EUVIMEDEUVIMED entdecken
Crossref

REAL-TIME IOT HEALTHCARE MONITORING USING WEARABLE SENSORS AND HYBRID DEEP LEARNING MODELS

Neeta Suryakant Brahme, Jameer Kotwal

International Journal of Data Science and Artificial Intelligence · 30.08.2025 · 130

DOI: 10.66135/ijdsai0304p005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Data Science and Artificial Intelligence, online erschienen am 30.08.2025. Verfasst von Neeta Suryakant Brahme und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The healthcare industry is evolving at a quick pace, and that necessitates the integration of effective, scalable, and secure solutions that will manage the increasing volume of sensitive patient data. This is because of the aging population, increased cases of chronic diseases, and the necessity to track patients in real-time efficiently. To improve remote diagnosis and decrease reliance on hospital-based treatment, the Internet of Things (IoT) and Wireless Sensor Networks (WSNs) have been combined to allow constant monitoring of vital indicators such as heart rate, blood pressure, temperature, and oxygen saturation.However, there are still issues with current IoT-enabled healthcare systems, such as high communication latency, scalability restrictions, impacts about data privacy and security in cloud storage, and a lack of intelligence in analyzing complicated biomedical data. To overcome these issues, this paper proposes an improved Internet of Things (IoT) healthcare monitoring system that combines wearable biomedical sensors, a Raspberry Pi CPU, and fast 5G connectivity for data transfer in almost real-time. The system captures minor changes in biological signals by preprocessing physiological data and using Renyi Entropy to extract important characteristics. These are categorized using a hybrid Temporal Convolutional Network Bidirectional Long Short-Term Memory (TCN-BiLSTM) model that can recognize trends over the short and long term. For remote monitoring, data is safely kept in the cloud and accessed through a web app. Evaluation metrics such as encryption time, decryption time, response time and computation cost.

Zitieren

APA

Brahme, N. S., & Kotwal, J. (2025). REAL-TIME IOT HEALTHCARE MONITORING USING WEARABLE SENSORS AND HYBRID DEEP LEARNING MODELS. International Journal of Data Science and Artificial Intelligence, 130. https://doi.org/10.66135/ijdsai0304p005

Vancouver

Brahme NS, Kotwal J. REAL-TIME IOT HEALTHCARE MONITORING USING WEARABLE SENSORS AND HYBRID DEEP LEARNING MODELS. International Journal of Data Science and Artificial Intelligence. 2025:130. doi:10.66135/ijdsai0304p005

BibTeX
@article{Brahme2025,
  author = {Brahme, Neeta Suryakant and Kotwal, Jameer},
  title = {REAL-TIME IOT HEALTHCARE MONITORING USING WEARABLE SENSORS AND HYBRID DEEP LEARNING MODELS},
  journal = {International Journal of Data Science and Artificial Intelligence},
  year = {2025},
  pages = {130},
  doi = {10.66135/ijdsai0304p005}
}
Kostenlos starten →