Journal of Science Engineering Technology and Management Science

Continuous observation of patient health conditions is essential for early detection of medical emergencies and timely intervention. However, conventional monitoring systems often require frequent hospital visits or rely heavily on internet-based infrastructures, which may not always be available in remote or resource-limited environments. To address these challenges, this paper presents a Real-Time Patient Health Monitoring System using an ESP32 microcontroller integrated with GSM-based notification technology. The proposed system continuously measures vital physiological parameters including heart rate, blood oxygen saturation (SpO₂), and body temperature, while also incorporating a fall detection mechanism to identify accidental movements or patient collapse. The collected data from biomedical sensors is processed in real time using the ESP32 controller. The monitored parameters are displayed on a 16×2 LCD screen, allowing patients and caregivers to easily observe health conditions locally. To enhance patient safety, the system includes a threshold-based alert mechanism. When any monitored parameter exceeds predefined safe limits or when a fall event is detected, an audible buzzer alert is triggered locally. Simultaneously, the integrated GSM communication module automatically sends SMS notifications containing patient status information to caregivers, medical staff, or emergency contacts. Unlike many IoT-based monitoring systems that depend on continuous internet connectivity, the proposed solution operates using cellular communication, ensuring reliable alert delivery even in remote areas. The system is particularly beneficial for elderly individuals, patients with chronic illnesses, and home healthcare monitoring environments. Experimental evaluation demonstrates that the system provides stable real-time monitoring, rapid alert response, and reliable emergency notification, making it a cost-effective and practical solution for modern remote healthcare applications.

Keywords :

Author : R.Chinna Rao1, T Rakesh2

Title : Configurable FIFO Buffer ASIC Flow with Gate-Level Simulation & Assertions

Volume/Issue : 2024;01(01)

Page No : 209-216

Behavioural pattern recognition in enterprise software platforms represents a critical capability for product analytics, user experience optimisation, fraud detection, and customer health monitoring. This paper presents a hybrid deep learning architecture that combines Bidirectional Encoder Representations from Transformers (BERT) for contextual feature extraction, Convolutional Neural Networks (CNN) for local pattern detection, and Bidirectional Gated Recurrent Units (BiGRU) for temporal sequence modelling. The proposed architecture addresses the fundamental challenge that enterprise user behaviour is simultaneously contextual, locally patterned, and temporally dependent. We evaluate the hybrid model on three enterprise use cases: user churn prediction, feature adoption forecasting, and anomalous behaviour detection. Experimental results on production datasets from a SaaS platform serving over 200 enterprise clients demonstrate that the hybrid architecture achieves a 7.3% improvement in F1-score over the best single-architecture baseline and a 4.1% improvement over existing ensemble methods. We also present a production deployment framework addressing latency constraints, model serving infrastructure, and continuous learning pipelines for enterprise-grade behavioural analytics.

Keywords : deep learning, BERT, CNN, BiGRU, behavioural analytics, enterprise SaaS, churn prediction, anomaly detection, hybrid architecture, user behaviour modelling

Author : Hitesh Acharya

Title : Applying Hybrid Deep Learning to Behavioural Pattern Recognition in Enterprise Platforms

Volume/Issue : 2024;01(01)

Page No : 217-223