Real-time System Research Articles

Sleep Posture Detection via Embedded Machine Learning on a Reduced Set of Pressure Sensors.

Sleep posture is a key factor in assessing sleep quality, especially for individuals with Obstructive Sleep Apnea (OSA), where the sleeping position directly affects breathing patterns: the side position alleviates symptoms, while the supine position exacerbates them. Accurate detection of sleep posture is essential in assessing and improving sleep quality. Automatic sleep posture detection systems, both wearable and non-wearable, have been developed to assess sleep quality. However, wearable solutions can be intrusive and affect sleep, while non-wearable systems, such as camera-based approaches and pressure sensor arrays, often face challenges related to privacy, cost, and computational complexity. The system in this paper proposes a microcontroller-based approach exploiting the execution of an embedded machine learning (ML) model for posture classification. By locally processing data from a minimal set of pressure sensors, the system avoids the need to transmit raw data to remote units, making it lightweight and suitable for real-time applications. Our results demonstrate that this approach maintains high classification accuracy (i.e., 0.90 and 0.96 for the configurations with 6 and 15 sensors, respectively) while reducing both hardware and computational requirements.

Implementation of a Low-Cost, Real-Time Assessment System for Primary School Classrooms

The integration of technology in educational surroundings has evolved from a supplemental enhancement to an essential element of modern education. In response to this shift, there is a growing need for cost-effective tools that can increase student engagement and streamline the assessment process for primary students. This study presents the design and implementation of a low-cost, real-time assessment system tailored specifically for primary school classrooms. Utilizing Arduino-based receivers and student-operated remote controllers, the system provides an affordable and scalable alternative to traditional student response systems. Field tests were conducted with 26 students aged 9 to 10 in a public primary school, where the system's effectiveness was evaluated through teacher observations and student feedback. Results indicate that the system significantly increased student participation, focus, and enjoyment during assessments compared to traditional paper-based methods. Despite some challenges, the system demonstrates great potential as a practical tool for resource-constrained educational environments, with future development focusing on addressing scalability and technical limitations.

Compact single-shot multispectral polarization imager through joint spectral-polarization encoding.

The technique of spectral polarization imaging (SPI) is a potent detection tool in various fields due to its ability to capture multi-dimensional information. However, existing SPI systems usually face challenges associated with architectural complexity and computational requirements, rendering them unsuitable for handheld, on-board, and real-time applications. Consequently, a compact single-shot multispectral polarization imager (CSMPI) is proposed, which employs a combined spectral-polarization encoding strategy to address the aforementioned issues. It incorporates a coded aperture for encoding multiple spectral channels together with linear polarization into a single measurement, enabling the simultaneous detection of up to nine light components with just one exposure. The resulting prototype consists solely of a color polarization detector and an imaging lens inserted with the small and easily fabricable coded aperture, which features compact dimensions of Φ5.5 cm × 21.5 cm and a light weight of approximately 670 g. This is particularly advantageous for application areas that require system miniaturization and rapid multi-dimensional detection.

Real-Time Systems and HIL Experiments for Power Electronic and Electric Energy Systems—Theory and Applications

Real-Time Systems and HIL Experiments for Power Electronic and Electric Energy Systems—Theory and Applications

Enhancing the electrical performance of chitosan-based triboelectric nanogenerator using graphene nanoplatelets for real-time sports application

Enhancing the electrical performance of chitosan-based triboelectric nanogenerator using graphene nanoplatelets for real-time sports application

Development and Optimization of a Real-Time Monitoring System of Small-Scale Multi-Purpose Juice Extractor.

According to the concept of smart postharvest management, an information and communication technology sensor-based monitoring system is required in the juicing process to reduce losses and improve process efficiency. Such technologies are considered economically burdensome and technically challenging for small-scale enterprises to adopt. From this perspective, this study aimed to develop a smart monitoring system for the juicing processes in small-scale enterprises and to identify the optimal operating conditions based on the monitoring data. The system developed is equipped with two weight sensors attached to the twin-screw juice extractor, allowing for the automatic measurement of the weight of the raw material and the resulting juice product. The measured data are automatically transmitted and stored on a computer. Additionally, the system was designed to remotely control the speeds of the juicing and feeding screws, which are the primary controlling factors of the twin-screw juicer. Juice yield and processing time were optimized using carrots and pears. The optimal juicing and feeding speeds for pear yield were found to be 167.4 rpm and 1557 rpm, respectively; carrots achieved an optimal yield at a juicing speed of 502.2 rpm and feeding speed of 1211 rpm. In contrast, the processing time was minimized at juicing-feeding speeds of 6-6 and 7-5 for pears and carrots, respectively. Consequently, it was challenging to determine the optimal conditions for simultaneously optimizing the yield and processing time. This also suggests that the juicing process is affected by the properties of the fruits and vegetables being processed. By developing a system capable of accumulating the data necessary for the digitization of postharvest management and food processing, this research offers a valuable platform for the smart monitoring and optimization of the juicing process.

Architectural Challenges in Building Real-Time Data Processing Systems for Search and Recommendations

Architectural Challenges in Building Real-Time Data Processing Systems for Search and Recommendations

Materials Design and Structural Health Monitoring of Horizontal Axis Offshore Wind Turbines: A State-of-the-Art Review.

In recent decades, Offshore Wind Turbines (OWTs) have become crucial to the clean energy transition, yet they face significant safety challenges due to harsh marine conditions. Key issues include blade damage, material corrosion, and structural degradation, necessitating advanced materials and real-time monitoring systems for enhanced reliability. Carbon fiber has emerged as a preferred material for turbine blades due to its strength-to-weight ratio, although its high cost remains a barrier. Structural Health Monitoring Systems (SHMS) play a vital role in detecting potential faults through real-time data on structural responses and environmental conditions. Effective monitoring approaches include vibration analysis and acoustic emission detection, which facilitate early identification of anomalies. Additionally, robust data transmission technologies are essential for SHMS effectiveness. This paper reviews material design strategies, data acquisition methods, and safety assessment techniques for OWTs, addressing current challenges and future directions in the field.

IoT-Based Real-Time Water Quality Monitoring and Sensor Calibration for Enhanced Accuracy and Reliability

The increasing water pollution levels and the growing demand for clean water necessitate advanced monitoring solutions. This study aims to develop an Internet of Things (IoT)-based real-time water quality monitoring system that addresses the limitations of traditional methods, which are often time-consuming and lack continuous monitoring capabilities. The system integrates pH, temperature, and turbidity sensors with an Arduino microcontroller and NodeMCU for Wi-Fi connectivity, transmitting data to a cloud platform for real-time access and analysis. The methodology involved interfacing these sensors with the microcontroller, displaying LCD data, and providing LED alerts. The findings indicate that the prototype’s readings closely align with laboratory measurements, with minor deviations in pH and temperature values and slightly more significant differences in turbidity readings. This demonstrates the prototype’s reliability and accuracy in real-time environmental monitoring. The conclusion emphasises the system’s potential to enhance water resource management through continuous and accurate tracking, enabling timely interventions. Future recommendations include improving sensor calibration, expanding the range of monitored parameters, and integrating advanced data analytics for predictive capabilities. The system’s real-time data logging capabilities significantly enhance water management by providing timely alerts and enabling proactive responses to water quality issues. The impact of this system is substantial, offering a scalable and cost-effective solution for continuous monitoring, thus contributing to improved water resource management and public health protection.

Identification and Mitigation of Risk Factors in the Implementation of the Probolinggo-Banyuwangi Toll Road Project Package 2

This study focuses on identifying and mitigating risks associated with constructing the Probolinggo-Banyuwangi Toll Road Project Package 2, a vital segment of Indonesia's Trans-Java Toll Network. The background highlights the project's significance in enhancing regional connectivity and supporting economic growth alongside the challenges it faces from technical, managerial, financial, social, and environmental factors. This research aims to identify critical risks and develop effective mitigation strategies. The methodology involves data collection through interviews, surveys, and document analysis, prioritizing risks based on their probability and impact. Key findings reveal that delayed delivery, rising material prices, and lack of skilled labor are the most significant risks, demanding targeted mitigation strategies. The conclusion emphasizes the importance of implementing real-time risk monitoring systems, improving logistics coordination, and fostering stakeholder collaboration, particularly with government agencies. By prioritizing critical risks and developing comprehensive mitigation strategies, this research contributes valuable insights for managing complex infrastructure projects, ensuring project sustainability and success.

Unlocking the application of AI for portfolio maximization investment decision

Purpose of research The aim of the study is to examine the transformative role of artificial intelligence (AI) in maximizing portfolio investment decision-making process. AI application tools specifically focus on data processing & analysis, portfolio optimization, algorithmic trading & automated execution, chatbots & robotic advisory services, and predictive analytics. The purpose of study is to provide how these technologies can maximize the investment strategies by improving the precision of forecasting, return optimization and risk management. Moreover, conceptual framework that shows the dynamic interaction between AI application tools, investors, and financial markets. Design/Methodology The conceptual approach evaluates the integration of AI application tools into investment decisions. The analysis of current applications of AI in finance develops detailed conceptual model that maps the flow of information between investors, AI application tools, in financial markets. The study uses secondary data from existing literature, research papers, and case studies to validate the efficiency of AI-driven investment strategies. Results/Findings The results show that AI significantly improves investment decision-making processes accuracy and efficiency. The conceptual framework developed in this study establishes how AI-driven application such as portfolio optimization and predictive analytics directly contribute to maximizing returns on investments while minimizing risks. Furthermore, the role of chatbots and robotic advisory services in providing tailored investment advice, which eventually results in more strategic investment decisions. Practical Implications Artificial intelligence (AI) can help investors, financial institution that make specific investment plans, and financial advisory services. The findings of this research indicate that AI tools significantly improve investment portfolio performance by providing real-time database management system. The conceptual framework aids in understanding the association between AI application tools and financial markets. This study concludes that combining AI application tools into investment strategies signifies a key innovation for achieving competitive edge in a dynamic financial market.

Transmission line trip faults under extreme snow and ice conditions: a case study

Extreme weather events, particularly snow and ice storms, present significant threats to the stability and reliability of high-voltage transmission lines, leading to substantial disruptions in power supply. This study delves into the causes and consequences of transmission line trip faults that occur under severe winter conditions, with a focused case study in Inner Mongolia—an area frequently impacted by snow and ice hazards. By systematically analyzing field data collected during critical periods of ice accumulation, this research identifies and examines key factors contributing to faults, such as conductor galloping, insulator degradation, and structural fatigue. These issues are often exacerbated by prolonged exposure to low temperatures and high wind speeds, which further compromise the integrity of transmission infrastructure. In addition to field observations, comprehensive testing of the affected insulators and components reveals mechanical and electrical vulnerabilities that play a significant role in the occurrence of trip faults. To combat these challenges, the paper proposes a series of mitigation and prevention strategies. These include enhancing design specifications to ensure resilience against increased ice and wind loads, deploying real-time monitoring systems capable of detecting early indicators of conductor galloping and ice accumulation, and employing advanced de-icing technologies to reduce the risk of ice-related failures. Moreover, the integration of unmanned aerial vehicles (UAVs) and artificial intelligence (AI)-based fault detection tools presents promising opportunities for improving remote monitoring capabilities and enabling proactive maintenance interventions. By leveraging these innovative technologies, the resilience of transmission lines in harsh climates can be significantly enhanced. The findings of this study not only provide a comprehensive framework for minimizing the impact of extreme weather on transmission infrastructure but also contribute valuable insights toward fostering a more reliable and resilient power grid capable of withstanding the challenges posed by an increasingly volatile climate.

A real-time approach for surgical activity recognition and prediction based on transformer models in robot-assisted surgery.

This paper presents a deep learning approach to recognize and predict surgical activity in robot-assisted minimally invasive surgery (RAMIS). Our primary objective is to deploy the developed model for implementing a real-time surgical risk monitoring system within the realm of RAMIS. We propose a modified Transformer model with the architecture comprising no positional encoding, 5 fully connected layers, 1 encoder, and 3 decoders. This model is specifically designed to address 3 primary tasks in surgical robotics: gesture recognition, prediction, and end-effector trajectory prediction. Notably, it operates solely on kinematic data obtained from the joints of robotic arm. The model's performance was evaluated on JHU-ISI Gesture and Skill Assessment Working Set dataset, achieving highest accuracy of 94.4% for gesture recognition, 84.82% for gesture prediction, and significantly low distance error of 1.34mm with a prediction of 1s in advance. Notably, the computational time per iteration was minimal recorded at only 4.2ms. The results demonstrated the excellence of our proposed model compared to previous studies highlighting its potential for integration in real-time systems. We firmly believe that our model could significantly elevate realms of surgical activity recognition and prediction within RAS and make a substantial and meaningful contribution to the healthcare sector.

Real-time human–computer interface based on eye gaze estimation from low-quality webcam images: integration of convolutional neural networks, calibration, and transfer learning

Abstract Eye gaze estimation represents a well-established research domain within computer vision. It has a wide range of practical applications in numerous fields, including human–computer interaction (HCI) for cursor control, health care, and virtual reality, enhancing its suitability for adoption throughout the scientific community. Different methods have been used for eye gaze estimation, such as model based, feature based, and appearance based. The appearance-based method is mainly used because it directly estimates an individual’s gaze direction from images/videos rather than depending on specific features or geometric models. This article developed an appearance-based, real-time generic eye gaze system for HCI to control the cursor through the eye using the convolutional neural network (CNN), calibration, and transfer learning. The study employed low-quality eye images captured from a conventional desktop webcam, enabling the proposed methodology to be implemented on any computer system equipped with a similar web camera without the need for supplementary hardware. Initially, the labeled dataset of both eyes is collected using the webcam. Then, a CNN model is trained by inputting left and right eye images to predict the gaze coordinate as output. We applied the calibration and transfer learning approach to the trained models to make a generic model for new users. In real-time use, the first step is calibration, where the user’s eye images are captured for various screen coordinates, and transfer learning is employed to fine-tune the pre-trained model according to the user’s eyes. Then, the fine-tuned model is used for eye gaze prediction to control the cursor. The system’s performance is evaluated using a test group of multiple users, and it demonstrated an average visual angle accuracy of 2.08 degrees before calibration, which notably improved to 1.81 degrees after the calibration process.

Enhancing the Travel Experience for People with Visual Impairments through Multimodal Interaction: NaviGPT, A Real-Time AI-Driven Mobile Navigation System.

Assistive technologies for people with visual impairments (PVI) have made significant advancements, particularly with the integration of artificial intelligence (AI) and real-time sensor technologies. However, current solutions often require PVI to switch between multiple apps and tools for tasks like image recognition, navigation, and obstacle detection, which can hinder a seamless and efficient user experience. In this paper, we present NaviGPT, a high-fidelity prototype that integrates LiDAR-based obstacle detection, vibration feedback, and large language model (LLM) responses to provide a comprehensive and real-time navigation aid for PVI. Unlike existing applications such as Be My AI and Seeing AI, NaviGPT combines image recognition and contextual navigation guidance into a single system, offering continuous feedback on the user's surroundings without the need for app-switching. Meanwhile, NaviGPT compensates for the response delays of LLM by using location and sensor data, aiming to provide practical and efficient navigation support for PVI in dynamic environments.

Novel Visualization of Building Earthquake Response Recorded by a Dense Network of Sensors.

The strong motion records collected in full-scale structures provide the ultimate evidence of how real structures, in situ, respond to earthquakes. This paper presents a novel method for visualization, in three dimensions (3D), of the collective motion recorded by a dense array of sensors in a building. The method is based on one- and two-dimensional biharmonic spline interpolation of the motion recorded by multiple sensors on the same or multiple floors. It is demonstrated on novel data that have been recorded recently in a 50-story skyscraper, uniquely instrumented with multiple triaxial accelerometers per floor, approximately at every five floors above ground and at two basement levels, and with rotational seismometers and two borehole arrays measuring the motion of the soil very near the building foundation. The method is computationally efficient and suitable for real-time application and rapid assessment of structural health. The animations provide invaluable insight into the 3D structural response of the building as a whole, including wave propagation through the structure and the interplay between translations and rotations, which will be useful for testing existing and developing new methods for structural health monitoring of buildings and for the further development of building design codes. Animations of selected earthquakes can be found on YouTube at @TPYC-seismic.

Efficient State Synchronization in Distributed Electrical Grid Systems Using Conflict-Free Replicated Data Types

Modern electrical grids are evolving towards distributed architectures, necessitating efficient and reliable state synchronization mechanisms to maintain structural and functional consistency. This paper investigates the application of conflict-free replicated data types (CRDTs) for representing and synchronizing the states of distributed electrical grid systems (DEGSs). We present a general structure for DEGSs based on CRDTs, focusing on the Convergent Replicated Data Type (CvRDT) model with delta state propagation to optimize the communication overhead. The Observed Remove Set (ORSet) and Last-Writer-Wins Register (LWW-Register) are utilized to handle concurrent updates and ensure that only the most recent state changes are retained. An actor-based framework, “Vigilant Hawk”, leveraging the Akka toolkit, was developed to simulate the asynchronous and concurrent nature of DEGSs. Each electrical grid node is modelled as an independent actor with isolated state management, facilitating scalability and fault tolerance. Through a series of experiments involving 100 nodes under varying latency degradation coefficients (LDK), we examined the impact of network conditions on the state synchronization efficiency. The simulation results demonstrate that CRDTs effectively maintain consistency and deterministic behavior in DEGSs, even with increased network latency and node disturbances. An effective LDK range was identified (LDK effective = 2 or 4), where the network remains stable without significant delays in state propagation. The linear relationship between the full state distribution time (FSDT) and LDK indicates that the system can scale horizontally without introducing complex communication overhead. The findings affirm that using CRDTs for state synchronization enhances the resilience and operational efficiency of distributed electrical grids. The deterministic and conflict-free properties of CRDTs eliminate the need for complex concurrency control mechanisms, making them suitable for real-time monitoring and control applications. Future work will focus on addressing identified limitations, such as optimizing message routing based on the network topology and incorporating security measures to protect state information in critical infrastructure systems.

Real-Time Driver Drowsiness Detection System Using Machine Learning

Driver fatigue is a leading cause of road accidents globally, with significant fatalities and injuries reported annually. This paper presents a real-time Driver Drowsiness Detection System leveraging computer vision and machine learning techniques. Using Convolutional Neural Networks (CNNs), the system monitors key behavioural indicators, such as eye closure and yawning frequency, from live video feeds. Preprocessing techniques like grayscale conversion and normalization ensure robustness under varied conditions. Alerts are triggered immediately upon detecting drowsiness, enhancing road safety. The system’s non-intrusive design ensures scalability and affordability, making it suitable for integration into Advanced Driver Assistance Systems (ADAS). This paper also discusses challenges and potential enhancements, such as IoT integration and edge computing. Key Words: Driver Drowsiness Detection, Machine Learning, CNNs, Real-Time Monitoring, Road Safety.

Design and experimental study of tillage depth control system for electric rotary tiller based on LADRC

This paper proposes an adaptive real-time tillage depth control system for electric rotary tillers, based on Linear Active Disturbance Rejection Control (LADRC), to improve tillage depth accuracy in tea garden intercropping with soybeans. The tillage depth control system comprises a body posture sensor, a control unit, and a hybrid stepper motor, integrating sensor data to drive the motor and achieve precise depth control. Real-time displacement sensor signals are compared with target values, enabling closed-loop control of the rotary tiller. Field experiments conducted at 0.5 km/h and 0.8 km/h, with preset tillage depths of 80 mm and 100 mm, demonstrated the system’s effectiveness. The average standard deviation of tillage depth for the LADRC system was 3.2 mm, compared to 10.5 mm for fuzzy proportional-integral-derivative (PID) control. The LADRC control reduced the rate of change in tillage depth by 68.9% compared to fuzzy PID. This system effectively mitigates potential deviations during operation, ensuring stable and reliable tillage depth control.

Ion Sensing via Modulation of Charge Transfer in Donor-pi-Acceptor Molecules: Structure, Mechanism & Photophysical Aspects.

This review article highlights the importance of novel charge transfer (CT) sensing approach for the detection of ions which are crucial from environmental and biological point of view. The importance, principles of charge transfer, ion sensing, its different types, and its basic process will all be covered here. The strategy has been reported with enormous sensitivity and fast signaling response owing to the fact that strong electronic connection communication exists between donor (D) and acceptor (A) part. Important discoveries made since 2010 will be examined. Herein, we will showcase the binding constants, conditions employed for sensing, and limit of detection of crucial ions via CT based sensors that researchers have bough forth for real-time applications. Additionally, the focus will be on the mechanistic aspects and signaling response as a result of the interaction between ion and sensor molecule.