Intelligent Based Novel Embedded System Based IoT Enabled Air Pollution Monitoring System

Intelligent Based Novel Embedded System Based IoT Enabled Air Pollution Monitoring System

3.1 OBJECTIVE

With the rapid growth of industry and transport within this contemporary progress, there was sufficient consideration given to air quality monitoring. Still, conventional air quality monitoring methods are inefficient to produce adequate spatial and temporal resolutions of the air quality information by cost-effective also the period time clarifications. During the chapter, we propose a distinct methodology to achieve the air quality monitoring system, using this Fog computing-based Internet of Things (IoT). In this chapter proposed an embedded system, where sensors collect the air quality information within period time and send it over the fog nodes. Every fog node may be an extraordinarily virtualized program hosted at a committed computing node implemented with a connection interface. Data gathered by Microprocessor based IoT sensing things do not seem to be causing on into the cloud server to the process. Preferably, they do send through the adjacent fog node to get quick, including high-rise rate service. Though, fog node will refine non-actionable data (e.g., regular device measurement) also forward them to the Cloud for lengthy run storage and batch analytics. The Cloud may be a convenient location to run world analytics at information gathered from commonly shared devices over sustained periods (months, years). General-purpose processor (Microprocessor)  and IoT cloud platforms were involved in developing this whole infrastructure and model for analysis. Empirical outcomes reveal that this advanced method is responsible for sensing air quality, which serves to expose the modification patterns regarding air quality through a certain level.

3.2 INTRODUCTION

Rapid development in manufacturers and transportation, pollution has recently grown a significant drawback for developing countries that have been given raised consideration by each government also the people. Consistent with a recent report, long-term exposure to outdoor and indoor particulate matter that may be a type of air pollution caused concerning 5 million deaths, and it ranks fifth worldwide among all risks. Pollution causes numerous impacts on human health. Together with a respiratory problem, hospitalization for heart or lung diseases likes bronchial asthma, chronic bronchitis, and respiratory illness that worsens their conditions. If air quality stays to worsen, the harness of pollution price might convert a significant difficulty for governments. Therefore, monitoring systems of air quality helped monitor air pollution efficiently before the situation turns critical.  Air pollution means the presence of high concentrations of harmful gases such as dust, smoke. Inhaling these gases can increase the chances of health problems. Dust, when inhaled, can cause breathing problems, damage lung tissue, and boost up existing health problems. Greenhouse gases trap heat and make the earth warmer. Human activities are responsible for almost all of the increases in greenhouse gases. Therefore, every federal government has stringent regulations that require prevention and reduction of emission levels.

Conventionally, air quality monitoring station is distinctive of high prices to installation and big sizes and sustain that limit it’s high possible in substantial deployment in cities. Though the specific measurement can produce results, long methods are needed offline. Hence, air quality data can provide in real-time in that manner. On the other hand, information on air quality knowledge of each high temporal and spatial resolution in both temporal and spatial dimensions desired remarkably, which signifies the concentrate of this chapter. The IoT is under the spotlight of innovations that can provide inexhaustible advantages to our community. The evolution of the IoT is getting ready to strike a platform at that numerous of the things about us can have the power to attach to the web to interact with each other without human interference. Initially, the IoT seemed to decrease human data record efforts and use various types of sensors to gather data from the atmosphere and allow the electronic storage and process of those data. Essentially restricted computations characterize the IoT in case of processing power and storage, and it experiences several problems like privacy, performance, security, and reliability. The consolidation of IoT, including cloud computing, produces numerous benefits for several applications of IoT. Conversely, as there is a wide IoT device range through the heterogeneous platform, the new IoT applications development may be a hard job. Hence it will result in IoT applications that generate a vast amount of information from sensors and additional devices.

The enormous report examined to see decisions concerning numerous activities. Distribution of these data to the Cloud needs too high network bandwidth. A new computing model called fog computing has been evolved to overcome the above problems. The Fog computing term was coined first by Cisco. It is a unique knowledge that gives several advantages to entirely various fields, predominantly the IoT. The same as the Cloud, fog computing offers services to IoT users like storage and data processing. Fog computing relies upon implementing capabilities of data processing and storage close by to fog devices, if possible, of converting them to the Cloud. Each FogFog and Cloud offers computing, networking, and storage resources.  The fog computing scope within the IoT is to increase effectiveness, performance, and diminish this data quantity stimulated to the processing, cloud analysis, and storage. Consequently, the information collected by sensors is going to be sending to edge devices of the network for temporary storage and processing in place of transferring them to the cloud, therefore reducing latency and traffic of the network. Figure 3.1 represents the air monitoring system’s Classifications

Figure 3.1 Air monitoring system’s Classifications

The primary air quality monitoring system offline based on gas analyzers, which were bulky, expensive and had less efficiency. With technological advancement both in hardware and software domains, the system has moved from being offline to online and has been able to take a massive stride in terms of technology improvisation, reduction in size, as well as cost and this, has allowed individuals to set up their station and carry on with air quality monitoring. This chapter presents a complete review of pollution monitoring desires, existing monitoring system, their limitations, and current challenges long-faced by these monitoring systems. We analyze through the problems, infrastructure, data processing, and finding of designing and deploying a combined sensing node for observant indoor/outdoor pollution. An associate air monitoring system model is utilizing the Fog computing architecture with IoT, assuring measurement accuracy, low latency, and location awareness with minimum price. A model developed with the General purpose processor, and experimental analysis has been conducted in numerous sets to evaluate the system’s viability.

3.2.1 Air Quality Index(AQI)

The Air Quality Index may be a describing system and a necessary tool for risk communication. It notifies the general public about the level of ambient air quality. Accordingly, the possible health risk it might impose, especially on vulnerable groups like children, the older, and people with living cardiovascular and respiratory diseases. The AQI is used to make decisions on activities that are outdoor in general, mostly by people. These activities projects as an example, schools, and sports organizations could check the newest AQI figures to determine whether or not out of doors sporting events should be conducted on a particular day. AQI usually changes the weighted importance of different pollution-related parameters (e.g., SO₂, NO₂, CO₂, visibility) toward a specific variety or set of numbers. Several countries use this method for air quality communication and decision making activities. Air quality index converts advanced air quality data of different pollutants into a single number (index value), word, and value. Numeric values ranging from 0 to 500 used to represent AQI. If the costs are 0, it is the usual efficient air quality, and the most dangerous air quality has a score of 500(Higher AQI higher pollution). The AQI divided into six classifications based upon the ambient density values of the pollutants of air and its health consequences (identified as health breakpoints). These six classifications are as results: Good (safe), Moderate, Unhealthy for sensitive groups, Unhealthy, Very unhealthy, Dangerous.

Air quality index (AQI) is an internationally used numerical value used to evaluate the level of air pollution. High AQI values indicate poor air quality and hence adverse health effects. Each country has its air quality index, corresponding to the national air quality standards. At present, AQI computation usually done with air pollutant concentration values measured over a specified averaging period by the air quality monitoring sites. Due to the high construction cost, these monitoring stations sparsely placed and hence could give only a limited coverage over the vast urban area. Therefore, the air quality data collected by these monitoring stations is not self-sufficient to portray the real severity of air pollution. Table 3.1 represents the Health Statements for AQI categories.

Table 3.1 Health Statements for AQI categories

3.2.2 Air Quality monitoring system

Air quality monitoring systems may be categorized because the indoor and outdoor pollution monitoring depends upon the place where the event occurs. Outdoor air pollution denotes to the open and industrial location. In discrepancy, the indoor case is that the pollution of the air in a tiny room inside homes, workplaces, offices. Because of their various settings and pollutant types, monitoring systems for indoor and outdoor air have complex related requirements, as mentioned in Table 3.2.

Table 3.2 Air pollution monitoring systems and related requirements

Air quality is a major environmental issue in many areas. When meteorological and emissions data are available for a region, its air quality levels can be modelled based on different scenarios, such as:

• The formation of photochemical smog;
• The impact of population growth; or
• Increased motor vehicle use.

Most economic activities, involving the use and conversion of energy, and transportation prominently among them, are accompanied by emissions of air pollutants, thus degrading the environment, and in particular, the urban environment. An emission is a compound or pollutant as it enters the atmosphere from an emission source, e.g., flue gas, as it comes out of exhaust or chimney. Often emissions are also called primary pollutants. Once emitted, the pollutants are dispersed in the atmosphere, more or less quickly depending on the weather conditions. Numerous chemical reactions take place during this dispersion. This produces more stable compounds that can be detected and analyzed in measuring stations. These are the pollutants that we breathe or which deposited on the ground.

3.2.3 FOG COMPUTING

The Cisco proposes the term of fog computing. It is the most advanced technology that gives numerous advantages to entirely different fields, significantly the IoT. The same because of the FogFog, cloud computing offers IoT services users like data storage and processing. Fog computing relies upon implementing data processing capability and storage space nearby to fog devices rather than transferring them to the Cloud. Every Cloud and FogFog give storage, computing, and networking resources.  The determination of fog computing within the IoT is to improve performance, reliability, and to decrease the pack of data transferred for making the process in the Cloud and to analyze the data and subsequently store it. Hence the collected data is going to be sent to network edge devices for processing and temporary storage, preferably transferring them into the Cloud, decreasing network traffic and latency.

Fog computing is usually the subversion or merely the extension of the Cloud and possibly the most related to the things that work in IoT data. Figure 3.2 describes the intercessor connecting the cloud and edge devices that bring storage, networking, and processing services themselves closer to the edge devices. Specific devices are known as fog nodes. The devices might signify extended everywhere by using a network connection. A fog node can be any of the nodes which have the storage, network connectivity, and computing capacity. These devices include automated controllers, switches, routers, embedded servers.

Figure3.2 System architecture.

3.2.4 Fog computing for the Air pollution Monitoring Systems

In this Section, We discuss a fog-computing dependent IoT architecture for the system of pollution monitoring. As shown in Figure 3.2, the monitoring system works layered IoT architecture. Three layers are defined, namely the Device layer, the Fog layer, and the Cloud layer, sequentially. These whole three layers communicate via Wi-Fi, though the usage of other similar technology for this purpose also shows. The total workload is even and scattered over these three layers consistent with the fog-computing mechanism. Fog nodes are heterogeneous. They range from high-end servers, edge routers, access points, set-top boxes, and even end devices such as vehicles, sensors, mobile phones, etc., ranging from high-speed links connecting enterprise data centers and the core to multiple wireless access technologies towards the edge. The Fog platform should provide necessary means for distributed policy-based orchestration, resulting in scalable management of individual subsystems and the overall service.

3.2.4.1 Device layer 

It holds the basis for the whole system of air quality monitoring, which is initially useful for data reporting and sensing air quality. Because of these leading things of the sensing layer, the monitoring nodes of air quality are battery-powered and comprehensively installed across a large geographic area. Thus, large-scale air quality data collected by these nodes. The features of the monitoring node implemented within the following section.

3.2.4.2 Fog layer 

This layer includes fog computing devices (IoT gateways). It is necessary to interact with the opposite two layers. Every fog node is an extremely virtualized program hosted on an applied computing node implemented with an interface communication, or access point, switch. Data gathered by devices of IoT sensing are not communicating immediately to the cloud server for processing. Preferably, they sent to nearby fog node to achieve fast and extraordinary rate service. Fog node can separate data that were non-actionable and transfer them to the Cloud for batch analytics and long-term storage.

The Fog layer hides the platform heterogeneity and exposes a uniform and programmable interface for seamless resource management and control. The layer provides generic APIs for monitoring, provisioning and controlling physical resources such as CPU, memory, network and energy. The layer also exposes generic APIs to monitor and manage various hypervisors, OSes, service containers, and service instances on a physical machine (discussed more later). The layer includes necessary techniques that support virtualization, specifically the ability to run multiple service containers on a physical device to improve resource utilization. Virtualization enables the fog layer to support multi-tenancy. The layer exposes generic APIs to specify security, privacy and isolation policies for service containers belonging to different tenants on the same physical machine. Explicitly, the following multi-tenancy features are supported:

• Data and resource isolation guarantees for the various tenants on the same physical infrastructure.
• The capabilities to inflict no collateral damage to the multiple parties at the minimum.
• Expose a single, consistent model across the physical machine to provide these isolation services.
• The abstraction layer exposes both the material and the logical network to administrators, and the resource usage per-tenant.

3.2.4.3 Cloud layer

The cloud layer is liable for sensed data processing and implementing interactive assistance to users. It is of two parts, i.e., IoT cloud and user applications. Once it takes the data arrived from the fog computing device, it stores the data within the database of the cloud layer and gives data visualization in many ways.

3.2.5 Fog Nodes

The fog nodes are the central processing units located close to the data nodes. They process the data captured by the sensor node and are also responsible for filtering and delivering the relevant data to store in the Cloud. Their two main tasks can described as follows:

3.2.5.1 Complex event processing (CEP)

This task refers to the processing fusion of the data collected by the sensor nodes. The primary outcome of this task is to notify stakeholders of patterns derived from events of the lower level. A fog node processes the different events based on the information extracted from the data collected by the sensor nodes. At the edge level, an initial analysis carried out. As the second step, the fog node sends the data and events to the core level via the Internet, reducing the processing and analysis to be done at the core level.

3.2.5.2 Edge and edge-to-core communications

Fog nodes are in charge of sending (1) local alerts to the subscribers and (2) the sensed data and events to the core level via the Internet. Nowadays, many platforms use the MQTT protocol: a light-weight protocol where the devices send (publish) information with a label (topic) to a server that works as a broker. The broker sends data to all subscribers; that is, (i) the communication mechanisms are implemented in a local broker performed at the fog node and (ii) a global broker built into the cloud facilities.

The fog computing-based air pollution and air quality monitoring system enables efficient features such as less expensive, good accuracy, less power consumption, easy system deployment, easy maintenance, scalability and upgradation easily.

3.2.6 Challenges in air pollution monitoring system

The air pollution monitoring system subjected to the various incapable factors to be attained such as

• Cost and Maintenance
• Accuracy
• Data attainment
• Active Monitoring
• Flexibility and Scalability
• Power consumption

3.3 PROBLEM STATEMENT

Air pollution is one of the essential issues that cannot ignored. An inhaling of the pollutants for a long time causes damages in human health.  From the areas with lingering nonattainment problems with ozone and particulate matter to heightened awareness and concern over exposure to air toxics; from the relatively high background levels of air pollution.  The available sensors work close to their limit of detection to provide the low ppb or µg/m3 level of sensitivity required for any of the typical ambient air quality applications. However, several systems offered for these applications provide readings in ppm or even % level readings – which makes them inappropriate for ambient air monitoring. Some are also not fit for long-term outdoor use, as they are not fully weatherproof or cannot cope with the expected temperature ranges for the air pollution monitoring systems. Traditional air quality methods provide expensive air quality monitoring stations across the cloud framework. To overcome these challenges, proposed fog computing enabled the air pollution monitoring system efficiently through the HTTP server.

3.4 PROPOSED METHODOLOGY

The System Implementation involves the hardware and software components, with the detailed explanation provided below.

 3.4.1 Hardware Model

The hardware of the system necessarily includes the Device Unit (DU) and fog computing devices (FCD), as shown in Figure4. The device unit receives the real-time air pollution data and transfers this information to the FCD into a wireless channel. Figure 3.3 shows the embedded Processor-Based Sensing unit and Fog Computing Devices.

Figure 3.3 Embedded Processor Based Sensing unit and Fog Computing Devices

3.4.2 Sensor Module:

To make the system cost-efficient, we have got a tendency to use the low-cost sensor for more insignificant pollutants and added right sensors; the leading unavoidable contaminants present within the air. Because of the sophisticated technique, these sensors can estimate the air quality in a few moments. Though the accuracy of this sensor’s strength is not similar to conventional monitoring stations, it is adequately able to determine the trend of the air quality level. This module planned to maintain six completely different sensors, GP2Y1014AU0F, DSM501, MQ-7, GSNT11, SO2-AF, and MiCS2610-11, to the exposure of PM₁₀, PM_2.5, CO, NO₂, SO₂, and O₃. Additionally, a DHT11 humidity & temperature sensor was connected to solve temperature and also humidity dependency.

3.4.3 Power Module:

The node contains rechargeable Lithium battery-powered and the control node. The battery connected to the control module that transforms 9v to 5v and 3v. Hence could result in a protected and trustworthy power offer for additional sub-modules.

Figure 3.4 Hardware Functional Units for Proposed System Design

3.4.4 Fog Node module:

As displayed in Figure 3.4, the Fog node in on the second layer, which is the network layer achieved by employing a general-purpose processor (GPP) based open-source Software Defined Radio (SDR) platform. For the aim of simplicity and to keep the prices low, this platform is meeting the current prototype requirements, though any other advances and for device development, much sturdy board will be in use.

3.4.5 Processing module:

This module is useful for estimating the AQI, data analysis, and power management. To model, the local database SD card would join with a device that stores hourly data, with individually the daily AQI or AQI sliding window on being revealed to the Cloud, as an outcome of it saves power and communication bandwidth. This system is scalable and can work in various modes, as well as regular, hourly, and sliding windows modes. A sliding window case is where the AQI is posted to the Cloud only if it varies sufficiently to change the range window that reflected in Figure 3.5. Mode selection is subordinate to the application and user needs. Sensor Module: This module includes low price electrochemical sensors from the MQ range (MQ-135, MQ-6, MQ-7, MQ-9) for indoor area pollutants and dangerous gases. The GP2Y1014AU0F established to cover the dust and particle matters. Additionally, a DHT11 humidity and temperature sensor were connected to solve temperature and humidity dependency.

3.4.6 Communication modules

The IEEE 802.15.4K protocol utilized for communicating and exchanging the data within the sensing module and Fog node module.

3.5 Software Implementation

As displayed in Figure 3.5. A large number of software programs are needed not just in the IoT cloud but more in the client so that users can obtain the full use of the services given by the processed system.

Figure 3.5 Proposed Fog Computing based IoT Architecture for the Air pollution Monitoring

3.5.1 Fog node

Fog computing signifies an upcoming method, which in turn produces data storage, processing, and analytics adjacent to the network edge. In particular, devices and properties in common through cloud computing, though, FogFog will be identified from Cloud with its contiguity to end-user, the dense environmental relationships, and its dependence on mobility. Figure 3.3 shows the position of Fog Computing in IoT systems. Fog cannot replace the Cloud, however, complements its services by entering a single intermediate layer formed of geo-distributed Fog nodes. Every fog node is a remarkably virtualized platform hosted on a dedicated computing node implemented with a connection interface, or resource-poorer devices like a set-top box, access point, router, and switch. The IoT sensing devices accumulate the data and send it to the nearby fog node, preferably of passing it to the cloud server for data processing. It done to make quick and high-rate service. However, the experience is that the non-actionable data are typically filtered out by the fog node, and these data sent to the Cloud for batch analytics and extended-term storage. Cloud could be an actual place to run international analytics on data collected from publicly distributed devices over extended periods (months, years).

3.5.2 HTTP Server

The protocol HTTP does apply to implement help to the users, and therefore, an HTTP server will receive an exploitation Servlet and JSP ( JavaServer Pages). Through a web container, it deployed, i.e., Tomcat, that is efficient toward the attainment of the servlet’s lifecycle. The server HTTP, in turn, communicates to the clients within the mode of two-way Request-Response, mainly GETS and POST method. Furthermore, this gives APIs for clients to demand the quality of air data by manipulating a web browser or a mobile APP.

3.5.3 DISPLAY APPLICATIONS

As abovementioned, a mobile or a website APP can handled to show the quality of air data to users’ end. Our front page contains exploitation JavaScript, CSS, and HTML, and an APP android will also offered. Figure 3.6   and Figure 3.7 illustrate the GUI interfaces of the web site and even the mobile APP, respectively. Within the application display, the information of air quality can revealed in real-time,

e.g.,

• AQI trend of the current day;
• AQI trend in last week/month.
• Current Air Quality Indicator (AQI)

Figure 3.6 Mobile App Interface for SO2, NO2

Figure 3.7 Mobile App Interface for PM 2.5 and PM 10

3.5.4 Data processing

3.5.4.1 Pre-calibration

Properties of the low-cost sensor practice difficulty from the sensor to sensor and from making loT to making loT. Hence, various sensors require pre-calibration to determine gas capability precisely. Algorithm1 reveals the measures for pre-calibration, hereabouts coefficient x and y are extrapolated from the curves implemented within the sensor’s datasheet, for example, features curve for the MQ 135 detector will take.

Algorithm 1: Pre-Calibration for Gas Sensors

1. Estimation of   (sensor resistance in the fresh air)
2. Estimation of  (sensor resistance appearance of specific gas)
3. Analog interpret sensor pin
4. Get various samples and estimate the aggregate (S)
5. = S / fresh air element
6. Generalize coefficients x and y
7. Compute ppm, ppm =

3.5.4.2 Auto Calibration (Temperature and Humidity Dependency)

Low-cost sensors are normally influenced by temperature and humidity, as described in their datasheets. Accordingly, pre-calibrated conditions need to be changed concerning the temperature and humidity dependency to validate sensing accuracy. Algorithm 2 features how to implement the auto-calibration. The calibrated value of the gas sensors is calculated as:

Where is the sensor resistance in the appearance of a certain gas,  is the sensor resistance in the fresh air, and  is the temperature and humidity dependence estimation value for the calibration. The ratio of the sensor resistances,, is accomplished by:

Where is the external resistance, temperature, and the humidity dependence estimation value for the calibration, can be accomplished by:

Where  is the current temperature and  is the humidity dependency value.

Algorithm 2: Auto Calibration for Temperature and the Humidity Dependency

(Calibrated data of the gas sensors), (Temperature),  (Humidity Value),

(Current Analog read value of gas sensor),(The external load resistance),

(The maximum analog read value of a),    (resistance ratio)

1: Read sensors information,, and )

2: Transform the estimated values to dependency values (_, , and )

3: Estimate the value of temperature and humidity dependency,   with Equation (3)

4: Estimate the   using (2)

5: Estimate the calibrated valueusing (1)

3.5.4.3 Data Smoothing Algorithm

The Computations that considerably differ from the traditional model of the determined data referred to as outliers. They have to be found and removed to obtain reliable data. A data smoothing algorithm used to filtering out this noise. To smooth values the gas sensor data, essential data trends were recorded in a very continual statistical manner and standard deviation with ±3σ used for limitation. Algorithm 3 explains the soothing algorithm.

Algorithm 3: Sensor Data Smoothing

1. (Sensor Resistor)
2. (Load Resistor)
4. if
5. then completecategorisation
6. else Keep
7. end if

3.5.5 Data Transmission Strategy

Algorithm 4 performed to decrease the ability using at the sensing node and hence, the fog computing device. The critical plan behind this algorithm is that the data can only transfer if it’s helpful. The sensing node only transmits the data to the fog computing device if the evaluated value was considerably ranging from the previous value, and the quantity of distinction is such as by the ∆. The fog computing devices estimate the AQI and update it to the Cloud, given that the AQI changes its window. If the variation of the AQI is within a similar window, it’ll not be posted to the Cloud (on an hourly update case), for instance, if the AQI ranges from 51 to 100, it resides within the moderate window. If the value meets the limit and progress to the next window, it’ll be updated. Algorithm 5 illustrates the multiple Sensor Module scenarios and the inclusion of their individual AQI to improve data accuracy.

Algorithm 4:  Data Transition Strategy for Fog Computing Device

For FCD

1: if

2. then Don’t send data to Cloud and mobile  app
3. else
4. if
5. if
6. then inform the AQI on the cloud/user application

Algorithm 5: Data Transition Strategy for Sensor Node

(Total Air quality index at time t)

1: if

2: then Don’t send data to the fog node

3: else

4: if

5: if

6: then update the AQI on the cloud / user end

Algorithm 6: Improving the Competence of the Total AQI

1: Average estimation of single AQI of each pollutant

2: Estimation of total AQI

3: Average estimation of AQI from every Sensing Node

4. if

5: then:

6: else

7: if

3.5.6 EXPERIMENTAL EVALUATION

To evaluate the effectiveness of the system, the sensing module, fog computing device, and IoT cloud platform was integrated. As a metric to indicate the air quality, AQI “IAQI” is calculated by measuring six primary pollutants.  The critical points for the six air pollutants are given by India’s Ministry Environmental Protection and other bodies. A discrete score  is assigned to the level of each pollutant as calculated by Equation, and also the absolute AQI(IAQI) is that the highest of them as described by the Equation.

: Air Quality Index of the  pollutant

:

According to the above equation will be the individual AQI of the relevant pollutant that obtains the highest value. According to the traditional statistics of standard AQI data, the significant and dominant pollutant is PM2.5. The overall functionality of the system exhibited by conducting the experiments in different settings living room and open environment. In the small-size living room (4m x 3m), it estimated that one sensing node was adequate, which placed in the medial side of the room at the height of 1.8m. For the open environment, the sufficient height of the node kept at 9m.

3.5 RESULTS AND DISCUSSION

The overall functionality of the system was demonstrated by carrying the experiments in distinctive settings – classroom and an open environment. At the school – (8m*10m), it was assessed that one sensing node was sufficient, placed within the center aspect of the room at the height of 2m for the open atmosphere, at 9m the adequate height of the node kept.  Air pollution monitoring analysis, measurements have been carried within the boy’s hostel building of the K.L.N. College of Information Technology from 1 May to 15 May 2018. We decided 15 consecutive days and 24 readings each day (every hour) to determine the consistency of the measurement. Each monitoring example analyzed various environmental and weather parameters like temperature, relative humidity, and wind speed.

Air monitoring information examination AQI for PM2.5 revealed in figure 3.8. The validation of the trustability and the achievement of the system is to be measured; additional data sets and identified PM2.5 provided other data sets, as shown in figure 3.9. Over to verify the trustworthiness of the system, more information sets were acquired from recognized PM2.5 databases http://app.cpcbccr.com/AQI_India. These datasets are correlated in Figures 3.8 and 3.9 for outdoor and indoor environments, respectively.

Figure 3.8 Indoor measurement of data analysis in PM2.5 AQI value association with official data, for 15 days from 1 May to 15 May 2019.

Figure 3.9 free measurement of data analysis in PM2.5 AQI value association with official data, for 15 days from 1 May to 15 May 2019.

It is evident from Figure 3.10 that the aims of the AQI range accord were well when measured with various sensing nodes as correlated to the single-node illustration. Although the data trends were equivalent to official data in the single node (N=1) scenario, the gap and difference are higher than in the multiple node (N=2) cases. The sensing performance increases with the study of more sensing nodes because it improves the quality of the data by recognizing the sensor drift and improving the coverage capability. Additionally, the multiple node method somehow combats the issue of non-uniform pollution density. The inconsistency between the measurements and reference data may be due to many factors, such as the various measurement locations, respective environment, data acquisition techniques, and the type of the consolidated sensors.

Figure 3.11 shows the AQI trends measured in the indoor environment. Those measurements have a more concise discrepancy as correlated to the outdoor fields; this is because environmental factors have some effects in the closed environment. Consequently, the air quality information collected by this monitoring system was able to determine the accuracy and reliability necessities.

Figure 3.10 Comparison between the measurements with single and multiple sensing nodes from 01-15 May 2019

Figure 3.11 Comparison between the measurement and reference data on total AQI (Indoor) from 01-15 May 2019.

Some of the atmospheric properties like wind speed, temperature, and humidity have a link to PM2.5 concentrations. The effect of these parameters on PM2.5 concentrations observed; Figure 3.12 plots the relationships among PM2.5 and the wind speed. Now, observation says that from 1 May to 15 May the PM 2.5 concentrations improved progressively with the wind speeds touching approximately 3.5 m/s. Subsequently, the speeds decreased slowly and held in a lower range, which was owing to the dispersal of the pollutants by strong winds. It is possible to decide that AQI depends on the wind speed variation to some extent, as PM2.5 is an essential participant of the AQI.

Figure 3.12 Result of the wind speed on PM 2.5 concentration (microgram per cubic meter)

3.6 SUMMARY

Air Quality is a significant problem that immediately influences human health. In this chapter, Microprocessor based hardware-implemented an air quality monitoring system by exploiting the advanced IoT techniques. The model is ready to monitor multiples gases and particular matter accompanying humidity and temperature. Algorithms appropriated to avoid temporary sensor errors and to control the cross-sensitivity issues. Automatic calibration implemented to assure the accuracy of the sensors reporting. Another algorithm revealed to decrease redundant network traffic and to decrease power consumption. IoT devices are active and have limited storage and processing capabilities. Still, these common centralized clouds have several difficulties, like high latency and network failure. To solve specific problems, fog computing has promoted as an extension of the Cloud, despite closer to the IoT devices in which all data processing is going to done at fog nodes through reducing latency, particularly for time-sensitive applications. The proposed system has no boundaries on the installation place. IoT cloud was employed to examine air quality data and to produce the data visualizations for the end-user. The urban environments are the hosts of many experiments to verify the reliability of the proposed system. When analyzing the air quality trend and comparable alternative data, some fascinating facts will unfold it. Likely, long-term and large-scale air monitoring will significantly support us to know air pollution and understand the process to solve the problem of air pollution at least partially.