International Journal Of Drug Delivery Technology
Volume 16, Issue 11s, 2026 | PG 478-484 | Article No 47

Machine Learning And IoT-Enabled Signal Processing For Adaptive Drug Delivery Technologies

Ranjeet Ramesh Suryawanshi1, Kommu Kishore Babu2, Anil S Naik3, Srinivas D4, Krishna Chandra Patra5, P. Kokulasandhiya6

1Assistant Professor, Department of Electronics & Telecommunication Engineering, Bharati Vidyapeeth's College of Engineering, Kolhapur, India. Email: rrs.bvcoek@gmail.com

2Assistant Professor, Department of CSE, Vignan's Foundation for Science, Technology and Research, Hyderabad (Deemed to be University), Off Campus, Deshmukhi Village, Pochampally (M), Yadadri-Bhuvanagiri District, Telangana, India. Email: kishore143babu@gmail.com

3Assistant Professor, Department of Cyber Security and Digital Forensics, National Forensic Sciences University Dharwad Campus, Dharwad, Karnataka, India. Email: anil.naik@nfsu.ac.in

4School of Business, SR University, Warangal, Telangana, India. Email: sridharmula@gmail.com

5Assistant Professor, Department of Mechanical Engineering, Indira Gandhi Institute of Technology, Sarang, India. Email: kcpmechcvrce@gmail.com

6Assistant Professor, Department of Mechanical Engineering, V.S.B Engineering College, Karur, Tamilnadu, India.


ABSTRACT

The adaptation technology of drug delivery can be transformed with the union of Machine Learning (ML) and Internet of Things (IoT)-based signal processing. He or she discusses an original idea that uses predictive analytics offered by machine learning algorithms and combines it with real-time monitoring via the use of the IoT to devise dynamic and adaptive drug delivery systems. Such systems are created to help maintain drug doses constantly depending on the real-time physiological information, which improves the accuracy of treatment and leads to better patient outcomes. The paper also involves the use of IoT-based sensors to collect data continuously (e.g., blood glucose levels, blood pressure, etc.), and the use of ML tools (e.g. reinforcement learning, regression model, and a neural network), to predict the optimal dose and change the delivery accordingly. Experimental simulation results indicate that the proposed system is effective in terms of drug levels and in-current therapeutic range maintenance, and drug administration efficiency and mitigation of adverse effects. The results indicate that IoT and ML integration have a great potential to add more personalized, efficient, and safe therapy to patients.

Keywords: Machine Learning, Internet of Things (IoT), Signal Processing, Adaptive Drug Delivery, Real-Time Monitoring, Personalized Medicine, Predictive Analytics, Drug Dosage Optimization, Healthcare Innovation, Patient Outcomes.

How to cite this article: Suryawanshi RR, Babu KK, Naik AS, Srinivas D, Patra KC, Kokulasandhiya P. Machine Learning and IoT-Enabled Signal Processing for Adaptive Drug Delivery Technologies. Int J Drug Deliv Technol. 2026;16(11s): 478-484. DOI: 10.25258/ijddt.16.11s.47

Source of support: Nil.

Conflict of interest: None