Automatic Warning System Research Articles

Assessment of harmful gases emission and its impact using IoT and geospatial technology

Numerous industries in our daily lives use a variety of dangerous chemical gases, and workers are frequently exposed to these gases. The losses due to harmful gases can be reduced by developing an automatic harmful gases detection and alerting system. This study aims to design, develop, and implement an automatic warning system using series of gas sensors to deduct. The designed system is implemented to monitor 3 locations to detect the hazardous pollutions parameters, namely Large-Scale industries, wood burning sites and residential housings and analysed to understand the pollution level. This study observed elevated temperatures (35–45 °C) and heat index (30–50 °C) in large-scale industries, along with higher harmful gases compared to wood-burning sites and homes. Interestingly, wood-burning sites exhibited higher humidity (60–70 %) and peak ozone and methane levels compared to other locations. These variations underscore the unique environmental characteristics of each site, emphasizing the need for tailored monitoring and safety measures.

Increasing the prospective capacity of global crop and rangeland monitoring with phenology tailored seasonal precipitation forecasts

Droughts are more and more often a limiting factor to agricultural production and can have severe negative effects on food security in vulnerable countries. Global agriculture early warning systems monitor agriculture in near real-time by analyzing meteorological data (e.g. precipitation and temperature) and optical remote sensing data as proxy vegetation health to detect possible negative anomalies and trigger warnings. Seasonal climate forecast can add a predictive component and inform about upcoming precipitation deficits, thus allowing anticipation and improved planning of response actions. Here, we propose a scheme to adapt the standard precipitation forecast from the seasonal Copernicus Climate Change Service multi-system to crop and rangeland phenology, making them suitable for agricultural early warning. Precipitation forecasts are first elaborated into tercile maps showing the probability of the most likely tercile (i.e. drier than normal, normal, wetter than normal) and associated skills of all possible monthly periods combinations included in the six months forecasting horizon. Afterwards, agronomically relevant tercile maps are produced for the closest season in time at any location. These maps are obtained by mosaicking the forecasts for the appropriate growing season period at each grid cell. The resulting map shows the tercile probability for the remaining part of the ongoing growing season (if any at time of analysis) or the probability of the next upcoming season (if in between growing season at time of analysis). The proposed methodology offers a precipitation seasonal forecast product ready to use by agricultural analysts and directly ingestible by automatic warning systems.

RESEARCH ON WIDE SPECTRUM FULL-COLOR NIGHT VISION ELDERLY FACIAL VIDEO HEART RATE AUTOMATIC MEASUREMENT AND WARNING SYSTEM

In recent years, the prevalence of cardiovascular diseases has been growing geometrically, especially among the elderly. Real-time heart rate monitoring becomes an effective measure for preventing cardiovascular diseases. Traditional contact-based real-time heart rate measurement methods require long-term wearing of contact electrodes, which can cause inconvenience to the elderly population. In this study, a wide spectrum full color night vision elderly face video heart rate automatic measurement and early warning system was designed and developed by combining imaging photoplethysmography (IPPG), video acquisition equipment based on starlight wide spectrum camera and high-speed face recognition signal processing algorithm based on deep learning. By constructing a software and hardware platform, a comprehensive evaluation of the system’s application in elderly facial video heart rate measurement experiments was conducted.

Developing an automatic warning system for anomalous chicken dispersion and movement using deep learning and machine learning

Chicken is a major source of dietary protein worldwide. The dispersion and movement of chickens constitute vital indicators of their health and status. This is especially evident in Taiwanese native chickens (TNCs), a local variety which is high in physical activity when healthy. Conventionally, the dispersion and movement of chicken flocks are observed in patrols. However, manual patrolling is laborious and time-consuming. Moreover, frequent patrols increase the risk of carrying pathogens into chicken farms. To address these issues, this study proposes an approach to develop an automatic warning system for anomalous dispersion and movement of chicken flocks in commercial chicken farms. Embendded systems were developed to acquire videos of chickens from overhead view in a chicken house, in which approximately 20,000 TNCs were raised for a period of 10 wk. Each video was 5-min in length. The videos were transmitted to a remote cloud server and were converted into images. A You Only Look Once-version 7 tiny (YOLOv7-tiny) object detection model was trained to detect chickens in the images. The dispersion of the chicken flocks in a 5-min long video was calculated using nearest neighbor index (NNI). The movement of the chicken flocks in a 5-min long video was quantified using simple online and real-time tracking algorithm (SORT). The normal ranges (i.e., 95% confidence intervals) of chicken dispersion and movement were established using an autoregressive integrated moving average (ARIMA) model and a seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) model, respectively. The system allows farmers to check up on the chicken farm only when the dispersion or movement values were not in the normal ranges. Thus, labor time can be saved and the risk of carrying pathogens into chicken farms can be reduced. The trained YOLOv7-tiny model achieved an average precision of 98.2% in chicken detection. SORT achieved a multiple object tracking accuracy of 95.3%. The ARIMA and SARIMAX achieved a mean absolute percentage error 3.71% and 13.39%, respectively, in forecasting dispersion and movement. The proposed approach can serve as a solution for automatic monitoring of anomalous chicken dispersion and movement in chicken farming, alerting farmers of potential health risks and environmental hazards in chicken farms.

Pedestrian Safety and Early Warning System Based on Green Energy

In Taiwan, pedestrians are run over by vehicles often in many intersectionsdue to poor lighting or lack of traffic lights. Thus, we developed a green energy-driven automatic warning system to ensure the safety of drivers and pedestrians. A variety of sensing modules, such as Hall sensors and coil loops, were used in the system to detect approachingvehicles. When an approaching vehicle was detected, the LED warning light warned pedestrians and drivers. In addition, according to data released by the government, sensors or detectors were set up at a sufficient distance from the crosswalk to ensure that the vehicle could stop before it reached the sidewalk. In the system, green energy was used to ensure that the entire system was operated for a long time and reduced energy consumption. It was verified that the proposed system could be used in various environments such as suburbs or remote intersections to improve safety.

Driving Alert System based on Facial Expression Recognition

Abstract: Inattention is one of the major factors and causes of many road accidents and unforeseen crashes. As a result, it is vital to develop an automatic warning system for drivers, which will send timely warning signals to them. Based on the driver's facial expressions, this issue involves determining the driver's mental state. In applications such as driver warning systems, automated facial emotion recognition has become a recent development in the image processing world. There are existing methods for recognizing facial emotions regardless of whether the signal is noisy or imperfect data, but ultimately it lacks accuracy. It is also useless and not getting proper output in dealing with spontaneous feeling, and recognition. The proposed approach develops a driver warning system that extracts the facial expressions based on a novel efficient Local Octal Pattern (LOP) and effectively recognizes the facial expressions based on Deep Neural Networks, Convolutional Neural Networks (CNN). The LOP feature map provides as an input to CNN and guides in the selection of CNN learning data thereby improving and further enhancing the understanding and learning of CNN. It also has an ability to recognize both natural and spontaneous feeling, considered input as a image as well as video. The experimental results considering YawDD dataset indicates that the proposed system has been efficiently evaluated by considering the with metrics such as Precision, Recall and F-Score and thereby it is observed and inferred that the proposed system obtained a high recall rate of 96.09% in comparison with the other state-of-the-art methods

Методика оценивания оперативности информационного обеспечения автоматизированных систем предупреждения об опасных ситуациях в околоземном космическом пространстве

This article presents the structure and content of the main stages of the methodology for assessing the efficiency of information support for automated warning systems about dangerous situations in near-Earth outer space when observing space objects in high orbits by optical means of observing outer space with the use of a software and hardware information collection complex. Problem statement: development of a technique for detecting deviations of space objects from the calculated orbits of their movement by ground-based means of observing outer space, taking into account various options for constructing orbital groupings and a network of ground-based optical means of observation. Results: A methodology has been developed for assessing the efficiency of information support for automated warning systems about dangerous situations in near-Earth outer space, taking into account various ways of organizing an information support system and allowing dynamically evaluating the efficiency of detecting deviations of space objects from calculated orbits. Practical significance: the proposed methodology makes it possible to identify optimal ways of organizing information support for automated warning systems about dangerous situations in near-Earth outer space based on an assessment of the efficiency of detecting deviations of space objects from calculated orbits with dynamic changes in the space environment and the state of operation of space surveillance facilities and to form recommendations for improving information support for automated warning systems about dangerous situations in near-Earth outer space. Discussion: the novelty of the proposed formulation of the problem lies in the fact that the structure of the developed methodology allows us to take into account various ways of organizing the information support system and to build probabilistic estimates of the efficiency of its functioning on the basis of dynamic changes in the space situation and the state of ground-based means of observing outer space.

Technological solutions for the efficient protection of workers in the track area

Abstract: Work on and in the vicinity of active railway tracks or other tracks is particularly hazardous work. They involve high risks for workers who may be hit or run over by moving rail vehicles or track machinery. Workers may also be electrocuted by the overhead catenary or overhead electrical network, which for non-traction purposes is supplied with 3000 volts DC. To ensure an adequate level of safety during this type of work, active tracks should be cordoned off and marked in accordance with railway regulations. Guidelines for securing the site of works carried out on closed track during the operation of railway vehicles on live track at a speed of V ≥ 100 km/h are defined in Railway Instruction Id-18. All types of construction work on live railway lines and overhead contact lines may only be carried out on the basis of the Instruction for Safe Work Performing (IBWR), which is an annex to the Safety and Health Plan (Safety and Health Plan). It is important to remember that the site protection systems used should be certified and approved for use on railway lines. Rail transport is a particularly demanding area in terms of safety. The key to increasing its level is to continue existing and take new measures to promote the idea of safety. Automatic Warning Systems are still an innovative solution in Poland, which has been successfully proven in Europe for several years and is a safer option for the railway signalman. The system is responsible for the safe warning of railway traffic in the area of the repaired and adjacent track. Risks arising due to human fallibility or caused by human error are eliminated to a minimum. Keywords: Technological solutions; Trackway; Railway line

MO357: Nephrology Consultation to Improve Acute Kidney Injury Outcome on General Wards

Abstract BACKGROUND AND AIMS Acute kidney injury (AKI) affects up to one in five hospitalized patients and is independently associated with high morbidity and mortality. Additionally, patients have an increased risk for developing chronic kidney disease (CKD) after AKI. The combined impact of short- and long-term consequences and the high incidence of AKI results in a significant financial burden. Adequate intervention and follow-up might reduce the clinical impact of AKI, however the evidence for this remains inconclusive. The aim of this prospective cohort study was to evaluate whether nephrology consultation had an impact on patient follow-up and clinical outcome after AKI. METHOD All patients, admitted to VU medical centre in Amsterdam between October 2018 and April 2019, were screened for AKI by an automatic warning system integrated into the hospital's electronic patient record. This warning system sent a signal if serum creatinine would rise >27 µmol/L in 48 h or increased by a factor of at least 1.5 within 7 days (KDIGO criteria for AKI). The nephrology or internal medicine resident would then assess eligibility. Exclusion criteria were: a rise in serum creatinine that did not represent an actual AKI, admittance to the intensive care unit at the time of the signal, admission for kidney transplantation and patients that died before consultation was possible. After identification, nephrology consultation was provided. For the least severe AKI cases (KDIGO stage 1), this was done by telephone after review of the patient record, and for severe AKI cases (KDIGO stage 2 and 3) by full clinical review. Patients were grouped according to adherence (consult or no consult) to this protocol. Adequate follow-up was defined as a specific post-AKI referral to a nephrologist or general practitioner after hospital discharge. Recovery of serum creatinine and 6-month mortality were used as primary measures of clinical outcome. RESULTS A total of 371 cases of possible AKI were identified by the warning system. Of those case, 218 cases were eligible for inclusion. In 160 cases, nephrology consultation was performed (consult group). In 58 cases, there was no consult (no-consult group). The average age was 67.4 years. The consult and no-consult groups were similar at baseline (mean age, male/female, incidence of hypertension and diabetes), besides a higher incidence of CKD in the consult group (79% versus 64%; P = 0.034). The consult group had a significantly larger percentage of severe AKI cases (stage 2 or 3 in 29.4% of cases versus 12.1%; P = 0.021). Treatment was initiated in 93.1% of consult cases and in 70.6% of no-consult cases (P < 0.001) and there was a more profound decrease in the serum creatinine level from peak till 6 months (–33.7% versus –19.4%; P = 0.033)). All-cause mortality (34.1% versus 27.6%; P = 0.510), post-AKI follow-up (83% versus 73.2%; P = 0.116) and median serum creatinine value at six months (119 µmol/L versus 100 µmol/L; P = 0.334) did not differ between the consult and no-consult group. A 6-month serum creatinine was only available for 50% of cases in both groups. CONCLUSION When compared with cases of generally less severe AKI in which nephrology consultation was not performed, cases with nephrology consultation were associated with higher rates of treatment of AKI, faster recovery of kidney function and similar mortality. The data are in line with earlier non-randomized research which concluded that nephrology consultation can be linked to improved outcome in AKI. Before any definitive conclusions can be drawn, these associations should be found replicable in a randomized multi-centre setting and cost-effectiveness and feasibility should be analysed.

Method of forest fire automatic early warning and alarm system design

Forest is a huge green wealth bestowed by nature to mankind, but forest fire will cause great harm. Automatic forest fire early warning and alarm system can warn the high fire risk areas in the forest, or find and alarm the forest fire as early as possible, which is of great significance to reduce the loss of forest fire. This paper introduces a construction method of forest fire automatic early warning and alarm system, which provides knowledge and experience accumulation for the subsequent research and development of related systems.

Fatality Prediction for Motor Vehicle Collisions: Mining Big Data Using Deep Learning and Ensemble Methods

Motor vehicle crashes are one of the most common causes of fatalities on the roads. Real-time severity prediction of such crashes may contribute towards reducing the rate of fatality. In this study, the fundamental goal is to develop machine learning models that predict whether the outcome of a collision will be fatal or not. A Canadian road crash dataset containing 5.8 million records is utilized in this research. In this study, ensemble models have been developed using majority and soft voting to address the class imbalance in the dataset. The prediction accuracy of approximately 75% is achieved using Convolutional Neural Networks. Moreover, a comprehensive analysis of the attributes that are important in distinguishing between fatal vs. non-fatal motor vehicle collisions has been presented in this paper. In-depth information content analysis reveals the factors that contribute the most in the prediction model. These include roadway characteristics and weather conditions at the time of the crash, vehicle type, time when the collision happen, road user class and their position, any safety device used, and the status of traffic control. With real-time data based on weather and road conditions, an automated warning system can potentially be developed utilizing the prediction model employed in this study.

Automatic Warning System for Weather Station Power Supply

Weather observation is one of the important factors in agriculture. Data from weather observations can be used for various things, including to predict future risks due to these weather conditions. An Automatic Weather Station (AWS) is needed to read weather conditions continuously. Some of the devices that will be built for the AWS system are data communication, sensors, and power supply. AWS is usually installed in certain areas where there is no power source. Hence, it takes a power supply system that can stand alone and has a security system that can monitor the components connected to the system in real-time.
 This research successfully designed a power supply system for a weather station that is equipped with current and voltage measurement features for its load as well as a warning system feature in case of interference on GSM SIM900-based Weather Station. Based on the results of the study the system using solar cell modules has an efficiency of 14,1% and is supported with the help of batteries that can be recharged through solar energy. Using the INA219 sensor to measure the voltage and load current connected to devices that have an error percentage value of less than 1%, the data is then uploaded to Thingspeak. Testing of warning systems at the Weather Station is conducted using Magnetic reed sensors capable of detecting changes when the separation distance between the sensor and other magnets is more than 3cm.

Design and Application of Automatic Monitoring System of Water Environment Using GIS

in order to achieve more effective management and monitoring of water environment, an automatic monitoring system is designed for the water environment of Heihe River Basin in Zhangye through GIS (geographic information system). The EFDC (environmental fluid dynamics code) model is used to establish the automatic monitoring model of water environment, and the annual average data of permanganate index of Yingluoxia, Gaoya hydrological station, and Liubaqiao in Heihe River Basin from 2015 to 2019 are used to fit and verify the water quality model. The trend suggests that the simulated data of the three observation points are close to the measured data. The fitting degree reveals that the R index of fitting curve of Liubaqiao is 0.793, while that of Yingluoxia, and Gaoya hydrological station is higher than 0.8, with good fitting degree. The average relative error between the simulated value and the measured value of permanganate index (mg/L) is small, the change trend is basically consistent, and the prediction error is small. The model is successfully established and applied to the automatic monitoring and early warning system of total phosphorus index.

Online monitoring of the morphology of an industrial sugarcane biofuel yeast strain via in situ microscopy

In industrial yeast fermentation processes, single-cell yeast suspensions are usually preferable to cells in aggregates, as single cells exhibit a larger contact area with the nutrient medium, which in many cases helps optimize the process. In addition to affecting fermentation time and efficiency, cell aggregates (e.g., pseudohyphal yeast morphology) may also impair centrifugation systems, one of the most expensive and complex steps of the production process that involves the recovery of yeast cells for subsequent fermentation cycles. To date, no standard technique allows for a systematic diagnosis of yeast morphology in real time during sugarcane biofuel fermentation. Accordingly, we investigate an in situ microscope (ISM) for online monitoring of the density and morphology of an industrial Saccharomyces cerevisiae strain widely used in Brazilian distilleries (PE-2). During batch and repeated batch sugarcane molasses fermentation, the instrument revealed single cells, budding yeast cells, and pseudohyphae, all in a variety of sizes and shapes. The ISM image analysis indicated that the volume of single yeast cells increased by roughly 40% over the lag phase before budding and remained approximately constant thereafter. Pseudohyphae with three and more cells appeared mostly during the stationary phase. Cooling problems were simulated by raising the temperature from 33 to 45 °C. During this thermal stress, single cells as well as budding cells and pseudohyphae forming cells became smaller and exhibited intracellular inhomogeneities. From these results, we conclude that an ISM is a useful tool for monitoring yeast morphology during sugarcane fermentation. Atypical morphologies can be detected early and be used as an automatic warning system.

Control and Integration of Automatic Flood Warning and Alert System Using Internet of Things

The information capability of an impending flash flood or release of water from the dam which is available for the people near the catchment area of the river is deficient and unsystematic. Therefore in order to make it sufficient and systematic, information gathering the opening of dams, its capacity and its rapid increase in the level are monitored accurately. The data of the monsoonal shift and the climatic change are merged as the cloud data. The PA system along with the OPGW cables and the GSM based system which are used for making alert for the people in the catchment area gives direction over the elevated region for their safety which in turn saves the life of the people a lot.

Design and Development of Automatic Water Level and Quality Warning System of Latphrao Canal Community Bangkok, Thailand

The objectives of this research were to design and develop an automatic water level warning system for communities living along Khlong Lad Phrao (Lad Phrao Canal) in Bangkok. The development of the system was divided into the following four main parts: 1) a water level measurement system; 2) a precipitation measurement system; 3) a water quality testing system covering dissolved oxygen, pH, turbidity and electrical conductivity and 4) an internet alert system utilizing the LINE application and web-based application information display. The first three parts were to be solar-powered. The design and development effort showed that the system successfully measured water levels along with water quality with speed and precision. Moreover, the system was easy to measure results and was able to alert through the LINE application when water in Khlong Lad Phrao approached critical levels, thereby reducing damage from water levels. Precision testing of the developed water level and quality measurement systems found that precision was in the range of 99.74-99.77%.

Development of Automatic Warning System for Water Salinity in Bangkachao, Thailand

Development of Automatic Warning System for Water Salinity in Bangkachao, Thailand

Assessment of a Smartphone-Based Camera System for Coastal Image Segmentation and Sargassum monitoring

Coastal video monitoring has proven to be a valuable ground-based technique to investigate ocean processes. Presently, there is a growing need for automatic, technically efficient, and inexpensive solutions for image processing. Moreover, beach and coastal water quality problems are becoming significant and need attention. This study employs a methodological approach to exploit low-cost smartphone-based images for coastal image classification. The objective of this paper is to present a methodology useful for supervised classification for image semantic segmentation and its application for the development of an automatic warning system for Sargassum algae detection and monitoring. A pixel-wise convolutional neural network (CNN) has demonstrated optimal performance in the classification of natural images by using abstracted deep features. Conventional CNNs demand a great deal of resources in terms of processing time and disk space. Therefore, CNN classification with superpixels has recently become a field of interest. In this work, a CNN-based deep learning framework is proposed that combines sticky-edge adhesive superpixels. The results indicate that a cheap camera-based video monitoring system is a suitable data source for coastal image classification, with optimal accuracy in the range between 75% and 96%. Furthermore, an application of the method for an ongoing case study related to Sargassum monitoring in the French Antilles proved to be very effective for developing a warning system, aiming at evaluating floating algae and algae that had washed ashore, supporting municipalities in beach management.

Research on design and implementation of pedestrian red light automatic early warning system based on face recognition

Research on design and implementation of pedestrian red light automatic early warning system based on face recognition

Effect of nonpharmacological interventions for the prevention of delirium in the intensive care unit: A systematic review and meta-analysis

PurposeWe aimed to classify nonpharmacological interventions used for preventing delirium in the intensive care unit (ICU), and estimate their effect size. Materials and methodsIn this systematic review and meta-analysis, the literature was searched and studies were selected based on the PRISMA flow chart. Data sources included MEDLINE, Cochrane, CINHAHL, PsyInfo, and EMBASE. We used Cochrane's Effective Practice and Organisation of Care (EPOC) criteria in study design and quality assessment of the meta-analysis. ResultsThis systematic review and meta-analysis included 35 and 15 studies, respectively. Studies were grouped into nine intervention types: multicomponent (16 studies), physical environment (9), daily interruption of sedation (2), exercise (2), patient education (2), automatic warning system (1), cerebral hemodynamics improving (1), family participation (1), and sedation reducing protocol (1). The effect size of preventive nonpharmacological interventions had an odds ratio (OR) of 0.66 (95% confidence interval [CI], 0.50–0.86) for delirium occurrence, and an OR of 0.31 (95% CI, 0.10–0.94) for delirium duration. Although relevant studies by interventions were lacking, a partial subgroup analysis by intervention was performed. ConclusionsNonpharmacological interventions were effective in reducing the duration and occurrence of delirium. Consistent application and development of nonpharmacological interventions for use in the ICU are important.