Real-time Data Collection System Research Articles

GIS Constructed Water Monitoring Network System Via IOT

Monitoring the quality of water plays a vital role in the advancement towards intelligent and smart agriculture. It also facilitates the seamless transition to automated monitoring of essential components of human daily needs, as new technologies continue to be developed and adopted in both agricultural and human daily life, particularly in relation to water. Assessing water stress requires accurate measurement of water usage [1]. The objective of this study is to optimize the distribution strategy and achieve more efficient and rapid distribution, while also making better use of technology to address the urgent need for water conservation. One of the criteria for the second filtering phase, which utilized a realtime data collection system, focused on the implementation of water quality monitoring and characterization methods. Water measurement sensors and the Internet of Things (IoT) can provide immediate information on water flow and pressure rates. This information is crucial for the analysis and surveillance of water [2]. At the RCEW campus, online smart water monitoring is imperative to ensure a more efficient and sustainable use of water. By combining the Internet of Things and geographic information systems (GIS), an online smart water monitoring prototype was developed specifically for RCEW [3]. This cutting-edge technology has proven to be highly successful in providing real-time information on water parameters, saving both time and money, while enabling the continuous study of water consumption patterns. This innovative technology seamlessly integrates IoT and GIS for effective water surveillance [4,5].

Using machine learning to assist decision making in the assessment of mental health patients presenting to emergency departments

Objective The objective of this study was to assess the predictability of admissions to a MH inpatient ward using ML models, based on routine data collected during triage in EDs. This research sought to identify the most effective ML model for this purpose while considering the practical implications of model interpretability for clinical use. Methods The study utilised existing data from January 2016 to December 2021. After data pre-processing, an exploratory analysis revealed the non-linear nature of the dataset. Six different ML models were tested: Random Forest, XGBoost, CatBoost, k-Nearest Neighbours (kNN), Explainable Boosting Machine (EBM) using InterpretML, and Support Vector Machine using Support Vector Classification (SVC). The performance of these models was evaluated using various metrics including the Matthews Correlation Coefficient (MCC). Results Among the models evaluated, the CatBoost model achieved the highest MCC score of 0.1952, demonstrating superior balanced accuracy and predictive power, particularly in correctly identifying positive cases. The InterpretML model also performed well, with an MCC score of 0.1914. While CatBoost showed strong predictive capabilities, its complexity poses challenges for clinical interpretation. Conversely, the InterpretML model, though slightly less powerful, offers better transparency and is more practical for clinical use. Conclusion The findings suggest that the CatBoost model is a compelling choice for scenarios prioritising the detection of positive cases. However, the InterpretML model's ease of interpretation makes it more suitable for clinical application. Integrating explanation methods like SHAP with non-linear models could enhance model transparency and foster clinician trust. Further research is recommended to refine non-linear models within decision support systems, explore multi-source data integration, understand clinician attitudes towards ML, and develop real-time data collection systems. This study highlights the potential of ML in predicting MH admissions from ED data while stressing the importance of interpretability, ethical considerations, and ongoing validation for successful clinical implementation.

A demographic and qualitative analysis of the determinants of success in a National Supported Employment project.

People with an intellectual disability and/or autism experience low employment rates compared to the general population. This study shows what the determinants of success are in getting this group of young people into paid employment. The research is based on data collected on 1008 young people, aged 16-25, participating in the Engage to Change project across Wales, to support young people to achieve employment. A real-time data collection system was used from their engagement and throughout their journey to employment. This research indicates an overall employment rate of 23% for the project to date, based on total referral. Young people who engaged in 'significant work experience', such as paid placement or supported internship, had a greater employment rate of 37%. Previous and current real work experiences increased the chances of young people of becoming employed, above the effect of supported employment and job coach support.

Implementing 21st century "end-to-end" and technology-enhanced care for young people.

Implementing 21st century "end-to-end" and technology-enhanced care for young people.

A comparison of instrument response correction methods: Post-processing and real-time methods

Industrial vibration monitoring often requires sensors with adjustable sensitivity and suitable frequency range. In practice, most industrial studies utilize either geophones (velocimeters) or accelerometers. In some cases, where low frequency content is of interest, larger sensor will be required. In difficult installation conditions, it can be advantageous to utilize smaller, higher frequency sensor elements (geophones or accelerometers) to simplify installation and maintenance. A frequency correction of sensors or the recorded waveforms will be needed to accommodate the frequency range of interest. Most accelerometers have relatively smaller sensitivity at low frequency which can affect the calculation of vibration velocity and displacement at low frequencies. Geophones are limited by their frequency response, which drops-off significantly their sensitivity below the resonant frequency of the sensor. Structural and ground vibrations that occur under the resonant frequency could be observed at test sites, but the recorded waveforms cannot be used directly for real-time assessment, and therefore it can be beneficial to artificially expand the frequency range below the sensor's frequency cutoff. Methods for such expansion, were developed and are well established in seismological studies and exploratory geophysics. Usually, these procedures are applied in data post-processing. These methods are not applicable when an operator requires real-time feedback of the measured vibrational amplitude, for example, monitoring of machinery foundations, where excitation control is necessary to avoid infrastructure damage.This paper presents an approach for instrument frequency extension in the necessary low-frequency range of common geophone elements in real-time applications and compares the results of the proposed technique in post-processing and in real time data collection systems.

Evaluation of an electronic health record structured discharge summary to provide real time adverse event reporting in thoracic surgery

BackgroundThe reporting of adverse events (AE) remains an important part of quality improvement in thoracic surgery. The best methodology for AE reporting in surgery is unclear. An AE reporting system...

Early Operational Experience at a One-million Tonne CCS Demonstration Project, Decatur, Illinois, USA

After four years of site-specific work, carbon dioxide (CO2) injection began at the Illinois Basin Decatur Project (IBDP) in Decatur, Illinois USA on 17 November 2011. The IBDP is a demonstration project in one of the Regional Carbon Sequestration Partnerships (Phase III) funded by the US Department of Energy. Work at IBDP was preceded by two years of regional basin studies and identification of a CO2 source located optimally with respect to a major saline reservoir, the Mount Simon Sandstone, believed capable of safely and effectively containing gigatonne-scale quantities of sequestered CO2 in the Illinois Basin of Illinois, southwestern Indiana, and western Kentucky, USA. Early operational experience has been a function of reservoir properties and the infrastructure put in place to demonstrate carbon capture and storage (CCS). Development of the site included construction of a compression/dehydration facility and a 1.9km pipeline, drilling of three wells, and development of a real-time data collection system to monitor operational parameters. As of 11 October 2012, 288,000 tonnes of dense-phase (supercritical) CO2 have been injected, and injection continues at a rate of 1,000 tonnes per day.

Inter-rater reliability of data elements from a prototype of the Paul Coverdell National Acute Stroke Registry.

BackgroundThe Paul Coverdell National Acute Stroke Registry (PCNASR) is a U.S. based national registry designed to monitor and improve the quality of acute stroke care delivered by hospitals. The registry monitors care through specific performance measures, the accuracy of which depends in part on the reliability of the individual data elements used to construct them. This study describes the inter-rater reliability of data elements collected in Michigan's state-based prototype of the PCNASR.MethodsOver a 6-month period, 15 hospitals participating in the Michigan PCNASR prototype submitted data on 2566 acute stroke admissions. Trained hospital staff prospectively identified acute stroke admissions, abstracted chart information, and submitted data to the registry. At each hospital 8 randomly selected cases were re-abstracted by an experienced research nurse. Inter-rater reliability was estimated by the kappa statistic for nominal variables, and intraclass correlation coefficient (ICC) for ordinal and continuous variables. Factors that can negatively impact the kappa statistic (i.e., trait prevalence and rater bias) were also evaluated.ResultsA total of 104 charts were available for re-abstraction. Excellent reliability (kappa or ICC > 0.75) was observed for many registry variables including age, gender, black race, hemorrhagic stroke, discharge medications, and modified Rankin Score. Agreement was at least moderate (i.e., 0.75 > kappa ≥; 0.40) for ischemic stroke, TIA, white race, non-ambulance arrival, hospital transfer and direct admit. However, several variables had poor reliability (kappa < 0.40) including stroke onset time, stroke team consultation, time of initial brain imaging, and discharge destination. There were marked systematic differences between hospital abstractors and the audit abstractor (i.e., rater bias) for many of the data elements recorded in the emergency department.ConclusionThe excellent reliability of many of the data elements supports the use of the PCNASR to monitor and improve care. However, the poor reliability for several variables, particularly time-related events in the emergency department, indicates the need for concerted efforts to improve the quality of data collection. Specific recommendations include improvements to data definitions, abstractor training, and the development of ED-based real-time data collection systems.

Real-time Speed Limit Sign Recognition Based on Locally Adaptive Thresholding and Depth-First-Search

Road inventory for a highway includes a variety of traffic signs, such as stop signs and speed limit signs, pavement width, lane number, and others. This article describes a current research project being undertaken by the Georgia Department of Transportation to re-engineer and streamline the existing road inventory data collection process, in order to develop a real-time data collection system that is accurate, efficient, and safe. The authors present an algorithm for recognizing speed limit signs (SLS) from video imaging and extracting the numerical numbers of SLS to support real-time road inventory data collection operations. The algorithm consists of color segmentation based on locally adaptive thresholding extraction of regions of interest (ROI) using a depth-first-search algorithm, followed by speed limit sign detection and speed limit number extraction by means of optical character recognition and 2D correlation. The average processing time for an image of 1200 x 800 pixels is about 125 ms. Experimental results from 1,401 video images show 0 percent false positives out of 1,278 images containing no SLS, and 3 percent false negatives out of 123 images containing SLS. Signs that are tilted up to 15 degrees and surrounded by white and non-white backgrounds can be correctly detected independent of lighting conditions. Partly shadowed, partly blocked, or severely blurred SLSs (due to a fast-moving camera) would not be correctly detected.

Partners for child passenger safety: a unique child-specific crash surveillance system

Insurance claims data were combined with telephone survey and on-site crash investigation data to create the first large scale, child-focused motor vehicle crash surveillance system in the US. Novel data management and transfer techniques were used to create a nearly real-time data collection system. In the first year of this on-going project, known as Partners for Child Passenger Safety, over 1200 children ≤15 years of age per week were identified in crashes reported to State Farm Insurance Co. from 15 states and Washington, D.C. Partners for Child Passenger Safety is similar in its design and overall objectives to National Automotive Sampling System (NASS), the only other population-based crash surveillance system currently operating in the US.

Control of complex manufacturing processes: a comparison of SPC methods with a radial basis function neural network

Manufacturing processes are increasingly subject to tighter control and more frequent monitoring, in many cases using real time data collection systems. It is now recognized that complex interactions of auto and cross-correlation exist in data observations from process industries, batch processes, and the traditional parts industry. New control models that capture both multivariate and time series effects are needed to effectively monitor manufacturing processes. In this research, we investigate the ability of radial basis function neural networks to monitor and control complex manufacturing processes that exhibit both auto and cross-correlation. We demonstrate that the radial basis function network is superior to three control models recently proposed for complex manufacturing processes: multivariate Shewhart, multivariate EWMA, and a feed forward neural network with logistic units trained by back-propagation (often called a back-propagation neural network).

The accident consequence tree method and its application by real-time data collection in the finnish furniture industry

The identification of accident consequences is of great importance in cost calculations. Various classifications of consequences have been published, but there is a need to develop them further. The Accident Consequence Tree (ACT) Method was developed on the basis of the fault tree method for calculating accident costs. With the aid of the consequence tree it is possible to identify the consequences that an accident causes to the injured person, the company and to the national economy. The consequence tree consists of 128 branches altogether. The ACT Method was applied to workplace accidents which were followed during the course of 12 months in 18 Finnish furniture factories of different sizes and production types. A real-time data collection system was organized. The foremen were trained to fill out the follow-up form. The foremen and injured persons were interviewed by the researchers. The 214 accidents registered were lost-time injuries; there were no permanent disabilities. The accidents caused a total of 4300 identified consequences according to the ACT Method, on an average 20 consequences per accident. Every accident resulted in an injury, temporary disability, future production loss, medical treatment, and loss of company productivity. Lost production time was the most notable consequence to the companies. The accidents caused 472 visits to health care centres, on average 2.2 visits per accident. Two accidents led to hospitalization. As the material consisted only of temporary disabilities, this must be taken into account when generalizations are being made. Permanent disabilities and fatalities do occur and they probably cause more losses. Theoretically an accident process should include one additional phase — a consequence phase.

A real-time data collection system for problem-solving protocols

A computer program was developed to collect solution protocols with written explanations, with a level of detail difficult to obtain with traditional pencil-and-paper tasks. The program automatically presents the instructions, problems, solution entered, changes to the solution, explanation prompts, solution feedback, and system help in a Windows environment. The time to make each move and type each explanation is recorded, making it possible to compare solution times across treatment groups. Protocols are stored in individual ASCII files, eliminating transcription, and a summary data set for all protocols is created. The program was tested in a study where individual protocols were collected in small groups. This program can readily be adapted to different experimental contexts and can be a useful educational tool.

A computer-automated laboratory for studying complex perception-action skills

In this paper, we describe a computer-based laboratory for collecting and analyzing real-time performance and eye-movement data by using video game-like tasks. These tasks assess skills that require the integration of varying numbers of perception and action components. Customized hardware and software are described for configuring tasks, collecting data, reconstructing performance, and organizing, editing, and reducing data. General design considerations are emphasized for solving several of the problems encountered in constructing a real-time data collection system. The paper concludes with examples of data that illustrate the system’s usefulness for studying complex perception-action skills.

ReDS—A dynamic planning, scheduling, and control system for manufacturing

Abstract Classical scheduling theory has not solved the practical needs of factory management. Management objectives are often many, ill-defined, and changing. Management is generally interested in decision support tools to facilitate specification of changed objectives, to react to shop floor changes, and to make short and long-term planning decisions. This paper describes a dynamic, intelligent, real-time factory scheduling system known as Requirements Driven Scheduling (ReDS). ReDS combines Artificial Intelligence (AI) and Operational Research (OR) techniques to find solutions that are not always optimal but are acceptable to the changing needs of management. ReDS uses a number of techniques such as least commitment planning and abstraction in order to make a plan. To optimize the allocation of resources, heuristics are applied from order and shop-floor points of view. ReDS works in time and event-driven modes of operation. ReDS uses real-time data for two purposes; short term feedback to reconfigure the current schedule, and long-term feedback to adjust heuristics. Using this feedback, ReDS can automatically conform the factory in which it operates. An essential partner for ReDS operation is a data collection and equipment monitoring system. The results of coupling ReDS to a real-time data collection system in a VLSI development line are encouraging. The data collection system receives data from and returns instructions to the shop floor.

Temperature, pressure and film thickness measurements for an offset half bearing

A fluid film journal bearing test rig with a shaft, 70 mm in diameter, was developed and an offset half journal bearing was tested at five vertical loads and two rotational speeds. The bearing had a length-to-diameter ratio of 1.00, a pre-load factor of 0.51 and an offset factor of 1.0. Loads from 0 to 4450 N and speeds of 2250 and 1650 rev min −1 were tested. On-rotor instrumentation and amplification are used to measure continuous fluid film pressures around the bearing, film thicknesses and journal temperatures. Slip ring telemetry is used to transmit the data to a real time data collection system. External instrumentation is used to measure film pressures and temperatures in discrete locations on the bearing surface, thus, allowing comparison with the on-shaft measurements. The eccentricity ratio and attitude angle are pressure measurements obtained indicate agreement within 5% between the results recorded by the on-shaft and the external pressure transducers. The experimental film thickness, temperature and pressure profiles and journal eccentricity agree with the expected behavior for this bearing type and are presented for Sommerfeld numbers from 0.41 to 2.2.

Feeding behavior responses of Zucker rats to naloxone

The effects of naloxone on feeding patterns were studied in both obese and lean Zucker rats during both light and dark phases of the diurnal cycle. Eight female obese (471±9 g) and lean (225±6 g) Zucker rats were trained to bar press for food. They were administered 0, 0.5, 1.0 or 2.0 mg/kg naloxone at the initiation of the light or dark phase of the diurnal cycle and feeding behavior was recorded for the subsequent 12 hr using an automated real-time data collection system. First meal size and duration were decreased and first postmeal interval was increased by naloxone and responses did not vary with phenotype or phase of the diurnal cycle. Naloxone decreased food intake during the 12-hr period by decreasing average meal size but meal frequency was not affected. Overall, the feeding behavior responses of obese rats to naloxone were greater than those of lean rats, supporting the hypothesis of an association between opioid peptides and obesity. Opioid involvement in diurnal control of food intake is also supported by the greater responses generally demonstrated in the light compared with dark phases.

On-line simulation of solar systems heating

This paper deals with the programming of a minicom puter system which is connected to a small solar heating system to create a model of a larger solar heating system. The program enables the computer to serve as an on-line control and real-time data col lection system. The small solar heating system is heavily instrumented to provide dynamic input data to the computer. The output of the computer program simulates the operation of a much larger solar heat ing system. This combination of software with the hardware has proven to be a broadly useful research tool for solar-heating investigations. This paper describes both aspects of the simulation model.