Smart Gravimetric System for Enhanced Security of Accesses to Public Places Embedding a MobileNet Neural Network Classifier

Addabbo, Tommaso; Fort, Ada; Mugnaini, Marco; Vignoli, Valerio; Intravaia, Matteo; Tani, Marco; Bianchini, Monica; Scarselli, Franco; Corradini, Barbara Toniella

doi:10.1109/tim.2022.3162270

Cited by 11 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast with the adopted methodology for the design phase of the audio NN, different architectures were not explored for the picture NN, as MobileNetV2 largely proved to be effective for the classification problems to be carried out by low computational power devices, as can be verified from the literature. Indeed, the application scenarios are countless, including ensuring security in accesses to public places [ 49 ], image processing [ 50 ], cactaceae detection [ 51 ], analysing the quality of corn [ 52 ], waste management [ 53 , 54 ], body temperature and face mask detection [ 55 ], and food classification [ 56 ].…”

Section: System Overviewmentioning

confidence: 99%

Fight Fire with Fire: Detecting Forest Fires with Embedded Machine Learning Models Dealing with Audio and Images on Low Power IoT Devices

Peruzzi

Pozzebon

Meer

2023

Sensors

View full text Add to dashboard Cite

Forest fires are the main cause of desertification, and they have a disastrous impact on agricultural and forest ecosystems. Modern fire detection and warning systems rely on several techniques: satellite monitoring, sensor networks, image processing, data fusion, etc. Recently, Artificial Intelligence (AI) algorithms have been applied to fire recognition systems, enhancing their efficiency and reliability. However, these devices usually need constant data transmission along with a proper amount of computing power, entailing high costs and energy consumption. This paper presents the prototype of a Video Surveillance Unit (VSU) for recognising and signalling the presence of forest fires by exploiting two embedded Machine Learning (ML) algorithms running on a low power device. The ML models take audio samples and images as their respective inputs, allowing for timely fire detection. The main result is that while the performances of the two models are comparable when they work independently, their joint usage according to the proposed methodology provides a higher accuracy, precision, recall and F1 score (96.15%, 92.30%, 100.00%, and 96.00%, respectively). Eventually, each event is remotely signalled by making use of the Long Range Wide Area Network (LoRaWAN) protocol to ensure that the personnel in charge are able to operate promptly.

show abstract