Monitoring System For Detection Research Articles

Hyperspectral imaging for early identification of strawberry leaves diseases with machine learning and spectral fingerprint features

Anthracnose and gray mold are two most devastating diseases of strawberries which can spread to healthy plants in short time and can cause large-scale yield losses worldwide. However, early identification of anthracnose and gray mold in strawberries is challenging due to that they rise fast and their course is short. Early identification of anthracnose and gray mold in strawberries is of great significance for managing strawberry production, achieving precise target spraying, avoiding the large-scale spread of disease as well as improving the yield and quality of strawberries. In this study, six machine learning-aided methods were developed based on the selected spectral fingerprint features for early identification of anthracnose and gray mold in strawberries using a hyperspectral imaging system. First, infection strawberry leaf dataset was artificially prepared by an expert, and the hyperspectral images (during the spectrum range of 400–1000 nm) of heathy, anthracnose-infected and gray-mold-infected leaves (149 of each type), and fungus-infected leaves respectively had three stages of infection (24 h:43; 48 h:47; 72 h:59). Second, the full spectra of ROI were extracted, and chemometric methods in spectral domain were used to explore the spectral fingerprint features for early identification of anthracnose and gray mold with machine learning. Third, six classification models for identification of anthracnose and gray mold in strawberries were developed, and the classification performance were evaluated and compared. For early detection of anthracnose and gray mold in strawberries, most classification models obtain relatively good accuracy (100%) and robust performance, recognizing the asymptomatic fungus infections classes before the obvious signs of disease appear notably in the strawberry. This study provides a foundational basis for the development of the rapid online inspection as well as the real-time monitoring system for field plant disease detection.

Vision-based in-situ monitoring system for melt-pool detection in laser powder bed fusion process

A low-cost, lateral off-axis non-IR imaging system is proposed to inspect the melt-pool in the Laser Powder Bed Fusion (L-PBF) processing of IN718 powder and stainless steel 316 L powder. In the proposed system, a perspective transformation method is applied to transform the captured side-view image into a top-view image and the melt-pool boundary is then determined based on an inspection of the gray-level intensity profile of the captured image and its first derivative. For the IN718 L-PBF process, the measurement results obtained for the melt-pool width and melt-pool length vary by no more than 13% and 3%, respectively, from the experimental results reported in the literature. For the SS316L, the measured melt-pool width is within 6% of the ex-situ measurements obtained by optical microscopy, while the melt-pool length differs by no more than 9% from the numerical predictions. Overall, the results show that the proposed system provides a viable means of detecting potential build failures during the L-PBF process and improving the yield of the fabrication process as a result.

Innovative Carbon-Doped Composite Pavements with Sensing Capability and Low Environmental Impact for Multifunctional Infrastructures

Recently, smart composites that serve as multi-functional materials have gained popularity for structural and infrastructural applications yielding condition assessment capabilities. An emerging application is the monitoring and prediction of the fatigue of road infrastructure, where these systems may benefit from the ability to detect and estimate vehicle loads via weigh-in-motion (WIM) sensing without interrupting the traffic flow. However, off-the-shelf applications of WIM can be improved in terms of cost and durability, both on the hardware and software sides. This study proposes a novel multi-functional pavement material that can be utilized as a pavement embedded weigh-in-motion system. The material consists of a composite fabricated using an eco-friendly synthetic binder material called EVIzero, doped with carbon microfiber inclusions. The composite material is piezoresistive and, therefore, has strain-sensing capabilities. Compared to other existing strain-sensing structural materials, it is not affected by polarization and exhibits a more rapid response time. The study evaluates the monitoring capabilities of the novel composite according to the needs of a WIM system. A tailored data acquisition setup with distributed line electrodes is developed for the detection of moving loads. The aim of the paper is to demonstrate the sensing capabilities of the newly proposed composite pavement material and the suitability of the proposed monitoring system for traffic detection and WIM. Results demonstrate that the material is promising in terms of sensing and ready to be implemented in the field for further validation in the real world.

A sustainable IoHT based computationally intelligent healthcare monitoring system for lung cancer risk detection

A sustainable healthcare focuses on enhancing and restoring public health parameters thereby reducing gloomy impacts on social, economic and environmental elements of a sustainable city. Though it has uplifted public health, yet the rise of chronic diseases is a concern in sustainable cities. In this work, a sustainable lung cancer detection model is developed to integrate the Internet of Health Things (IoHT) and computational intelligence, causing the least harm to the environment. IoHT unit retains connectivity continuously generates data from patients. Heuristic Greedy Best First Search (GBFS) algorithm is used to select most relevant attributes of lung cancer data upon which random forest algorithm is applied to classify and differentiates lung cancer affected patients from normal ones based on detected symptoms. It is observed during the experiment that the GBFS-Random forest model shows a promising outcome. While an optimal accuracy of 98.8 % was generated, simultaneously, the least latency of 1.16 s was noted. Specificity and sensitivity recorded with the proposed model on lung cancer data are 97.5 % and 97.8 %, respectively. The mean accuracy, specificity, sensitivity, and f-score value recorded is 96.96 %, 96.26 %, 96.34 %, and 96.32 %, respectively, over various types of cancer datasets implemented. The developed smart and intelligent model is sustainable. It reduces unnecessary manual overheads, safe, preserves resources and human resources, and assists medical professionals in quick and reliable decision making on lung cancer diagnosis.

Analytics in Extracting Intelligence from IoT-Based Sensors in Transportation, Healthcare and Natural Gas Detection

Networking of sensors and the development of sensor systems have become routine technological endeavors. The advent of Internet-of-Things (IoT) technologies has enabled an expanding matrix of applications for integration of specialized sensor systems. The focus on innovation is now on driving costs down, while increasing performance. Additive manufacturing techniques and topological improvements are key drivers of innovation for sensors.As sensors and sensor systems transform their capabilities from (strictly) data generation and gathering, the focus now shifts on how to increase the utility of the sensor and sensor system.SensorComm defines the utility of a sensor as its ability to provide intelligence. Intelligence comes from the collection of data. Through data-analytics, information can be extracted. The final step of interpreting the information is through the generation of intelligence. Off-the-shelf tools are available that include machine learning, artificial intelligence, and even toolboxes in platforms like MATLAB, all of which have changed the way we obtain information. The next step is obtaining the intelligence.SensorComm has applied this methodology of intelligence extraction in three areas: 1) transportation 2) healthcare and now 3) natural gas monitoring/detection.In transportation, we will describe how intelligence is obtained from SensorComm’s IoT-based mobile pollution monitoring system. Installed at the tailpipe, Wi-NOx™ captures the real-time pollution footprint of vehicles. The system extracts, analyzes and transforms NOx emissions data into real-time information providing transportation managers with business intelligence that leads to operational efficiencies and measurable savings. Wi-NOx™ is the cornerstone of a global pollution mitigation strategy that enables fuel savings, emissions reduction, vehicle optimization and extended asset life (to responsibly delay significant infrastructure investments like electrification).The Wi-NOx™ system was developed to monitor emissions from vehicles. Recently, we have modified it to remotely monitor patients in healthcare applications, and now, to monitor natural gas for oil & gas applications.In healthcare, Sensorcomm has developed a wrist-worn temperature monitoring system for COVID-19 detection using the Data-Centric Care™ model. Data-Centric Care™ focuses on data to provide the necessary intelligence to correctly assess the situation. The system uses (near) continuous temperature monitoring of individuals to identify at-risk persons who may or may not be symptomatic (for COVID-19 and beyond). The system uses a smart wearable device (wrist-worn) that monitors temperature as a trigger for second-tier screening from which a corresponding response is implemented (e.g. return to daily activity, isolate, elevated care). The continuous monitoring allows for the development of individualized thresholds (average temperature and fever threshold) rather than using population thresholds. The system identifies at-risk individuals (people with anomalies in their daily temperature profiles) for additional screening, prior to entering a facility.The most recent development at SensorComm is the partnership with the Center for Micro-Engineered Materials at the University of New Mexico, who is developing mixed-potential methane sensors using additive manufacturing. Mitigating environmental effects and financial costs of methane leaks requires a robust, widely deployable, low-cost sensing technology to provide continuous monitoring of natural gas infrastructure. Since methane emissions originate from multiple sources (agricultural or wetlands sites), sensors need to distinguish between natural gas or one of these other sources. Strategies for gathering the data, extracting the information and providing intelligence will be discussed.This talk will discuss the different techniques utilized in the data analytics and will provide key examples of how intelligence is extracted in the various applications.This material is based upon work supported by the U.S. Department of Energy, National Energy Technology Office program under Award Number DE-FOA-0031864, and partially by the National Science Foundation under Grant No. 1632498. Figure 1

Utilization of Micro-Doppler Radar to Classify Gait Patterns of Young and Elderly Adults: An Approach Using a Long Short-Term Memory Network.

To develop a daily monitoring system for early detection of fall risk of elderly people during walking, this study presents a highly accurate micro-Doppler radar (MDR)-based gait classification method for the young and elderly adults. Our method utilizes a time-series of velocity corresponding to leg motion during walking extracted from the MDR spectrogram (time-velocity distribution) in an experimental study involving 300 participants. The extracted time-series was inputted to a long short-term memory recurrent neural network to classify the gaits of young and elderly participant groups. We achieved a classification accuracy of 94.9%, which is significantly higher than that of a previously presented velocity-parameter-based classification method.

A Survey on Ship Detection Technology in High-Resolution Optical Remote Sensing Images

Objectives: Ship detection in large-scale, high-resolution optical remote sensing images, especially in visible spectral remote sensing images, plays an important role in both military and civilian fields. It has always been an on-going and challenging research topic in the past decades, due to the complexity and variability of the backgrounds, the multi-scale, multi-type, and multi-posture diversity of ship targets. Methods: In order to promote the development of ship detection based on high-resolution optical remote sensing images (HRORSI), this paper provides an overview of existing study on ship detection methods of HRORSIover the past decades. We start by introducing all the existing monitoring systems for ship detection, but subsequently focus only on HRORSI. Then, a number of topics have been discussed in this paper, including the methodology system, the development history, the recent state of the art detection methods, detection datasets and metrics. Results: It is shown that current ship detection methods based on deep learning in HRORSI, have greatly expanded the adaptability of the complexity of the detection scene and the variation of the target distribution, and the speed and accuracy of the results have been greatly improved.It is also found that different influence factors make a big difference in choosing the corresponding ship detection models. Conclusions: Existing methods from different perspectives such as extracting richer features, multi-level and multi-scale feature fusion, more accurate target locating, scale aware ship detection, have made vigorous performance.However, there is still a big gap between efficient and intelligent ship interpretation in actual complex applications.We suggest that the future ship detection methods should adaptively support a variety of backgrounds, scales and optical sensors; the detection model can be effectively transfer to out-distributed target domain scenarios as well as resource-constrained scenarios; and more in-depth target recognition capabilities.

Design of IoT-Based Home Fire Detection System Equipped with a Data Logger

In Industrial Era 4.0, one of the solutions to secure a house from potential fires is to design a smart home. The smart home design described in this paper is the design of a home monitoring system for potential fires. Home fire early detection monitoring system is designed based on the IoT concept and is equipped with a data logger. Data loggers function as data logging and data recorders from time to time. The hardware system design consists of Arduino Mega2560, ESP8266, fire sensor, gas sensor and datalogger module as data storage. The software design that also functions as a system monitoring display is the Blynk application on Android smartphones. Fire sensor and gas sensor activities were recorded on the data logger module. The system test was carried out around the gas stove in the kitchen room. The system design results were displayed via the Blynk application on a smartphone. Fire detection system is a change in the Virtual Button from the initial color to red. While the monitoring display of the gas detection system is in the form of moving the Virtual Level when a gas leak is detected. Fire sensor activity recording data from the datalogger is displayed in the form of a graph of the relationship of the working voltage of the fire sensor versus time. While the data recording of gas sensor activity from the datalogger is displayed in the form of a graph of the relationship of gas concentration versus time. All system response results and graphic data are displayed in realtime through the Blynk application on a smartphone. In addition, system performance data records are stored on a micro SD card for further analysis. From the results of the design of this system is expected to be a reference of home monitoring technology from potential fire equipped with a data storage system.

Railway Vehicle Wheel Flat Detection with Multiple Records Using Spectral Kurtosis Analysis

The gradual deterioration of train wheels can increase the risk of failure and lead to a higher rate of track deterioration, resulting in less reliable railway systems with higher maintenance costs. Early detection of potential wheel damages allows railway infrastructure managers to control railway operators, leading to lower infrastructure maintenance costs. This study focuses on identifying the type of sensors that can be adopted in a wayside monitoring system for wheel flat detection, as well as their optimal position. The study relies on a 3D numerical simulation of the train-track dynamic response to the presence of wheel flats. The shear and acceleration measurement points were defined in order to examine the sensitivity of the layout schemes not only to the type of sensors (strain gauge and accelerometer) but also to the position where they are installed. By considering the shear and accelerations evaluated in 19 positions of the track as inputs, the wheel flat was identified by the envelope spectrum approach using spectral kurtosis analysis. The influence of the type of sensors and their location on the accuracy of the wheel flat detection system is analyzed. Two types of trains were considered, namely the Alfa Pendular passenger vehicle and a freight wagon.

PotSpot: Participatory sensing based monitoring system for pothole detection using deep learning

Proper maintenance of roads is an extremely complex task and also an important issue all over the world. One of the most critical road monitoring and maintenance activities is the detection of road anomalies such as potholes. Identification of potholes is necessary to avoid road accidents, prevent damage of vehicles, enhance travelling comforts, etc. Although maintenance of roads is considered to be a serious issue by the authorities over the years, lack of proper detection and mapping of road potholes makes the issue more severe. To overcome this problem, an end-to-end system called PotSpot is built for real-time detection, monitoring, and spatial mapping of potholes across the city A Convolutional Neural Network (CNN) model is proposed and evaluated on real-world dataset for pothole detection. Additionally, real-time pothole-marked maps are generated with the help of Google Maps API (Application Programming Interface). To provide an end-to-end service through this system, both the pothole detection and pothole mapping are integrated through an android application. The proposed model is also compared with six baselines namely Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and three pre-trained CNN models InceptionV3, VGG19 and VGG16 in terms of performance metrics to verify its effectiveness. The proposed model achieves better accuracy (≈ 97.6 %) as compared to the above-mentioned baseline methods. It is also observed that the Area Under the Curve (AUC) value for the proposed pothole detection model (AUC= 0.97) is higher than the baseline methods.

Real-World Performance of a Self-Operated Home Monitoring System for Early Detection of Neovascular Age-Related Macular Degeneration.

The real-world performance of a home telemonitoring strategy (ForeseeHome AMD Monitoring System®, Notal Vision, Inc.,Manassas VA, USA) was evaluated and compared to the device arm of the AREDS2-HOME study among patients with intermediate AMD (iAMD) who converted to neovascular AMD (nAMD). All patients with confirmed conversion to nAMD who used the home monitoring system from 10/2009 through 9/2018 were identified by Notal Vision Diagnostic Clinic’s medical records. Selected outcome variables were evaluated, including visual acuity (VA) at baseline and at conversion, and change in visual acuity (VA) from baseline to time of conversion. In total, 8991 patients performed 3,200,999 tests at a frequency of 5.6 ± 3.2 times/week. The 306 eyes that converted from iAMD to nAMD over the study period (a 2.7% annual rate) were included in the analyses. There was a median (interquartile range) change of −3.0 (0.0–(−10.0)) letters among converted eyes, 81% [95% confidence interval (72–88%)] maintained a VA ≥ 20/40 at the time of conversion, while 69% of the conversion detections were triggered by system alerts. The real-world performance of an at-home testing strategy was similar to that reported for the device arm of the AREDS2-HOME study. The home telemonitoring system can markedly increase early detection of conversion to nAMD.

Remote Health Patient Monitoring System for Early Detection of Heart Disease

This paper presents a heart disease prediction model. Among the recent technology, internet of things-enabled healthcare plays a vital role. The medical sensors used in healthcare provide a huge volume of medical data in a continuous manner. The speed of data generation in IoT healthcare is high so the volume of data is also high. In order to overcome this problem, the proposed model is a novel three-step process to store and analyze the large volumes of data. The first step focuses on a collection of data from sensor devices. In Step 2, HBase has been used to store the large volume of medical sensor data from a wearable device to the cloud. Step 3 uses Mahout for devolving logistic regression-based prediction model. At last, ROC curve is used to find the parameters that cause heart disease.

Intelligent monitoring system for biogas detection based on the Internet of Things: Mohammedia, Morocco city landfill case

Mechanization is a depollution activity, because it provides an energetic and ecological response to the problem of organic waste treatment. Through burning, biogas from mechanization reduces gas pollution from fermentation by a factor of 20. This study aims to better understand the influence of the seasons on the emitted biogas in the landfill of the city Mohammedia. The composition of the biogas that naturally emanates from the landfill has been continuously analyzed by our intelligent system, from different wells drilled in recent and old waste repositories. During the rainy season, the average production of methane, carbon dioxide, and oxygen and nitrogen are currently 56%, 32%, and 1%, respectively, compared to 51%, 31%, and 0.8%, respectively, for old waste. Hazards levels, potential fire, and explosion risks associated with biogas are lower than those of natural gases in most cases. For this reason a system is proposed to measure and monitor the biogas production of the landfill site remotely. Measurement results carried out at various sites of the landfill in the city of Mohammedia by the system show that the biogas contents present dangers and sanitary risks which are of another order.

Monitoring System for Early Detection of Fire in Wetlands based Internet of Things (IoT) using Fuzzy Methods

In Indonesia, especially the province of South Kalimantan is a province with a high frequency of forest and wetland fires. These fires seem to be a routine annual natural disaster. BNPB (National Disaster Management Agency) and BPBD (Regional Disaster Management Agency) Central Kalimantan recorded that during 2014 to early 2019, the largest area of forest and wetlands fires in Central Kalimantan occurred in 2015 with a total burned area of 583,833.44 ha. The fire early detection monitoring system that will be made based on Arduino Uno uses the MQ-2, DHT-22 sensor, and flame detector sensor and is integrated with the Thingspeak IoT, which functions to receive data sent from the Arduino Uno microcontroller using the ESP8266 module, then Thingspeak will send the data to an Android smartphone in the form of a real-time display and also a pop-up notification when a potential fire is detected. Finally, the fuzzy method is also added so that later the reading data from the MQ-2, DHT-22, and flame detector sensors will be more accurate before being sent to Thingspeak. The level of accuracy obtained from the readings of the three sensors against the tests that have been carried out is 90%.

The Working Principles of a Multifunctional Bondline with Disbond Stopping and Health Monitoring Features for Composite Structures

In comparison to bolted joints, structural bonds are the desirable joining method for light-weight composite structures. To achieve a broad implementation of this technology in safety critical structures, the issues of structural bonds due to their complex and often unpredictable failure mechanisms have to be overcome. The proposed multifunctional bondline approach aims at solving this by adding two safety mechanisms to structural bondlines. These are a design feature for limiting damages to a certain size and a structural health monitoring system for damage detection. The key question is whether or not the implementation of both safety features without deteriorating the strength in comparison to a healthy conventional bondline is possible. In previous studies on the hybrid bondline, a design feature for damage limitations in bondlines by means of disbond stopping features was already developed. Thus, the approach to evolve the hybrid bondline to a multifunctional one is followed. A thorough analysis of the shear stress and tensile strain distribution within the hybrid bondline demonstrates the feasibility to access the status of the bondline by monitoring either of these quantities. Moreover, the results indicate that it is sufficient to place sensors within the disbond stopping feature only and not throughout the entire bondline. Based on these findings, the three main working principles of the multifunctional are stated. Finally, two initial concepts for a novel multifunctional disbond arrest feature are derived for testing the fundamental hypothesis that the integration of micro sensors into the disbond stopping feature only enables the crack arrest and the health monitoring functions, while reaching the mechanical strength of a conventional healthy epoxy bondline. This work therefore provides the fundamentals for future investigations in the scope of the multifunctional bondline.

A cloud-based condition monitoring system for fault detection in rotating machines using PROFINET process data

This work presents a methodology for a cloud-based condition monitoring system for fault detection and identification in rotating machines, such as uncoupling, angular and parallel misalignment, by data mining PROFINET network and PROFIdrive profile process data. The proposed methodology involves a new strategy for feature selection of unsupervised data set and employs SVM (Support Vector Machine) and OCSVM (One-Class Support Vector Machine) for operation status classification. The present diagnostic system represents a low-cost solution to the manufacturing process of small and medium enterprises, because it does not require dedicated sensors for fault detection and high featured hardware, and it employs an online cloud-based services. The experimental tests resulted in an accuracy between 87.5% and 100%, and high robustness among different operating conditions. In addition, the proposed feature selection strategy reduced the total execution time by 97.5%.

Experimental investigation of damage detection on structures with friction stir welding (FSW) junctions

A Structural Health Monitoring system for damage detection is proposed in this paper. The Probability Ellipses method (PE) is a non-destructive method based on Guided waves. This method estimates a global index called Damage Index (DI), that represents a way to measure how much critical is the related sensing-path (actuator-sensor). The DI is high when the damage is closer to the sensing-path and it increases again when the damage severity grows. The work is being developed in the framework of the Clean Sky 2 specifically for More Affordable Small Aircraft Manufacturing (SAT-AM) project, whose main goal is the development of new technologies to be employed in the development of next generation of small aircrafts category responding to CS/FAR-23 certification specification Rules. The Friction Stir Welding (FSW) is one of key technologies to reduce cost, time and manufacturing costs. Conversely, the low historical data on structural degradation of FSW joints require a conservative approach during design stage. A possible answer to the lack of structural knowledge behavior could be overpassed by using structural health monitoring system that periodically evaluates the born of any criticalities of the FSW structures. Preliminary experimental investigations of the ET method, applied to structures with Friction Stir Welding (FSW) junctions, are illustrated. Aluminum panels were joined with FSW technique and damage was produced in the junctions. The structures were instrumented with piezoelectric actuators and sensors. The Guided waves were acquired on both undamaged and damaged configurations and the PE method was applied to identify the damage position.

IOT Based Driver Drowsiness Detection and Health Monitoring System

IOT Based Driver Drowsiness Detection and Health Monitoring System

Construction and Experimental Verification of Novel Online Partial Discharge Monitoring System Using Power Line Communication

In this research, we aim to construct a completely new partial discharge (PD) monitoring system that applies inexpensive power line communication (PLC). We have proposed a PD detection method and monitoring system (PDMS-PLC) on the basis of PLC signal transfer rare is affected by an error due to disturbance. An attempt is made to identify PD source from the quadrant dependence of information transmission rate (hereinafter referred to PHY rate [Mbps]) by selecting a pair of quadrants of applied voltage phase; i.e. 1st and 3rd quadrants, or 2nd and 4th ones. It was found that the PHY (Abbreviation for the lowest physical layer in the OSI (open systems interconnection) hierarchical model.) rate number distribution reflects the PD characteristics obtained by the phase resolved PD (PRPD) pattern. Environmental noise level is also measured at an actual substation using PDMS-PLC. Consequently, the applicability of PDMS-PLC to PD signal detection and defect type identification is suggested.

Design and Fabrication of Temperature-Insensitive MEMS Pressure Sensor Utilizing Aluminum-Silicon Hybrid Structures

In order to meet the requirements for high sensitivity and low temperature drift of pressure sensors in the field of meteorological detection or tire pressure monitoring system (TPMS), this paper proposes a MEMS chip-level pressure sensor based on two pairs of aluminum-silicon hybrid structures, which are etched on the SOI wafer. The pressure sensor achieves the amplified piezoresistive effect by the micron thick ohmic contact between the boron-doped silicon and external aluminum shunt, as verified by finite element numerical simulation and experiment. Four symmetrical L-shaped raised structures are distributed around the square strained membrane, which enhance the stress of the pair of stress-sensitive aluminum-silicon hybrid structures. The other pair of hybrid structures placed outside the strained membrane of the sensor chip enables differential sensor output which is highly insensitive to temperature. The offset drift of differential output is reduced to −4.39%FS compared with that of single aluminum-silicon hybrid structure. Cooperated with temperature compensation structures, an additional thermodynamic control system by using PID algorithm to keep the working temperature stable can eliminate the temperature drift of sensor output. The feasibility of the thermodynamic control system is verified by steady-state thermal simulation. Experiment test results show that the sensitivity of a single aluminum-silicon hybrid structure can reach 0.283 mV/V/kPa at constant heating temperature of 50 °C, and whose thermal coefficient of offset (TCO) can be reduced from −6.92E-1 to −1.51E-3 %FS/°C in ambient temperature ranges of −20 to 50 °C.