IoT Wallet: Machine Learning-based Sensor Portfolio Application

Šolić, Petar; Kapetanovic, Ante Lojic; Županović, Tomislav; Kovacevic, Ivo; Perković, Toni; Popovski, Petar

doi:10.23919/splitech49282.2020.9243699

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we provide the proof-of concept measurements of the proposed antenna in the controlled environment in order to investigate the feasibility of the approach. Based on our previous work [6,12,13], this approach together with the ML techniques, can improve soil moisture estimation by using the signal strength approach in the proposed novel sensorless low-power wide-area network (LPWAN) radio technology.…”

Section: Introductionmentioning

confidence: 99%

Self-Sensing Antenna for Soil Moisture: Beacon Approach

Skiljo

Blazevic

Rodić

et al. 2022

Sensors

View full text Add to dashboard Cite

On the way from the Internet of things (IoT) to the Internet of underground things (IoUT) the main challenge is antenna design. The enabling technologies still rely on simple design and low cost, but the systems are more complex. The LoRa-based system combined with a machine learning approach can be used for the estimation of soil moisture by using signal strength data, but for the improvement of the system performance we propose the optimization of the antenna for underground use. The soil properties are frequency-dependent and varying in time, which may cause variations in the signal wavelength and input impedance of the antenna underground. Instead of using wideband antenna design or standard helical antenna provided in LoRa module, which are typical in the IoUT research community for communication links, we propose a narrow-band antenna design for the application in soil moisture sensing. It is shown that the approach of simply matching the antenna buried in dry sand can provide a substantial signal level difference, ranging from approximately 10 dB (achieved by proof-of-concept measurements) to as much as 40 dB (calculated by a full wave simulator) in reflection coefficient when the moisture content is being increased by 20%. This can ensure more reliable radio sensing in novel sensorless technology where soil moisture information is extracted from the signal strength of a transmitting device.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-Sensing Antenna for Soil Moisture: Beacon Approach

Skiljo

Blazevic

Rodić

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Emerging techniques, like Machine Learning and intelligent sensing in car parks, might be able to efficiently reduce the parking search time and improve mobility [19]. Similarly, it has been observed that the measurement of the received signal strength from the LoRa radio module could serve as a humidity indicator for the purpose of soil moisture detection [35,36]. In the parking environment, when something changes, such as when the car goes over the sensor device covering the parking lot, signal strength at the receiver side will change.…”

Section: Introductionmentioning

confidence: 99%

Sensing Occupancy through Software: Smart Parking Proof of Concept

et al. 2020

View full text Add to dashboard Cite

In order to detect the vehicle presence in parking slots, different approaches have been utilized, which range from image recognition to sensing via detection nodes. The last one is usually based on getting the presence data from one or more sensors (commonly magnetic or IR-based), controlled and processed by a micro-controller that sends the data through radio interface. Consequently, given nodes have multiple components, adequate software is required for its control and state-machine to communicate its status to the receiver. This paper presents an alternative, cost-effective beacon-based mechanism for sensing the vehicle presence. It is based on the well-known effect that, once the metallic obstacle (i.e., vehicle) is on top of the sensing node, the signal strength will be attenuated, while the same shall be recognized at the receiver side. Therefore, the signal strength change conveys the information regarding the presence. Algorithms processing signal strength change at the receiver side to estimate the presence are required due to the stochastic nature of signal strength parameters. In order to prove the concept, experimental setup based on LoRa-based parking sensors was used to gather occupancy/signal strength data. In order to extract the information of presence, the Hidden Markov Model (HMM) was employed with accuracy of up to 96%, while the Neural Network (NN) approach reaches an accuracy of up to 97%. The given approach reduces the costs of the sensor production by at least 50%.

show abstract