Air Quality Monitoring with Speech Announcements

Abstract

In this project, we design and develop an advanced weather station system using an ESP32 microcontroller, temperature sensor, humidity sensor, and air quality sensor. The primary objectives of this project are data collection, visualization, and auditory feedback. The ESP32 microcontroller acts as the central processing unit and connects to the internet via Wi-Fi to transmit real-time sensor data to an IoT platform. This platform stores and manages the data, making it accessible from anywhere with an internet connection. Users can monitor temperature, humidity, and air quality remotely through a user-friendly web interface Additionally, the project incorporates a display screen that provides local, real-time weather information for on-site users. This display enhances the accessibility of weather data, even in the absence of internet connectivity. To ensure inclusivity and accessibility, the system employs a speech-to-text algorithm implemented in Python. At predefined intervals, the system announces the sensor data via a speaker using text-to-speech (TTS) technology. This feature aids visually impaired individuals in accessing weather information in an auditory format. The combination of sensor integration, IoT connectivity, data visualization, and text-to-speech capabilities creates a comprehensive and user-friendly weather monitoring system suitable for both personal and public use. This project demonstrates the potential of IoT technologies to improve data accessibility and inclusivity in weather monitoring applications. IQ test continue to be one of most reliable tools to measure intelligence skills of the human. The Intelligence Quotient (IQ) tests and the corresponding psychometric explanations dominate both the scientific and popular views about human intelligence. Though the IQ tests have been in currency for long, there exists a gap in what they are believed to measure and what they do. While the IQ tests index the quality of cognitive functioning in selected domains of mental repertoire, the applied settings often inflate their predictive value leading to an interpretive gap.

Introduction

I. INTRODUCTION

Air quality is a critical component of our environment, profoundly affecting human health and the quality of life. With the increasing urbanization and industrialization of our cities, monitoring and managing air quality has become a pressing concern. In this context, this project introduces an innovative solution for air quality detection and real-time voice announcements, designed to provide accurate information and enhance awareness of air quality conditions. This introductory section outlines the literature survey, discusses the limitations of existing systems, and presents the proposed system as a comprehensive response to these challenges. Air is getting polluted because of the release of toxic gases by industries, vehicle emissions and increased concentration of harmful gases and particulate matter in the atmosphere. The level of pollution is increasing rapidly due to factors like industries, urbanization, increase in population, vehicle use which can affect human health. Particulate matter is one of the most important parameters having a significant contribution to the increase in air pollution. This creates a need for measurement and analysis of real-time air quality monitoring so that appropriate decisions can be taken in a timely period.

In an era characterized by the proliferation of smart technologies and interconnected devices, the Internet of Things (IoT) has emerged as a transformative force, revolutionizing the way we collect, process, and utilize data. Within the realm of IoT applications, environmental monitoring stands as a pivotal domain with profound implications for public safety, health, and general well-being. The Internet of Things (IoT) describes the network of physical objects “things” that are embedded with sensors, software, and other technologies for the purpose of connecting and exchanging data with other devices and systems over the internet. These devices range from ordinary household objects to sophisticated industrial tools. For air quality monitoring, a number of heterogeneous sensors are used in each sensor mote to measure several to dozens of parameters, such as particulate matter, ozone, sulfur oxides, volatile oxide compounds, ammonia, carbon oxides, nitrogen oxides, and other meteorological variables. The number of sensor motes are also densely located over the study area for comprehensive coverage and high spatiotemporal resolution of the collected data. 

II. RELEVANCE OF WORK

The relevance of this project is underscored by the growing concern for environmental health, safety, and climate change. IoT-based weather stations have the potential to empower individuals, industries, and governments with actionable insights. Additionally, the integration of voice announcements amplifies its relevance by making this data more accessible and immediate for a broader audience.

This project's implications extend beyond mere data collection; it aligns with broader initiatives aimed at enhancing environmental stewardship, public safety, and accessibility. It offers a glimpse into a future where our environment is monitored and communicated with unprecedented precision and clarity.

In the ensuing sections, we will delve deeper into the existing literature, elaborate on the relevance of this work, outline our proposed methodologies, and describe the experimental and analytical approaches that underpin this innovative IoT-based Weather Station with Voice Announcement project.

III. LITERATURE REVIEW

“Air Quality Sensing and Reporting System using IOT”, Second International Conference on Inventive in Computing Applications (ICIRCA), 2020- (Rohan Kumar Jha)

The system presented in this paper is an advanced real time air quality reporting system supported with Internet Of things (IOT) architecture. Degrading air quality has been a matter of concern nowadays and real time monitoring of air quality helps us to keep a check on it.Air Quality Index(AQ I) is the scale to measure how polluted the air is. Greater AQI indicates more dangerous air is for human health. The model presented here uses a combination of the Arduino UNO software and hardware along with a Gas sensor - MQ135, MQ7 and dust sensor GP2Y1010AU0F which help in detecting gases like NO2, CO and PM2.5 while measuring their amount decently. Further, this research work monitor the Air Quality over an IOT analytics platform - ThingSpeak using internet connected with the hardware via the Wi-Fi module ESP8266. It can also integrate the real time data into our mobile phone app which is specifically created for this purpose using Android Studio. The circuit finally displays the PPM values as well as Air Quality level of gases on an Android application which fetches data from ThingSpeak. The current model is implemented successfully and can be deployed for real system implementations.

“IoT based Indoor Air Quality Monitoring system using Raspberry Pi4”, International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2020- (Syed Faiazuddhin, M.V. Lakshmaianh, K. Tanveer Alam, M. Ravikiran)

Poor quality is a major concern in urbanized areas. With more than 85% of people exposed to high levels of a particular matter. According to the World Health Organization, people are more cautious to look up the quality of air, their health by focusing on the spaces where they spend most of their time at home, school etc., and in their car. In this concept, a system with low power and data consumption is introduced. In this article, the air quality using a Raspberry Pi4 with Grove - Air Quality Sensor v1.3, CCS811 CO2 Air Quality Sensor, DHT 11 Temperature and Humidity Sensor were discussed. The communication between the sensor and Raspberry Pi4 will be through a serial port communication protocol and the code is implemented on the Python interface. Air pollution is a global environmental health problem many peoples are dying every year due to some of the visible and invisible parameters like small particles, gases and so on. Most of the parameters of the environment to be monitored such as volume of CO, CO2, Temp, Humidity, Gas Leakage, Smoke, temperature sensor, and etc. These parameters information can received by Rasp Pi4, Arduino Uno and process the information and transmitted to clouds where they are being continuously monitored and information will be stored in the cloud database.

“Bus as a sensor: A mobile sensor nodes network for the air quality monitoring”, IEEE 13th International Conference on Wireless and Mobile Computing Networking and Communication (WiMob), 2017- (Salvatore Michele Biondi, Vincenzo Catania, Salvatore Monteleone, Carmelo Polito)

Air pollution is an important issue due to its direct impact on human health. To cope with this problem, in urban areas a “monitor and react” approach, based on measurements provided use of static monitoring stations, is commonly adopted introducing constrains to the amount of areas that can be monitored within the city. With the rise of the Internet of Things paradigm, new air monitoring models based on mobile sensors networks have been proposed. In this paper, we present the concept of Bus as a Sensor (BaaS): an air quality monitoring system based on mobile sensor nodes placed upon buses. This work aims to provide a high-resolution air quality map to report pollutants measurements and facilitate the analysis to support the government decisions in order to reduce the pollution. The proposed paper describes the system architecture and the requirements of sensor nodes to depict the implementation concepts and lay the foundations for future experiments on field.

IV.  PROPOSE SYSTEM

1. The proposed air quality detection and voice announcement system addresses the limitations of existing systems by integrating multiple gas sensors (including MQ7, MQ6, MQ3, MQ135), a temperature and humidity sensor (DHT11), and a NodeMCU ESP32 for data collection and upload to the ThingSpeak platform.
2. In addition, a Raspberry Pi is employed to process data from ThingSpeak and generate voice announcements using text-to-speech technology.
3. This system offers a comprehensive solution for air quality monitoring, ensuring real-time data accessibility, and immediate user awareness through voice announcements.
4. It represents a significant step toward enhancing air quality awareness and promoting informed decision-making in the face of growing environmental challenge.

V. OBJECTIVE

1. To create an advanced Air Quality Reporting Station.
2. To continuously monitor air quality parameters in real-time.
3. To implement a Python-based speech announcement system for immediate communication.
4. To provide a user-friendly interface for data access. Through Things Speak platform collected data can be analyzed, stored and visualized using graphs and charts to give a better understanding of Air quality.

VI.  METHODOLOGY

The methodology section outlines the strategies and approaches to achieve the project's objectives, combining both experimental and analytical methods:

A. Experimental Methodology

1. Hardware Setup: Assemble the NodeMCU, sensors (MQ7, MQ135, MQ6, DHT11), and power supply components into a cohesive system.
2. Data Collection: Employ the sensors to collect environmental data in real-time.
3. Communication Setup: Configure the NodeMCU to establish a secure Wi-Fi connection to the ThingSpeak server.
4. Voice Integration: Develop Python scripts to convert textual data into voice announcements.
5. Alert Mechanisms: Program the system to trigger alerts based on predefined thresholds.
6. User Interface: Create a web-based user interface for monitoring and configuring the system remotely.
7. Testing and Validation: Conduct extensive testing to ensure accurate data collection, timely alerts, and voice announcement reliability.

B. Analytical Methodology

1. Data Analysis: Collect historical sensor data on ThingSpeak for analysis.
2. Trend Analysis: Identify trends in temperature, humidity, gas levels, and weather conditions.
3. Alert Validation: Verify the effectiveness of alert mechanisms under various scenarios.
4. User Feedback: Gather user feedback to fine-tune system performance and user interface.

C. Techniques to be Used

1. Data Acquisition: The NodeMCU ESP32 will read data from the MQ7, MQ6, MQ3, MQ135 gas sensors, and the DHT11 temperature and humidity sensor. The data from these sensors will be collected periodically.
2. Air Quality Calculation: The collected sensor data will be used to calculate air quality indices such as Air Quality Index (AQI) for different gases, which represent the overall air quality.
3. LCD Display: The system will employ an LCD screen to provide a local visual representation of air quality indices, temperature, and humidity.
4. Data Uploading: The NodeMCU ESP32 will use Wi-Fi connectivity to upload the sensor data to the ThingSpeak platform for remote monitoring and historical data storage.
5. Text-to-Speech (TTS): On the Raspberry Pi, a Python script will use TTS libraries, such as gTTS (Google Text-to-Speech) or pyttsx3, to convert air quality data into audible speech.
6. Audio Output: The Raspberry Pi will play the generated audio using built-in audio capabilities or an external speaker.

By integrating these components and techniques, the system can offer comprehensive air quality monitoring and user-friendly voice announcements, making it a valuable tool for enhancing indoor air quality awareness and decision-making.

D. System Architecture

E. Data Flow Diagram

VII. FUTURE WORK

The Air quality detection and voice announcement system has a promising future scope, with opportunities for further development and enhancements:

1. Sensor Expansion: We can extend the system's capabilities by integrating additional sensors to monitor more air quality parameters, such as PM2.5 and PM10 particulate matter, volatile organic compounds (VOCs), or other specific pollutants relevant to our region.
2. Machine Learning Integration: Incorporating machine learning algorithms can enhance the system's predictive capabilities. By analyzing historical data and weather conditions, the system can provide more accurate and context-aware air quality forecasts.
3. Mobile Application: Develop a mobile app that connects to the system, allowing users to access real-time air quality data and receive notifications on their smartphones. This app can also offer user-friendly visualizations and historical data analysis.
4. Geographical Expansion: Extend the system to cover larger geographic areas or multiple indoor environments. This can be particularly beneficial for public spaces, schools, workplaces, and smart cities.
5. Cloud Integration: Connect the system to cloud platforms like AWS or Google Cloud for robust data storage, processing, and analytics. Cloud integration can provide scalability and data security.
6. Smart Home Integration: Integrate the system with smart home devices and automation systems. For instance, the system could trigger air purifiers or HVAC systems to improve indoor air quality based on sensor readings.
7. Community-Driven Data: Encourage community involvement by allowing users to contribute their air quality data. Crowdsourced data can enhance the accuracy and coverage of the system.
8. Advanced Voice Interfaces: Utilize advanced voice recognition and natural language processing (NLP) technologies for more interactive and context-aware voice announcements. This could include answering user queries and providing personalized recommendations.
9. Environmental Reporting: Expand the system's capabilities to generate detailed environmental reports and trend analysis, enabling users to make informed decisions about long-term exposure to air pollutants.
10. Regulatory Compliance: Align the system with local air quality regulations and standards, making it a valuable tool for both individuals and businesses to comply with environmental requirements.
11. Educational Tools: Develop educational resources to raise awareness about air quality and its impact on health. The system can be used as an educational tool in schools, universities, and community outreach programs.
12. Low-Cost Variants: Explore options for creating low-cost versions of the system to make it more accessible to underserved communities and regions with limited resources.
13. Energy Efficiency: Optimize the power consumption of the system components to make it more energy-efficient, suitable for deployment in remote or off-grid areas.

The future of air quality monitoring and notification systems holds immense potential for improving public health, environmental awareness, and decision-making. As technology advances and the need for clean air becomes more pressing, the system can continue to evolve and provide valuable solutions for individuals, communities, and governments.

Conclusion

In conclusion, the development of an air quality detection and voice announcement system represents a significant step toward enhancing air quality awareness and providing timely information for informed decision-making. This system, which integrates various hardware components and software modules, offers a valuable tool for monitoring air quality and delivering critical information to users. In an era where environmental concerns are paramount, the air quality detection and voice announcement system addresses an essential need. By enhancing awareness and providing users with actionable data, this system contributes to the well-being of individuals and the sustainable development of communities, setting the stage for a healthier and more informed future.

References

[1] International Journal of Advanced Research in Computer and Communication Engineering ISO 3297:2007 Certified Vol. 5, Issue 9, September 2016 [2] International Journal of Engineering Trends and Technology (IJETT) – Volume 32Number 2-February 2016 [3] International Journal of Engineering Science and Computing, May 2017 [4] Sagar J. S. T., M. S. Balamurugan and J. A. Vivek, “A wireless framework for automotive monitoring systems,” in Indian Journal of Science and Technology, Vol 8(19), IPL0146, August 2015 [5] https://www.openhacks.com/uploadsproductos/rain_sensor_modul e.pdf [6] http://designinformaticslab.github.io/productdesign_tutorial/2017/01/24/soilmoisture_sensor.html [7] content://com.sec.android.app.sbrowser/readinglist/0721190655.mhtml [8] https://www.hackster.io/techmirtz/using-16x2-lcd-with-arduino-d89028 [9] https://www.arduino.cc/en/Guide/ArduinoUnoWiFi

Copyright

Copyright © 2023 Prof. Sadhana Chougule, Vaishnavi Lad, Sayali Patil, Gauri Pise, Sourabh Pethkar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.