Journal of Electronic & Information Systems

Robotic Triage Systems: Bridging the Gap in Initial Call and Emergency Assessment

Kshitij Shinghal, Amit Saxena, Rajul Misra, Avnesh Verma — Mon, 20 Apr 2026 00:00:00 +0800

Nowadays healthcare and clinical facilities have become an essential part of modern life. The triage system in hospitals and clinics plays a crucial role in the initial assessment of patients and emergency care. However, conventional triage processes that rely on human judgment often suffer from variability, limited resources, and the possibility of human error. In many situations, the lack of trained personnel further worsens the problem, leading to delays and the potential misclassification of high-acuity patients. To address these challenges, this work proposes an autonomous robotic sensor-based triage system (RTS) designed to automate the initial patient assessment process. By using sensors for data collection, the system standardizes information gathering and reduces errors associated with manual triage. The RTS is designed with a robust and adaptable architecture that can be easily integrated with existing clinical systems and electronic health record (EHR) platforms without disrupting current hospital workflows. The system utilizes non-contact sensors to capture physiological parameters, ensuring patient comfort and reducing the risk of contamination, particularly during infectious disease situations. Embedded artificial intelligence analyzes the collected data and generates a structured symptom report, which is processed by a Clinical Acuity Measurement (CAM) unit to assign a Clinical Acuity Score (CAS) within four minutes. Experimental results demonstrate 92.5% accuracy with expert clinical consensus and 98.1% sensitivity in identifying high-acuity patients, while reducing the time required for initial assessment by nearly 70%.

Development of an IoT-Based Real-Time Monitoring System for Light Intensity, Temperature, and Humidity in Dragon Fruit Farms

Tue, 13 Jan 2026 00:00:00 +0800

The rapid advancement of smart agriculture under the Industry 4.0 paradigm has accelerated the integration of digital and IoT technologies into modern farming systems, aiming to enhance productivity, optimize resource utilization, and promote environmental sustainability. Meanwhile, dragon fruit is a major export fruit of Vietnam, grown mostly in Binh Thuan, Long An, and Tien Giang provinces. Following the above trend, this study presents the design and implementation of an Internet of Things (IoT)-based climate monitoring system that allows real-time observation and recording of light intensity, temperature, and humidity parameters at dragon fruit farms. The system integrates an ESP32 microcontroller, a DFRobot SEN0390 light sensor, and a digital temperature and humidity sensor SHT30. Data is transmitted via Wi-Fi to a cloud platform for real-time display, IoT MQTT (Message Queuing Telemetry Transport) Panel application, web interface and automatically stored in Google Sheets for long-term analysis. A key improvement of this study lies in the integration of wide-range light sensors compared to previous greenhouse IoT system studies. Experimental validation demonstrates stable system performance, with average data latency under two seconds and high measurement accuracy, confirming the reliability and scalability. The system provides an agricultural environmental monitoring solution for farmers, setting a basis for big data analytics and future automation in Vietnam.

Transformer Fault Diagnosis: A Shallow Learning Approach for DGA-Based Incipient Fault Detection

Deepika Bhalla, Avnesh Verma — Tue, 07 Jan 2025 00:00:00 +0800

Power transformers are exposed to electrical, thermal, and mechanical stresses during operation, leading to the degradation of insulation and the generation of dissolved gases. Utilities use IEEE and IEC standards use dissolved gas analysis (DGA) to detect incipient faults in oil-filled in-service transformers. Traditional gas ratio-based DGA methods, at times inconclusive diagnoses, limiting their effectiveness in scheduling preventive maintenance. This study presents the application of a shallow learning Backpropagation Neural Network (BP-NN) for assessing the condition of normal ageing and classification of incipient faults in oil-immersed power transformers. The model is trained using the concentrations (ppm) of five key gases—H₂, CH₄, C₂H₂, C₂H₄, and C₂H₆—as input features. The classified condition of a transformer is normal ageing and five fault type, namely partial discharge, low-energy and high-energy discharges, and thermal faults across two varying temperature ranges. The data set used for the classification of incipient faults within transformers is that where the fault type is confirmed by physical inspection. The 256 samples used in this work are from published sources, including the IEC TC10 database. The results achieved by the BP-NN demonstrate its capability to accurately classify normal ageing and diagnose five types of faults. For evaluating the performance of the trained NN, the IEEE/IEC method of classification, the benchmark used is the actual fault type. The shallow network of pattern recognition successfully identified the presence of normal ageing and the five fault types. The performance of the test set is 94.73%. The results highlight the potential of BP-NNs for enhanced transformer condition monitoring and early fault detection. As more high-quality labelled data become available, the diagnostic accuracy and robustness of the model are expected to improve further.

Seasonal Analysis of Real-Time Derived and ITU-R Modeled Surface Radio Refractivity in a Tropical Region Using a Low-Cost Developed Device

Fri, 24 Apr 2026 00:00:00 +0800

This study investigates seasonal and diurnal variations of surface radio refractivity in a tropical region by comparing real-time derived values from a low-cost automated Global System for Mobile Communication Signal Strength and Radio Climatological (GSM-RC) monitoring device with those modeled by ITU-R P.453-13. The GSM-RC device, installed at 3-m height, provided real-time, in-situ measurements of temperature, pressure, and humidity. Refractivity was derived in real-time from this high-resolution data and compared against model outputs across four months representing distinct climatic phases: January (dry season), April (commencement of rainy season), July (intense rainy season), and October (fading season). Results show a strong correlation between datasets, with seasonal atmospheric dynamics driving clear patterns. The dry season exhibited large diurnal fluctuations due to low humidity and high solar radiation, while the intense rainy season showed minimal variability from persistently high humidity and reduced temperature gradients. Transitional months displayed moderate instability. Although the ITU-R model provided reliable smoothed approximations, real-time derived data proved superior at capturing transient fluctuations, particularly during atmospheric instability. These findings underscore the value of locally-sourced real-time data for capturing dynamic refractivity behaviour and highlight opportunities to enhance climatological propagation models. By linking observed patterns to West African monsoon phases, this work provides valuable insight for telecommunications system design, weather prediction, and regional atmospheric monitoring in tropical environments.

Intelligent GA-PID Control of STATCOM for Voltage Sag Mitigation in Transmission Lines

Tue, 21 Apr 2026 00:00:00 +0800

The paper presents an intelligent control approach for a Static Synchronous Compensator (STATCOM) using a Genetic Algorithm-optimized Proportional-Integral-Derivative (GA-PID) controller to mitigate voltage sags in power transmission systems. This shunt-connected device is part of the FACTS family and dynamically injects reactive power compensation through the Voltage Source Converter to hold stable voltage magnitudes. Conventional PID controllers have shortcomings due to non-productive manual tuning and poor transient response performance. A Genetic Algorithm optimization approach has been implemented to automatically select optimum PID parameters for the improvement of control accuracy with increased system response speed. Performance of both GA-PID and traditional PID controllers is analyzed under voltage sag situations through MATLAB/Simulink simulations. The STATCOM controlled by GA-PID shows better performance with a reduced overshoot of 4.17%, a faster rise time of 0.0000504 s, and the shortest settling time of 0.000538 s. Thus, it has been established that these parameters significantly improve transient and steady-state performances by reducing the steady-state error, which in turn enhances voltage stability and power quality. The adaptive control reduces harmonic distortion and maintains the best performance of the system even in the presence of disturbances. This has proven that the integration of Genetic Algorithm optimization and PID control provides a robust, adaptive, efficient strategy to improve the performance of STATCOM, hence improving voltage regulation, the reliability of power, and efficiency for modern high-voltage transmission systems.

Semantic Variational Bayes Based on Semantic Information G Theory for Solving Latent Variables

Chenguang Lu — Fri, 17 Apr 2026 00:00:00 +0800

The minimum variational free energy criterion comprises two criteria: the maximum semantic information criterion and the maximum information efficiency criterion, but it does not provide a method for balancing them. The Semantic Information G Theory, the author proposed in his early years, extends the rate-distortion function R(D) to the rate-fidelity function R(G), where R is the minimum mutual information for given semantic mutual information G. Semantic Variational Bayes (SVB) is based on the parameter solution of R(G), where the variational and iterative methods originated from Shannon et al.'s research on the rate-distortion function. SVB not only uses likelihood functions but also truth, membership, similarity, distortion, and copula density functions as constraint functions. It explicitly uses the maximum information efficiency (G/R) criterion and facilitates the trade-off between maximum semantic information and maximum information efficiency. The computational experiments include 1) using some mixture models as an examples to show that mixture models converges as G/R increases; 2) demonstrating the application of SVB in data compression with a group of error ranges as the constraint; 3) illustrating how the semantic information measure and SVB can be used for maximum entropy control and reinforcement learning in control tasks with given range constraints, providing numerical evidence for balancing control's purposiveness and efficiency. The limitation of SVB is that it does not account for parameter probability distributions. Further research is needed to apply SVB to deep learning.