Air Pollution Monitoring Using WSN Nodes with Machine Learning Techniques: A Case Study

2021 ◽  
Author(s):  
Paul D Rosero-Montalvo ◽  
Vivian F López-Batista ◽  
Ricardo Arciniega-Rocha ◽  
Diego H Peluffo-Ordóñez
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Classification Performance ◽  
Pollution Monitoring ◽  
Machine Learning Techniques ◽  
Related Factors ◽  
Air Pollution Monitoring ◽  
Pollution Levels ◽  
Learning Techniques ◽  
High Pollution

Abstract Air pollution is a current concern of people and government entities. Therefore, in urban scenarios, its monitoring and subsequent analysis is a remarkable and challenging issue due mainly to the variability of polluting-related factors. For this reason, the present work shows the development of a wireless sensor network that, through machine learning techniques, can be classified into three different types of environments: high pollution levels, medium pollution and no noticeable contamination into the Ibarra City. To achieve this goal, signal smoothing stages, prototype selection, feature analysis and a comparison of classification algorithms are performed. As relevant results, there is a classification performance of 95% with a significant noisy data reduction.

scholarly journals Intelligent Air Pollution Monitoring System for Smart Cities Using IoT and Machine Learning

2021 ◽  
Vol 10 (2) ◽  
pp. 1399-1407
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Smart Cities ◽  
Machine Learning Algorithms ◽  
Control Measures ◽  
Pollution Monitoring ◽  
World Health ◽  
Air Pollution Monitoring ◽  
Pollution Levels ◽  
The World

Today, almost everything is going under automation. Air pollution has become one of the major crises across the globe. According to the report of the World Health Organization (WHO), around 580,000 people died due to air pollution. This document deals with the effective monitoring of air pollution systems. The proposed technique uses machine learning algorithms for the intelligent monitoring of air pollution. The concept of the Internet of Things (IoT) is implemented in the system to make it more reliable and accessible from anywhere throughout the world. ESP32 is used as a microprocessor for decision making purposes. The system uses Arduino software to build an algorithm. The DHT11 module is used to sense the humidity as well as temperature. MQ-2, MQ-7 and MQ-135 are used for sensing the level of methane, carbon monoxide and for measuring air quality, respectively. A buzzer is used to identify any unusual condition. Our work considers pollution caused by vehicles and provides an in-the-moment solution that does not directly monitor pollution levels, as well as control measures for reducing traffic in extremely polluted areas. This system will undoubtedly be on humans' behalf in such a way that a smart city will have much less time for spending, and there will undoubtedly be other industries, and the air will undoubtedly be extra polluted, and this device will undoubtedlyallow people to understand how safe the air is.

scholarly journals Application of deep and machine learning techniques for multi-label classification performance on psychotic disorder diseases

2021 ◽  
Vol 23 ◽  
pp. 100545
Author(s):  
Israel Elujide ◽  
Stephen G. Fashoto ◽  
Bunmi Fashoto ◽  
Elliot Mbunge ◽  
Sakinat O. Folorunso ◽  
...  
Keyword(s):  
Machine Learning ◽  
Psychotic Disorder ◽  
Classification Performance ◽  
Machine Learning Techniques ◽  
Learning Techniques

scholarly journals Machine Learning for Epidemiological Analysis in The Industrial Area for a Sustainable Life

2019 ◽  
Vol 9 (2S2) ◽  
pp. 1017-1025
Keyword(s):  
Machine Learning ◽  
Air Pollution ◽  
Industrial Area ◽  
Epidemiological Studies ◽  
Machine Learning Techniques ◽  
Learning Approach ◽  
Learning Techniques ◽  
Machine Learning Approach ◽  
Air Pollution Exposure ◽  
Pollution Exposure

Pollution exposure and human health in the industry contaminated area are always a concern. The need for industrialization urges to concentrate on sustainable life of residents in the vicinity of the industrial area rather than opposing the industrialists. Literature in epidemiological studies reveal that air pollution is one of the major problems for health risks faced by residents in the industrial area. Main pollutants in industry related air pollution are particulate matter (PM2.5, PM10), SO2 , NO2 , and other pollutants upon the industry. Data for epidemiological studies obtained from different sources which are limited to public access include residents’ sociodemographic characters, health problems, and air quality index for personal exposure to pollutants. This combined data and limited resources make the analysis more complex so that statistical methods cannot compensate. Our review finds that there is an increase in literature that evaluates the connection between ambient air pollution exposure and associated health events of residents in the industrially polluted area using statistical methods, mainly regression models. A very few applies machine learning techniques to figure out the impact of common air pollution exposure on human health. Most of the machine learning approach to epidemiological studies end up in air pollution exposure monitoring, not to correlate its association with diseases. A machine learning approach to epidemiological studies can automatically characterize the residents’ exposure to pollutants and its associated health effects. Uniqueness of the model depends on the appropriate exhaustive data that characterizes the features, and machine learning algorithm used to build the model. In this contribution, we discuss various existing approaches that evaluate residents’ health effects and the source of irritation in association with air pollution exposure, focuses machine learning techniques and mathematical background for epidemiological studies for residents’ sustainable life.

scholarly journals Research on an Iot Based Air Pollution Monitoring System

2019 ◽  
Vol 8 (9S2) ◽  
pp. 553-558
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Quality Index ◽  
Life Forms ◽  
Pollution Monitoring ◽  
Wireless Sensor ◽  
Pollution Level ◽  
Air Pollution Monitoring ◽  
Pollution Levels ◽  
Different Sources

Humankind, moving to a period centered upon improvement has overlooked the significance of supportability and has been the real guilty party behind the rising Pollution levels in the world's air among all other living life forms. The Pollution levels at certain spots have come to such high degrees that they have begun hurting our very own It will being. An IoT based Air Pollution observing framework incorporates a MQ Series sensor interfaced to a Node MCU outfitted with an ESP8266 WLAN connector to send the sensor perusing to a Thing Speak cloud. Further extent of this work incorporates an appropriate AI model to foresee the air Pollution level and an anticipating model, which is fundamentally a subset of prescient displaying. As age of poisonous gases from ventures, vehicles and different sources is immensely expanding step by step, it winds up hard to control the dangerous gases from dirtying the unadulterated air. In this paper a practical air Pollution observing framework is proposed. This framework can be utilized for observing Pollutions in demeanor of specific territory and to discover the air peculiarity or property examination. The obligated framework will concentrate on the checking of air poisons concentrate with the assistance of mix of Internet of things with wireless sensor systems. The investigation of air quality should be possible by figuring air quality index (AQI)

Sign in / Sign up

Export Citation Format

Share Document