Engineering Headway Vol. 29

Abstract: Prolonged use of electronic devices such as computers, mobile phones, laptops, and tablets can lead to adverse health effects, particularly Low Back Pain (LBP) and Cervical Root Syndrome (CRS). Traction therapy, a non-invasive treatment involving pulling force to the lumbar and cervical spine, has proven effective in relieving LBP and CRS. This study presents the design of an integrated lumbar and cervical traction system that is ergonomic and easy to operate. To determine the ergonomics of traction, a risk analysis of body injury was carried out using the Rapid Upper Limb Assessment (RULA) method. This assessment was conducted and yielded a score of 2, indicating an ergonomic design. As a preliminary step, a traction frame design was carried out, followed by a structural analysis using ANSYS Workbench 2024 R2. The simulation results showed that with a load of 150 kg of a structural steel frame, the critical stress on the bed was 147.55 MPa and 191.47 MPa in the overall traction frame. Both values were lower than the tensile yield strength of structural steel, which is 250 MPa, confirming the safety of the full traction frame.

Abstract: Point-of-care diagnostic systems face challenges because they are mainly designed for laboratory settings. Biosensor detection plays a crucial role in modern healthcare by enabling real-time monitoring of biomolecules, facilitating rapid diagnosis, and allowing for timely interventions. These sensors are vital for various applications, including glucose monitoring, infectious disease detection, and environmental analysis. The reader-disposable approach is gaining popularity in both research and commercial point-of-care devices. Open-source hardware projects based on microcontrollers are increasingly favored for biosensing applications due to their cost-effectiveness and flexibility. However, biosensors that operate in the nanoampere range still encounter issues with power supply, signal amplification, and result display. This research focuses on designing and developing a portable amperometric device for low-current detection. The system includes a multi-stage circuit featuring a voltage converter, voltage amplifier, microcontroller, display, and power supply. A shunt resistor converts input current to voltage, with an op-amp MAX4238 IC amplifying the voltage at a gain of 100. A NodeMCU microcontroller reads the output voltage and displays it on an LCD. For simulation, LTspice, Proteus 8 Pro, and Arduino software are used. Experimental testing involves using a voltage source and variable resistor to verify accuracy, comparing theoretical, simulation, and experimental results. The system demonstrated a sensitivity down to approximately 45 nA, with output linearity maintained across the tested range. The average error margin between experimental and theoretical values remained within ±2.5%. This advancement improves sensitivity in detecting low currents, enhancing point-of-care biosensing applications.

Abstract: Technological advances in health have introduced new methods to monitor physiological parameters, particularly the integration of heart rate measurement capabilities into smartphone applications based on photoplethysmography (PPG) technology. These applications offer a more accessible alternative compared to conventional devices such as oximeters. This study aims to compare the accuracy of conventional oximeters and smartphone applications in measuring beats per minute (BPM). This study involved the simultaneous collection of heart rate data from 30 subjects using conventional oximeters represented by the Vital Signs Monitor (VSM) VT200A, and several smartphone applications. The data were then analyzed using Pearson's correlation coefficient to assess the consistency, reliability, and accuracy between smartphone applications and oximeters in measuring BPM under resting and active conditions. The results showed that of the three smartphone applications tested, the second application (application B) had the closest accuracy to the results from the VSM. Under resting conditions, the difference in measurements between the smartphone application and the VSM was around 1.47 - 3.13 BPM. However, during activity conditions, the difference increased to 2.87 - 5.93 BPM. Although smartphone applications can be used for everyday heart rate monitoring, for medical purposes it is still recommended to use a device that has been recognized as the gold standard, such as an oximeter.

Abstract: This study investigates the effectiveness of the Angler smart neck pillow in improving sleep quality among young adults with insomnia. The Angler neck pillow, equipped with advanced features such as vibration therapy, soothing sound, and an integrated sleep assistant application, offers a comprehensive solution to address sleep issues. The research utilized pre-test and post-test measurements with the Insomnia Severity Index (ISI) and Pittsburgh Sleep Quality Index (PSQI) to evaluate changes in sleep quality. The results showed a significant improvement in sleep quality, as indicated by a decrease in both ISI and PSQI scores from pre-test to post-test. The Wilcoxon rank test further confirmed these findings, with a p-value of less than 0.05, supporting the effectiveness of the intervention. The Angler pillow’s vibration feature provides a customizable massage to the neck area, promoting muscle relaxation, while the sound feature allows users to listen to soothing music, creating a calm atmosphere conducive to sleep. Additionally, the integrated sleep assistant application enables users to personalize their experience by adjusting vibration intensity, music selection, and volume. Manufactured with memory foam, the pillow ensures optimal comfort and support, adapting to the user’s neck and head for enhanced sleep quality. These findings highlight Angler as an innovative solution that combines comfort and technology to improve sleep patterns and provide relief for insomnia sufferers

Abstract: This study develops a multi-agent medical diagnosis system using Adaptive Particle Swarm Optimization (APSO) and Firefly Algorithm (FA) for healthcare applications. The primary objective of this research is to enhance the precision and efficacy of medical diagnosis by leveraging the collective computational capacity of multi-agent systems. The system has been developed to address the inherent complexity of large and diverse medical datasets, thereby facilitating more accurate and rapid diagnosis recommendations. The primary case study in this research focuses on the diagnosis of diabetes. Adaptive Particle Swarm Optimization (APSO) is a meta-heuristic algorithm that has been shown to improve the performance of agents in a system, facilitating dynamic adaptation to changing data and environmental conditions. Concurrently, the Firefly Algorithm (FA) is employed to enhance the capacity to identify optimal solutions, emulating the natural behavior of fireflies. It is hypothesized that the integration of these two algorithms will overcome the shortcomings of each method when used separately. The findings indicated that the implementation of a multi-agent system utilizing APSO and FA resulted in a significant enhancement in performance when compared to conventional methodologies. The accuracy of diagnoses increased by up to 15%. The system's efficacy was assessed through the implementation of standard medical datasets, yielding promising results. These findings suggest that the system possesses considerable potential for implementation in authentic medical practice settings. This research paves the way for further development in the integration of artificial intelligence technologies in the healthcare field, particularly in medical decision support systems. Consequently, it is anticipated to effectuate a favorable transformation in the quality of healthcare on a global scale.

Abstract: Skin plays a vital role as the body's first line of defense, making its health crucial. Diagnosing skin diseases can be challenging due to symptoms such as redness, nodules, lesions, and texture changes. This study leverages artificial intelligence, particularly deep learning, to address this challenge by developing a mobile application for skin disease detection. Two Convolutional Neural Network (CNN) architectures, MobileNet and Xception, were implemented using transfer learning techniques to identify skin diseases. The models were trained on a dataset consisting of 7,000 images covering nine types of skin diseases, validated by dermatologists. The evaluation metrics included accuracy, precision, recall, F1-score, confusion matrix, and AUC-ROC curves. Results indicate that transfer learning improved model accuracy, with MobileNet achieving 98.65% accuracy and Xception reaching 98.25%. MobileNet outperformed in computational efficiency with an AUC of 0.96 compared to Xception's 0.95. The system was integrated into an Android platform, allowing users to upload skin images for real-time diagnosis. .

Abstract: Emotions are complex responses influenced by physiological systems and environmental conditions. Societal stereotypes often depict that women are more emotional than men, although some researchers are still trying to show a clear biological basis for this assumption. Therefore, it is important to explore gender differences in emotional responses from a neurological perspective. This study aims to investigate gender differences in emotional responses using EEG (Electroencephalography) recordings, focusing on Power Spectral Density (PSD) analysis to compare the level of brain activity in men and women during the emotional states of "happy" and "sad", looking at specific frequency ranges. We recorded EEG signals from 16 participants (8 men and 8 women). We calculated PSD feature values for the Alpha, Beta, and Gamma frequency ranges, specifically in the F8 and FP2 channels related to emotional processing. The results showed that women had higher PSD values in the "happy" condition, especially in the F8 and FP2 channels, indicating greater brain activity compared to men. However, in the "sad" condition, women had lower PSD values than men. These findings suggest that women may experience or express happiness with more intense brain activity than men. Implications of this research include the development of more effective cognitive and emotional therapies with a gender-specific approach, as well as a deeper understanding of gender-specific neural mechanisms in emotional responses.

Abstract: Smart Healthcare Revolution is a service optimization innovation with a futuristic hospital concept driven by advanced and innovative technology to improve all aspects of health facilities, from diagnosis to patient management. Artificial Intelligence (AI), Machine Learning, the Internet of Things (IoT), and Big Data Analysis technologies are the main pillars of the system that will be developed according to the government's three concepts in realizing intelligent hospitals. This innovation creates a practical and rapid healthcare ecosystem that offers significant benefits in diagnostic accuracy, operational efficiency and improved patient experience. This innovation is expected to improve the overall quality of healthcare and create better collaboration among healthcare providers, including hospitals, physicians and other related parties. The Smart Healthcare Revolution innovation idea in Indonesia has the potential for significant impact in the areas of health, economy and human resources. In healthcare, hospital technology can improve service quality, speed up diagnosis and provide more effective treatment. Enhanced operational efficiency and disease prevention through technology can help reduce healthcare expenditures and generate positive economic outcomes. With this innovation, the country is projected to save approximately IDR 150 trillion annually in overseas medical expenses. Furthermore, it is expected to cut the cost of importing pharmaceutical raw materials by up to 50%. In addition, it has the potential to stimulate the growth of Indonesia’s healthcare technology industry, generate employment opportunities, and increase investment in research and development.