Real-time System Applications Research Articles

Blockchain Sensor Network Based CPS Analysis in Healthcare System for Real Time Applications Using 6G IoT Model and Deep Learning Techniques

Blockchain Sensor Network Based CPS Analysis in Healthcare System for Real Time Applications Using 6G IoT Model and Deep Learning Techniques

FireXplainNet: Optimizing Convolution Block Architecture for Enhanced Wildfire Detection and Interpretability

The early detection of wildfires is a crucial challenge in environmental monitoring, pivotal for effective disaster management and ecological conservation. Traditional detection methods often fail to detect fires accurately and in a timely manner, resulting in significant adverse consequences. This paper presents FireXplainNet, a Convolutional Neural Network (CNN) base model, designed specifically to address these limitations through enhanced efficiency and precision in wildfire detection. We optimized data input via specialized preprocessing techniques, significantly improving detection accuracy on both the Wildfire Image and FLAME datasets. A distinctive feature of our approach is the integration of Local Interpretable Model-agnostic Explanations (LIME), which facilitates a deeper understanding of and trust in the model’s predictive capabilities. Additionally, we have delved into optimizing pretrained models through transfer learning, enriching our analysis and offering insights into the comparative effectiveness of FireXplainNet. The model achieved an accuracy of 87.32% on the FLAME dataset and 98.70% on the Wildfire Image dataset, with inference times of 0.221 and 0.168 milliseconds, respectively. These performance metrics are critical for the application of real-time fire detection systems, underscoring the potential of FireXplainNet in environmental monitoring and disaster management strategies.

Forward solution of shield tunneling pose based on the Newton–Raphson method

To achieve precise control of the shield tunneling pose, obtaining a real-time shield pose state during the excavation process is necessary to achieve closed-loop feedback control of the shield pose. This study proposes a forward solution method to address the high cost and low efficiency of direct measurement methods, such as using lasers and gyroscopes, for measuring shield pose. This method relies on the real-time measurement of the strokes of hydraulic thrust cylinders during shield tunneling. Based on the inverse kinematics of the shield machine, the Newton–Raphson method was used to calculate the shield tunneling pose. Accordingly, a forward solution algorithm for shield pose was developed using MATLAB, and the effectiveness of the proposed method was verified through an example analysis. The results demonstrated the high computational efficiency of the method, proving its potential application in real-time control systems for shield tunneling poses.

Real Time Chat Application using React and Firebase

Abstract: This paper presents the development of a real-time chat application leveraging modern web technologies, including React for front-end development, Tailwind CSS for styling, and Firebase for backend services. The chat application addresses the need for seamless communication among users in various contexts. We discuss the architectural design, implementation details, and performance evaluation of the application. Our findings demonstrate the effectiveness and scalability of the proposed solution, paving the way for future enhancements and applications in real-time communication systems.

Development of real-time brain-computer interface control system for robot

Electroencephalogram (EEG)-based brain-computer interfaces (BCI) have been considered a prevailing non-invasive method for collecting human biomedical signals by attaching electrodes to the scalp. However, it is difficult to detect and use these signals to control an online BCI robot in a real environment owing to environmental noise. In this study, a novel state recognition model is proposed to determine and improve EEG signal states. First, a Long Short-Term Memory Convolutional Neural Network (LSTM-CNN) was designed to extract EEG features along the time sequence. During this process, errors caused by the randomness of the mind or external environmental factors may be generated. Thus, an actor-critic based decision-making model was proposed to correct these errors. The model consists of two networks that can be used to predict the final signal state based on both the current signal state probability and past signal state probabilities. Subsequently, a hybrid BCI real-time control system application is proposed to control a BCI robot. The Unicorn Hybrid Black EEG device was used to acquire brain signals. A data transmission system was constructed using OpenViBE to transfer data. An EEG classification system was built to classify the BCI commands. In this experiment, EEG data from five subjects were collected to train and test the performance and reliability of the proposed control system. The system records the time spent by the robot and the moving distance. Experimental results were provided to demonstrate the feasibility of the real-time control system. Compared to similar BCI studies, the proposed hybrid BCI real-time control system can accurately classify seven BCI commands in a more reliable and precise manner. Overall, the offline testing accuracy was 87.20%. When we apply the proposed system to control a BCI robot in a real environment, the average online control accuracy is 93.12%, and the mean information transmission rate is 67.07 bits/min, which is better than those of some state-of-the-art control systems. This shows that the proposed hybrid BCI real-time control system demonstrated higher reliability, which can be used in practical BCI control applications.

Implementation of a High-Accuracy Neural Network-Based Pupil Detection System for Real-Time and Real-World Applications.

In this paper, the implementation of a new pupil detection system based on artificial intelligence techniques suitable for real-time and real-word applications is presented. The proposed AI-based pupil detection system uses a classifier implemented with slim-type neural networks, with its classes being defined according to the possible positions of the pupil within the eye image. In order to reduce the complexity of the neural network, a new parallel architecture is used in which two independent classifiers deliver the pupil center coordinates. The training, testing, and validation of the proposed system were performed using almost 40,000 eye images with a resolution of 320 × 240 pixels and coming from 20 different databases, with a high degree of generality. The experimental results show a detection rate of 96.29% at five pixels with a standard deviation of 3.38 pixels for all eye images from all databases and a processing speed of 100 frames/s. These results indicate both high accuracy and high processing speed, and they allow us to use the proposed solution for different real-time applications in variable and non-uniform lighting conditions, in fields such as assistive technology to communicate with neuromotor-disabled patients by using eye typing, in computer gaming, and in the automotive industry for increasing traffic safety by monitoring the driver's cognitive state.

Advancing real-time drilling trajectory prediction with an efficient nonlinear DDE model and online parameter estimation

This study introduces a streamlined approach to predict planar drilling trajectory by employing an efficient nonlinear Delay Differential Equation (DDE) model with high computational speed and predictive accuracy. The efficient model is validated and compared with other models by utilizing not just data from existing literature but also two sets of experimental data with two distinct rigs. Following the validation, the model is integrated with an online estimation technique—calibrating one parameter in real-time using historical data—empowering it to forecast drill bit paths with remarkable fidelity. The validation of the model and its estimation strategy underscores their potential for application in real-time drilling control systems, setting a new benchmark for future advancements in the field.

Improved Re-Parameterized Convolution for Wildlife Detection in Neighboring Regions of Southwest China.

To autonomously detect wildlife images captured by camera traps on a platform with limited resources and address challenges such as filtering out photos without optimal objects, as well as classifying and localizing species in photos with objects, we introduce a specialized wildlife object detector tailored for camera traps. This detector is developed using a dataset acquired by the Saola Working Group (SWG) through camera traps deployed in Vietnam and Laos. Utilizing the YOLOv6-N object detection algorithm as its foundation, the detector is enhanced by a tailored optimizer for improved model performance. We deliberately introduce asymmetric convolutional branches to enhance the feature characterization capability of the Backbone network. Additionally, we streamline the Neck and use CIoU loss to improve detection performance. For quantitative deployment, we refine the RepOptimizer to train a pure VGG-style network. Experimental results demonstrate that our proposed method empowers the model to achieve an 88.3% detection accuracy on the wildlife dataset in this paper. This accuracy is 3.1% higher than YOLOv6-N, and surpasses YOLOv7-T and YOLOv8-N by 5.5% and 2.8%, respectively. The model consistently maintains its detection performance even after quantization to the INT8 precision, achieving an inference speed of only 6.15 ms for a single image on the NVIDIA Jetson Xavier NX device. The improvements we introduce excel in tasks related to wildlife image recognition and object localization captured by camera traps, providing practical solutions to enhance wildlife monitoring and facilitate efficient data acquisition. Our current work represents a significant stride toward a fully automated animal observation system in real-time in-field applications.

Enhancing fall prediction in the elderly people using LBP features and transfer learning model

In an era where the detection and prevention of falls are crucial for the well-being of elderly and vulnerable individuals, achieving high accuracy in identifying such incidents is of utmost importance. This study introduces a modified NASNet, a novel transformer learning model designed for the classification of fall and not fall people based on local binary patterns (LBP) features. The modified NASNet model demonstrates high performance, achieving an accuracy, precision, recall, and F1 score of 99% with LBP features in differentiating fall from not fall. To assess the performance of NASNet, this research work conducted a comparative analysis with other prominent deep learning, and transfer learning models, as well as state-of-the-art machine learning frameworks. The findings indicate NASNet's enhanced performance in fall detection, highlighting its potential for application in real-time fall detection systems, contributing to a safer environment for individuals at risk. This research sets the stage for enhanced healthcare and assistance for vulnerable populations, addressing a critical concern in the healthcare sector.

Energy efficient FPGA implementation of an epileptic seizure detection system using a QDA classifier

Epilepsy is a severe neurological disorder that causes seizures. It is detected by analyzing the electrical impulses of the human brain. Monitoring the brain is commonly done using an electroencephalogram (EEG). Seizure detection from the large recorded EEG dataset is a demanding task. However, numerous machine learning classifiers and the appropriate features can detect seizures. The Hjorth and statistical parameters are used in this study to provide an effective method for field programmable gate array (FPGA) realization of epileptic seizure detectors from EEG signals. Mobility, interquartile range (IQR), median absolute deviation (MAD), energy, non-linear energy, and simple square integral (SSI) are the various features analyzed in this work. The hardware architecture of the seizure detection system is captured in Verilog hardware descriptive language and realized on the Artix-7 FPGA. This paper presents three separate seizure detection models designed by pairing three different features with the Quadratic discriminant analysis (QDA) classifier. Among these three models, the energy and non-linear energy-based seizure detection system offers better performance than existing seizure detection systems because it possesses the lowest dynamic power consumption (0.116 µW), the highest design accuracy (99.4 %), and the highest sensitivity (100 %), which makes it the best seizure detection system for real-time applications.

Design of Arduino UNO based smart irrigation system for real time applications

The fundamental principle of the paper is that the soil moisture sensor obtains the moisture content level of the soil sample. The water pump is automatically activated if the moisture content is insufficient, which causes water to flow into the soil. The water pump is immediately turned off when the moisture content is high enough. Smart home, smart city, smart transportation, and smart farming are just a few of the new intelligent ideas that internet of things (IoT) includes. The goal of this method is to increase productivity and decrease manual labour among farmers. In this paper, we present a system for monitoring and regulating water flow that employs a soil moisture sensor to keep track of soil moisture content as well as the land’s water level to keep track of and regulate the amount of water supplied to the plant. The device also includes an automated led lighting system.

Real-Time Performance Benchmarking of RISC-V Architecture: Implementation and Verification on an EtherCAT-Based Robotic Control System

RISC-V offers a modular technical approach combined with an open, royalty-free instruction set architecture (ISA). However, despite its advantages as a fundamental building block for many embedded systems, the escalating complexity and functional demands of real-time applications have made adhering to response time deadlines challenging. For real-time applications of RISC-V, real-time performance analysis is required for various ISAs. In this paper, we analyze the real-time performance of RISC-V through two real-time approaches based on processor architectures. For real-time operating system (RTOS) applications, we adopted FreeRTOS and evaluated its performance on HiFive1 Rev B (RISC-V) and STM3240G-EVAL (ARM M). For real-time Linux, we utilized Linux with the Preempt-RT patch and tested its performance on VisionFive 2 (RISC-V), MIO5272 (x86-64), and Raspberry Pi 4 B (ARM A). Through these experiments, we examined the response times on the real-time mechanisms of each operating system. Additionally, in the Preempt-RT experiments, scheduling latencies were evaluated by means of the cyclictest. These are very important parameters for implementing real-time applications comprised of multi-tasking. Finally, in order to show the real-time capabilities of RISC-V practically, we implemented motion control of a six-axis collaborative robot, which was performed on the VisionFive 2. This implementation provided a comparative result of RISC-V’s performance against the x86-64 architecture. Ultimately, the results indicated that the real-time performance of RISC-V for real-time applications was feasible. A noticeable achievement of this research is its first implementation of an EtherCAT master on RISC-V designed for real-time applications. The successful implementation of the EtherCAT master on RISC-V shows real-time capabilities for a wide range of real-time applications.

Spike sorting in the presence of stimulation artifacts: a dynamical control systems approach

Objective. Bi-directional electronic neural interfaces, capable of both electrical recording and stimulation, communicate with the nervous system to permit precise calibration of electrical inputs by capturing the evoked neural responses. However, one significant challenge is that stimulation artifacts often mask the actual neural signals. To address this issue, we introduce a novel approach that employs dynamical control systems to detect and decipher electrically evoked neural activity despite the presence of electrical artifacts. Approach. Our proposed method leverages the unique spatiotemporal patterns of neural activity and electrical artifacts to distinguish and identify individual neural spikes. We designed distinctive dynamical models for both the stimulation artifact and each neuron observed during spontaneous neural activity. We can estimate which neurons were active by analyzing the recorded voltage responses across multiple electrodes post-stimulation. This technique also allows us to exclude signals from electrodes heavily affected by stimulation artifacts, such as the stimulating electrode itself, yet still accurately differentiate between evoked spikes and electrical artifacts. Main results. We applied our method to high-density multi-electrode recordings from the primate retina in an ex vivo setup, using a grid of 512 electrodes. Through repeated electrical stimulations at varying amplitudes, we were able to construct activation curves for each neuron. The curves obtained with our method closely resembled those derived from manual spike sorting. Additionally, the stimulation thresholds we estimated strongly agreed with those determined through manual analysis, demonstrating high reliability ( R2=0.951 for human 1 and R2=0.944 for human 2). Significance. Our method can effectively separate evoked neural spikes from stimulation artifacts by exploiting the distinct spatiotemporal propagation patterns captured by a dense, large-scale multi-electrode array. This technique holds promise for future applications in real-time closed-loop stimulation systems and for managing multi-channel stimulation strategies.

Machine learning-based real-time kinetic profile reconstruction in DIII-D

Kinetic equilibrium reconstruction plays a vital role in the physical analysis of plasma stability and control in fusion tokamaks. However, the traditional approach is subjective and prone to human biases. To address this, the consistent automatic kinetic equilibrium reconstruction (CAKE) method was introduced, providing objective results. Nonetheless, its offline nature limits its application in real-time plasma control systems (PCSs). To address this limitation, we present RTCAKENN, a machine learning model that approximates 7 CAKE-level output profiles, namely pressure, inverse q, toroidal current density, electron temperature and density, carbon ion impurity temperature and rotation profiles, using real-time available inputs. The deep neural network consists of an encoder layer, where the scalars and interdependent inputs such as plasma boundary coordinates and motional Stark effect data are encoded using multi-layer perceptrons (MLPs), while profile inputs are encoded by 1D convolutional layers. The encoded data is passed through a MLP for latent feature extraction, before being decoded in the decoding layers, which consist of upsampling and convolutional layers. RTCAKENN has been implemented in the DIII-D PCS and our model achieves accuracy comparable to CAKE and surpasses existing real-time alternatives. Through clever dropout training, RTCAKENN exhibits robustness and can operate even in the absence of Thomson scattering data or charge exchange recombination data. It executes in under 8 ms in the real-time environment, enabling future application in real-time control and analysis.

Experimental investigation of CaCO3/CaO reaction pair in a fixed bed reactor for CSP application

CaCO3/CaO thermochemical energy storage (TCES) system has been widely studied on laboratory scale for its potential in concentrated solar power (CSP) plants. However, there is still need for the large-scale experiments based on which a detailed analysis can be obtained to improve this system for real-time applications. In this study, we developed a packed bed reactor capable of operating at high temperature and pressure providing the carbonation and decarbonation reactions of CaCO3/CaO reaction pair. The heat storage process is studied with the aspect of different decarbonation temperatures and different sample sizes (amount of sample in grams) placed in the reactor. Furthermore, we compared the heat storage performance of pure and composite samples. The heat release process is performed by varying the concentration of CO2 and the sample size of the loaded material. The results showed that the heat storage rate and efficiency improve by increasing the temperature of the decarbonation, implying that this reaction must be carried out above 925 °C for better performance. The heat is released smoothly and at a good rate when the concentration of CO2 is high in the reactor. Also, carbonation reaction (heat release process) depicts that CaCO3/CaO TCES system has a great potential to be used as a heat pump and is capable of upgrading the temperature of the released heat from lower to higher value.

An extended Kalman-Bucy filter for state of charge estimation of 2-RC network modelled Li-ion battery

Li-ion batteries have increased dramatically in the automobile industry over the past few decades. Lithium-ion batteries are viewed more favourably due to their high energy density, specific energy, etc. Optimising the performance of lithium-ion batteries requires accurate modelling and estimation of the state of charge (SOC). This article introduces an efficient second-order resistor-capacitor (2RC) network battery model and an optimised extended Kalman-Bucy filter (EKBF) as the most effective way to model a battery and estimate its state of charge (SOC). The operating parameters of a lithium-ion battery are measured with the least-squares curve fitting method. At a temperature of 20 °C, the proposed method for estimating SOC has a mean absolute error (MAE) of 0.72 % and a root mean square error (RMSR) of 0.71 %. In addition, the operational characteristics of the proposed EKBF were validated by simulating its operation at temperatures ranging from 0 °C to 40 °C. Under all conditions, the proposed method maintained an average error rate of 0.40%. The output of the proposed topology was validated using OPAL-RT (OP5700) hardware-in-the-loop real-time simulator. Consequently, the proposed method is preferable for accurate and dependable SOC estimation in real-time battery management system (BMS) applications.

38 Application of Real-Time Location Systems for Automated Behavioral Monitoring in Sheep

Abstract Evaluating how, when, and where an animal moves in their environment can provide insights into their health and welfare states. Spatial tracking systems for monitoring sheep are less well developed than accelerometer-based systems, but have the potential to add important behavioral information to Precision Livestock Farming (PLF) applications. Global Positioning Systems (GPS) can be used to track pasture-based animals, but are not suitable to establish indoor locations. Real-Time Location Systems (RTLS) are a recent development that use radio-frequency signals emitted by tags to track the indoor location of an animal online and continuously. Raw RTLS data in the form of x, y coordinates can be used to calculate multiple spatial metrics, including velocity, acceleration, distance moved, the proportion of time an animal spends in different functional areas, social network attributes, and range size. RTLS can also be integrated with accelerometers to potentially improve predictive accuracy of behavioral algorithms. RTLS have been primarily tested and validated for indoor tracking of dairy cattle and have been used to assess behavioral time budgets and to detect space-use changes related to estrus or health status. For on-farm applications, these data must be transformed into threshold-based algorithms to generate notifications on changes in the health or welfare status of an animal. Algorithm development needs to account for confounding factors such as breed, sex, age, parity, and stage of lactation, as well as environmental variability that can influence the performance of decision-making tools under real-life conditions. In addition, independent validation studies of commercial systems are lacking, and many calculate positioning error with stationary objects rather than moving animals, potentially inflating accuracy estimates. In conclusion, there is growing empirical support for the use of RTLS as a PLF technology for on-farm animal health and welfare assessment. However, research is needed to validate these systems in sheep and identify spatial metrics that are accurate and robust predictors of health and welfare states for commercial applications.

SISTEM MONITORING KETINGGIAN OMBAK AIR LAUT SECARA REAL-TIME BERBASIS IoT

Indonesia is an archipelagic country where most of its territory is water, so all activities carried out in water, especially the sea, are an important part of the life of the Indonesian people. The height of the sea waves is a phenomenon that greatly affects the efficiency and safety of people when they are in sea waters. The process of obtaining sea wave height data requires an appropriate system. So this study designed a prototype system for monitoring the height of sea waves in real-time based on IoT. The method used is the waterfall, where the ultrasonic sensor will be connected to the ESP-8266 nodemcu so that real-time sea wave height data is obtained through the user interface on the Thinger IO Platform. In addition, the system uses red, yellow, and green LEDs as indicators of the height of the water waves. These results indicate that the application of real-time IoT-based sea wave height systems has good capabilities. This is indicated by the user being able to see real-time monitoring data on sea wave height based on IoT with the display of numbers, graphs, and LED indicator lights. For the seawater level scale used in the system, the LED indicator lights in red are 0-10 cm,yellow are 11-20 cm, and green are 21-30 cm.

Real-time transient stability estimation of power system considering nonlinear limiters of excitation system using deep machine learning: An actual case study in Iran

One of the most important features of a reliable power system is its capability to supply the demand continuously. This continuous supply has been maintained by the transient stability of the system against large disturbances. The study of this type of stability is examined through different indicators. One of the common indicators to evaluate the transient stability of the power system is the well-known Critical Clearing Time (CCT) index. Conventional methods for calculating CCT have presented good accuracy, however, their computational cost is very high which makes them not suitable for real-time applications and real large-scale networks. Considering their ability to feature extraction of big data, deep neural networks can be utilized as reliable tools to cover these deficiencies. In this regard, to cover the shortcomings of the conventional methods, this paper proposes a method based on deep Convolutional Neural Networks (CNN) to estimate the CCT index in real-time power system applications. Moreover, to analyze a realistic case, nonlinear limiters of the excitation systems which have a considerable effect on transient stability index are considered in this study. Thanks to the using of several deep layers and the comprehensive established database, the accuracy of proposed method is appropriately high. Numerical studies on IEEE standard networks as well as a real case in Iran Power Grid (IPG) represents the advantages of the proposed method.

An adaptive gravitational search optimization (AGSO)‐based convolutional neural network—long short‐term memory (CNN‐LSTM) approach for face recognition and classification

SummaryFace recognition and classification have gained increasing attraction in the recent decades due to their widespread adoption in real time application systems. Most of the conventional research efforts focused on developing face recognition frameworks using enhanced optimization‐based classification methods, they are hampered by issues such as computational complexity, increased overhead, limited capacity to handle large datasets, and lengthy processing time. The novel contribution of this paper is to develop a highly competent and precise face recognition methodology through an innovative mechanism. In this framework, the initial step involves face detection from input images using an analytical face parts detection methodology. Subsequently, the tutor face filtering (TFF) technique is applied to preprocess the face image, enhancing its quality and filtering out noise content. Following this preprocessing step, features are extracted from the processed image using the direction‐based pattern extraction (DBPE) model. To improve classifier accuracy, a novel adaptive gravitational search optimization (AGSO) technique is employed to select the optimal features during model training. Finally, an integrated deep learning model, referred to as convolutional neural network—long short‐term memory (LSTM), is utilized for accurate face image recognition based on the selected optimal features. To assess and compare the system's performance, various metrics are employed in the results analysis to demonstrate the superiority of the proposed approach.