Accelerometer-based activity recognition on a mobile phone using cepstral features and quantized gmms

Leppänen, Jussi; Eronen, Antti

doi:10.1109/icassp.2013.6638306

Cited by 12 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This suggests that preferable parts to mount the accelerometers are in the main body, such as pelvis [12], chest [13] or head [14]. Recently, such techniques have been integrated into mobile phones [15][16][17], or deployed with additional sensors to improve accuracy, such as gyroscopes [18], microphones [19], and floor sensors [20].…”

Section: Related Workmentioning

confidence: 97%

Multi-scale Conditional Random Fields for first-person activity recognition on elders and disabled patients

Zhao

Faux

Ramos

2015

Pervasive and Mobile Computing

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 97%

Multi-scale Conditional Random Fields for first-person activity recognition on elders and disabled patients

Zhao

Faux

Ramos

2015

Pervasive and Mobile Computing

View full text Add to dashboard Cite

“…For the purposes of this paper, sensor-based activity recognition is considered. Sensor-based activity recognition may be further classified into wearable and mobile sensor-enabled recognition [3,8,15,17], and smart home-enabled activity recognition [9,12]. In terms of real-time activity recognition, the vast majority of documented research is based upon wearable accelerometer sensors, which usually stream sensor data continuously at a fixed frequency.…”

Section: Related Researchmentioning

confidence: 99%

Dynamic sensor event segmentation for real-time activity recognition in a smart home context

Wan

O’Grady

O’Hare

2014

Pers Ubiquit Comput

101

View full text Add to dashboard Cite

Activity recognition is fundamental to many of the services envisaged in pervasive computing and ambient intelligence scenarios. However, delivering sufficiently robust activity recognition systems that could be deployed with confidence in an arbitrary real-world setting remains an outstanding challenge. Developments in wireless, inexpensive and unobtrusive sensing devices have enabled the capture of large data volumes, upon which a variety of machine learning techniques have been applied in order to facilitate interpretation of and inference upon such data. Much of the documented research in this area has in the main focused on recognition across pre-segmented sensor data. Such approaches are insufficient for near real-time analysis as is required for many services, such as those envisaged by ambient assisted living. This paper presents a novel near real-time sensor segmentation approach that incorporates the notions of both sensor and time correlation.

show abstract

“…In the case of human activity recognition, often the recognition is done using user-independent models and good recognition rates have been achieved (for instance [2], [3], [4], [5]). However, it has been shown that user-independent models do not work accurately for instance if trained with healthy study subjects and tested with subjects who have difficulties to move [6].…”

Section: Problem Statement and Related Workmentioning

confidence: 99%

“…In addition, in the real-life many other unseen contingencies can happen and the training data set used to train the recognition models cannot include all of these. This means that model that seem to work really well when tested with testing data do not work as well when it is used online, in real-time, real-life applications [1].In the case of human activity recognition, often the recognition is done using user-independent models and good recognition rates have been achieved (for instance [2], [3], [4], [5]). However, it has been shown that user-independent models do not work accurately for instance if trained with healthy study subjects and tested with subjects who have difficulties to move [6].…”

mentioning

confidence: 99%

Personal models for eHealth - improving user-dependent human activity recognition models using noise injection

Siirtola

Koskimäki

Röning

2016

2016 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

Abstract-In this paper, a noise injection method to improve personal recognition models is presented. The idea of the method is to build more general recognition models for eHealth using a small original data set and by expanding the area covered by training data using noise injection. This way, it is possible to train models that are less vulnerable to changing conditions, and thus more accurate, but still the data gathering phase can be non-burdensome. The proposed method was tested using two classifiers (linear discriminant analysis and quadratic discriminant analysis) and three human activity recognition data sets collected using inertial sensors of a smartphone. Two of these data sets are open data sets. The results show that noise injection improves the true positive recognition rates. With first data set the improvement varies from 1.3 to 2.0 percentage units, with second from 1.4 to 4.5 percentage units, and with third the highest improvement was 2.5 percentage units. Moreover, the results show that the method improves precision and reduces false positive rates. In addition, experiments were made using different training set sizes to show that the improvement in true positive rate is bigger if the original training data set is small. In this study, the method is experimented using human activity data sets but it is not limited to this application area and can be used with any time series data.Index Terms-Activity recognition; eHealth; noise injection; smartphone; inertial sensors; accelerometer; personal models; I. PROBLEM STATEMENT AND RELATED WORKIn eHealth it is often important to recognize what a person is doing or a condition of a person. However, people are different, and therefore, a user-independent recognition model that provides accurate recognition results for one person does not necessary provide as high results for other person. There are many possible reasons for this phenomena. For instance, person's can be different: physical characteristics, health state or gender can have an effect to the recognition results. On the other hand, external factor such as weather, terrain and location can cause problems to recognition models. In addition, in the real-life many other unseen contingencies can happen and the training data set used to train the recognition models cannot include all of these. This means that model that seem to work really well when tested with testing data do not work as well when it is used online, in real-time, real-life applications [1].In the case of human activity recognition, often the recognition is done using user-independent models and good recognition rates have been achieved (for instance [2], [3], [4], [5]). However, it has been shown that user-independent models do not work accurately for instance if trained with healthy study subjects and tested with subjects who have difficulties to move [6]. Personal models could solve this problem. In fact, it has been shown that user-dependent models are more accurate than user-independent ones [7]. However, in [8] it was shown...

show abstract

Accelerometer-based activity recognition on a mobile phone using cepstral features and quantized gmms

Cited by 12 publications

References 11 publications

Multi-scale Conditional Random Fields for first-person activity recognition on elders and disabled patients

Multi-scale Conditional Random Fields for first-person activity recognition on elders and disabled patients

Dynamic sensor event segmentation for real-time activity recognition in a smart home context

Personal models for eHealth - improving user-dependent human activity recognition models using noise injection

Contact Info

Product

Resources

About