Improvement of battery life of iPhones Inertial Measurement Unit by using edge computing (original) (raw)

Improvement of battery life of iPhones Inertial Measurement Unit by using edge computing. Application to cattle behavior

2017

Smartphones, particularly iPhones, can be relevant instruments for researchers because they are widely used around the world in multiple domains of applications such as animal behavior. iPhones are readily available on the planet, contain many sensors and require no hardware development. They are equipped with high performance inertial measurement units (IMU) and absolute positioning systems analyzing user's movements, but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. Using smartphones to study animal behavior requires the improvement of the autonomy to allow the acquisition of many variables at a high frequency over long periods of time on a large number of individuals for their further processing through various models and decision-making tools. Storing, treating data at the iPhone level with an optimal consumption of energy to maximize battery life was achieved by using edge computing on the iPhone. It reduced the size of the raw data by 42% on average by eliminating redundancies. The decrease in sampling frequency, the selection of the most important variables and postponing calculations to the cloud allowed also an increase in battery life by reducing of amount of data to transmit.

Web-based cattle behavior service for researchers based on the smartphone inertial central

Procedia Computer Science, 2017

Smartphones, particularly iPhones, can be relevant instruments for researchers in animal behavior because they are readily available on the planet, contain many sensors and require no hardware development. They are equipped with high performance inertial measurement units (IMU) and absolute positioning systems analyzing users' movements, but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. The study of animal behavior using smartphones requires the storage of many high frequency variables from a large number of individuals and their processing through various relevant variables combinations for modeling and decision-making. Transferring, storing, treating and sharing such an amount of data is a big challenge. In this paper, a lambda cloud architecture and a scientific sharing platform used to archive and process high-frequency data are proposed. An application to the study of cattle behavior on pasture on the basis of the data recorded with the IMU of iPhones 4S is exemplified. The package comes also with a web interface to encode the actual behavior observed on videos and to synchronize observations with the sensor signals. Finally, the use of fog computing on the iPhone reduced by 42% on average the size of the raw data by eliminating redundancies. Abstract Smartphones, particularly iPhones, can be relevant instruments for researchers in animal behavior because they are readily available on the planet, contain many sensors and require no hardware development. They are equipped with high performance inertial measurement units (IMU) and absolute positioning systems analyzing users' movements, but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. The study of animal behavior using smartphones requires the storage of many high frequency variables from a large number of individuals and their processing through various relevant variables combinations for modeling and decision-making. Transferring, storing, treating and sharing such an amount of data is a big challenge. In this paper, a lambda cloud architecture and a scientific sharing platform used to archive and process high-frequency data are proposed. An application to the study of cattle behavior on pasture on the basis of the data recorded with the IMU of iPhones 4S is exemplified. The package comes also with a web interface to encode the actual behavior observed on videos and to synchronize observations with the sensor signals. Finally, the use of fog computing on the iPhone reduced by 42% on average the size of the raw data by eliminating redundancies.

Edge Computing for Cattle Behavior Analysis

IEEE, 2020

Smartphones, particularly iPhone, can be relevant instruments for researchers because they are widely used around the world in multiple domains of applications such as animal behavior. iPhone are readily available on the market, contain many sensors and require no hardware development. They are equipped with high performance inertial measurement units (IMU) and absolute positioning systems analyzing user's movements , but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. Using smartphones to study animal behavior requires the improvement of the autonomy to allow the acquisition of many variables at a high frequency over long periods of time on a large number of individuals for their further processing through various models and decision-making tools. Indeed, storing, treating data at the iPhone level with an optimal consumption of energy to maximize battery life was achieved by using edge computing on the iPhone. This processing reduced the size of the raw data by 42% on average by eliminating redundancies. The decrease in sampling frequency, the selection of the most important variables and postponing calculations to the cloud allowed also an increase in battery life by reducing of amount of data to transmit. In all these use cases, the lambda architectures were used to ingest streaming time series data from the Internet of Things. Cattle, farm animals' behavior consumes relevant data from Inertial Measurement Unit (IMU) transmitted or locally stored on the device. Data are discharged offline and then ingested by batch processing of the Lambda Architecture.

Cloud services integration for farm animals' behavior studies based on smartphones as activity sensors

Journal of Ambient Intelligence and Humanized Computing, 2019

Smartphones, particularly iPhone, can be relevant instruments for researchers in animal behavior because they are readily available on the planet, contain many sensors and require no hardware development. They are equipped with high performance Inertial Measurement Units (IMU) and absolute positioning systems analyzing users' movements, but they can easily be diverted to analyze likewise the behaviors of domestic animals such as cattle. The study of animal behavior using smart-phones requires the storage of many high frequency variables from a large number of individuals and their processing through various relevant variables combinations for modeling and decision-making. Transferring, storing, treating and sharing such an amount of data is a big challenge. In this paper, a lambda cloud architecture innovatively coupled to a scientific sharing platform used to archive, and process high-frequency data are proposed to integrate future developments of the Internet of Things applied to the monitoring of domestic animals. An application to the study of cattle behavior on pasture based on the data recorded with the IMU of iPhone 4s is exemplified. Performances comparison between iPhone 4s and iPhone 5s is also achieved. The package comes also with a web interface to encode the actual behavior observed on videos and to synchronize observations with the sensor signals. Finally, the use of Edge computing on the iPhone reduced by 43.5% on average the size of the raw data by eliminating redundancies. The limitation of the number of digits on individual variable can reduce data redundancy up to 98.5%. Keywords Animals' behavior · Smart agriculture · IMU · iPhone · Lambda architecture · Precision livestock farming

Wireless inertial sensors for monitoring animal behavior

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2007

Wireless sensors were designed which are small and light enough to be worn by small animals such as rats. These sensors are used to record three axes acceleration data from animals during natural behavior in a cage. The behavior of the animal is further extracted from the recorded acceleration data using neural network based pattern recognition algorithms. Successful recognition of eating, grooming and standing are demonstrated using this approach. Finally another potential application of this research is demonstrated in behavioral neuroscience by showing correlations between action potentials recorded from the motor cortex of a rat and acceleration data.