Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66384
Volume:
10 |
7 |
Jul 2026
Pages:
1-10
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science
G M University Davanagere
Department of Computer Science
G M University Davanagere
Allergic diseases are a problem for public health and it is getting worse. This is because the air is getting dirtier the climate is. We are around things that make us allergic more often. Most of the systems that try to predict allergies are not very good because they only use data or a few things about the environment. This means they are often wrong and not helpful to people.To fix this problem we made a new system called the Intelligent Real-Time Allergy Prediction System. This system uses machine learning. Gets information from the environment in real-time. It also uses information about the users health.The system starts by finding out where the user is using GPS. Then it gets information about the environment from sources. This includes things like the temperature how humid it's how fast the wind is blowing the air pressure, how good or bad the air is, how much bad stuff is in the air how strong the suns rays are, how much pollen is around and how many mold spores are in the air.This information, combined with the users health information is used by a machine learning model. The model says if the allergy risk is Low, Medium or High.This system does more than just predict if someone will have an allergy problem. It also gives the user personalized advice on how to stay safe and feel better. The system has a chatbot that users can talk to and get help away.By putting all these things finding the users location getting information about the environment predicting allergy problems giving personalized advice and using a chatbot. The system helps people take care of their allergies every day.We think this system will make predictions more accurate send out warnings on time and make it easier for people to make choices about their health. This makes it a good solution, for taking care of our health and monitoring the environment in a way.
KEYWORDS
The proposed Intelligent Real-Time Allergy Prediction System offers a practical and effective way to predict allergy risks by combining machine learning with live environmental data. By drawing on real-time weather parameters — such as AQI, PM2.5, UV index, pollen count, mold spores — along with GPS-based location, the system is able to accurately classify allergy risk as Low, Medium, or High. Beyond just prediction, it strengthens user support through personalized recommendations, advisory prescription suggestions, and multilingual voice guidance in English, Kannada, and Hindi. Together, the real-time data integration, intelligent prediction capabilities, and user-friendly design make this system a reliable tool for proactive allergy management, while also contributing meaningfully to the growing field of smart healthcare applications.
[1] C. Sarabu, S. Steyaert, and N. R. Shah, "Predicting Environmental Allergies from Real World Data Through a Mobile Study Platform," Journal of Medical Internet Research, vol. 23, no. 8, 2021. [2] M. Rajesh, R. Ganesh Babu, U. Moorthy, and S. V. Easwaramoorthy, "Machine Learning-Driven Framework for Real-Time Air Quality Assessment and Predictive Environmental Health Risk Mapping," International Journal of Intelligent Systems and Applications, vol. 17, no. 2, pp. 1–18, 2025. [3] P. M. Matricardi, T. Hoffmann, and S. Dramburg, "The 'Allergic Nose as a Pollen Detector' Concept: e-Diaries to Predict Pollen Trends," Allergy, vol. 78, no. 11, pp. 2958–2968, 2023. [4] S. Kim, A. Damialis, A. Charalampopoulos, D. H. Voelker, and A. C. Rorie, "The Effect of Climate Change on Allergen and Irritant Exposure," Current Allergy and Asthma Reports, vol. 25, no. 3, pp. 1–15, 2025. [5] P. V. S., N. Mohankumar, S. Sekar, B. Gopi, S. Dhanalakshmi, and S. Murugan, "IoT-Enhanced Airborne Pathogen Surveillance in Healthcare Environments Using Deep Generative Networks," IEEE Access, vol. 13, pp. 1–15, 2025. [6] A. Bansal, "Enhancing Pollen Allergy Severity Predictions Through Machine Learning," International Journal of Advanced Computer Science and Applications, vol. 16, no. 4, pp. 1–10, 2025. [7] N. Zounemat-Kermani, S. Naderi, C. H. Dilliway, et al., "An AI-Driven Framework for the Prediction of Personalised Health Response to Air Pollution," Environmental Research, vol. 270, 2026. [8] M. H. Shamji, M. Ollert, I. M. Adcock, I. Agache, et al., "EAACI Guidelines on Environmental Science in Allergic Diseases and Asthma: Leveraging Artificial Intelligence and Machine Learning," Allergy, vol. 78, no. 12, pp. 3200–3220, 2023. [9] K. C. H. Tsang, "Enhancing Asthma Self-Management with Environmental Passive-Monitoring Data and Machine Learning-Based Predictions," JMIR Medical Informatics, vol. 12, 2024. [10] A. Stanko, W. Wieczorek, A. Mykytyshyn, O. Holotenko, and T. Lechachenko, "Real-Time Air Quality Management: Integrating IoT and Fog Computing for Effective Urban Monitoring," Sensors, vol. 24, no. 9, pp. 1–22, 2024.
Publication Date
7/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
9
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...