Activity Recognition with Fuzzy Finite Automata

Ali, Haider; Amalarethinam, D. I. George

doi:10.1109/wccct.2014.34

Cited by 8 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Many works have focused on proposing techniques for the task of activity recognition, including fuzzy finite automata [1], ensemble methods combining support vector machines, artificial neural networks, and 1-nearest neighbors [57] or combining C4.5, multilayer perceptron and logistic regression [12], Hough transformation along with random projection trees [55], online multitask learning [49] or Naive Bayes and k-nearest neighbors [23]. A review of the topic's literature from the years 2011 and 2012 along with a proposal using C4.5 and AdaBoost is provided by Ugulino et al [50], while this work was published before the PAMAP2 dataset used in this work was released.…”

Section: Activity Recognition Systemsmentioning

confidence: 99%

Feature Set Optimization for Physical Activity Recognition Using Genetic Algorithms

Baldominos

Sáez

Isasi

2015

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Physical activity is recognized as one of the key factors for a healthy life due to its beneficial effects. The range of physical activities is very broad, and not all of them require the same effort to be performed nor have the same effects on health. For this reason, automatically recognizing the physical activity performed by a user (or patient) turns out to be an interesting research field, mainly because of two reasons: (1) it increases personal awareness about the activity being performed and its consequences on health, allowing to receive proper credit (e.g. social recognition) for the effort; and (2) it allows doctors to perform continuous remote patient monitoring.This paper proposes a new approach for improving activity recognition by describing an activity recognition chain (ARC) that is optimized by means of genetic algorithms. This optimization process determines the most suitable and informative set of features that turns out into higher recognition accuracy while reducing the total number of sensors required to track the user activity. These improvements can be translated into lower costs in hardware and less intrusive devices for the patients. In this work, for the assessment of the proposed approach versus other techniques and for replication purposes, a publicly available dataset on physical activity (PAMAP2) has been used.Experiments are designed and conducted to evaluate the proposed ARC by using leave-one-subject-out cross validation and results are encouraging, reaching an average classification accuracy of about 94%.

show abstract

Section: Activity Recognition Systemsmentioning

confidence: 99%

Feature Set Optimization for Physical Activity Recognition Using Genetic Algorithms

Baldominos

Sáez

Isasi

2015

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The data collected from triaxis accelerators seem insensitive, but they could be applied to discriminate the identity by means of machine learning. There have been several researches about recognizing one's identity by the data collected from triaxis accelerators [9][10][11].…”

Section: 2mentioning

confidence: 99%

“…We focus on the data collected by the triaxis accelerator for its popularity [9][10][11]15], and its insensitive impression. Experiment results would verify the effectiveness of the clustering -anonymity.…”

Section: Performance Evaluationmentioning

confidence: 99%

A Clustering K-Anonymity Privacy-Preserving Method for Wearable IoT Devices

Liu

2018

Security and Communication Networks

View full text Add to dashboard Cite

Wearable technology is one of the greatest applications of the Internet of Things. The popularity of wearable devices has led to a massive scale of personal (user-specific) data. Generally, data holders (manufacturers) of wearable devices are willing to share these data with others to get benefits. However, significant privacy concerns would arise when sharing the data with the third party in an improper manner. In this paper, we first propose a specific threat model about the data sharing process of wearable devices' data. Then we propose a -anonymity method based on clustering to preserve privacy of wearable IoT devices' data and guarantee the usability of the collected data. Experiment results demonstrate the effectiveness of the proposed method.

show abstract

“…The condensed group shown in fig.3 is called the condensed vector sequence (CVS) of and is represented by [26]. In the CVS the subsequent occurrence of a vector implies that the vector gets repeated a certain number of times in the actual data set.…”

Section: Figure 2 Observation Vectors and Activity Labelsmentioning

confidence: 99%

“…This is because the number, order, and duration of the different steps involved in such activities vary significantly, even when the activities are performed by the same user at different times. So, in our previous work [3] we proposed a method for constructing a fuzzy finite automata to recognize user activities directly from the streams of sensor data, with no user intervention. In this paper we propose to enhance it with the ability to recognize user activities in real time.…”

Section: Introductionmentioning

confidence: 99%

Automatic Construction of Finite Automata for Online Recognition of User Activities in Smart Environments

Ali¹

2013

IOSRJEN

View full text Add to dashboard Cite

Recognizing user activities unobtrusively is very important for offering context aware services in pervasive computing environments. Because of their ability to classify given inputs in a simple and efficient manner, Finite State Machine(FSM)s have good potential to be used for recognizing user activities. However, the manual construction of FSMs in the existing methods require a domain expert with enough insight to dissect the activity of interest into an FSM. Obviously, this requirement imposes huge burden on the experts when constructing FSMs for recognizing activities that are not so repetitive in nature. In this paper, we propose a method for automatic construction of an FSM that can be used to recognize user activities in real time. The proposed method gives promising results when tested with publicly available smart home datasets.

show abstract

Activity Recognition with Fuzzy Finite Automata

Cited by 8 publications

References 12 publications

Feature Set Optimization for Physical Activity Recognition Using Genetic Algorithms

Feature Set Optimization for Physical Activity Recognition Using Genetic Algorithms

A Clustering K-Anonymity Privacy-Preserving Method for Wearable IoT Devices

Automatic Construction of Finite Automata for Online Recognition of User Activities in Smart Environments

Contact Info

Product

Resources

About