Development Of Monitoring System Research Articles

Artificial Intelligence-Assisted Environmental DNA Metabarcoding and High-Resolution Underwater Optical Imaging for Noninvasive and Innovative Marine Environmental Monitoring

To effectively protect the marine environment, it is crucial to establish effective environ mental monitoring platforms. Traditional marine environmental monitoring methods heavily rely on morphological identification and field expertise, with the sampling process being disruptive and potentially destructive to vulnerable marine environments. In light of emerging biomonitoring needs and biodiversity declines, we reviewed the urgently needed, ongoing advances in developing effective, noninvasive, and innovative monitoring methods and systems to examine the complex marine environment for better strategic conservation and protection, using the coral ecosystem as one of the representative forefront examples in marine protection. This review summarizes current trends and efforts in transitioning into more standardizable and automatable utilizations of environmental DNA metabarcoding-based monitoring strategies and high-resolution underwater optical imaging monitoring systems as two of the promising pillars for the next generation of noninvasive biomonitoring and associated applications. The assistance of artificial intelligence for environmental DNA metabarcoding and high-resolution underwater optical imaging into an empowered, all-rounded monitoring platform for enhanced monitoring capacity is discussed as a highly potent direction for future research exploration. This review will be a cornerstone reference for the future development of artificial intelligence-assisted, noninvasive, and innovative marine environmental monitoring systems.

REAL-TIME DETECTION AND CLASSIFICATION OF FISH IN UNDERWATER ENVIRONMENT USING YOLOV5: A COMPARATIVE STUDY OF DEEP LEARNING ARCHITECTURES

This article explores techniques for the detection and classification of fish as an integral part of underwater environmental monitoring systems. Employing an innovative approach, the study focuses on developing real-time methods for high-precision fish detection and classification. The implementation of cutting-edge technologies, such as YOLO (You Only Look Once) V5, forms the basis for an efficient and responsive system. The study also evaluates various approaches in the context of deep learning to compare the performance and accuracy of fish detection and classification. The results of this research are expected to contribute to the development of more advanced and effective aquatic monitoring systems for understanding underwater ecosystems and conservation efforts.

특성화고등학교 이주배경학생 진로교육 문제점의 요인 및 개선방안: 외국출생 외국국적 학생을 중심으로

This study examines the current challenges and solutions in career education for migrant-background students in specialized vocational high schools in Korea. Based on in-depth interviews with five teachers and five experts, two key categories of limitations were identified: migrant-background characteristics and educational environment factors. The former includes difficulties arising from language barriers, residency restrictions, and cultural differences, while the latter encompasses inadequate teacher understanding, lack of parental support, and limitations in school programs. To address these, two improvement categories were proposed: support tailored to migrant-background characteristics-including customized Korean language education, easing residency requirements, and enhancing practical career preparation-and enhancements to the educational environment, such as strengthening teacher training, expanding dedicated personnel, and developing monitoring systems for post-employment management. These insights offer comprehensive strategies to improve career education for migrant-background students in vocational schools.

Development of indoor CO2 monitoring system with an integrated fixed sensor and a mobile measuring robot

Abstract This paper proposes an advanced system for optimizing indoor environmental quality (IEQ) in office environments that integrates fixed sensors with a mobile measuring robot (MMR). A demand-based measurement strategy that uses human detection and predictive analytics via machine learning is used to enhance data collection accuracy and efficiency. The system incorporates voice notifications to prompt occupants to perform actions that improve IEQ. The MMR's operational capabilities and coordination with fixed sensors allow the system to achieve high precision and efficiency in office environments. The system's effectiveness is validated through empirical studies (two preliminary experiments and two main experiments) in real office settings. The first preliminary experiment identified measurement blind spots and the second preliminary experiment tested the equivalence of environmental measurements between the MMR and fixed sensors. The first main experiment showed the system's human detection function for efficient and precise environmental measurement and the voice notification function for prompting occupants to perform actions that improve IEQ. The second main experiment showed the system's predictive accuracy in forecasting CO2 levels using neural network models. The main experiments demonstrate that the system can effectively guide MMR operations, reduce measurement times, and accurately predict environmental changes. The proposed system is a comprehensive solution for IEQ enhancement in office buildings.

Development and Application of a Novel Tsunami Monitoring System Based on Submerged Mooring.

Real-time data transmission and reliable operation are essential for a tsunami monitoring system to provide effective data. In this study, a novel real-time tsunami monitoring system is designed based on a submersible mooring system. This system is equipped with a data acquisition and tsunami wave identification algorithm, which can collect the measured data of the pressure sensor and detect a tsunami wave in real time. It adopts the combination design of underwater inductive coupling transmission and a redundant BeiDou communication device on the water surface to ensure the reliability of real-time data transmission. Compared with traditional tsunami monitoring buoys, it has the advantages of reliable communication, good concealment, high security, and convenient deployment, recovery, and maintenance. The results of laboratory and sea tests show that the system has high reliability of data transmission, stable overall operation of the system, and good application prospects in the field of real-time tsunami monitoring and early warning.

Implementation strategies for decentralized management of multidrug-resistant tuberculosis: insights from community health systems in Zambia

BackgroundDecentralized management approaches for multi-drug-resistant tuberculosis (MDR TB) have shown improved treatment outcomes in patients. However, challenges remain in the delivery of decentralized MDR TB services. Further, implementation strategies for effectively delivering the services in community health systems (CHSs) in low-resource settings have not been fully described, as most strategies are known and effective in high-income settings. Our research aimed to delineate the specific implementation strategies employed in managing MDR TB in Zambia.MethodsOur qualitative case study involved 112 in-depth interviews with a diverse group of participants, including healthcare workers, community health workers, patients, caregivers, and health managers in nine districts. We categorized implementation strategies using the Expert Recommendations for Implementing Change (ERIC) compilation and later grouped them into three CHS lenses: programmatic, relational, and collective action.ResultsThe programmatic lens comprised four implementation strategies: (1) changing infrastructure through refurbishing and expanding health facilities to accommodate management of MDR TB, (2) adapting and tailoring clinical and diagnostic services to the context through implementing tailored strategies, (3) training and educating health providers through ongoing training, and (4) using evaluative and iterative strategies to review program performance, which involved development and organization of quality monitoring systems, as well as audits. Relational lens strategies were (1) providing interactive assistance through offering local technical assistance in clinical expert committees and (2) providing support to clinicians through developing health worker and community health worker outreach teams. Finally, the main collective action lens strategy was engaging consumers; the discrete strategies were increasing demand using community networks and events and involving patients and family members.ConclusionThis study builds on the ERIC implementation strategies by stressing the need to fully consider interrelations or embeddedness of CHS strategies during implementation processes. For example, to work effectively, the programmatic lens strategies need to be supported by strategies that promote meaningful community engagement (the relational lens) and should be attuned to strategies that promote community mobilization (collective action lens).

Monitoring and Predicting Air Quality with IoT Devices

The growing concern about air quality and its influence on human health has prompted the development of sophisticated monitoring and forecast systems. This article gives a thorough investigation into forecasting the air quality index (AQI) with an Internet of Things (IoT) device that analyzes temperature, humidity, PM10, and PM2.5 levels. The dataset used for this analysis comprises 5869 data points across six critical parameters essential for accurate air quality prediction. The data from these sensors is sent to the ThingSpeak cloud platform for storage and preliminary analysis. The system forecasts AQI using a TensorFlow-based regression model, delivering real-time insights. The combination of IoT technology and machine learning improves the accuracy and responsiveness of air quality monitoring systems, making it a useful tool for environmental management and public health protection. This work presents comparatively the effectiveness of feedforward neural network models trained with the ‘adam’ and ‘RMSprop’ optimizers over different epochs, as well as the machine learning algorithm random forest with varying numbers of estimators to forecast AQI. The models were trained using both types of regression analysis: linear regression and random forest regression. The findings show that the model achieves a high degree of accuracy, with the predictions closely aligning with the actual AQI values, thus having the potential to significantly reduce the negative health impact associated with poor air quality, protecting public health and alerting users when pollution levels are higher than allowed. Specifically, the random forest model with 100 estimators delivers the best overall performance for both AQI 10 and AQI 2.5, achieving the lowest Mean Absolute Error (MAE) of 0.2785 for AQI 10 and 0.2483 for AQI 2.5. This integration of IoT technology and advanced predictive analysis addresses the significant worldwide issue of air pollution by identifying the pollution hotspots and allowing decision-makers for quick reactions, and the development of effective strategies to reduce pollution sources.

Development and prototyping of a concentrated ethanol gas monitoring system based on the MQ-3 sensor using the KAVi machine calibrator for environmental safety

This research outlines the development of a device for measuring concentrated ethanol gas concentrations using the MQ-3 sensor. The device is engineered utilizing an Arduino Uno microcontroller and an LCD as the output interface. The MQ-3 sensor has demonstrated optimal sensitivity and a linear response to ethanol gas. The range of ethanol gas concentrations tested, from 10% to 70%, was selected to match the capabilities of the KAVi machine in generating ethanol gas. The testing process of the sensor was conducted to generate data that were subsequently calibrated to ensure measurement accuracy. Validation results indicate that the MQ-3 sensor can measure ethanol gas concentrations with high accuracy and good linearity within this range. However, discrepancies between the sensor measurements and the calibrator values were observed and need attention. The development of this device provides improvements in the accuracy and linearity of the MQ-3 sensor compared to previous studies. It is important to note that the KAVi machine has limitations in producing ethanol gas concentrations above 70%, which should be considered in the practical applications of this device. Overall, this device shows great potential in applications for monitoring ethanol gas concentrations, with a note to consider the limitations of the ethanol gas production process from the KAVi machine for more optimal results.

A DATA DRIVEN APPROACH THROUGH IOMT BASED PATIENT HEALTHCARE MONITORING SYSTEM

The current circumstances underscore the pressing need to accelerate the adoption of Internet of Things platforms in realm of the medical field to improve the health of mankind. Given the present challenges, I propose the development of an Advancing healthcare monitoring system built on the foundation of Internet of Medical Things (IOMT). Advancing patients healthcare IOMT system serves as a communication conduit between patients and doctors, facilitated by the IoMT platform. This platform utilizes various medical sensors connected to a server through technologies such as WiFi and Bluetooth. The data collected and stored in the server is then leveraged to analyse patients' health conditions, guiding subsequent treatment protocols. In this proposed system, the microcontroller serves as an intermediary interface between the sensors and the server. This cutting-edge technology enables remote patient monitoring, eliminating the need for physical presence. Within the prototype, patients' summaries and information is supplied using an online platform. Through the adoption of Advancing Healthcare through Data-Driven IOMT Patient Monitoring, lives can be safeguarded from critical conditions, underscoring the vital importance of embracing such advanced technologies in healthcare.

Investigation of a Camera-Based Contactless Pulse Oximeter with Time-Division Multiplex Illumination Applied on Piglets for Neonatological Applications.

(1) Objective: This study aims to lay a foundation for noncontact intensive care monitoring of premature babies. (2) Methods: Arterial oxygen saturation and heart rate were measured using a monochrome camera and time-division multiplex controlled lighting at three different wavelengths (660 nm, 810 nm and 940 nm) on a piglet model. (3) Results: Using this camera system and our newly designed algorithm for further analysis, the detection of a heartbeat and the calculation of oxygen saturation were evaluated. In motionless individuals, heartbeat and respiration were separated clearly during light breathing and with only minor intervention. In this case, the mean difference between noncontact and contact saturation measurements was 0.7% (RMSE = 3.8%, MAE = 2.93%). (4) Conclusions: The new sensor was proven effective under ideal animal experimental conditions. The results allow a systematic improvement for the further development of contactless vital sign monitoring systems. The results presented here are a major step towards the development of an incubator with noncontact sensor systems for use in the neonatal intensive care unit.

A comparative DFT study on NO2 adsorption and sensing activities of pristine, reduced and Pr3+-doped CeO2 (110) surface

Surface site activation enhances the sensing properties of the CeO2 (110) surface. Herein, the adsorption of nitrogen dioxide (NO2) on pristine and modified CeO2 (110) surfaces has been studied in detail using quantum chemical calculation. The introduction of the single praseodymium atom on the CeO2 surface reduces its band gap from 1.93 to 0.53 eV, which in turn enhances the adsorption energy from -0.58 (pristine) to -1.34 eV (doped) and also prolongs the desorption time, indicating stronger adsorption ability. The density of states (DOS) and projected density of states (PDOS) analyses reveal that Pr doping modifies the electronic properties of the CeO2 (110) surface which improves NO2 sensitivity. Further, it is also observed that 0.57 eV increase in the work function for NO₂ adsorption on Pr doped CeO2 surface, indicating stronger interaction compared to the pristine CeO2. In contrast, reduced CeO2 surfaces do not exhibit any significant change in sensing properties. Thus, it is understood that Pr-doped CeO2 (Pr/CeO2) surfaces exhibit better stability and sensitivity towards NO2 adsorption compared to pristine and reduced surfaces. Therefore, this study provides insight into the rational design of advanced gas sensing materials based on modified CeO2 (110) surfaces, contributing to the development of an efficient air quality monitoring system.

Measurement Techniques for Low-Concentration Tritium Radiation in Water: Review and Prospects.

Tritium (3H) is one of the most critical nuclides for environmental monitoring, yet it is challenging to measure. Its high natural mobility and its potential to enter the human body through the food chain underscore the importance of not overlooking the radiation safety risks associated with tritium. The need for the online measurement of tritium at low concentrations is becoming increasingly apparent. This review examines the two principal stages of current measurement methodologies: sample preparation and radiation signal detection. It provides a summary of the tritium sample preparation and detection techniques, highlighting advances in the research with potential applications in online monitoring. The review concludes with an analysis of the issues inherent in the current techniques and offers perspectives on possible technological enhancements and future trajectories for the development of online monitoring systems for trace tritium levels.

Design and Development of a Real-Time Monitoring System for Highway Road Surface Anomalies

The recent unprecedented increase in highway networks in India has increased the need to maintain safe and smooth roads. The increasing number of road surface anomalies such as cracks, surface irregularities, and anomalies can lead to vehicle damage and accidents. This research work presents the design and development of a real-time monitoring system for detecting anomalies in highway road surfaces. The proposed system utilizes the machine vision model integrated with cameras, sensors, and edge computing to provide timely and accurate alerts for the drivers and also to the road maintenance authorities. The proposed solution is designed specially to work under different environmental conditions and enable large-scale deployment. The output generated from the proposed model is visual feedback of the detected anomalies and its severity analysis, enabling quick road maintenance actions.

Development of a subsurface monitoring system for land subsidence hazard in the Bandung basin: a laboratory prototype

Abstract Land subsidence is a global environmental hazard posed by urban area worldwide, causing degradation in environmental quality and leads to further disasters such as increased flood risk, contamination risk, and infrastructure damages. Anthropogenic causes, such as groundwater extraction and building weight, cause high land subsidence rates. The behaviour of the subsurface under the influence of anthropogenic causes must be well understood to mitigate this problem. Conventional subsurface monitoring is robust and costly. In this case, we aim to first develop a versatile and low-cost subsurface monitoring prototype for land subsidence at a laboratory scale using a model box. Methods employed were constructing an experiment model box, developing the monitoring system, and trial experiments in the laboratory. The sensors are linear vertical displacement transducer, potentiometer, water level and pressure sensors. The monitoring system uses Arduino microcontroller to convert sensors inputs to desirable outputs and a logger to record the real-time data and transmit it to personal computer in the laboratory. Land subsidence in the Gedebage area in Bandung basin was taken as a model case. The model box was filled with soil from Gedebage, Bandung. A scenario of exploitation of confined groundwater and weight of building was applied for the model case. The results show that the laboratory prototype can monitor the subsurface changes due to the applied anthropogenic forces. In the case of Bandung soil, groundwater exploitation did not immediately cause subsidence instantaneously. There is a time delay between the drawdown of groundwater level and the subsequent vertical deformation. The rate of subsidence varies spatially inside the tank, the largest is close to the pump well and surface loads. A maximum of 2.88 mm subsidence over 663 days was recorded following 1 m groundwater drawdown. This information asserts the importance of long-time monitoring in subsidence areas.

Real-time Vertical Air Quality Monitoring System Development for Urban Scale

Real-time Vertical Air Quality Monitoring System Development for Urban Scale

Development of Safety Monitoring System Based on Visual Intelligence Technology

Development of Safety Monitoring System Based on Visual Intelligence Technology

Integrated health monitoring system for checking patients’ vitals

The increasing demand for efficient healthcare services has propelled the development of efficient health monitoring systems. This paper presents a comprehensive system designed to monitor the vital signs of patients in real-time, aimed at enhancing patient care and reducing the burden on healthcare providers. The system integrates various sensors to Data collected from these sensors are transmitted wirelessly to a central database, where it is processed and analyses using sophisticated algorithms. The results are accessible through a user-friendly interface for both healthcare professionals and patients. This health monitoring system offers several critical benefits. it provides real-time alerts for any abnormal vital signs, enabling prompt medical intervention. Secondly, the continuous monitoring allows for the early detection of potential health issues, which can significantly improve patient outcomes. The methodology involves is the analytical and systematic application of Arduino Nano Boards as microcontrollers, such as DS18B20, DHT11 and with WIFI Modula; which are driven- real time-based temperature frameworks for optimization and abstraction of accurate patient’s health data result. Results demonstrated the system's accuracy, reliability, and user satisfaction.

Development of monitoring system to prevent inflow of marine life into the nuclear power plant

Development of monitoring system to prevent inflow of marine life into the nuclear power plant

IOT Enabled Remote Monitoring Application For Telecom SMPS

This research paper presents a comprehensive study on the development of an IoT-enabled remote monitoring system for telecom SMPS (Switched-Mode Power Supply). The system aims to address the critical need for efficient power supply management in the telecom industry by utilizing a network of sensors to collect real-time data on key parameters such as voltage, current, temperature, and load. The collected data is securely transmitted to a central monitoring system for analysis and control.

Entropy-guided robust feature domain adaptation for electroencephalogram-based cross-dataset drowsiness recognition

To accurately identify driver drowsiness using Electroencephalogram (EEG), a significant amount of time is typically required to gather data from either the same subject or multiple subjects under the same experimental condition. The prolonged period required for data collection impedes the practical application of EEG. In this paper, we consider the challenging task of cross-dataset driver drowsiness recognition, where the EEG data collected by different devices are expected to be conveniently recognized by a classifier trained on an existing dataset. In order to solve the problem of distribution drift, we propose an Entropy-Guided Robust Feature (EGRF) adaptation framework. This framework utilizes the Entropy Minimization (EM) technique for domain alignment and an ensemble-like structure, consisting of multiple branch classifiers and a dropout layer, to enhance the robustness. The proposed method has been tested across two public datasets and achieves 2-class recognition accuracies of 77.4% and 85.9%. The innovative feature-robust block, combined with the EM loss, leads to substantial performance improvement, proving the effectiveness of our framework for cross-dataset driver drowsiness recognition. Our research demonstrates a promising direction for development of a calibration-free driver drowsiness monitoring system in the future.