Showing papers by "Nathalie Mitton published in 2020"

Practical evaluation of carrier sensing for a LoRa wildlife monitoring network

Abstract: We consider the technique of carrier sensing for application in a LoRa mesh network aimed at wildlife monitoring. A key challenge in this application is to limit collisions in order to increase the channel capacity. Since CSMA is very rarely applied in LoRa-based networks, our goal is to determine its practical viability. We evaluate the LoRa Channel Activity Detection (CAD) mechanism under laboratory and field conditions. Our results show that both preamble and payload symbols are detectable even at distances exceeding 4 km. Detecting LoRa preamble symbols had a SNR advantage of between 1 and 2 dB over payload symbols. Furthermore, we find that by taking at least 8 consecutive CAD measurements during payload frame time, a clear channel assessment (CCA) comparable to the LoRa frame reception rate can be achieved between two nodes.

Machine Learning Based Data Reduction in WSN for Smart Agriculture

Abstract: Nowadays, the agriculture domain faces a lot of challenges for a better usage of its natural resources. For this purpose, and for the increasing danger of climate change, there is a need to locally monitor meteorological data and soil conditions to help make quicker and more adapted decision for the culture. Wireless Sensor Networks (WSN) can serve as a monitoring system for those types of features. However, WSN suffer from the limited energy resources of the motes which shorten the lifetime of the overall network. Every mote periodically captures the monitored feature and sends the data to the sink for further analysis depending on a certain sampling rate. This process of sending big amount of data causes a high energy consumption of the sensor node and an important bandwidth usage on the network. In this paper, a Machine Learning based Data Reduction Algorithm (MLDR) is introduced. MLDR focuses on environmental data for the benefits of agriculture. MLDR is a data reduction approach which reduces the amount of transmitted data to the sink by adding some machine learning techniques at the sensor node level by keeping data availability and accuracy at the sink. This data reduction helps reduce the energy consumption and the bandwidth usage and it enhances the use of the medium while maintaining the accuracy of the information. This approach is validated through simulations on MATLAB using real temperature data-sets from Weather-Underground sensor network. Results show that the amount of sent data is reduced by more than \(70\%\) while maintaining a very good accuracy with a variance that did not surpass 2\(^\circ \).

Sélection d’interface de communication dans les réseaux de capteurs multi-technologies

Abstract: Les reseaux de capteurs sont composes de systemes generalement contraints en energie et communiquant via des liaisons sans fil. Cependant, le deploiement d'un tel reseau est limite par la portee radio et le debit de la technologie utilisee. Pouvoir choisir la technologie la plus adaptee au scenario permettrait de depasser cette limite et de reduire la consommation energetique tout en permettant la differenciation des flux de donnees. "Technique for Order of Preference by Similarity to Ideal Solution" (TOPSIS) est une methode permettant de comparer finement des technologies basees sur des attributs contradictoires. Mais elle est limitee par un phenomene d'anomalie de classement pouvant alterer la qualite de la selection. De plus, TOPSIS necessite des calculs complexes, augmentant la consommation d'energie sur du materiel contraint. Dans cet article, nous proposons une methode TOPSIS adaptee pour la selection d'interface de communication sur du materiel contraint. L'evaluation de notre solution avec des modules FiPy de Pycom montre une amelioration du temps de calcul de 40% tout en assurant une similarite de classement avec TOPSIS de 80%.

On-Node Correlation Based Data Reduction in WSN for Smart Agriculture

Abstract: Nowadays, climate change is one of the numerous factors affecting the agricultural sector. Optimizing the usage of natural resources is one of the challenges this sector faces. For this reason, it could be necessary to locally monitor weather data and soil conditions to make faster and better decisions locally adapted to the crop. Wireless sensor networks (WSNs) can serve as a monitoring system for these types of parameters. However, in WSNs, sensor nodes suffer from limited energy resources. The process of sending a large amount of data from the nodes to the sink results in high energy consumption at the sensor node and significant use of network bandwidth, which reduces the lifetime of the overall network. In this paper, for data reduction, a data correlation and prediction technique is proposed both at the sensor node level and at the sink level. The aim of this approach is to reduce the amount of transmitted data to the sink, depending on the degree of correlation between different parameters. In this work we propose the Pearson Data Correlation and Prediction (PDCP) algorithm to detect this correlation. This data reduction maintains the accuracy of the information while reducing the amount of data sent from the nodes to the sink. This approach is validated through simulations on MATLAB using real meteorological data-sets from Weather-Underground sensor network. The results show the validity of our approach by reducing the amount of data by a percentage up to 69% while maintaining the accuracy of the information. The humidity values prediction based on the temperature parameter is accurate and the deviation from the real value does not surpass 7% of humidity.