Olivier Debauche, Saïd Mahmoudi, S. Mahmoudi, P. Manneback, J. Bindelle, F. Lebeau
{"title":"牛行为分析的边缘计算","authors":"Olivier Debauche, Saïd Mahmoudi, S. Mahmoudi, P. Manneback, J. Bindelle, F. Lebeau","doi":"10.1109/EDiS49545.2020.9296471","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":119426,"journal":{"name":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"16","resultStr":"{\"title\":\"Edge Computing for Cattle Behavior Analysis\",\"authors\":\"Olivier Debauche, Saïd Mahmoudi, S. Mahmoudi, P. Manneback, J. Bindelle, F. Lebeau\",\"doi\":\"10.1109/EDiS49545.2020.9296471\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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.\",\"PeriodicalId\":119426,\"journal\":{\"name\":\"2020 Second International Conference on Embedded & Distributed Systems (EDiS)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-04-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"16\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Second International Conference on Embedded & Distributed Systems (EDiS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EDiS49545.2020.9296471\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Second International Conference on Embedded & Distributed Systems (EDiS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EDiS49545.2020.9296471","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
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.