An Implementation of Auditory Context Recognition for Mobile Devices

In personal context recognition many solutions rely on supervised learning that uses sensor data collected from the users' mobile devices. However, the recognition performance is significantly affected by the annotations’ quality. The problem lies in the fact that the annotator in such scenarios is usually the user herself which is not an expert and thus provides a significant amount of incorrect labels, while existing solutions can only tolerate a small fraction of mislabels. Our solution is Skeptical Learning, a framework for interactive machine learning where the machine uses all its available knowledge to check the correctness of its own and the user labeling. This allows to have a uniform confidence measure to be used when a contradiction arises that applies to both the annotator and the machine. The criteria of success is an improvement of the final recognition accuracy with respect to traditional supervised approaches.

Download Full-text

Deep Sensing: Inertia and Ambient Sensing for Activity Context Recognition Using Deep Convolutional Neural Networks

10.20944/preprints202005.0430.v1 ◽

2020 ◽

Author(s):

Abayomi Otebolaku ◽

Timibloudi Enamamu ◽

Ali Alfouldi ◽

Augustine Ikpehai ◽

Jims Marchang

Keyword(s):

Neural Networks ◽

Time Series ◽

Mobile Devices ◽

Convolutional Neural Networks ◽

Inertial Sensor ◽

Deep Convolutional Neural Networks ◽

Context Recognition ◽

Embedded Sensing ◽

Sensor Signals ◽

Ambient Sensing

With the widespread of embedded sensing capabilities of mobile devices, there has been unprecedented development of context-aware solutions. This allows the proliferation of various intelligent applications such as those for remote health and lifestyle monitoring, intelligent personalized services, etc. However, activity context recognition based on multivariate time series signals obtained from mobile devices in unconstrained conditions is naturally prone to imbalance class problems. This means that recognition models tend to predict classes with the majority number of samples whilst ignoring classes with the least number of samples, resulting in poor generalization. To address this problem, we propose to augment the time series signals from inertia sensors with signals from ambient sensing to train deep convolutional neural networks (DCNN) models. DCNN provides the characteristics that capture local dependency and scale invariance of these combined sensor signals. Consequently, we developed a DCNN model using only inertial sensor signals and then developed another model that combined signals from both inertia and ambient sensors aiming to investigate the class imbalance problem by improving the performance of the recognition model. Evaluation and analysis of the proposed system using data with imbalanced classes show that the system achieved better recognition accuracy when data from inertial sensors are combined with those from ambient sensors such as environment noise level and illumination, with an overall improvement of 5.3% accuracy.

Download Full-text

A content search system for mobile devices based on user context recognition

2012 IEEE Virtual Reality (VR) ◽

10.1109/vr.2012.6180950 ◽

2012 ◽

Cited By ~ 4

Author(s):

Tomohiro Mashita ◽

Daijiro Komaki ◽

Mayu Iwata ◽

Kentaro Shimatani ◽

Hiroki Miyamoto ◽

...

Keyword(s):

Mobile Devices ◽

Search System ◽

Context Recognition ◽

User Context ◽

Content Search

Download Full-text

Deep Sensing: Inertial and Ambient Sensing for Activity Context Recognition Using Deep Convolutional Neural Networks

Sensors ◽

10.3390/s20133803 ◽

2020 ◽

Vol 20 (13) ◽

pp. 3803 ◽

Cited By ~ 1

Author(s):

Abayomi Otebolaku ◽

Timibloudi Enamamu ◽

Ali Alfoudi ◽

Augustine Ikpehai ◽

Jims Marchang ◽

...

Keyword(s):

Time Series ◽

Mobile Devices ◽

Inertial Sensors ◽

Inertial Sensor ◽

Deep Convolutional Neural Networks ◽

Class Imbalance Problem ◽

Context Recognition ◽

Embedded Sensing ◽

Sensor Signals ◽

Ambient Sensing

With the widespread use of embedded sensing capabilities of mobile devices, there has been unprecedented development of context-aware solutions. This allows the proliferation of various intelligent applications, such as those for remote health and lifestyle monitoring, intelligent personalized services, etc. However, activity context recognition based on multivariate time series signals obtained from mobile devices in unconstrained conditions is naturally prone to imbalance class problems. This means that recognition models tend to predict classes with the majority number of samples whilst ignoring classes with the least number of samples, resulting in poor generalization. To address this problem, we propose augmentation of the time series signals from inertial sensors with signals from ambient sensing to train Deep Convolutional Neural Network (DCNNs) models. DCNNs provide the characteristics that capture local dependency and scale invariance of these combined sensor signals. Consequently, we developed a DCNN model using only inertial sensor signals and then developed another model that combined signals from both inertial and ambient sensors aiming to investigate the class imbalance problem by improving the performance of the recognition model. Evaluation and analysis of the proposed system using data with imbalanced classes show that the system achieved better recognition accuracy when data from inertial sensors are combined with those from ambient sensors, such as environmental noise level and illumination, with an overall improvement of 5.3% accuracy.

Download Full-text