Video sensor node with distributed video summary for Internet-of-Things applications

Due to the rapid development of Internet of Things (IoT), kinds of sensor nodes have been introduced to the different applications. Because of the variety of MCUs, sensors and radio modules, it’s challenging to reuse the device drivers between different sensor node platforms. To address this issue, a reusable device driver framework is proposed in this paper. Comparing with existed work, our framework is flexible, efficient, and easy to learn. The flexibility is achieved by layered encapsulation, which decouples the device driver with the sensor node operating system kernel. Our framework gives the reusability at the source code level, so it’s efficient. At the end, our framework is implemented in C programming language, which is the most common tool adopted by embedded system developing. This framework has applied to SenSpire OS, a micro-kernel real-time operating system for IoT sensor nodes.

Download Full-text

An Energy-Efficient Wireless Video Sensor Node for Moving Object Surveillance

IEEE Transactions on Multi-Scale Computing Systems ◽

10.1109/tmscs.2015.2478469 ◽

2015 ◽

Vol 1 (1) ◽

pp. 7-18 ◽

Cited By ~ 16

Author(s):

Jong Hwan Ko ◽

Burhan Ahmad Mudassar ◽

Saibal Mukhopadhyay

Keyword(s):

Energy Efficient ◽

Sensor Node ◽

Moving Object ◽

Wireless Video ◽

Video Sensor

Download Full-text

An Accurate Localization Method for Video Sensor Network Nodes

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.225-226.531 ◽

2011 ◽

Vol 225-226 ◽

pp. 531-535

Author(s):

Jun Xiang Gao ◽

Yan Tian

Keyword(s):

Sensor Networks ◽

Sensor Node ◽

Minimum Mean Square Error ◽

Sensor Nodes ◽

Network Nodes ◽

Practical Applications ◽

Accurate Localization ◽

Node Location ◽

Video Sensor Networks ◽

Video Sensor

Localization of the sensor nodes is a major obstacle for practical applications of video sensor networks. This paper present a novel localization technique based on vision in wireless sensor networks. On the assumption that sensor nodes can be recognized in an image, a sensor node firstly direct its Field-of-View (FoV) to an anchor or localized node, then we can get the orientation of anchor node relate to the sensor node to be localized. If two or more anchors can be found in sensing area, a series of equations will be obtained. They can be solved using minimum mean square error rule, and the solution of the overdetermined equations mentioned above is the estimation of the node position. The experiments indicate that a promising performance can be achieved in determining the exact node location using a small number of anchors.

Download Full-text

Monitoring and Predicting Water Quality in Swimming Pools

EPI International Journal of Engineering ◽

10.25042/epi-ije.082020.05 ◽

2021 ◽

Vol 3 (2) ◽

pp. 119-125

Author(s):

Lanny Sitanayah ◽

Apriandy Angdresey ◽

Vandri Josua Abram Sampul

Keyword(s):

Data Mining ◽

Water Quality ◽

Internet Of Things ◽

Temperature Sensor ◽

Sensor Node ◽

Ph Sensor ◽

Swimming Pools ◽

Wireless System ◽

Wireless Monitoring ◽

Dirty Water

Water quality in public swimming pools affects human health. While changing the water too soon is wasteful, postponing changing the dirty water is not hygiene. In this paper, we propose an Internet of Things-based wireless system to monitor and predict water quality in public swimming pools. Our system utilizes an Arduino Uno, an ESP8266 ESP-01 WiFi module, a DS18B20 temperature sensor, a pH sensor, and a turbidity sensor. We predict the water quality using a data mining prediction model, namely the decision tree Iterative Dichotomiser 3 algorithm. We show by experiment that our sensor node and the wireless monitoring system work correctly. We also show by simulation using Weka that we can get 100% accuracy with a kappa statistical value of 1 and 0% error rate.

Download Full-text