Journal of Scientific Research and Technology

Air Quality Prediction Using Machine Learning Techniques: A Case Study On Sulphur Dioxide Forecasting

Sunil, Dr. Shilpa B Kodli — Tue, 02 Sep 2025 00:00:00 +0000

Air pollution is one of the greatest problems being faced by mankind. Millions of people die each year because of reasons directly or indirectly related to air pollution. Effective strategies to counter the harmful effects of air pollution are an imperative need of the times. The responses to the air pollution problems are usually knee-jerk reactions, which don’t help in the long run. For developing an effective counter-strategy for combating air pollution, it is necessary to focus the efforts on the pollutants that are most responsible for the air pollution. Examining and protecting air quality has become one of the most essential activities for the government in many industrial and urban areas today. The meteorological and traffic factors, burning of fossil fuels, and industrial parameters play significant roles in air pollution. With this increasing air pollution, We are in need of implementing models which will record information about concentrations of air pollutants(so2,no2,etc).The deposition of this harmful gases in the air is affecting the quality of people’s lives, especially in urban areas. Lately, many researchers began to use Big Data Analytics approach as there are environmental sensing networks and sensor data available. In this project, machine learning techniques are used to predict the concentration of so2 in the environment. Sulphur dioxide irritates the skin and mucous membranes of the eyes, nose, throat, and lungs. Models in time series are employed to predict the so2 readings in nearing years or months.

Evaluating The Potential Of Biochar As Landfill Liner For Leachate Prevention

Rahul, Dr. Girish Bandi, Dr. Shrinivas Khstagi — Wed, 10 Sep 2025 00:00:00 +0000

This project aims is to create a of biochar based landfill liner. Leachate, a byproduct of landfill waste, contains various
hazardous substances that can pollute the surrounding environment if not managed properly. Traditional landfill liners
made of synthetic materials have been effective in preventing leachate seepage, but they are costly and can have negative
environmental impacts. Biochar, a type of charcoal produced from organic material (Sewage sludge in our case), has
been identified as a promising alternative liner material due to its high porosity and adsorption capacity. In this project
we plan on conducting laboratory experiment to test the effectiveness of biochar as a landfill liner material.

Classification Of Wheat Disease Using CNN

Prof. Dr.Sharanabasappa Madival, Akshata S Warad — Sun, 14 Sep 2025 00:00:00 +0000

Leaf rust, stem rust, and powdery mildew are just a few of plant diseases that may drastically reduce the productivity of wheat, a cereal crop that is crucial on a worldwide scale. In order to intervene quickly and implement sustainable farming techniques, early and precise disease diagnosis is essential. Automated disease classification in wheat utilizing CNN is presented in this paper as a deep learning-based technique. In order to make the model more generalizable, it was preprocessed and enhanced using a dataset of wheat leaf photos that included images of various diseases. Input photos were used to train a bespoke CNN architecture that could learn hierarchical features. Model's strong performance in differentiating amongst infected and healthy wheat samples was shown by its high classification accuracy. In terms of accuracy, recall, and total F1-score, CNN model outperforms conventional machine learning classifiers. With suggested approach, agronomists and farmers may have access to a scalable and effective tool for early disease identification in wheat, which would allow for more precise treatment and less yield loss.

Advanced Railway Track Fault Detection Using Internet Of Things (Iot)

Dinakumari, Shrinivas Gaddad — Sun, 14 Sep 2025 00:00:00 +0000

System advancement in railway sector has also resulted in the increase of railway traffic. Because of this the number of accidents in trains/railways have also increased. Every year, almost 11 million passengers travel by train. It is therefore very much important Railway is the backbone of transport system in India. Rail accidents occur more due to derailments than collision or fire in trains. These derailments are due to cracks in the railway tracks. Therefore, there is an immense need of crack detection and security system. This paper proposes the crack detection system in the rail tracks. This is to avoid rail accidents by using latest communication technologies. In this project GSM communication protocols are used to convey the message of crack detection via SMS. Crack detection is achieved by using the concept of eddy current losses implemented in the terms of Darlington pair circuit. With the detection of cracks, the system also alerts the railway authorities facilitating the security to involve such kind of technology which reduces the train accidents and hence human’s life. This paper is the analysis of various critical and unwanted situation, accidents, occurs in train system and how to prevent those accidents. In our paper we have included various approaches done by various researchers in order to avoid train accidents.

Conjunctivitis of Eye Detection Using CNN

Dr. Mohammed Abdul Waheed, Rajashree Madhav Nula — Sun, 14 Sep 2025 00:00:00 +0000

Conjunctivitis, commonly known as "pink eye," is a highly contagious inflammation of the conjunctiva that affects millions globally each year. Early and accurate detection is crucial for effective treatment and to prevent widespread transmission. Traditional diagnosis relies heavily on physical examination and clinical expertise, which may be time-consuming and prone to human error. This paper proposes an automated Conjunctivitis detection system using Convolutional Neural Networks (CNN), a deep learning technique well-suited for image classification tasks. The proposed model is trained on a curated dataset of eye images labeled as normal or conjunctivitis-infected. The CNN architecture extracts hierarchical visual features and learns patterns associated with conjunctivitis, enabling robust classification. The system achieves high accuracy in detecting infected eyes, providing a rapid, non-invasive, and scalable diagnostic tool. This approach has the potential to support ophthalmologists in early screening and can be deployed in GUI-based applications.

Noise Pollution Monitoring of Residential Areas In Sedam Taluka Kalaburgi Districts

Anil Kumar Yelmeli, Nitin mallinath kodle, Dr. Srinivas Kushtagi — Mon, 15 Sep 2025 00:00:00 +0000

Sound which is undesirable for human hearing is called as noise. When there is a lot of noise from various sources, it constitutes what is called as noise pollution. Noise pollution can be caused due to various sources there is street noise, traffic noise, and noise in public transport places, noise in playgrounds and parks etc.. One of the greatest sources of noise pollution is Heavy vehicles like Trucks and Buses. The Noise level in Sedam Taluka of Kalaburgi District of Karnataka, India has been increasing rapidly due to rapid urbanization, uncontrolled movements of vehicles.

In this paper we are trying to present about the result of noise level in dB (A) on various points of sedam Taluka of Kalaburgi District. It has been found out that noise levels are more than permissible in all the investigated various spots around the Sedam Taluka.

The minimum noise level by taking into account of morning, afternoon & evening hours is 60.30dB and the maximum noise level of morning, afternoon & evening is 76.88dB and the average of both is 68.83dB, which is more than the limits compared to CPCB Standards. Result shows, the noise should be identified as the major environmental problem and should take necessary steps to minimize it.