A new perspective on real-time monitoring and function interpretation of nitrification based on machine learning and mass-to-charge fingerprint.

Nowadays, researches on real-time monitoring system have developed greatly. This research is intended to develop a real-time water pressure monitoring system on water distribution networks. Pressure monitoring is very important in assuring the availability of water supply to the community. Therefore, it is reasonable to develop a web-based real-time water monitoring system which is more efficient and easier to use.This system utilized MPX5700AP as sensor to measure water pressure and Arduino UNO as system’s performance control center with GSM/GPRS Shield application enabling the system to communicate with the server through GSM/GPRS network. This system was designed by applying C Arduino, HTML, PHP, and SQL as programming languages.Result of the evaluations indicated system prototype operated well. System was able to measure water pressure and displaying graphics and data of the measurement on the webpage.

ObjectivesThis study aimed to develop and evaluate a real-time sensor-based monitoring and feedback system for enhancing four core football performance metrics, passing accuracy, sprint speed, agility, and shot power, each defined and quantified using validated wearable sensors and baseline‐referenced improvement thresholds.MethodsA randomized controlled trial (RCT) was conducted over eight weeks with 30 university-level male football players (aged 21.70 ± 1.28 years) from Zhengzhou University. Participants were randomly assigned to an experimental group (n = 15), which trained using the real-time monitoring system, or a control group (n = 15), which followed traditional training methods. The wearable system integrated accelerometers, gyroscopes, and magnetometers to provide real-time, skill-specific feedback during drills. Performance data were collected weekly and analyzed using repeated measures ANOVA with effect sizes calculated via partial eta squared (η²p).ResultsThe results demonstrated statistically and practically significant improvements in the experimental group across all measured parameters. Notably, the effect sizes ranged from large to very large (η²p = .59 to.89), indicating that the improvements were not only statistically reliable but also substantial enough to have meaningful impact on the players’ performance. Passing accuracy increased by 10.21% (F(1,27) = 210.02, p < 0.001, η²p = .88), sprint speed improved by 17.33% (F(1,27) = 92.00, p < 0.001, η²p = .76), agility improved by 10.90% (F(1,27) = 41.75, p < 0.001, η²p = .59), and shot power increased by 10.75% (F(1,27) = 247.32, p < 0.001, η²p = .89). The control group showed negligible or negative changes in all performance metrics. Performance improvements in the experimental group were progressive and sustained across the 8-week training period, with weekly data showing steady gains in passing accuracy, sprint speed, agility, and shot power. No performance regressions or plateaus were observed during the intervention period.ConclusionBy delivering instantaneous, sensor-validated feedback on precisely defined performance metrics, the system accelerated improvements in both technical and physical skills. These findings support the integration of wearable sensor technology into football training to achieve data-driven, individualized skill development. Future work should explore AI-driven personalization and long-term retention of gains.

ABSTRACTAmmonium (NH4+) is an important nitrogen (N) source for plant growth. Nevertheless, NH4+–N can be oxidized to nitrate (NO3−) by nitrification and then nitrate and nitrite can be leached into groundwater. The aims of this study were to investigate the effect of the water bicarbonate concentration, pH, and the presence, or not, of a nitrification inhibitor, on the nitrification process. Six treatments were established, changing the pH and the bicarbonate concentration, with or without the nitrification inhibitor. The results showed that an active nitrification process occurred in treatments with high pHs (8 and 7) and with no nitrification inhibitors. This causes an increase in the nitrate and nitrite concentration in the substrate. The use of N–NH4+ fertilizers joint to a nitrification inhibitor, especially in nutritive solutions with a high concentration of bicarbonate and a pH of 8 and 7, decreases nitrate and nitrite accumulation in substrate which can prevent nitrate and nitrite leaching.

Effects of commonly used nitrification inhibitors—dicyandiamide (DCD), 3,4-dimethylpyrazole phosphate (DMPP), and nitrapyrin—on soil nitrogen dynamics and nitrifiers in three typical paddy soils

Real-time crop harvest data acquisition from harvesters during harvesting operations is an important way to understand the distribution of crop harvest in the field. Most real-time monitoring systems for grain yield using sensors are vulnerable to factors such as low accuracy and low real-time performance. To address this phenomenon, a real-time grain yield monitoring system was designed in this study. The real-time monitoring of yield was accomplished by adding three pairs of photoelectric sensors to the elevator of the corn kernel harvester. The system mainly consists of a signal acquisition and processing module, a positioning module and a visualization terminal; the signal acquisition frequency was set to 1 kHz and the response time was 2 ms. When the system operated, the signal acquisition and processing module detected the sensor signal duration of grain blocking the scrapers of the grain elevator in real-time and used the low-potential signal-based corn grain yield calculation model constructed in this study to complete the real-time yield measurement. The results of the bench tests, conducted under several different operating conditions with the simulated elevator test bench built, showed that the error of the system measurement was less than 5%. Field tests were conducted on a Zoomlion 4YZL-5BZH combined corn kernel harvester and the results showed that the average error of measured yield was 3.72%. Compared to the yield measurement method using the weighing method, the average error of the bench test yield measurement was 7.6% and the average error of yield measurement in field trials with a mass flow sensor yield measurement system was 16.38%. It was verified that the system designed in this study has high yield measurement accuracy and real-time yield measurement, and can provide reference for precision agriculture and high yield management.

Real-Time nuclear power plant monitoring by feedforward neural network is described. For the training, standard backpropagation algorithm is used for an auto-associative network structure having 12 inputs/outputs. After initial training of the network, the real-time process signals are introduced to the network as input and plant status is monitored through the network’s response at the output At the same time the training of the network is performed in adaptive form so that the sensitivity of the network’s failure detection sensitivity is enhanced in the course of the operation. The real-time monitoring system considered is primarily for the Borssele nuclear power plant (NPP) from which signals are available on-line with a sophisticated data acquisition system [1]. The neural network uses a three-layered feedforward structure with 7 nodes in the hidden layer. Standard backpropagation algorithm with sigmoidal nonlinearity is used for training and adaptive learning. All input and output data are so normalized that the range extends from 0.1 to 0.9. The program is coded in FORTRAN and executed at VAX-4200. For initial training 1850 patterns covering start-up, steady-state and shut-down are used, so that the wide-range operation of the plant is considered. After the initial learning, real-time monitoring and adaptive learning starts to progress. The fault severity level (εf) that is, measured and estimated signals difference normalized by related range, is taken to be 0.1. The schematic block diagram of the monitoring system is shown in Fig.l where εmax is the error bound used during the training as well as in real time. To illustriate the training and real-time monitoring system’s performance, the results obtained from a process signal is given in Fig.2. The detailed description of this study is presented elsewhere [2].

Until now, the meteotsunamis reported in the Yellow Sea have been caused by sudden pressure disturbances; however, no suitable monitoring system has been established for these disturbances. With the maximum available pressure data based on 89 automatic weather stations (AWS), a real-time pressure disturbance monitoring system was developed for meteotsunami disaster prevention. When a pressure disturbance calculated from a rate of pressure change exceeds 1.2 hPa/10 min at a certain AWS, the monitoring system detects the occurrence of a pressure jump that can generate meteotsunamis in the Yellow Sea. The real-time monitoring system is operated by sending a short message service to hazard areas where destructive meteotsunamis are expected to occur by monitoring the intensity of the pressure disturbance and its propagation direction. During the pilot test from March to April 2018, the monitoring system detected four pressure jump events in total, two of which caused meteotsunamis. On the two meteotsunami event dates, the monitored pressure disturbances exceeded the intensity criteria for a common pressure jump and showed similar propagation patterns with the meteotsunamis. In particular, both meteotsunami events occurred only when the pressure jump, spatially characterized as a linear or bow type, propagated at least 12 m/s. Despite the limited number of events during the pilot test, this study provides an example of a meteotsunami-monitoring system and implications for additional pressure jump conditions favorable to meteotsunami occurrence.

Real-time indoor monitoring systems (RTIMS) are a key component of modern technological infrastructures in smart and automated buildings and facilities. They enable the continuous collection, analysis, and response to environmental data under strict time constraints, ensuring optimal system performance. These systems are designed to operate with high accuracy and low latency, making them essential in situations and events where timely decision-making is critical. Their applications range from industrial automation and production line monitoring to smart cities, smart homes, and healthcare for the elderly and disabled. The significant advances in electronics, communications, and software—particularly in Internet of Things (IoT) technologies and data transfer protocols—are reflected in the diversity of real-time monitoring systems, in terms of the parameters that can be monitored, the control and command systems that can be used, and the actuators that respond to commands. In this paper, the concepts, design, components, and working methods of these systems are discussed in detail. The latest research on real-time indoor monitoring systems published over the past five years is reviewed, resulting in the selection of 143 studies that met the inclusion criteria. This review synthesizes the technologies used for data capture, transmission, processing, storage, and visualization, as well as the approaches employed for alerts and system integration. By presenting these technical insights in a structured manner, the article provides a practical reference for researchers and practitioners aiming to design and implement real-time monitoring systems more efficiently and effectively.

Machine learning-based system for online quantitative monitoring of heavy metals across different aqueous matrices using spectroscopy of plasmas in liquids.

Marathon Oil operates several brownfields in the Rockies, most of which are approaching a producing life of 100 years. Most of the fields are on waterflood, with 86% of the oil production coming from the artificial lift method of electrical submersible pumps (ESPs). This ESP lift method has helped maximize the production of recoverable oil in these fields, achieving higher drawdowns and larger fluid volume handling. Prior to 2010, Marathon's 770 ESPs were operated with out downhole gauges or sensors and no ESP real time systems were in use. This made it difficult to properly monitor the well and the equipment, leading to improperly sized ESPs, limited artificial lift optimization and lost oil production. In 2010 Marathon began installing downhole sensors in all ESP wells that were pulled for either a failure or a workover and download the data into an ESP real-time monitoring, diagnosis and analysis software system. At the time of this paper, Marathon has installed downhole sensors in 430 of the 770 ESP wells. All ESP wells are presently being monitored via the ESP real-time monitoring and analysis software. During this short period of real-time monitoring, Marathon has realized production gains of more than 700 barrels of oil per day (BOPD) in one of the fields. This paper compares previous operations to the results and data from the installation and connection of downhole sensors to the real-time ESP monitoring program. Monitoring methodologies, analysis and proper ESP optimization are detailed in several case studies.

Electric vehicle (EV) development has produced a number of advantages in terms of sustainability and energy efficiency. The dependability and safety of EV systems must still be ensured, though. In-depth study of predictive modeling methods for EV fault finding is provided in this research. The work focuses on the creation and use of defect prediction models utilizing real-time data gathered from EV systems, building on the foundations of predictive analysis and machine learning. The approach for data collecting, preprocessing, feature extraction, and model training is described in detail, with an emphasis on the necessity of reliable and representative data for successful fault diagnosis. Additionally, it analyzes the performance criteria employed for assessing the precision and dependability of these models and illustrates the difficulties in incorporating predictive analytic models into EV designs. The research results illustrate how predictive analysis may be successfully applied to problem detection and diagnosis, highlighting its potential to improve the safety and effectiveness of EV systems. In order to achieve more robust and accurate defect prediction in EVs, the article finishes with insights into future research areas, highlighting the need for more breakthroughs in data gathering techniques, model optimization, and real-time monitoring systems. KEYWORDS—Electric vehicles; predictive analysis; fault detection; machine learning; data collection; data preprocessing; feature extraction; model training; performance metrics; real-time monitoring;

The banking industry is undergoing a significant transformation driven by the integration of data-driven approaches aimed at enhancing customer experience. This evolution is essential for banks to maintain competitive advantage, foster customer loyalty, and adapt to the rapidly changing digital landscape. By leveraging vast amounts of customer data, banks can gain profound insights into customer behavior, preferences, and needs, enabling the delivery of more personalized, efficient, and secure services. This review delves into the key techniques employed in data-driven banking and the consequential outcomes. Advanced data analytics allows banks to segment their customer base into distinct groups based on demographics, behaviours, and financial needs. Techniques such as machine learning algorithms and clustering identify patterns within the data, facilitating the creation of targeted products and services. For instance, digital banking solutions can be specifically designed for tech-savvy millennials, while tailored financial advice might be more suitable for older customers. This segmentation helps in addressing the unique needs of different customer groups more effectively. Utilizing historical data, predictive models can forecast future customer behaviors and trends. This capability enables banks to anticipate customer needs, such as predicting which customers might be interested in applying for a mortgage or those who could benefit from financial advisory services. Predictive analytics also aids in identifying customers at risk of churn, allowing banks to implement retention strategies proactively. Through data-driven insights, banks can offer highly personalized experiences. Recommendation systems, akin to those used by leading e-commerce platforms, suggest relevant financial products and services based on individual customer profiles and transaction histories. This level of personalization not only enhances the customer experience but also increases the likelihood of successful cross-selling and upselling efforts. Employing Natural Language Processing (NLP) and sentiment analysis, banks can analyze customer feedback from various sources, including social media, surveys, and call center interactions. Understanding customer sentiment helps banks promptly address issues, improve customer service quality, and build stronger, positive relationships with their customers. Data-driven approaches are pivotal in identifying and mitigating fraudulent activities. Machine learning models analyze transaction patterns to detect anomalies indicative of fraud. Real-time monitoring systems can flag suspicious activities, thereby protecting customers and maintaining their trust in the banking system. Personalized and proactive service offerings significantly boost customer satisfaction. Customers appreciate tailored experiences and quick resolution of issues, leading to higher levels of satisfaction and increased brand loyalty. Automation of routine tasks and predictive maintenance of customer relationships streamline banking operations. This efficiency reduces the workload on bank staff, allowing them to focus on more complex customer needs, resulting in cost savings and improved service delivery. Predictive analytics and real-time monitoring strengthen risk management capabilities. Banks can better assess credit risks, manage fraud, and ensure compliance with regulatory requirements, thus safeguarding their assets and reputation. Effective targeting and personalization drive increased product uptake and customer retention. Enhanced cross-selling and upselling opportunities contribute to revenue growth and profitability, as banks can better match products to customer needs. Insights derived from customer data inform the development of new products and services tailored to evolving customer needs. This continuous innovation keeps banks competitive in a rapidly changing financial landscape. The integration of data-driven approaches in banking significantly enhances customer experience by providing personalized, efficient, and secure services. The application of advanced data analytics, machine learning, and NLP not only boosts customer satisfaction and loyalty but also drives operational efficiency, improves risk management, and fosters revenue growth. As banks continue to innovate with data-driven strategies, the future of customer experience in banking appears promising and dynamic. The ability to adapt and evolve with technological advancements will be crucial in maintaining a customer-centric focus and staying ahead in the competitive financial sector. Keywords: Data-Driven, Banking, Customer Feedback.

Arnold Engineering Development Center (AEDC) has designed and built a high-speed data acquisition and processing system for real-time online dynamic data monitoring and analysis. The Computer Assisted Dynamic Data Monitoring and Analysis System (CADDMAS) provides 24 channels at high frequency and another 24 channels at low frequency for online real-time aeromechanical, vibration, and performance analysis of advanced turbo-engines and other systems. The system is primarily built around two different parallel processors and several PCs to demonstrate hardware independence and architecture scalability. These processors provide the computational power to display online and in real-time what can take from days to weeks using existing offline techniques. The CADDMAS provides online test direction and immediate hardcopy plots for critical parameters, all the while providing continuous health monitoring through parameter limit checking. Special in-house developed Front End Processors (FEP) sample the dynamic signals, perform anti-aliasing, signal transfer function correction, and bandlimit filtering to improve the accuracy of the time domain signal. A second in-house developed Numeric Processing Element (NPE) performs the FFT, threshold monitoring, and packetizes the data for rapid asynchronous access by the parallel network. Finally, the data are then formatted for display, hardcopy plotting, and cross-channel processing within the parallel network utilizing off-the-shelf hardware. The parallel network is a heterogeneous message-passing parallel pipeline configuration which permits easy scaling of the system. Advanced parallel processing scheduler/controller software has been adapted specifically for CADDMAS to allow quasi-dynamic instantiation of a variety of simultaneous data processing tasks concurrent with display and alarm monitoring functions without gapping the data. Although many applications of CADDMAS exist, this paper describes the features of CADDMAS, the development approach, and the application of CADDMAS for turbine engine aeromechanical testing.

研发了输电线路走廊山火风险实时监测与分析系统，提出结合国内外卫星遥感影像数据分析的山火风险评估模型。将该系统成功的应用于湖北电网输电线路山火风险评估，实现了湖北电网范围内的输电线路不同区域的风险分级，应用结果表明，本系统通过互联网技术和卫星遥感，专家系统，大数据挖掘等多重手段，有效的获取了山火风险高发区段，指导了冬春季节的山火预防工作。 In this paper, a real-time monitoring and analysis system for risk of wildfire in transmission line corridor is presented, which has been combined with wildfire risk assessment model based on domestic and international satellite image data. This system has been successfully applied in wild-fire risk assessment for transmission line power grid of Hubei province, which has also realized the classification of risk for different areas in transmission line. The final results have shown that, combined with multiple methods, such as, internet technology, remote sensing technology, expert system and data mining, areas in transmission line with high wildfire risk can be effectively ob-tained by the proposed system, which could be regarded as a guide for fire prevention in the sea-sons of spring and winter.

COD is an arbitrary indicator of the content of organic and inorganic compounds in wastewater. The aim of this research was to determine the effect of COD of industrial wastewater on the nitrification process. This research covered wastewater from acrylonitrile and styrene–butadiene rubbers, emulsifiers, polyvinyl acetate, styrene, solvents (butyl acetate, ethyl acetate) and owipian® (self-extinguishing polystyrene intended for expansion) production. The volume of the analyzed wastewater reflected the active sludge load in the real biological treatment system. This research was carried out by the method of short-term tests. The nitrification process was inhibited to the greatest extent by wastewater from the production of acrylonitrile (approx. 51%) and styrene–butadiene (approx. 60%) rubbers. In these wastewaters, nitrification inhibition occurred due to the high COD load and the presence of inhibitors. Four-fold dilution of the samples resulted in a two-fold reduction in the inhibition of nitrification. On the other hand, in the wastewater from the production of emulsifiers and polyvinyl acetate, a two-fold reduction in COD (to the values of 226.4 mgO2·dm−3 and 329.8 mgO2·dm−3, respectively) resulted in a significant decrease in nitrification inhibition. Wastewater from the production of styrene, solvents (butyl acetate, ethyl acetate) and owipian® inhibited nitrification under the influence of strong inhibitors. Lowering the COD value of these wastewaters did not significantly reduce the inhibition of nitrification.