Improper methods in irrigation causes a lot of problems for example reduction in the crop yield, fertility of soil  etc.  This affects the farmers, decreases their income, also affects the food supply. We are creating the smart Irrigation system that is using the latest technology including but not limited to Artificial intelligence, Image processing, Internet of Things. That will help in proper scheduling considering various environment parameters. The prototype of the proposed idea includes sensing of fields parameters, with the help of solar energy harvesting is currently present in the IIT JAMMU Campus

Smart irrigation system

The presence of toxic and harmful gases utterly dangers human health and environmental wellbeing. Selective detection of these gases is immediately required to meet the demands of the society. A promising and presently thriving area for monitoring volatile organic compounds (VOCs) and combustible gas items from the evolution of detection strategies blended with a novel, green, bio-inspired miracle leaf extracts that has been synthesized using Soxhlet Apparatus has been taken forward here. The synthesized leaf extracts were coated with three different copper coil and it was investigated for the detection of carbon dioxide at ambient temperature using laboratory made sensor setup. Three different plant extracts was coated in three different copper coil using dip coating. The sensing characteristics were monitored and compared by measuring the change in electrical resistivity on exposure to two different environmental conditions – in the presence and absence of Carbon dioxide. It is observed that the electrical response in terms of resistance of prepared miracle plant extracts towards carbon dioxide vapour has been scaled up after the passage of carbon dioxide gas. To the best of our knowledge, no study has been conducted on the synthesized miracle leaf extracts as a catalyst in line with sensing field towards carbon dioxide capture. 

SENSING AND CAPTURING THE GASEOUS STATE OF CARBON THROUGH NOVEL BIO CATALYTIC RESISTIVE SENSOR 

Air pollution is a concern for the health of all living beings. It is essential to check on the quality of air in the surroundings. This experiment was conducted to provide an IoT-based real-time air quality index (AQI) estimation technique using images and weather sensors in the Indian city of Hyderabad. A mixture of image features, i.e., traffic density, visibility, and sensor features, i.e., temperature and humidity, were used to predict the AQI. Object detection and localization-based Deep Learning (DL) methods, along with image processing techniques, were used to extract image features, while a Machine Learning (ML) model was trained on those features to estimate the AQI. In order to conduct this experiment, a dataset containing 5048 images along with co-located AQI values across different seasons was collected by driving on the roads of Hyderabad city in India. The experimental results report an overall accuracy of 82\% for AQI prediction. 

IoT-based AQI Estimation using Image Processing and Learning Methods

Amount of co2 in indoor air causes decrease in productivity and health. This issue is relevant to for example students and office workers. We have created an application which measures and predicts the co2 level so that the user can mitigate these effects.

Sensible meeter

This report proposes an IoT and machine learning (ML)-based novel method to estimate the air quality
index (AQI) using traffic data in real-time. With the help of particulate matter (PM) monitoring nodes
deployed in fifteen locations with diverse traffic scenarios of Indian roads, and using digital map service
providers, a rich traffic dataset with approximately 210,000 samples has been collected. Three different
ML models, namely random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP),
are trained on this dataset to predict the AQI category into five levels. The experimental results show an
accuracy of 82.60% with the F1-score of 83.67% on the complete dataset. Apart from this, ML models
were also trained on individual node datasets, and the behavior of AQI levels was observed.

IoT and ML-based AQI Estimation using Real-time Traffic Data

With a recent fall in air quality around us, individuals' health is at risk. The importance of a good atmosphere is evident now as people are experiencing symptoms of various illnesses. Some problems, such as fatigue, short breath, or restlessness, are caused by minute factors of the air, which are usually ignored. 
The solution presented as a result is a Smart Air Quality Monitoring system which shall serve as a means to act upon the degrading air quality and proactively avoid its ill effects

"Pawamaan" Smart Air Quality Monitoring System

Climate change is one of the major challenges in front of mankind. Air pollution is the primary reason for climate change and hence, monitoring air quality followed by air pollution abatement is essential to preserve the environment. Air quality monitoring can be done efficiently by developing compact, low power, and low cost sensors for sensing the air pollutants. We have developed MoS2 based sensors to detect NO2 at room temperature. A compact and low cost electronic circuit was designed and assembled to replace the table top read out circuit and make the device portable. The assembled circuit board can also facilitate interfacing the existing sensors that are available in the market such as temperature, humidity, CO. This work provides a proof-of-concept of developing a portable resistive sensor for detecting some of the air pollutants.

Chemiresistive Sensors for Environmental Monitoring

The first problem which was tried to solve is to speed-up a process of measuring different quantities in multiple points of an area. The second problem is the collected data visualization. All types of businesses are facing the same problem – inefficiency of processes, which they are always trying to solve. The quantities measuring is one of such processes and our solution helps to save time and other recourses of actual measuring. Our solution is to provide a driving robot with different sensors attached, as well as a software for sending sensor values to the server, saving them, and generating a map displaying measuring results in different points in the area. As a result, in about 7-10 minutes user will get the map for area of 1.5x3.0 square meters.

ESPC 2022 Competition Submissions