Activity recognition, a key component in pervasive healthcare monitoring, relies on classification algorithms that require labeled data of individuals performing the activity of interest to train accurate models. Labeling data can be performed in a lab setting where an individual enacts the activity under controlled conditions. The ubiquity of mobile and wearable sensors allows the collection of large datasets from individuals performing activities in naturalistic conditions. Gathering accurate data labels for activity recognition is typically an expensive and time-consuming process. In this paper we present two novel approaches for semi-automated online data labeling performed by the individual executing the activity of interest. The approaches have been designed to address two of the limitations of self-annotation: (i) The burden on the user performing and annotating the activity, and (ii) the lack of accuracy due to the user labeling the data minutes or hours after the completion of an activity. The first approach is based on the recognition of subtle finger gestures performed in response to a data-labeling query. The second approach focuses on labeling activities that have an auditory manifestation and uses a classifier to have an initial estimation of the activity, and a conversational agent to ask the participant for clarification or for additional data. Both approaches are described, evaluated in controlled experiments to assess their feasibility and their advantages and limitations are discussed. Results show that while both studies have limitations, they achieve 80% to 90% precision.

Artificial Neural Networks (ANNs) were created inspired by the neural networks in the human brain and have been widely applied in speech processing. The application areas of ANN include: Speech recognition, speech emotion recognition, language identification, speech enhancement, and speech separation, amongst others. Likewise, given that speech processing performed by humans involves complex cognitive processes known as auditory attention, there has been a growing amount of papers proposing ANNs supported by deep learning algorithms in conjunction with some mechanism to achieve symmetry with the human attention process. However, while these ANN approaches include attention, there is no categorization of attention integrated into the deep learning algorithms and their relation with human auditory attention. Therefore, we consider it necessary to have a review of the different ANN approaches inspired in attention to show both academic and industry experts the available models for a wide variety of applications. Based on the PRISMA methodology, we present a systematic review of the literature published since 2000, in which deep learning algorithms are applied to diverse problems related to speech processing. In this paper 133 research works are selected and the following aspects are described: (i) Most relevant features, (ii) ways in which attention has been implemented, (iii) their hypothetical relationship with human attention, and (iv) the evaluation metrics used. Additionally, the four publications most related with human attention were analyzed and their strengths and weaknesses were determined.

The scale of Internet of Things (IoT) systems has expanded in recent times and, in tandem with this, IoT solutions have developed symbiotic relationships with technologies, such as edge Computing. IoT has leveraged edge computing capabilities to improve the capabilities of IoT solutions, such as facilitating quick data retrieval, low latency response, and advanced computation, among others. However, in contrast with the benefits offered by edge computing capabilities, there are several detractors, such as centralized data storage, data ownership, privacy, data auditability, and security, which concern the IoT community. This study leveraged blockchain’s inherent capabilities, including distributed storage system, non-repudiation, privacy, security, and immutability, to provide a novel, advanced edge computing architecture for IoT systems. Specifically, this blockchain-based edge computing architecture addressed centralized data storage, data auditability, privacy, data ownership, and security. Following implementation, the performance of this solution was evaluated to quantify performance in terms of response time and resource utilization. The results show the viability of the proposed and implemented architecture, characterized by improved privacy, device data ownership, security, and data auditability while implementing decentralized storage.

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.

Activity recognition is one of the most active areas of research in ubiquitous computing. In particular, gait activity recognition is useful to identify various risk factors in people’s health that are directly related to their physical activity. One of the issues in activity recognition, and gait in particular, is that often datasets are unbalanced (i.e., the distribution of classes is not uniform), and due to this disparity, the models tend to categorize into the class with more instances. In the present study, two methods for classifying gait activities using accelerometer and gyroscope data from a large-scale public dataset were evaluated and compared. The gait activities in this dataset are: (i) going down an incline, (ii) going up an incline, (iii) walking on level ground, (iv) going down stairs, and (v) going up stairs. The proposed methods are based on conventional (shallow) and deep learning techniques. In addition, data were evaluated from three data treatments: original unbalanced data, sampled data, and augmented data. The latter was based on the generation of synthetic data according to segmented gait data. The best results were obtained with classifiers built with augmented data, with F-measure results of 0.812 ($\sigma$ = 0.078) for the shallow learning approach, and of 0.927 ($\sigma$ = 0.033) for the deep learning approach. In addition, the data augmentation strategy proposed to deal with the unbalanced problem resulted in increased classification performance using both techniques.