Towards Less Supervision in Activity Recognition from Wearable Sensors

Huỳnh, Tâm; Schiele, Bernt

doi:10.1109/iswc.2006.286336

Cited by 76 publications

(40 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We shape gadgets into three gatherings: picture gadgets, natural based gadgets, and wearable sensors. Motion picture gadgets are normally cameras that are introduced in the altered territories including the passageway/way out of everybody regions (to find individuals' hunt and activities), or in the living ranges or rooms [4] (to screen the customers' daily life). Cameras may likewise be found in robots for a significantly more solid evident information catch.…”

Section: A Inputs: Sensorsmentioning

confidence: 99%

Review on Various Data Mining Approaches on Smart Phone

Singh¹

2016

IJECS

View full text Add to dashboard Cite

Abstract-Smartphones are common and becoming more and heightened, with ever-growing computing, marketing, and feeling powers. It has been adjusting the landscape of people's everyday life and has subjected the options for several interesting data mining purposes, which range from wellness and health checking, particular biometric trademark, downtown computing, assistive design, and elder-care, to interior localization and navigation, etc. Individual task popularity is just a core making end behind these applications.

show abstract

Section: A Inputs: Sensorsmentioning

confidence: 99%

Review on Various Data Mining Approaches on Smart Phone

Singh¹

2016

IJECS

View full text Add to dashboard Cite

show abstract

“…However, as anticipated in the introduction, these systems suffer from serious scalability issues with respect to the number of considered context data. This challenging problem has been addressed (e.g., in [14]) by means of a combination of supervised and unsupervised learning techniques. We argue that, while similar techniques can be adopted to mitigate the problem, it is unlikely that they can provide a definitive solution.…”

Section: Related Workmentioning

confidence: 99%

COSAR: hybrid reasoning for context-aware activity recognition

Riboni

Bettini

2010

Pers Ubiquit Comput

247

159

View full text Add to dashboard Cite

Human activity recognition is a challenging problem for context-aware systems and applications. Research in this field has mainly adopted techniques based on supervised learning algorithms, but these systems suffer from scalability issues with respect to the number of considered activities and contextual data. In this paper, we propose a solution based on the use of ontologies and ontological reasoning combined with statistical inferencing. Structured symbolic knowledge about the environment surrounding the user allows the recognition system to infer which activities among the candidates identified by statistical methods are more likely to be the actual activity that the user is performing. Ontological reasoning is also integrated with statistical methods to recognize complex activities that cannot be derived by statistical methods alone. The effectiveness of the proposed technique is supported by experiments with a complete implementation of the system using commercially available sensors and an Android-based handheld device as the host for the main activity recognition module.

show abstract

“…but difficult to recognize ADLs (showering, grooming, preparing meals, etc.) using wearable sensors [7][8][9]. Home users perform an activity by interacting with appliances (or objects) within nearby location at a given time.…”

Section: Introductionmentioning

confidence: 99%

Two-Layer Hidden Markov Model for Human Activity Recognition in Home Environments

Hoque

Thapa

Yang

2016

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Activities of Daily Livings (ADLs) refer to the activities that are carried out by an individual for everyday living. Recognition of ADLs is key element for building intelligent and pervasive environments. We propose a two-layer HMM to build a ADLs recognition model that can represent the mapping between low-level sensor data and high-level activity based on the binary sensor data. We used embedded sensor with appliances or object to get object used sequence data as well as object name, type, interaction time, and location. In the first layer, we use location data of object used sensor to predict the activity class and in the second layer object used sequence data to determine the exact activity. We perform comparison with other activity recognition models using three real datasets to validate the proposed model. The results show that the proposed model achieves significantly better recognition performance than other models.

show abstract

Towards Less Supervision in Activity Recognition from Wearable Sensors

Cited by 76 publications

References 13 publications

Review on Various Data Mining Approaches on Smart Phone

Review on Various Data Mining Approaches on Smart Phone

COSAR: hybrid reasoning for context-aware activity recognition

Two-Layer Hidden Markov Model for Human Activity Recognition in Home Environments

Contact Info

Product

Resources

About