Monitoring Network Research Articles

Pipeline leakage identification method based on DPR-net and distributed optical fiber acoustic sensing technology

Real-time monitoring of natural gas pipeline network can ensure the life and health of human beings and property safety in the surrounding area of the pipeline. Therefore, how to realize the rapid identification of pipeline leakage signal when leakage occurs is extremely important. Distributed acoustic sensing (DAS) technology is widely used in the field of pipeline leakage monitoring because of its advantages of wide coverage and high sensitivity. In this paper, a pipeline leak identification method based on DAS and one dimensional DPR-net (DAS pipeline leakage recognition network) are proposed. Pipeline leakage signal samples are collected under different working conditions (leakage aperture, leakage pressure, leakage direction). In test, the recognition accuracy of this method reached over 99%. There are reasons to believe that this method will provide an important technical means for DAS to detect pipeline leakage.

A hybrid approach for integrating micro-satellite images and sensors network-based ground measurements using deep learning for high-resolution prediction of fine particulate matter (PM2.5) over an indian city, lucknow

The detrimental impacts of fine particulate matter (PM2.5) on human health, climate, ecosystems, crops, and building materials are well-established. However, there remain unresolved inquiries regarding the precise location of the sources of PM2.5. This study is the first attempt to use a calibrated sensors-based ambient air quality monitoring network (SAAQM network) and regulatory government monitors to train micro-satellite images for high spatial-resolution air pollution field determination of PM2.5 in Lucknow, Uttar Pradesh, India. A hybrid approach is developed to integrate three different datasets that include microsatellite images, PM2.5 ground measurements, and supporting information (meteorological parameters and geographical coordinates), to be fed into a Random Trees-Random Forest- Convolutional Neural Network (RT-RF-CNN) joint model to estimate PM2.5 concentrations at a sub-km level. The RT-RF-CNN joint model can derive PM2.5 concentrations at a spatial resolution of 500 m with statistically significant indicators such as spatial r of 0.9, a low root-mean-square error of 26.9 μg/m3 and a mean absolute error of 17.2 μg/m3. Based on our approach, the PM2.5 prediction maps using micro-satellite images (spatial resolution of 3m/pixel) and RT-RF-CNN joint model were generated for each day throughout the study period (December 2021–December 2022). The inter-grid comparison of these maps revealed the intra-urban local hotspots and coolspots at a fine-granular level seasonally, monthly, and daily. It is observed that the monsoon season has the highest number of coolspots (67%), while winter (0.1%), post-monsoon (0.5%) and summer (11%) have fewer. It is noted that the high temporal-spatial information of PM2.5 estimates from our integrated approach is not achievable by ground-based measurements and other existing satellite-based estimates alone. The findings of this study have potential applications on a diverse array, encompassing near real-time daily PM2.5 predicted maps, specific air pollution hotspot identification, PM2.5 exposure assessment at the neighbourhood level, and integration of remote sensing-based micro-satellite images and ground-based measurements.

Wavelet-based convolutional neural network for non-intrusive load monitoring of next generation shipboard Power Systems

In this study, a non-intrusive load monitoring (NILM) framework is developed for next generation shipboard power systems (SPS) based on a discrete wavelet transform signal processing and a convolutional neural network (CNN). We have applied the developed NILM method to a four-zone medium voltage direct current (MVDC) SPS to evaluate the effectiveness of the proposed method. Each zone of the MVDC SPS consists of multiple components, such as propulsion load, pulsed load, high ramp rate load, cooling load, and hotel load. The current signals from the main generators are the main inputs to the NILM model. The current signals are first processed through a discrete wavelet transform to create a coefficient vector that reflects the status of all the components in each zone. Then, a multi-class classification problem is formulated and solved using a CNN architecture model to monitor the load statuses in real time. The results of case studies show that the developed NILM model in comparison with benchmark methods can (i) accurately monitor the status of all components with a total accuracy of over 98%, (ii) identify unique pulsed loads with a total accuracy of over 99%, and (iii) sustain the functionality of load monitoring under extreme events such as cyber/physical attacks, load uncertainty, and noisy inputs.

Unveiling the potential of a novel portable air quality platform for assessment of fine and coarse particulate matter: in-field testing, calibration, and machine learning insights.

Although low-cost air quality sensors facilitate the implementation of denser air quality monitoring networks, enabling a more realistic assessment of individual exposure to airborne pollutants, their sensitivity to multifaceted field conditions is often overlooked in laboratory testing. This gap was addressed by introducing an in-field calibration and validation of three PAQMON 1.0 mobile sensing low-cost platforms developed at the Mining and Metallurgy Institute in Bor, Republic of Serbia. A configuration tailored for monitoring PM2.5 and PM10 mass concentrations along with meteorological parameters was employed for outdoor measurement campaigns in Bor, spanning heating (HS) and non-heating (NHS) seasons. A statistically significant positive linear correlation between raw PM2.5 and PM10 measurements during both campaigns (R > 0.90, p ≤ 0.001) was observed. Measurements obtained from the uncalibrated NOVA SDS011 sensors integrated into the PAQMON 1.0 platforms exhibited a substantial and statistically significant correlation with the GRIMM EDM180 monitor (R > 0.60, p ≤ 0.001). The calibration models based on linear and Random Forest (RF) regression were compared. RF models provided more accurate descriptions of air quality, with average adjR2 values for air quality variables in the range of 0.70 to 0.80 and average NRMSE values between 0.35 and 0.77. RF-calibrated PAQMON 1.0 platforms displayed divergent levels of accuracy across different pollutant concentration ranges, achieving a data quality objective of 50% during both measurement campaigns. For PM2.5, uncertainty ( ) was below 50% for concentrations between 9.06 and 34.99μg/m3 in HS and 5.75 and 17.58μg/m3 in NHS, while for PM10, it stayed below 50% from 19.11 to 51.13μg/m3 in HS and 11.72 to 38.86μg/m3 in NHS.

MpScope: Enabling multi-pipeline monitoring inside a switch

The core of programmable switches is the flexible data plane, composed of multiple programmable pipelines in existing programmable switches. These pipelines are isolated from each other and cannot share state and data. However, most of network monitoring systems ignore this condition and implicitly assume that the switch has only a single pipeline. This results in an inaccurate measurement and high communication overhead with the practical switch. To tackle this problem, we propose MpScope, a general multi-pipeline monitoring framework, which centers around the control plane, supporting accurate and efficient network monitoring. Specifically, MpScope combines the switch’s data plane and control plane to achieve comprehensive network monitoring of the whole switch scope. The control plane aggregates the statistical results from multiple pipelines and tunes the monitoring module residing in the different pipelines in the data plane dynamically. The data plane is responsible for real-time traffic measurement and statistic reports. Its behaviors can be adjusted periodically with the instructions from the control plane. Two typical monitoring applications, i.e., heavy hitter detection and distinct counting, are developed with MpScope to validate the effectiveness of multi-pipeline monitoring. Experiments show that MpScope significantly reduces communication overhead compared to the static threshold scheme while maintaining high detection accuracy over time.

Classification accuracy and compatibility across devices of a new Rapid-E+ flow cytometer

Abstract. The study evaluated a new model of a Plair SA airflow cytometer, Rapid-E+, and assessed its suitability for airborne pollen monitoring within operational networks. Key features of the new model are compared with the previous one, Rapid-E. A machine learning algorithm is constructed and evaluated for (i) classification of reference pollen types in laboratory conditions and (ii) monitoring in real-life field campaigns. The second goal of the study was to evaluate the device usability in forthcoming monitoring networks, which would require similarity and reproducibility of the measurement signal across devices. We employed three devices and analysed (dis-)similarities of their measurements in laboratory conditions. The lab evaluation showed similar recognition performance to that of Rapid-E, but field measurements in conditions when several pollen types were present in the air simultaneously showed notably lower agreement of Rapid-E+ with manual Hirst-type observations than those of the older model. An exception was the total-pollen measurements. Comparison across the Rapid-E+ devices revealed noticeable differences in fluorescence measurements between the three devices tested. As a result, application of the recognition algorithm trained on the data from one device to another led to large errors. The study confirmed the potential of the fluorescence measurements for discrimination between different pollen classes, but each instrument needed to be trained individually to achieve acceptable skills. The large uncertainty of fluorescence measurements and their variability between different devices need to be addressed to improve the device usability.

Comparing LUCAS Soil and national systems: Towards a harmonized European Soil monitoring network

A recent assessment states that 60–70% of soils in Europe are considered degraded. Protecting such valuable resource require knowledge on soil status through monitoring systems. In Europe, different types of monitoring networks currently exist in parallel. Many EU Member states (MS) developed their own national soil information monitoring system (N-SIMS), some being in place for decades. In parallel in 2009, the European Commission extended the periodic Land Use/Land Cover Area Frame Survey (LUCAS) led by EUROSTAT to sample and analyse the main properties of topsoil in EU in order to develop a homogeneous dataset for EU.Both sources of information are needed to support European policies on soil health evaluation. However, a question remains whether the assessment obtained by using soil properties from both monitoring programs (N-SIMS and LUCAS Soil) are comparable, and what could be the limitations of using either one dataset or the other.Conducted in the context of European Joint Programme (EJP) SOIL, this study shows the results of a comparison between N-SIMS and LUCAS Soil programs among 12 different EU member states including BE, DE, DK, EE, ES, FR, DE, HU, IT, NL, PL, SE and SK. The comparison was done on: (i) the sampling strategies including site densities, land cover and soil type distribution; (ii) the statistical distribution of three soil properties (organic carbon, pH and clay content); (iii) two potential indicators of soil quality (i.e. OC/Clay ratio and pH classes). The results underlined substantial differences in soil properties statistical distributions between N-SIMS and LUCAS Soil in many member states, particularly for woodland and grassland soils, affecting the evaluation of soil health using indicators. Such differences might be explained by both the monitoring strategy and sampling or analytical protocols exposing the potential effect of data source on European and national policies. The results demonstrate the need to work towards data harmonization and in the light of the Soil Monitoring Law, to carefully design the future of soil monitoring in Europe taking into account both LUCAS Soil and N-SIMS considering the significant impact of the monitoring strategies and protocols on soil health indicators.

Migration and natural attenuation of leachate pollutants in bedrock fissure aquifer at a valley landfill site

Groundwater pollution from valley type landfills is concerning, and natural attenuation by contaminants is increasingly relied upon. However, the reliability of natural attenuation in such complex sites has been called into question due to incomplete understanding of their attenuation mechanisms. Therefore, we conducted field investigations, monitoring analyses, mathematical statistics, and machine learning techniques to elucidate the natural attenuation mechanisms of pollutants within bedrock fissures at a prototypical valley type landfill located in the east Yanshan Mountains, China. Our results indicate that 50% of the monitored indicators showed extreme pollution in bedrock fissure aquifers, due to seepage from the valley type landfill site. Ammonia nitrogen, arsenic, cadmium, lead, iron, manganese, and mercury were among the contaminants that could pose serious risks to human health. Pollutant concentrations in bedrock fissure aquifers were lower during the rainy season compared to the dry season as the aquifer was rapidly recharged by strong rainfall runoff. The initial concentration of bedrock fissure water generally increased during the flow through the landfill. However, significant natural attenuation of total dissolved solids, oxygen consumption, ammonia, cadmium, and lead occurred after passing through the landfill (p<0.05), with attenuation coefficients of 0.0041 m-1, 2.56×E-5m-2, 4.18×E-5m-2、0.0015 m-0.99, and 6.83×E-33m-12.49, respectively. The driving mechanisms for natural attenuation include physical migration, leaching, microbiological degradation, and adsorption, primarily occurring within 600-650 m downstream of the landfill boundary. This study makes fundamental contribution to the understanding of the migration and natural attenuation process of leachate pollutants in bedrock fissure aquifer, which will provide a scientific basis for implementation of natural attenuation strategies in complex site remediation. Future research should examine more precise evidence of natural attenuation feasibility in complex sites in conjunction with monitoring networks.

Seasonal Variation of (Benzo[a]Pyrene) in Ambient Air of Urban to Peri-urban Areas of Panvel Municipal Corporation, Raigad with Reference to Particulate Matter

Polyaromatic Hydrocarbons (PAHs) in the environment have been linked to severe health effects. This study aims to assess the atmospheric pollutant and analyze the variation in PAHs, focussed on benzo[a]pyrene [B(a)P]. Among all PAHs, B(a)P is regarded as a marker for human carcinogenicity. This study reflects the B(a)P concentration and its correlation with the particulate matter (PM10 and PM2.5) in rural, peri-urban, and urban areas of Panvel Municipal Corporation, Maharashtra, India. Samples were collected during the pre &amp; post-monsoon season for two consecutive years (Yr. 2020 and Yr. 2021). B(a)P level was determined using high-performance liquid chromatography coupled with a diode array detector. It was observed that PM2.5 and PM10 show a strong positive correlation (r=0.8-0.9) with B(a)P. It is observed that B(a)P concentrations were high in pre-monsoon w.r.t. post-monsoon, and this concentration increased spatially as we moved from rural to urban areas. Pre-monsoon B(a)P concentration varies somewhat by 5% between rural to urban areas as compared to post-monsoon. High levels of vehicular emissions and industry were associated with the distribution of B(a)P in urban areas, whereas a combination of local emissions and metropolitan area diffusion was responsible for the presence of B(a)P in peri-urban and rural areas. Also, this study captures the variation of B(a)P levels during the period of COVID-19. In future studies, Artificial Intelligence (AI) can augment the determination of PAHs in soil by improving the accuracy and speed of analysis using predictive modeling based on different input parameters to determine outliers in soil PAH data, building sensor networks for real-time monitoring of PAH levels, leverage robotics for automated sample preparations, and rapid testing of samples to identify hotspots.

Load Recognition With Few-Shot Transfer Learning Based on Meta-Learning and Relational Network in Non-Intrusive Load Monitoring

Load Recognition With Few-Shot Transfer Learning Based on Meta-Learning and Relational Network in Non-Intrusive Load Monitoring

Dynamic Inner Canonical Variate Network for Incipient Fault Monitoring

Dynamic Inner Canonical Variate Network for Incipient Fault Monitoring

Establishing a Remote Area Network for an Automation System: A Case Study of Yeni Karpuzlu Drinking Water Automation

Yeni Karpuzlu is a town located in the Ipsala district of Edirne province. The drinking water needs of this town are supplied from a deep water well. Water is pumped from the deep well using a submersible pump and sent to a 500-m 3 capacity concrete water tank. Here, the water goes the town's water demand through natural flow. The water is then sent from the tank, which is located 30 meters above ground level, to the town. There is a distance of 800 meters between the well and the tank, and 6000 meters between the tank and the control center located in the town. A local network has been established using outdoor access points for communication between the industrial control devices located at these three points. Data from the instruments are collected at a speed of 300mbps. Additionally, it is sent to the video center via IP cameras for area security. All devices on this network communicate with each other and are controlled. This paper will discuss the operation of the automation system mentioned above. Operations include the pump operation based on tank levels, pressure control using an adjustable valve to maintain network pressure, and monitoring and control operations from the central unit.

A dataset of meteorological, moisture, and soil monitoring indicators for the national agricultural green development environmental monitoring network in Quzhou County (2021&amp;ndash;2023)

A dataset of meteorological, moisture, and soil monitoring indicators for the national agricultural green development environmental monitoring network in Quzhou County (2021&amp;ndash;2023)

Seasonal Patterns, Inter‐Annual Variability, and Long‐Term Trends of Mean Sea Level Along the Western Iberian Coast and the North Atlantic Islands

AbstractSea level rise is challenging for coastal communities and land management decision makers. Understanding the patterns of regional variations at different temporal and spatial scales is key to implement adaptation plans that mitigate the local impacts of sea level rise. In this study, in situ observations from 14 tide gauges were complemented with satellite altimetry data to assess seasonality, multidecadal variability and long‐term trends in mean sea level around the Western Iberian Coast (WIC) and the Portuguese archipelagos (Azores and Madeira). Results show varying spatial seasonal patterns between regions, with minimum (maximum) sea level observed in April (September) at the islands and minimum (maximum) observed in July (November) at the WIC. The influence of coastal upwelling on the seasonal mean sea level variations was detected over mainland. Although the influence of atmospheric patterns was observed on sea level inter‐annual variability, the Atlantic Multidecadal Oscillation (AMO) showed a greater correlation with the sea level inter‐decadal patterns. Finally, the trend analysis confirmed widespread sea level rise along the mainland and around the islands, which has intensified in recent decades. The regions of La Coruña and Cascais showed trends that were similar to the global average sea level rise since 1993, but the mainland regional average pointed to lower rates of rise (2.00 ± 0.06 mm/year). This work reinforces the need for long‐term monitoring networks of sea level, ensuring the vertical stability of instruments and platforms. The implementation of regional adaptation plans to sea level rise is deeply dependent on high quality information.

Tidally modulated seismic velocity changes observed using submarine dark fiber and the virtual-source method

Natural cyclical stress perturbations, including wet and solid earth tides, coupled with repeatable seismic monitoring approaches, provide a tool for understanding the elastic properties of rocks at depth. Ocean tides, in particular, perturb the overburden and pore pressure, affecting hydraulic and elastic rock properties. The recent emergence of distributed acoustic sensing (DAS) and seismology using existing dark telecom fiber offers an unprecedented opportunity to instrument the seas and oceans with seismic monitoring networks of large aperture, fine spatial resolution, and broadband sensitivity. We use a submarine dark-fiber array to methodologically assess whether the changes in seafloor seismic velocities are modulated by ocean tidal loading. Considering oceanic ambient noise (AN) in the frequency range between 1 and 5 Hz, we find it possible to retrieve reliable surface-wave estimates using relatively short time windows (approximately 60 min). Next, using the power of linear arrays to capture AN energy from the stationary-phase zones and AN processing techniques commonly used in DAS applications for subsurface monitoring in urban settings, we introduce a methodological approach to turn each segment of dark fiber into a short-offset monitoring array (2 km), providing redundant, hourly, surface-wave estimates. Using four days of AN data recorded by the Monterey Accelerated Research System (MARS) 20 km section offshore cable, we generate the virtual-source gathers for 10 segments spanning the whole MARS cable. We then use virtual-source data from one segment to estimate the hourly velocity changes that are then quantitatively compared with the tidal data. The results suggest that changes in seafloor seismic velocities are likely modulated by tidal height, even in regions without large tidal excursions. This advance demonstrates a new application of submarine telecom fibers for monitoring the seismic stress response of near-seafloor sediments.

Deep Convolutional Neural Network Algorithm Based on Optical Sensors and Wireless Mobile Networks for Real time Monitoring of Physical Health

Deep Convolutional Neural Network Algorithm Based on Optical Sensors and Wireless Mobile Networks for Real time Monitoring of Physical Health

Geographic Location, Population Dynamics, and Fruit Damage of an Invasive Citrus Mealybug: The Case of Delottococcus aberiae De Lotto in Eastern Spain.

The invasive mealybug Delottococcus aberiae De Lotto (Hemiptera: Pseudococcidae) has rapidly spread in the Mediterranean basin since its detection in 2009 in the Valencia Community in eastern Spain. The use of sticky traps baited with its sex pheromone, (4,5,5-trimethyl-3-methylenecyclopent-1-en-1-yl)methyl acetate, has allowed to determine the geographical distribution of D. aberiae by means of the surveillance network described in the present work. The population monitoring of the pest over a five-year period (2019-2023) has revealed an increase from 31% to 70% of the affected citrus-growing area. The monitoring network has also allowed a better understanding of the pests' biological cycle throughout the year. The populations start growing from March to June and reach their maximum in July-August. During autumn, there is a gradual decline in the population. Although the highest annual populations were detected in 2022 and 2023, the greatest crop losses were recorded in 2020 and 2021, with mean values near 18%. Data suggest that the damage responsible for fruit deformation, and thus the economic losses, are related to the population levels in spring (April-May) rather than those in summer (July-August). The findings of this study can be valuable for future research and development of effective pest control strategies.

Integrating AI enhanced remote sensing technologies with IOT networks for precision environmental monitoring and predicative ecosystem management

Detection of hazardous substances in the environment is paramount in safeguarding human health and ecosystems. With the continuous advancement of technology, artificial intelligence (AI) has emerged as a promising tool in the development of sensors capable of efficiently detecting and analyzing these substances. Environmental monitoring, modeling, and management are very essential for gaining a deeper insight into the fundamental processes and methodologies employed in handling environmental transformations. Hence, the objective of this study is to investigate recent progress in the utilization of AI, sensors, and IoT devices for monitoring environmental pollution, while considering the challenges associated with predicting and monitoring these variations due to the dynamic nature of the environment. The integration of these systems is actively revolutionizing environmental monitoring and enhancing our understanding of how to implement a comprehensive approach to the management of natural resources and ecological processes that are crucial for our societal, economic, and cultural well-being. Consequently, we are able to uncover the transformative impact of this collaborative effort on our comprehension of Earth, as it tackles obstacles, conducts in-depth analysis of long-term environmental data monitoring, and lays the foundation for a promising future.

Datadog with Zigbee Wireless Communication Network Protocol for an Internal Implementation in an Educational Institution

Wireless Sensor Networks are the most powerful technique for monitoring Environmental factors. As the role of WSN relies totally on the service life of the sensor nodes, it is necessary to have complete monitoring of networks. Energy efficiency has always been a key concern for Wireless sensor networks. This paper presents a detailed literature review that examines how an artificial intelligence networking tool(datalog)can be used with ZIGBee-based network protocol for continuous Real-time data quality monitoring to detect bad data quality issues in an educational organization It also Tracks and improves application speed by following requests from beginning to end and monitoring application performance. By using AI algorithms for routing choices and optimization methods, the study aims to improve network performance, energy efficiency, and system scalability. The analysis of different routing strategies with AI implementations will be covered, emphasizing the potential advantages and challenges of this innovative approach in an organization.

FiberFlex: Real-time FPGA-based Intelligent &amp; Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This paper proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing FPGA high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing, and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on 5 test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 watts of power, 33 watts in the optical DAS system, and 22 watts in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let's use fiber optic touch instead.