of classes. CAMP could thus be a viable choice for solving classification problems in environments with extreme demands on low resource consumption

Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 10070
National Category
Media and Communication Technology
Research subject
Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-60640 (URN)10.1007/978-3-319-48799-1_42 (DOI)000389507400042 ()2-s2.0-85009786711 (Scopus ID)978-3-319-48798-4 (ISBN)978-3-319-48799-1 (ISBN)
Conference
10th International Conference, UCAmI 2016, San Bartolomé de Tirajana, Gran Canaria, Spain, November 29 – December 2, 2016
Available from: 2016-11-23 Created: 2016-11-23 Last updated: 2018-07-10Bibliographically approved
Kostenius, C., Hallberg, J. & Lindqvist, A.-K. (2016). A slice of the win-win game: Swedish schoolchildren’s ideas on gamification to promote physical activity and cognitive ability (ed.). Paper presented at Nordic Health Promotion Research Conference : 20/06/2016 - 22/06/2016. Paper presented at Nordic Health Promotion Research Conference : 20/06/2016 - 22/06/2016.
Open this publication in new window or tab >>A slice of the win-win game: Swedish schoolchildren’s ideas on gamification to promote physical activity and cognitive ability
2016 (English)Conference paper, Poster (with or without abstract) (Other academic)
National Category
Other Health Sciences Physiotherapy Media and Communication Technology
Research subject
Health Science; Physiotherapy; Mobile and Pervasive Computing
Identifiers
urn:nbn:se:ltu:diva-30367 (URN)425e854f-28e3-4b53-8d05-21d965785f15 (Local ID)425e854f-28e3-4b53-8d05-21d965785f15 (Archive number)425e854f-28e3-4b53-8d05-21d965785f15 (OAI)
Conference
Nordic Health Promotion Research Conference : 20/06/2016 - 22/06/2016
Note
Godkänd; 2016; 20160627 (andbra)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2018-04-23Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3191-8335

Search in DiVA

Show all publications