It is widely accepted that human activities largely contribute to global emissions and thus, greatly impact climate change. Awareness promotion and adoption of green transportation mode could make a difference in the long term. To achieve behavioural change, we investigate the use of a persuasive game utilising online transportation mode recognition to afford bonuses and penalties to users based on their daily choices of transportation mode. To facilitate an easy identification of transportation mode, classification predictive models are built based on accelerometer and gyroscope historical data. Preliminary results show that the classification true-positive rate for recognising 10 different transportation classes can reach up to 95% when using a historical set (66% without). Results also reveal that the random tree classification model is a viable choice compared to random forest in terms of sustainability. Qualitative studies of the trained classifiers and measurements of Android-device gravity also raise several issues that could be addressed in future work. This research work could be enhanced through acceleration normalisation to improve device and user ambiguity.

Activity recognition (AR) from an applied perspective of ambient assisted living (AAL) and smart homes (SH) has become a subject of great interest. Promising a better quality of life, AR applied in contexts such as health, security, and energy consumption can lead to solutions capable of reaching even the people most in need. This study was strongly motivated because levels of development, deployment, and technology of AR solutions transferred to society and industry are based on software development, but also depend on the hardware devices used. The current paper identifies contributions to hardware uses for activity recognition through a scientific literature review in the Web of Science (WoS) database. This work found four dominant groups of technologies used for AR in SH and AAL—smartphones, wearables, video, and electronic components—and two emerging technologies: Wi-Fi and assistive robots. Many of these technologies overlap across many research works. Through bibliometric networks analysis, the present review identified some gaps and new potential combinations of technologies for advances in this emerging worldwide field and their uses. The review also relates the use of these six technologies in health conditions, health care, emotion recognition, occupancy, mobility, posture recognition, localization, fall detection, and generic activity recognition applications. The above can serve as a road map that allows readers to execute approachable projects and deploy applications in different socioeconomic contexts, and the possibility to establish networks with the community involved in this topic. This analysis shows that the research field in activity recognition accepts that specific goals cannot be achieved using one single hardware technology, but can be using joint solutions, this paper shows how such technology works in this regard.

Smartphone-based approaches for Human Activity Recognition have become prevalent in recent years. Despite the amount of research undertaken in the field, issues such as cross-subject variability are still posing an obstacle to the deployment of solutions in large scale, free-living settings. Personalized methods (i.e. aiming to adapt a generic classifier to a specific target user) attempt to solve this problem. The lack of labeled data for training purposes, however, represents a major barrier. This is especially the case when taking into consideration that personalization generally requires labeled data to be user-specific. This paper presents a novel personalization method combining a semi-population based approach with user adaptation. Personalization is achieved through the following. Firstly, the proposed method identifies a subset of users from the available population as best candidates for initializing the classifier to the target user. Subsequently, a semi-population Neural Network classifier is trained using data from this subset of users. The classifier’s network weights are then updated using a small amount of labeled data from the target user subsequently implementing personalization. This approach was validated on a large publicly available dataset collected in a free-living scenario. The personalized approach using the proposed method has shown to improve the overall F-score to 74.4% compared to 70.9% when using a generic non-personalized approach. Results obtained, with statistical significance being confirmed on a set of 57 users, indicate that model initialization using the semi-population approach can reduce the amount of labeled data required for personalization. As such, the proposed method for model initialization could facilitate the real-world deployment of systems implementing personalization by reducing the amount of data needed for personalization.

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).

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.

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.

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.

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.

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.