Abstract
The indoor location of individuals is a key contextual variable for commercial and assisted location-based services and applications. Commercial centers and medical buildings (e.g., hospitals) require location information of their users/patients to offer the services that are needed at the correct moment. Several approaches have been proposed to tackle this problem. In this paper, we present the development of an indoor location system which relies on the human activity recognition approach, using sound as an information source to infer the indoor location based on the contextual information of the activity that is realized at the moment. In this work, we analyze the sound information to estimate the location using the contextual information of the activity. A feature extraction approach to the sound signal is performed to feed a random forest algorithm in order to generate a model to estimate the location of the user. We evaluate the quality of the resulting model in terms of sensitivity and specificity for each location, and we also perform out-of-bag error estimation. Our experiments were carried out in five representative residential homes. Each home had four individual indoor rooms. Eleven activities (brewing coffee, cooking, eggs, taking a shower, etc.) were performed to provide the contextual information. Experimental results show that developing an indoor location system (ILS) that uses contextual information from human activities (identified with data provided from the environmental sound) can achieve an estimation that is 95% correct.
Highlights
The physical indoor location of a user has become an important context variable because it is fundamental information that is needed to increase the capabilities of other systems to offer location-based services (LBSs) and improve the user’s situation [1]
In this paper, we propose a context information indoor location system (ILS) which relies on the human activity recognition (HAR) process and how it can describe the location with environmental sound as information source, based on contextual information to estimate the user’s location in an indoor environment
The method uses feature extraction and a well-known machine learning technique (RF) that can be implemented in several platforms and deployed in different types of devices to provide context information
Summary
The physical indoor location of a user has become an important context variable because it is fundamental information that is needed to increase the capabilities of other systems to offer location-based services (LBSs) and improve the user’s situation [1]. The use of radio waves that include technologies such as Bluetooth, radio frequency identification (RFID), ultrasonic sensors, and Zigbee, among others [3,4,5], which uses available radio signals generated by other devices in the environment [6] These approaches have been combined to develop robust ILS, taking advantage of devices that include more than one sensor (e.g., smartphones, as mentioned in [7,8]). These technologies have allowed the development of well-accepted proposals based on these technologies, such as Active Badge [9], Active bat [10], Cricket [11], LANDMARC [12], Bluepos [13], LOSNUS [14], and CLIPS [15] These approaches require a dedicated infrastructure, and in most of them the position of the devices is used to calculate the final indoor location. The lack of scalability is another disadvantage, because the dedicated infrastructure requires devices to be added in order to increase the coverage of these systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
