scholarly journals A Review on the Stingless Beehive Conditions and Parameters Monitoring using IoT and Machine Learning

2021 ◽  
Vol 2107 (1) ◽  
pp. 012040
Author(s):  
M A A Che Ali ◽  
B Ilias ◽  
N Abdul Rahim ◽  
S A Abdul Shukor ◽  
A H Adom ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Habitat ◽  
Stingless Bee ◽  
Eye Infections ◽  
Colony Collapse ◽  
Use Of The Internet ◽  
The Tropics ◽  
Bee Colonies ◽  
The Internet Of Things ◽  
Future Condition

Abstract One of the stingless bee types named Heterotrigona Itama are widespread in the tropics and subtropics especially in Malaysia. Due to its excellent nutritional content, stingless bee honey has gained favour in recent years. According to some studies, stingless bee honey has been used to cure eye infections, open wounds, diabetes, hypertension, and a variety of other diseases. Additionally, this stingless bee is non-venomous and smaller in size than common bees. Nevertheless, beekeepers may encounter a number of obstacles that may result in colony failure and under-production. These problems can be attributed to a variety of factors such as surrounding temperature, surrounding humidity and predators. Numerous stingless bee colonies and other bee species lost in 2006 due to Colony Collapse Disorder as a result of this problem. Therefore, this article will review previous research on optimizing stingless beehive conditions via the use of the Internet of Things (IoT) and machine learning to minimise this issue. To begin, a review of existing research on the characteristics of stingless bees, particularly the Heterotrigona Itama species, has been conducted to understand the natural habitat of Heterotrigona Itama. Following that, the articles on colony division was reviewed in order to transition the colony from the conventional hive to the artificial hive which also reviewed its design from the past article to simplify the sensors installation, IoT monitoring system and honey harvesting. Then, the prior article on sensors and IoT deployment was examined to monitor and analysis the data online without disturbing the colony activity inside the beehives. Finally, the article on the application of machine learning with the beehive dataset was reviewed the most precise and accurate machine learning method to predict the existence of bee activity in the hives and the future condition of beehive.

scholarly journals Keyword Recognition Device Cloud Based

2021 ◽  
Vol 9 (VIII) ◽  
pp. 87-89
Author(s):  
Apurv Singh Yadav
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Speech Recognition ◽  
Internet Of Things ◽  
Recognition System ◽  
The Internet ◽  
Speech Recognition System ◽  
The Past ◽  
Use Of The Internet ◽  
The Internet Of Things

Over the past few decades speech recognition has been researched and developed tremendously. However in the past few years use of the Internet of things has been significantly increased and with it the essence of efficient speech recognition is beneficial more than ever. With the significant improvement in Machine Learning and Deep learning, speech recognition has become more efficient and applicable. This paper focuses on developing an efficient Speech recognition system using Deep Learning.

Detecting Abnormal Behavior of an IoT Device in the Network Based on a Traffic Model

Telecom IT ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 50-55
Author(s):  
D. Saharov ◽  
D. Kozlov
Keyword(s):  
Machine Learning ◽  
Internet Of Things ◽  
Mobile Networks ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Abnormal Behavior ◽  
Traffic Model ◽  
The Internet ◽  
Wide Spread ◽  
The Internet Of Things

The article deals with the СoAP Protocol that regulates the transmission and reception of information traf-fic by terminal devices in IoT networks. The article describes a model for detecting abnormal traffic in 5G/IoT networks using machine learning algorithms, as well as the main methods for solving this prob-lem. The relevance of the article is due to the wide spread of the Internet of things and the upcoming update of mobile networks to the 5g generation.

Improved estimates of future fire emissions under CMIP6 scenarios and implications for aerosol radiative forcing

2021 ◽  
Author(s):  
Matthew Kasoar ◽  
Douglas Hamilton ◽  
Daniela Dalmonech ◽  
Stijn Hantson ◽  
Gitta Lasslop ◽  
...  
Keyword(s):  
Machine Learning ◽  
Biomass Burning ◽  
Radiative Forcing ◽  
Learning Methods ◽  
Aerosol Radiative Forcing ◽  
Fire Emissions ◽  
Machine Learning Methods ◽  
The Tropics ◽  
In Fire ◽  
Aerosol Radiative

<p>The CMIP6 Shared Socioeconomic Pathway (SSP) scenarios include projections of future changes in anthropogenic biomass-burning.  Globally, they assume a decrease in total fire emissions over the next century under all scenarios.  However, fire regimes and emissions are expected to additionally change with future climate, and the methodology used to project fire emissions in the SSP scenarios is opaque.</p><p>We aim to provide a more traceable estimate of future fire emissions under CMIP6 scenarios and evaluate the impacts for aerosol radiative forcing.  We utilise interactive wildfire emissions from four independent land-surface models (CLM5, JSBACH3.2, LPJ-GUESS, and ISBA-CTRIP) used within CMIP6 ESMs, and two different machine-learning methods (a random forest, and a generalised additive model) trained on historical data, to predict year 2100 biomass-burning aerosol emissions consistent with the CMIP6-modelled climate for three different scenarios: SSP126, SSP370, and SSP585.  This multi-method approach provides future fire emissions integrating information from observations, projections of climate, socioeconomic parameters and changes in vegetation distribution and fuel loads.</p><p>Our analysis shows a robust increase in fire emissions for large areas of the extra-tropics until the end of this century for all methods.  Although this pattern was present to an extent in the original SSP projections, both the interactive fire models and machine-learning methods predict substantially higher increases in extra-tropical emissions in 2100 than the corresponding SSP datasets.  Within the tropics the signal is mixed. Increases in emissions are largely driven by the temperature changes, while in some tropical areas reductions in fire emissions are driven by human factors and changes in precipitation, with the largest reductions in Africa. The machine-learning methods show a stronger reduction in the tropics than the interactive fire models, however overall there is strong agreement between both the models and the machine-learning methods.</p><p>We then use additional nudged atmospheric simulations with two state-of-the-art composition-climate models, UKESM1 and CESM2, to diagnose the impact of these updated fire emissions on aerosol burden and radiative forcing, compared with the original SSP prescribed emissions.  We provide estimates of future fire radiative forcing, compared to modern-day, under these CMIP6 scenarios which span both the severity of climate change in 2100, and the rate of reduction of other aerosol species.</p>

scholarly journals IMPROVING INTERNET OF THINGS PARKING SYSTEMS

2021 ◽  
Vol 19 (3) ◽  
pp. 163
Author(s):  
Dušan Bogićević
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cloud Computing ◽  
Internet Of Things ◽  
Information Needs ◽  
Vehicle Classification ◽  
The Internet ◽  
Parking Space ◽  
Automated Systems ◽  
The Internet Of Things

Edge data processing represents the new evolution of the Internet and Cloud computing. Its application to the Internet of Things (IoT) is a step towards faster processing of information from sensors for better performance. In automated systems, we have a large number of sensors, whose information needs to be processed in the shortest possible time and acted upon. The paper describes the possibility of applying Artificial Intelligence on Edge devices using the example of finding a parking space for a vehicle, and directing it based on the segment the vehicle belongs to. Algorithm of Machine Learning is used for vehicle classification, which is based on vehicle dimensions.

scholarly journals Development of an IoT System for Environmental Monitoring: Software

2021 ◽  
Author(s):  
Benjamin Secker
Keyword(s):  
Environmental Monitoring ◽  
Low Cost ◽  
Proof Of Concept ◽  
Embedded Devices ◽  
Data Loggers ◽  
Environmental Monitoring System ◽  
Use Of The Internet ◽  
High Level ◽  
Monitoring Software ◽  
The Internet Of Things

Use of the Internet of Things (IoT) is poised to be the next big advancement in environmental monitoring. We present the high-level software side of a proof-of-concept that demonstrates an end-to-end environmental monitoring system,<br><div>replacing Greater Wellington Regional Council’s expensive data loggers with low-cost, IoT centric embedded devices, and it’s supporting cloud platform. The proof-of-concept includes a Micropython-based software stack running on an ESP32 microcontroller. The device software includes a built-in webserver that hosts a responsive Web App for configuration of the device. Telemetry data is sent over Vodafone’s NB-IoT network and stored in Azure IoT Central, where it can be visualised and exported.</div><br>While future development is required for a production-ready system, the proof-of-concept justifies the use of modern IoT technologies for environmental monitoring. The open source nature of the project means that the knowledge gained can be re-used and modified to suit the use-cases for other organisations.

Sign in / Sign up

Export Citation Format

Share Document