An increasing number of the elderly population wish to live an independent lifestyle, rather than rely on intrusive care programmes. A big data solution is presented using wearable sensors capable of carrying out continuous monitoring of the elderly, alerting the relevant caregivers when necessary and forwarding pertinent information to a big data system for analysis. A challenge for such a solution is the development of context-awareness through the multidimensional, dynamic and nonlinear sensor readings that have a weak correlation with observable human behaviours and health conditions. To address this challenge, a wearable sensor system with an intelligent data forwarder is discussed in this paper. The forwarder adopts a Hidden Markov Model for human behaviour recognition. Locality sensitive hashing is proposed as an efficient mechanism to learn sensor patterns. A prototype solution is implemented to monitor health conditions of dispersed users. It is shown that the intelligent forwarders can provide the remote sensors with context-awareness. They transmit only important information to the big data server for analytics when certain behaviours happen and avoid overwhelming communication and data storage. The system functions unobtrusively, whilst giving the users peace of mind in the knowledge that their safety is being monitored and analysed.

An Intelligent Information Forwarder for Healthcare Big Data Systems With Distributed Wearable Sensors

The research area of ambient assisted living has led to the development of activity recognition systems (ARS) based on human activity recognition (HAR). These systems improve the quality of life and the health care of the elderly and dependent people. However, before making them available to end users, it is necessary to evaluate their performance in recognizing activities of daily living, using data set benchmarks in experimental scenarios. For that reason, the scientific community has developed and provided a huge amount of data sets for HAR. Therefore, identifying which ones to use in the evaluation process and which techniques are the most appropriate for prediction of HAR in a specific context is not a trivial task and is key to further progress in this area of research. This work presents a systematic review of the literature of the sensor-based data sets used to evaluate ARS. On the one hand, an analysis of different variables taken from indexed publications related to this field was performed. The sources of information are journals, proceedings, and books located in specialized databases. The analyzed variables characterize publications by year, database, type, quartile, country of origin, and destination, using scientometrics, which allowed identification of the data set most used by researchers. On the other hand, the descriptive and functional variables were analyzed for each of the identified data sets: occupation, annotation, approach, segmentation, representation, feature selection, balancing and addition of instances, and classifier used for recognition. This paper provides an analysis of the sensor-based data sets used in HAR to date, identifying the most appropriate dataset to evaluate ARS and the classification techniques that generate better results.

Sensor-Based Datasets for Human Activity Recognition – A Systematic Review of Literature

Optimizing multi-sensor deployment via ensemble pruning for wearable activity recognition

Activity recognition and anomaly detection in smart homes

This paper proposes a novel feature extraction framework from mutli-party multimodal conversation for inference of personality traits and emergent leadership. The proposed framework represents multi modal features as the combination of each participant's nonverbal activity and group activity. This feature representation enables to compare the nonverbal patterns extracted from the participants of different groups in a metric space. It captures how the target member outputs nonverbal behavior observed in a group (e.g. the member speaks while all members move their body), and can be available for any kind of multiparty conversation task. Frequent co-occurrent events are discovered using graph clustering from multimodal sequences. The proposed framework is applied for the ELEA corpus which is an audio visual dataset collected from group meetings. We evaluate the framework for binary classification task of 10 personality traits. Experimental results show that the model trained with co-occurrence features obtained higher accuracy than previously related work in 8 out of 10 traits. In addition, the co-occurrence features improve the accuracy from 2 % up to 17 %.

/pdf/personality-trait-classification-via-co-occurrent-multiparty-3pzeuoeae0.pdf

Personality Trait Classification via Co-Occurrent Multiparty Multimodal Event Discovery

This paper addresses the problem of predicting the performance of decision-making groups. Towards this goal, we evaluate the predictive power of group attributes and discussion dynamics by using automatically extracted features, such as group members' aural and visual cues, interaction between team members, and influence of each team member, as well as self-reported features such as personality- and perception-related cues, hierarchical structure of the group, and individual- and group-level task performances. We tackle the inference problem from two angles depending on the way that features are extracted: 1) a holistic approach based on the entire meeting, and 2) a sequential approach based on the thin slices of the meeting. In the former, key factors affecting the group performance are identified and the prediction is achieved by support vector machines. As for the latter, we compare and contrast the classification performance of an influence model-based novel classifier with that of hidden Markov model (HMM). Experimental results indicate that the group looking cues and the influence cues are major predictors of group performance and the influence model outperforms the HMM in almost all experimental conditions. We also show that combining classifiers covering unique aspects of data results in improvement in the classification performance.

Predicting the Performance in Decision-Making Tasks: From Individual Cues to Group Interaction

Activity recognition is a key task for the development of advanced and effective ubiquitous applications in fields like ambient assisted living. A major problem in designing effective recognition algorithms is the difficulty of incorporating long-range dependencies between distant time instants without incurring substantial increase in computational complexity of inference. In this paper we present a novel approach for introducing long-range interactions based on sequential pattern mining. The algorithm searches for patterns characterizing time segments during which the same activity is performed. A probabilistic model is learned to represent the distribution of pattern matches along sequences, trying to maximize the coverage of an activity segment by a pattern match. The model is integrated in a segmental labeling algorithm and applied to novel sequences, tagged according to matches of the extracted patterns. The rationale of the approach is that restricting dependencies to span the same activity segment (i.e., sharing the same label), allows keeping inference tractable. An experimental evaluation shows that enriching sensor-based representations with the mined patterns allows improving results over sequential and segmental labeling algorithms in most of the cases. An analysis of the discovered patterns highlights non-trivial interactions spanning over a significant time horizon.

/pdf/improving-activity-recognitionby-segmental-pattern-mining-38aelzwci0.pdf

Improving Activity Recognitionby Segmental Pattern Mining

Activity recognition is a key task for the development of advanced and effective ubiquitous applications in fields like Ambient Assisted Living. Most automated approaches for the task fail to incorporate dependencies between non-close time instants. In this paper we present a simple approach for introducing longer-range interactions based on sequential pattern mining. The algorithm searches for patterns characterizing time segments during which the same activity is performed. Novel sequences are tagged according to matches of the extracted patterns. An experimental evaluation shows that enriching sensor-based representations with the mined patterns allows improving results of sequential and segmental labeling algorithms on most of the cases.

/pdf/improving-activity-recognition-by-segmental-pattern-mining-4b708rjib8.pdf

Improving activity recognition by segmental pattern mining

In this paper, we investigate the links between the interaction among the group members and team performance, as well as the group composition Towards this goal, we extract nonverbal audio-visual behavioral features from the group interaction and apply a multivariate binary Influence Model to quantify interactions between team members We compare and contrast the differences between forms of interaction for distinct performance clusters and describe the factors affecting group performance in terms of group members' influences on each other and traits such as dominance Our results show that different performance clusters have different interaction types and the groups with high and low performance have a structure where the group members are influenced by one or more people, in contrast to one-to-one pairwise influences The performance of individuals with specific traits, such as leaders and competent people, has a significant correlation with the group performance, with a correlation coefficient of over 050

http://publications.idiap.ch/downloads/papers/2014/Avci_UM3I_2014.pdf

Effect of nonverbal behavioral patterns on the performance of small groups

We propose an activity discovery framework that aims at identifying activities within data streams in the absence of data annotation. The process starts with dividing the full sensor stream into segments by identifying differences in sensor activations characterizing potential activity changes. Then, extracted segments are clustered in order to find groups of similar segments each representing a candidate activity. Lastly, parameters of a sequential labeling algorithm are estimated using segment clusters found in the previous step and the learned model is used to smooth the initial segmentation. We present experimental evaluation for two real world datasets. The results obtained show that our segmentation approaches perform almost as good as the true segmentation and that activities are discovered with a high accuracy in most of the cases. We demonstrate the effectiveness of our model by comparing it with a technique using substantial domain knowledge.

/pdf/a-fully-unsupervised-approach-to-activity-discovery-3d8pnkgc7n.pdf

Umut Avci

Papers

Predicting the Performance in Decision-Making Tasks: From Individual Cues to Group Interaction

Improving Activity Recognitionby Segmental Pattern Mining

Improving activity recognition by segmental pattern mining

Effect of nonverbal behavioral patterns on the performance of small groups

A Fully Unsupervised Approach to Activity Discovery