Selected work

Representative Papers

Advancing Remote and Continuous Cardiovascular Patient Monitoring through a Novel and Resource-efficient IoT-Driven Framework

May 06, 2025

To address the challenge of home-based cardiovascular disease monitoring for aging populations in low-infrastructure regions such as Pakistan, this study proposes a lightweight embedded–cloud–edge collaborative IoT system. The hardware integrates low-power sensors—including MAX30102 and AD8232—to concurrently acquire heart rate, blood pressure, blood oxygen saturation, body temperature, and ECG signals. A dual-mode LoRa/WiFi communication protocol enables energy-efficient data transmission to an AWS cloud platform, supporting scalable remote health monitoring. The system introduces a novel threshold-driven, millisecond-level anomaly detection algorithm with automated clinician alerts, achieving end-to-end alert latency under 800 ms. Clinical validation (n=20) demonstrates measurement errors <2% relative to gold-standard clinical devices across all key parameters; the system sustained uninterrupted operation for over 30 days. This architecture significantly enhances accessibility and reliability of chronic disease management in resource-constrained settings.

0 citationsRead paper

A Multi-Scale Feature Extraction and Fusion Deep Learning Method for Classification of Wheat Diseases

Jan 01, 2025Journal of Computer Science

Accurate discrimination of morphologically similar wheat diseases—such as loose smut, leaf rust, and crown rot—remains challenging in field conditions. To address this, we propose a deep learning ensemble framework integrating multi-scale feature extraction with semantic segmentation. Our approach introduces a novel collaborative architecture combining Xception, InceptionV3, and ResNet50, augmented by pixel-level segmentation to enhance lesion localization. Furthermore, we design a dual-path ensemble strategy comprising both majority voting and stacking mechanisms. Evaluated on the publicly available 2020 wheat disease dataset, the framework achieves an overall classification accuracy of 99.75%, with the Xception submodel attaining state-of-the-art performance—surpassing existing methods significantly. This work delivers a highly robust, interpretable, and fine-grained diagnostic solution for in-field wheat disease identification.

0 citationsRead paper

Recent publications

Latest Papers

Advancing Remote and Continuous Cardiovascular Patient Monitoring through a Novel and Resource-efficient IoT-Driven Framework

May 06, 2025

To address the challenge of home-based cardiovascular disease monitoring for aging populations in low-infrastructure regions such as Pakistan, this study proposes a lightweight embedded–cloud–edge collaborative IoT system. The hardware integrates low-power sensors—including MAX30102 and AD8232—to concurrently acquire heart rate, blood pressure, blood oxygen saturation, body temperature, and ECG signals. A dual-mode LoRa/WiFi communication protocol enables energy-efficient data transmission to an AWS cloud platform, supporting scalable remote health monitoring. The system introduces a novel threshold-driven, millisecond-level anomaly detection algorithm with automated clinician alerts, achieving end-to-end alert latency under 800 ms. Clinical validation (n=20) demonstrates measurement errors <2% relative to gold-standard clinical devices across all key parameters; the system sustained uninterrupted operation for over 30 days. This architecture significantly enhances accessibility and reliability of chronic disease management in resource-constrained settings.

0 citationsRead paper

A Multi-Scale Feature Extraction and Fusion Deep Learning Method for Classification of Wheat Diseases

Jan 01, 2025Journal of Computer Science

Accurate discrimination of morphologically similar wheat diseases—such as loose smut, leaf rust, and crown rot—remains challenging in field conditions. To address this, we propose a deep learning ensemble framework integrating multi-scale feature extraction with semantic segmentation. Our approach introduces a novel collaborative architecture combining Xception, InceptionV3, and ResNet50, augmented by pixel-level segmentation to enhance lesion localization. Furthermore, we design a dual-path ensemble strategy comprising both majority voting and stacking mechanisms. Evaluated on the publicly available 2020 wheat disease dataset, the framework achieves an overall classification accuracy of 99.75%, with the Xception submodel attaining state-of-the-art performance—surpassing existing methods significantly. This work delivers a highly robust, interpretable, and fine-grained diagnostic solution for in-field wheat disease identification.

0 citationsRead paper