Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68916
Volume:
10 |
11 |
Nov 2026
Pages:
1-6
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 and Engineering
Don Bosco Institute of Technology

Department of Computer Science and Engineering
Don Bosco Institute of Technology

Department of Computer Science and Engineering
Don Bosco Institute of Technology

Department of Computer Science and Engineering
Don Bosco Institute of Technology

Department of Computer Science and Engineering
Don Bosco Institute of Technology
Drink spiking has become a major safety concern in social environments such as bars, clubs, parties, and public gatherings. Traditional methods for detecting harmful substances in beverages require laboratory testing and are not suitable for real-time personal safety applications. In this study, an AI-powered smart drink safety system using embedded sensors, machine learning, and mobile application integration is proposed. The proposed system analyzes beverage properties using pH, conductivity, temperature, and optical sensing modules integrated within a portable smart detection pen. The collected sensor data is processed using a machine learning model to classify beverages as Safe, Suspicious, or High Risk. The system also enables real-time wireless communication with a mobile application to provide beverage analysis and instant contamination alerts. A background notification mechanism is implemented to notify users even when the application is closed. The proposed approach provides a portable, low-cost, and real-time solution for improving personal safety and preventing drink spiking incidents.
KEYWORDS
The ORA project presents an experimental IoT-based liquid monitoring and sensor-data analysis system that integrates sensor modules, an ESP32 microcontroller, a native Android application, cloud services, and a machine learning component. The primary objective of the system is to collect selected liquid measurement parameters and provide a platform for presenting and analysing the available sensor information through a mobile application. The hardware component uses an ESP32 microcontroller connected to sensor modules for obtaining measurements related to Nitrogen, Phosphorus, Potassium, pH, Electrical Conductivity, Turbidity, and Temperature. The ESP32 acts as the central unit for acquiring and processing sensor information, with compatible sensor modules communicating through their configured interfaces, including RS485 Modbus communication where applicable. The Android application, developed using Kotlin and Jetpack Compose, provides the user interface for interacting with the ORA system. Firebase Authentication supports user registration and login, while Cloud Firestore provides cloud-based storage and retrieval of application-related information. The application also includes analysis-related functionality and PDF report generation using the native Android PdfDocument API. Kotlin Coroutines support asynchronous operations where required to maintain responsive application behaviour. The project also explores the use of machine learning for analysing collected sensor measurements. A customized experimental dataset containing 14 records was prepared using normal water samples and experimentally prepared water samples containing Dolo 650. Logistic Regression was used as the initial classification algorithm to study the relationship between the selected sensor features and the assigned experimental labels. Overall, the development of ORA demonstrates the integration of IoT hardware, sensor data acquisition, Android application development, cloud database services, and machine learning within a single prototype. The project provides practical experience in combining these technologies for experimental liquid monitoring and sensor-data analysis. However, limitations related to sensor calibration, dataset size, experimental validation, and detection capability must be addressed before the system can be considered a validated solution for identifying specific substances or determining drinking-water safety. Future development can focus on independent sample collection, larger and more diverse datasets, improved sensor calibration, laboratory-based validation, enhanced machine learning evaluation, and more reliable real-time communication. With these improvements, the ORA prototype can provide a stronger foundation for further research and development in sensor-based liquid monitoring and analysis.
[1] F. Nowshad, M. N. Islam, and M. S. Khan, “Concentration and Formation Behavior of Naturally Occurring Formaldehyde in Foods,” Agriculture & Food Security, vol. 7, no. 17, 2018. [2] S. P. S. Brighty, G. S. Harini, and N. Vishal, “Detection of Adulteration in Fruits Using Machine Learning,” in Proceedings of the International Conference on Machine Learning Applications, 2024. [3] Y. Wang, Y. Yang, and H. Liu, “A Review of High-Throughput Optical Sensors for Food Detection Based on Machine Learning,” Foods, vol. 15, no. 133, 2026. [4] F. Nowshad, M. N. Islam, and M. S. Khan, “Concentration and Formation Behavior of Naturally Occurring Formaldehyde in Foods,” Agriculture & Food Security, vol. 7, no. 17, 2018. [5] S. P. S. Brighty, G. S. Harini, and N. Vishal, “Detection of Adulteration in Fruits Using Machine Learning,” in Proceedings of the International Conference on Machine Learning Applications, 2024. [6] Y. Wang, Y. Yang, and H. Liu, “A Review of High-Throughput Optical Sensors for Food Detection Based on Machine Learning,” Foods, vol. 15, no. 133, 2026. [7] A. Sharif, Q. H. Abbasi, K. Arshad, S. Ansari, M. Z. Ali,J. Kaur, H. T. Abbas, and M. A. Imran, “Machine Learning Enabled Food Contamination Detection Using RFID and Internet of Things System,” Journal of Sensor and Actuator Networks, vol. 10, no. 63, 2021. [8] K. K. Pulluri and V. N. Kumar, “Qualitative and Quantitative Detection of Food Adulteration Using a Smart E-Nose,” Sensors, vol. 22, no. 7789, 2022. [9] A. Wang, Y. Zhu, L. Zou, H. Zhu, R. Cao, and G. Zhao, “Combination of Machine Learning and Intelligent Sensors in Real-Time Quality Control of Alcoholic Beverages,” Food Science and Technology, vol. 42, 2022. [10] Q. Ouyang, J. Zhao, Q. Chen, and H. Lin, “Classification of Rice Wine According to Different Marked Ages Using a Novel Artificial Olfactory Technique Based on Colorimetric Sensor Array,” Analytical Methods, vol. 4, no. 2012, pp. 1–5, 2012. [11] Y. Chen and L. Wang, “Machine Learning for Real-Time Detection of Microbial and Chemical Contaminants in Food,” Journal of Advances in Engineering and Technology, vol. 2, no. 3, 2025.
Publication Date
11/13/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
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...