Improving Human Activity Recognition and its Application in Early Stroke Diagnosis

Villar, José R.; González, Silvia; Sedano, Javier; Chira, Camelia; Trejo-Gabriel-Galán, J.M.

doi:10.1142/s0129065714500361

Cited by 60 publications

(24 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further research is needed in order to make the SAX4HAR algorithm more robust in this type of scenario. In addition, the SAX4HAR approach has been compared with a well-known HAR method: the GFFSM proposed in [2], adapted in [15] and outperformed in [48]. The two versions of this latter work will be used in the comparison; namely the enhanced Pittsburgh GFFSM (wGFFSM) and the Michigan-style classifier using boosting and single winner inference (bGFFSM).…”

Section: Evaluation Of the Har Methodsmentioning

confidence: 99%

“…In a previous study, a HAR method making use of GFFSM [6] was adapted in [15] and enhanced [48]. However, there is a limit on the number of activities that can be considered, and finding valid alternatives might enhance the overall HAR and assist with the correct definition of the aforementioned limit.…”

Section: Proposed Approach For Stroke Episode Recognition and Stroke mentioning

confidence: 99%

“…A two-stage HAR method has recently been proposed in [48]: on the one hand, a Feature Selection (FS) stage reduces the input domain dimensionality; on the other, GFFSM modeling generates the classifier. The cross validation considered the crossing of individuals rather than the crossing of data samples.…”

Section: Human Activity Recognition Using Gffsmmentioning

confidence: 99%

“…The last stage of the proposal referred to in [48] deals with the learning of the final GFFSM models once the feature subset has been chosen. The original GFFSM -where the 3DACC were placed on the center of the individual's back-has been adapted to the current problem.…”

Section: Human Activity Recognition Using Gffsmmentioning

confidence: 99%

“…A method based on Genetic Fuzzy Finite State Machines (GFFSM) was recently proposed for Human Activity Recognition (HAR) [6], and applied in the early stroke diagnosis [48].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A hybrid intelligent recognition system for the early detection of strokes

Villar

Chira

Sedano

et al. 2015

ICA

Self Cite

View full text Add to dashboard Cite

Abstract. The increasing prevalence of wearable sensors and low-cost mobile devices have prompted the development of systems for automated diagnosis. Here we focus on models and algorithms for the early detection of strokes that are implanted in a wearable device that generates warning alarms and automatically connects to e-health services, ensuring timely interventions at the onset of a stroke. The proposed approach employs two wearable devices to monitor movement data that involve two main stages: Human Activity Recognition (HAR) and alarm generation. Two different HAR methods capable of classifying current human activity are developed and compared: one uses genetic fuzzy finite-state machines, and the other relies on Time Series (TS) analysis. Furthermore, an algorithm using Symbolic Aggregate approXimation (SAX) TS representation is proposed for alarm generation purposes, which is triggered by the detection of anomalous movements. The proposed methods are evaluated using realistic data gathered from healthy individuals. A discussion of topics related to the learning issues involved in these techniques is included. It is worth mentioning that the proposed algorithms can be easily transferred to embedded systems and can benefit from reduced learning costs.

show abstract

Section: Evaluation Of the Har Methodsmentioning

confidence: 99%

Section: Proposed Approach For Stroke Episode Recognition and Stroke mentioning

confidence: 99%

Section: Human Activity Recognition Using Gffsmmentioning

confidence: 99%

Section: Human Activity Recognition Using Gffsmmentioning

confidence: 99%

“…A method based on Genetic Fuzzy Finite State Machines (GFFSM) was recently proposed for Human Activity Recognition (HAR) [6], and applied in the early stroke diagnosis [48].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A hybrid intelligent recognition system for the early detection of strokes

Villar

Chira

Sedano

et al. 2015

ICA

Self Cite

View full text Add to dashboard Cite

show abstract

DTW as Alignment Function in the Context of Time Series Balancing

Cal

Villar

Sedano

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Peak Detection Enhancement in Autonomous Wearable Fall Detection

Villar

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Fall Detection (FD) has drawn the attention of the research community for several years. A possible solution relies on on-wrist wearable devices including tri-axial accelerometers performing FD autonomously. This type of approaches makes use of an event detection stage followed by some pre-processing and a final classification stage. The event detection stage is basically performed using thresholds or a combination of thresholds and finite state machines. In this research, a novel event detection is proposed avoiding the use of user predefined thresholds; this fact represents the main contribution of this study. It is worth noticing that avoiding the use of thresholds make solutions more general and easy to deploy. Moreover, a new set of features are extracted from a time window whenever a peak is detected, classifying it with a Neural Network. The proposal is evaluated using the UMA Fall, one of the publicly available simulated fall detection data sets. Results show the improvements in the event detection using the new proposal, outperforming the base line method; however, the classification stage still needs improvement. Future work includes introducing a finite state machine in the event detection method, adding extra features and a pre-classification of the post-peak interval and a better training configuration of the Neural Networks.

show abstract

Improving Human Activity Recognition and its Application in Early Stroke Diagnosis

Cited by 60 publications

References 46 publications

A hybrid intelligent recognition system for the early detection of strokes

A hybrid intelligent recognition system for the early detection of strokes

DTW as Alignment Function in the Context of Time Series Balancing

Peak Detection Enhancement in Autonomous Wearable Fall Detection

Contact Info

Product

Resources

About