Bee Swarm Activity Acoustic Classification for an IoT-Based Farm Service.

Andrej Zgank

doi:10.3390/s20010021

Abstract

Beekeeping is one of the widespread and traditional fields in agriculture, where Internet of Things (IoT)-based solutions and machine learning approaches can ease and improve beehive management significantly. A particularly important activity is bee swarming. A beehive monitoring system can be applied for digital farming to alert the user via a service about the beginning of swarming, which requires a response. An IoT-based bee activity acoustic classification system is proposed in this paper. The audio data needed for acoustic training was collected from the Open Source Beehives Project. The input audio signal was converted into feature vectors, using the Mel-Frequency Cepstral Coefficients (with cepstral mean normalization) and Linear Predictive Coding. The influence of the acoustic background noise and denoising procedure was evaluated in an additional step. Different Hidden Markov Models’ and Gaussian Mixture Models’ topologies were developed for acoustic modeling, with the objective being to determine the most suitable one for the proposed IoT-based solution. The evaluation was carried out with a separate test set, in order to successfully classify sound between the normal and swarming conditions in a beehive. The evaluation results showed that good acoustic classification performance can be achieved with the proposed system.

Highlights

Digital farming is one of the key technologies which has been gaining support through different research initiatives in the last decade
The approach proved the applicability of the experimental setup and methods used, but the results showed that further attention should be given to acoustic modeling to improve the results
The assessment of the proposed Internet of Things (IoT)-based acoustic classification system was done on a test set with

Summary

Introduction

Digital farming is one of the key technologies which has been gaining support through different research initiatives in the last decade. The fundamental digital farming setup consists of the central management platform [1], human–computer interfaces [2] and particular IoT modules [3], which monitor the animals, their behavior and facilities. All these building blocks are connected [4] into a common platform, using communication networks which are, today, frequently based on IoT architecture combined with cloud or edge-based functionalities. An intelligent ambiance for farming needs to include different sensors and sensor networks These are necessary for the system to be able to build on various information collected as part of context modeling. A broad range of information processing applications [5] and Information and Communication Technology (ICT)

Methods

Results

Conclusion