Development Of Monitoring System Research Articles

Development and application of a high-resolution monitoring system for a large-displacement rapid landslide

Development and application of a high-resolution monitoring system for a large-displacement rapid landslide

Development of an Arduino-Based Monitoring System for Pico-Hydro Power Plants

One of the problems faced by people in remote areas is the unavailability of infrastructure for power distribution. The available rivers can be used to generate electrical energy. The developed systems must be inexpensive, easy to operate and reliable. It should be equipped with a monitoring system to display the output. This study aims to develop a pico-hydro power plant and its monitoring system to meet the power needs in remote areas. The power plant consists of a small turbine, a generator, a battery charger, and a battery while the monitoring system consists of a current sensor, voltage sensor, Arduino Nano, and a display. The system was tested in the laboratory and the river. The test of the DC voltage sensor, AC voltage sensor, and DC current sensor produces errors of 1.88%, 5.24%, and 1.25% respectively. The no-load test shows that the system generates a voltage of 12.77 - 16.6 VDC and 224 - 245 VAC when rotated at 696 - 1363 RPM. When loaded, the system generates voltages of 12 - 12.8 VDC and 225 - 247 VAC when rotated at 1332 - 1564 RPM. The developed system can be used by people in remote areas to meet their power needs.

Design and Development of a University Outdoor Air Quality Monitoring System

An increase in air quality monitoring research using low-cost air quality sensors has been observed. Existing air quality monitoring systems provide real-time data on at most five primary pollutants, cover a short area, and could be made expandable. An air quality monitoring system utilizing a scalable, low power wide area network, centralized system, and low cost sensors is proposed. The nodes gather data on air pollutants and environmental factors. Data conversion, storage, and calculation of air quality indices were processed on the central subsystem and visualization through IoT cloud. The results suggest improvement in the design and integration of prediction models, battery, and power management techniques.

Accurate classification of wheat freeze injury severity from the color information in digital canopy images.

This paper explores whether it is feasible to use the RGB color information in images of wheat canopies that were exposed to low temperatures during the growth season to achieve fast, non-destructive, and accurate determination of the severity of any freeze injury it may have incurred. For the study presented in this paper, we compared the accuracy of a number of algorithmic classification models using either meteorological data reported by weather services or the color gradation skewness-distribution from high-definition digital canopy images acquired in situ as inputs against a reference obtained by manually assessing the severity of the freeze injury inflicted upon wheat populations at three experimental stations in Shandong, China. The algorithms we used to construct the models included in our study were based on either K-means clustering, systematic clustering, or naïve Bayesian classification. When analyzing the reliability of our models, we found that, at more than 85%, the accuracy of the Bayesian model, which used the color information as inputs and involved the use of prior data in the form of the reference data we had obtained through manual classification, was significantly higher than that of the models based on systematic or the K-means clustering, which did not involve the use of prior data. It was interesting to note that the determination accuracy of algorithms using meteorological factors as inputs was significantly lower than that of those using color information. We also noted that the determination accuracy of the Bayesian model had some potential for optimization, which prompted us to subject the inputs of the model to a factor analysis in order to identify the key independent leaf color distribution parameters characterizing wheat freeze injury severity. This optimization allowed us to improve the determination accuracy of the model to over 90%, even in environments comprising several different ecological zones, as was the case at one of our experimental sites. In conclusion, our naïve Bayesian classification algorithm, which uses six key color gradation skewness-distribution parameters as inputs and involves the use of prior data in the form of manual assessments, qualifies as a contender for the development of commercial-grade wheat freeze injury severity monitoring systems supporting post-freeze management measures aimed at ensuring food security.

Development of a Very Low-Cost Deforestation Monitoring System Based on Aerial Image Clustering and Compression Techniques

Development of a Very Low-Cost Deforestation Monitoring System Based on Aerial Image Clustering and Compression Techniques

Development of Intelligent Monitoring and Control System for Electrostatic Precipitators in Cement Plants

Cement plants are crucial industrial entities that supply cement for various applications, including the construction of buildings and bridges. While these plants play a vital role in infrastructure development, they are also recognized as significant sources of environmental pollution. To mitigate air pollution, Electrostatic Precipitators (ESPs) are employed, capable of reducing air pollution by approximately 99.99%. Consequently, ESPs warrant in-depth study, and development. This project focuses on investigating, and developing a monitoring, and control system for ESPs utilizing intelligent devices. The initial step involved deriving a mathematical model based on input/output data from the critical unit, the transformer/rectifier (T/R set). The Grey Wolf Optimization algorithm was employed to determine the optimal parameters (Kp=988, Ki=37.7, Kd=88.5) for the PID controller using the MATLAB package.

Hybrid retrieval of grass biophysical variables based-on radiative transfer, active learning and regression methods using Sentinel-2 data in Marakele National Park

Biophysical variables such as leaf area index (LAI) and leaf chlorophyll content (LCC) are cited as essential biodiversity variables. A comprehensive comparison and integration of retrieval methods is needed for the estimation of biophysical variables such as LAI and LCC over a multispecies grass canopy. This study tested an assortment of five potentially robust, nonparametric regression methods (NPRMs) for inversion of radiative transfer model (RTM) to retrieve grass LAI and LCC in the Marakele National Park (MNP) of South Africa. The NPRMs used were, namely (i) Partial least squares regression (PLSR), (ii) Principle components regression (PCR), (iii) Kernel ridge regression (KRR), (iv) Random forest regression (RFR), and (v) K-nearest neighbours regression (KNNR). Furthermore, the study attempted to constrain the inversion process by using active learning (AL) techniques which ensured the selection of informative samples from a large pool of RTM simulations. Results show the most accurate grass LAI and LCC retrievals had lower relative root mean squared errors (RRMSEs) of 39.87% and 16.58% respectively. These findings have significant implications for the development of transferable rangeland monitoring systems in protected mountainous regions.

Computer simulation of DDOS attacks on continuous monitoring systems

The task of building models and analyzing the protection of continuous monitoring systems from cyber-attacks is currently becoming particularly relevant due to the rapid development and implementation of monitoring systems in various industries. Despite the constant development of the field, the task of identifying potential information threats to such systems remains at the same level with the development of means and methods of conducting cyber-attacks. The purpose of this work is to develop a DDOS attack model for a spatially distributed continuous monitoring system with a hierarchical structure of connections between sensors. To define various criteria for the functionality of a spatially distributed continuous monitoring system when exchanging messages between the elements (sensors) of the system. Results. During the study, the authors performed a number of experiments using computer modeling. Computer simulations of DDoS attacks on a spatially distributed continuous monitoring system were carried out in cases of system operation with and without load. The criteria of the system's operability over time are defined, and an approach to determining the system's serviceability based on Amdahl's law and evaluating the acceleration of the system is proposed. It is shown by the example of computer experiments that the model has practical significance, and the results of applying the model can be used to reduce the risks associated with DDoS attacks.

Development of a patient health monitoring system based on the internet of things with a module for predicting vital signs

<span>Recent issues related to human health in the world have shown the importance of telemedicine considering necessities to perform the remote monitoring of patients. In this study, using a patient smart monitoring system (PSMS), we collected 5,000 samples of heart rate and blood saturation vital signs from 4 volunteers and tried to find better correlation algorithms to develop a module to predict what these vital signs will be in the next 60 seconds. The following regression algorithms recurrent neural network (long short-term memory) (RNN(LSTM)), autorregresive integrated moving average (ARIMA), value-added reseller vector autoregression (VAR) were used to forecast the patient's state of health in the next 60 seconds. Further, the support vector machine (SVM) and Naive Bayes classification algorithms use the data forecasted by the regression algorithms as input to predict the health status of the patients. When comparing algorithms, we focused on the F measure, a metric used to evaluate the performance of machine learning algorithms. As a result, RNN(LSTM) and SVM showed the performance score value of machine learning algorithms F 0.84, RNN(LSTM) and Naive Bayes 0.81, VAR and SVM 0.82, and VAR and Naive Bayes 0.75. Compared to them, the correlation of ARIMA regression algorithms and SVM classification showed a better F score of 0.86 for machine learning algorithms than the others.</span>

Measurement of conductive fabrics electrical resistance by combining of image processing and convolutional neural network methods

This study proposes the use of a CNN model to predict the resistance of conductive fabrics by utilizing the brightness information from their images, aiming to address the limitations of traditional contact-based measurement methods and explore the feasibility of non-contact resistance measurement. Conductive fabrics were produced using environmentally friendly cellulose fiber as a base material, with a dip-coating and padding process involving water-based single-walled carbon nanotube (SWCNT). After scanning the produced conductive fabrics and meticulously preprocessing the images, a dataset for CNN training was constructed, comprising label values corresponding to the sheet resistance of each image. ANOVA analysis confirmed a statistically significant relationship ( p-value = 8.04145e^-18) between the brightness of conductive fabric images and their sheet resistance. By leveraging the relationship between the brightness of fabric images and sheet resistance, training of the CNN model yielded an RMSE of 0.0558 and an R-squared value of 0.9557, validating the effectiveness of the designed CNN model for image-based resistance prediction. This research is expected to contribute to the development of future real-time monitoring and control systems, providing a crucial foundation for the advancement of data-driven measurement and control systems based on computer vision and machine learning techniques. Furthermore, it is anticipated to unveil new possibilities for various applications of conductive fabrics.

Development of digital livestock monitoring in Sambilawang Village, Serang, Banten

The stockbreeders in Sambilawang Village face challenges in managing their livestock using traditional methods, resulting in inefficiencies and potential income losses. This study aims to develop a mobile application-based monitoring system to enhance livestock management for stockbreeders in Sambilawang Village while fostering collaboration with potential investors. The proposed system is designed to offer an interactive digital platform that enables stockbreeders to monitor livestock growth, health, and condition efficiently. Notifications will be implemented to inform both stockbreeders and investors about key events such as readiness for sale, breeding, or milking, simplifying the process of buying and selling livestock. The implementation of the digital monitoring platform significantly improves the management of livestock in Sambilawang Village. Stockbreeders can now maintain accurate records and provide timely updates to potential investors, enhancing their income and facilitating collaboration with buyers. The application also streamlines the livestock sales process, reducing disruptions in meat distribution. In conclusion, the development of this mobile application-based monitoring system represents a crucial step in addressing the challenges faced by stockbreeders in Sambilawang Village. By promoting efficient livestock management and fostering collaboration with investors, this solution has the potential to stabilize the stockbreeding profession and benefit the entire community.

Development of a Real-Time Geometric Quality Monitoring System for Extruded Filaments of 3D Concrete Printing Construction

Development of a Real-Time Geometric Quality Monitoring System for Extruded Filaments of 3D Concrete Printing Construction

Development of an environmental monitoring system in the period of war and post-war transformation: a legal view

Development of an environmental monitoring system in the period of war and post-war transformation: a legal view

IntelliCare: Integrating IoT and Machine Learning for Remote Patient Monitoring in Healthcare: A Comprehensive Framework

The development of smart health monitoring systems has emerged as a consequence of the integration of Internet of Things (IoT) and Machine Learning (ML) technologies within the healthcare sector. This transformation has significantly reshaped patient care methodologies, shifting from traditional approaches to electronic healthcare systems. Leveraging IoT technology fosters a contemporary medical device ecosystem, fostering seamless communication among healthcare professionals, patients, and medical devices. Through the deployment of IoT devices, encompassing sensors and transmitters, coupled with Machine Learning algorithms, various applications have arisen, spanning from remote patient monitoring to real-time health assessment during ambulance transit to medical facilities. This proposed framework aims to monitor essential physiological parameters including body temperature, blood pressure, heart rate, sweat analysis, glucose levels, ECG, EEG, and pulse oximetry, transmitting pertinent data for tailored processing and analysis. Implantable IoT devices serve as conduits for wireless communication, data storage, centralized computation, and portable processing, facilitating connectivity among sensors, GPS-enabled ambulances, medical practitioners, and patients. To mitigate potential health risks, sensors are equipped with Machine Learning capabilities to promptly assess illness severity and recommend appropriate interventions, potentially triggering automated alerts to healthcare providers. This seamless exchange of information via IoT and wireless networks enables rapid communication between doctors and patients, facilitating personalized medical recommendations, prescription management, and hospital selection based on individual health profiles.

Identification of Damage in a Wind Turbine Blade Using Mechanical Measurements and Artificial Neural Networks

Due to the stochastic nature of environmental loadings, a lot of interest is paid in the discovery of possible damages of the involved equipment in modern industry. In wind turbines’ blades, the development of a smart structural health monitoring system is essential. In this paper, a large-scale composite wind turbine blade model is designed and used for the detection of several damage scenarios. The process is mainly based on the development of monitoring techniques which exploit the capabilities of artificial neural networks. These techniques can provide the exact position of possible damages, under given external loading scenarios. Moreover, the use of such methods decreases significantly the need of external intervention and at the same time it increases the accuracy of the whole approach. The above processes are simulated using the finite element method. The goal is to develop a neural network which realizes the correlation of measurements with damage patterns. The goal is focused on the solution of inverse problems involving elastically deformable structures, based on remote mechanical measurements. The correlation between measurements and damages, which is much more complicated in comparison to image analysis, is studied by means of neural networks.

Применение моделей машинного обучения для контроля качества вибродиагностических данных

Article aims to determine the most effective machine learning model for clustering vibration diagnostics data. The research includes analysis of various models and methods such as-means, Agglomerative Clustering, TimeSeriesKMeans and CatBoost. The goal is to select a method that can best identify the data structure and improve understanding of the characteristics of vibration signals. The results of the study can be useful for the development of effective monitoring and diagnostic systems for equipment, as well as for improving the reliability and performance of technical systems.

In Situ Assessment of Oil Quality Sensor Performance in Engine Lubricant Flow

Assessing the functional quality of an engine lubricant through real-time sensing could pave the way for development of comprehensive engine health monitoring systems. In this study, a permittivity-based, commercial off-the-shelf (COTS) oil quality sensor was implemented in the lubricant flow of a diesel engine after detailed evaluation on a benchtop test facility. The sensor was mounted on the oil filter housing of the engine in the post-filter oil flow, and its implementation required no modifications to the engine block. Simultaneously, the lubricant flow was visualized by incorporating a novel test cell in the oil flow path. Both the sensor assembly and the flow visualization cell were fully characterized on the benchtop facility prior to implementation on the engine. In these experiments, fresh and used samples of the engine’s recommended oil were tested, and the sensor’s oil quality measurements showed noticeable differences between the engine and benchtop studies, a feature attributable to the observed presence of aeration intrinsic to the engine oil flow. These results prove that the adaptation of permittivity-based sensors for effective real-time engine lubricant quality monitoring will require comparative assessment of oil quality measurements in aerated and nonaerated flow fields.

Pneumatic Fault Monitoring and Control for Sustainable Compressed Air Systems

Sustainable development in the industrial sector has been widely explored in recent years, to achieve a carbon-neutral industry. Compressed air systems are widely used in the industrial sector. Numerous energy-saving improvements have been studied within this scope, as leaks make these systems inefficient. Nevertheless, it has yet to be seen how different optimisation techniques can be utilised to mitigate fault effects. This study shows how fault monitoring was performed on a multi-actuator system, using different time domain indicators including, mean and standard deviation. This was followed by exploring the system behaviour when pressure and flowrate control strategies were executed to minimize fault impacts. Fault monitoring, using the indicator data, was successful. For instance, as a 1 mm leak was induced and the consumption increased by 34%, the standard deviation in pressure drop reduced by 6% and the mean actuation time decreased by 13%. Though the mean in pressure drop was useful for fault monitoring other pressure indicators, including standard deviation, provided additional monitoring capabilities. During this monitoring exercise, it was also found that improved sensor accuracy resulted in less reading variations, obtaining more conclusive results and identifying faults of smaller sizes. As faults were accurately identified and characterised, it was then possible to mitigate their effects via pressure and flowrate adjustments. Results proved promising, as both contributed to air consumption decreases of 16% and 11%, respectively. Although such modifications decreased the production rate by 2-5%, the previously mentioned savings outweighed this decrease. This work highlights the need for development of fault monitoring and control systems which maintain the productivity and energy performance of pneumatic systems.

Digitalization Of Marketing as Innovation Tool of Customers’ Evaluation

This paper analyses the digitalization of museum marketing as an innovative tool for customer evaluation. The content analysis of digital tools created by the most visited museums in the world on social networks such as Facebook, Twitter and Instagram were carried out. To obtain statistical information about the pages of museums in social networks, the social media analytics and management tool Fanpage Karma was used. According to the selected indicators, Fanpage Karma filters the rating of the networks’ current strongest content. The correlation between the number of museum visits and indicators showing the interaction of the museum with visitors using social networks, such as the number of fans, the page performance index, the number of posts per day, the growth rate of followers, post interactions, and the number of total reactions and comments, was evaluated. The aim of this paper is to analyse the impact of museum marketing digitalization processes on museum visits by tourists and, as a result, the economic development of the museum business. To monitor the digitalization strategy of the museum’s marketing activities, a mixed approach based on qualitative and quantitative analysis was used. Multivariate analysis was carried out to determine the relationship between museum attendance and the interaction between museums and subscribers in social networks. It has been proven that the introduction of digital technologies in museum marketing can attract visitors and put the institution at the new informational level. The number of museum visits and the number of fans, the number of posts per day, interactions, and the number of reactions and comments are the same across all social networks. The paper allows us to know the potential audience of the museum and its needs and requests and to predict the interests of certain categories of museum visitors. The scientific novelty and originality of the research consists of the use of digital marketing tools for evaluating their influence on client behaviour. The results of the study may be useful for the development of monitoring systems and strategic management of marketing when evaluating the behaviour of consumers on the content of social networks at enterprises in various industries.

Off-axis optical system for the monitoring of the Laser Metal Deposition process

The Laser Metal Deposition (LMD) is emerging among the additive manufacturing (AM) technologies of metals for its versatility. It takes advantage of the flexibility of a laser source and a powder flow to fabricate or repair components with very complex features. The challenging process conditions that characterize the processing of metallic materials (temperatures and stresses) underlie the occurrence of several defects that plague such AM processes. Thus, the necessity to develop monitoring systems that can comprehensively analyze the production phase arises. In the present work, an innovative off-axis optical system consisting of three cameras with appropriate filters is proposed for the monitoring of LMD process. The peculiarity of this system lies in the capability of monitoring the spatial evolution of the melt pool, enabling eventually a complete control of the deposition process. In fact, through the use of properly developed image processing algorithms, the system enables the tridimensional definition of the size and shape of the melt pool and at the same time the reconstruction of each deposited layer. The potential of the monitoring system was tested on a series of thin-walled components. Subsequently, the analysis results were validated by comparison with 3D scanning of the parts and analyses performed using a coaxial monitoring system.