LoRaWAN-Enabled Smart Campus: The Dataset and a People Counter Use Case
Eldeeb, Eslam; Alves, Hirley (2023-09-28)
IEEE
28.09.2023
E. Eldeeb and H. Alves, "LoRaWAN-Enabled Smart Campus: The Data Set and a People Counter Use Case," in IEEE Internet of Things Journal, vol. 11, no. 5, pp. 8569-8577, 1 March1, 2024, doi: 10.1109/JIOT.2023.3320182.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202402011525
https://urn.fi/URN:NBN:fi:oulu-202402011525
Tiivistelmä
Abstract
Smart Campus is one of the essential use cases in the Internet of Things (IoT). This work describes a LoRaWAN-based smart campus dataset comprising measurements of several sensors in hundreds of IoT devices. In addition, the dataset contains information about the PHY and MAC layers of the LoRaWAN network. Therefore, we first describe the LoRa network, the connection between devices and gateway, and the gateway and network server. As the wireless network is prone to errors, e.g., outages, collisions, and interference, among other factors, the collected data may contain missing transmissions. To alleviate the problem of missing values, we resort to a k-nearest neighbor approach. For example, once the data imputation phase is complete, we employ a long short-term memory (LSTM) architecture to predict future sensor readings. Then, we build a deep neural network (DNN) to predict the room occupancy based on the selected sensor’s readings. Our results show that our model achieves an accuracy of 95% in predicting the number of people in a room. Furthermore, the dataset is openly available and described in detail, which is an opportunity to explore other features and applications in Smart Campus.
Smart Campus is one of the essential use cases in the Internet of Things (IoT). This work describes a LoRaWAN-based smart campus dataset comprising measurements of several sensors in hundreds of IoT devices. In addition, the dataset contains information about the PHY and MAC layers of the LoRaWAN network. Therefore, we first describe the LoRa network, the connection between devices and gateway, and the gateway and network server. As the wireless network is prone to errors, e.g., outages, collisions, and interference, among other factors, the collected data may contain missing transmissions. To alleviate the problem of missing values, we resort to a k-nearest neighbor approach. For example, once the data imputation phase is complete, we employ a long short-term memory (LSTM) architecture to predict future sensor readings. Then, we build a deep neural network (DNN) to predict the room occupancy based on the selected sensor’s readings. Our results show that our model achieves an accuracy of 95% in predicting the number of people in a room. Furthermore, the dataset is openly available and described in detail, which is an opportunity to explore other features and applications in Smart Campus.
Kokoelmat
- Avoin saatavuus [38841]