Monitoring System Research Articles

Abstract 1820: Investigating whether FLASH radiotherapy spares late-responding organs using a rat spinal cord model

Abstract Purpose: FLASH radiotherapy (FLASH-RT) delivers curative dose to tumors at ultra-high dose rates (UHDR, >40 Gy/s) while offering normal tissue protection via the FLASH effect. Most supporting evidence relies on acute toxicity, but data on late-responding tissues are limited. Inadequate understanding of dose-response relationships has led to severe late toxicity, such as bone necrosis, halting a FLASH trial in cats. To establish FLASH-RT as a clinical modality, determining the dose-response for late-responding organs is essential. The spinal cord, with its steep dose-response curve and risk of myelopathy, serves as an ideal model. This study investigates whether FLASH-RT mitigates late toxicity using the rat spinal cord, a critical step for clinical translation. Methods: The cervical-thoracic spine (C1-T2) of rats was irradiated with an 18 MeV LINAC-based FLASH beam with a posterior-anterior 2×1cm2 field in a single fraction. A pulse control and monitoring system was developed to ensure precise delivery at single-pulse resolution required to establish the dose response curve. A scintillation detector was placed within the C1-T2 region of a rat carcass for validating Monte Carlo (MC) dose calculations. A custom immobilization device, combined with portable X-ray imaging, was used for precise C1-T2 localization for irradiation. An ion chamber was placed beneath the electron cone to monitor Bremsstrahlung as the surrogate for real-time UHDR output measurement. Dose groups were based on the reported median effective dose (ED50) for conventional dose rate (CONV) treatments (20.4-21.5 Gy) and dose-modifying factors (DMF) for FLASH (1-1.4). Sprague Dawley rats were irradiated with FLASH doses ranging from 15.3 to 28.4 Gy. The dose-related paresis incidence was assessed over a 7-month follow-up period to determine the dose-response curve and whether FLASH enhances spinal cord tolerance compared to CONV-RT. Results: MC calculations demonstrated that the 18 MeV FLASH achieved profile non-uniformity of <5% along the 12 mm length of the C1-T2, effectively mitigating the dose-volume effect, and was reproducible across animals. The dose rate achieved 390 Gy/s, exceeding the threshold of 40 Gy/s. Radiation-induced skin damage healed spontaneously by 10 weeks post-irradiation. The animals showed steady weight gain after irradiation, suggesting that no significant radiation-induced esophagitis was observed. Preliminary results indicated that 3 out of 8 rats in both 21.8 and 28.4 Gy FLASH groups exhibited paralysis. The data collection is still ongoing, and the full dose-response curves for both UHDR and CONV irradiation will be established. Conclusions: Our project addresses a critical knowledge gap in FLASH-RT by elucidating the FLASH dose-response relationships for a key late-responding organ, the spinal cord. The findings will have significant implications for the use of FLASH-RT in clinical setting. Citation Format: Banghao Zhou, Lixiang Guo, Yi-Chun Tsai, Albert van der Kogel, John Wong, Iulian Iordachita, Rongxiao Zhang, Varghese Anto Chirayath, Robert Timmerman, Weiguo Lu, Kai Jiang, Chul Ahn, Paul Medin, Ken Kang-Hsin Wang. Investigating whether FLASH radiotherapy spares late-responding organs using a rat spinal cord model [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 1820.

IOT Based Automatic Plant Irrigation System

The IoT-based automatic plant irrigation system is a sustainable solution that combines solar energy and smart technology to optimize water usage and reduce manual intervention. IoT sensors monitor soil moisture levels, automating irrigation based on real-time data. Solar panels provide renewable energy, while Amazon Alexa integration enables voice-controlled operation and system monitoring. This innovative approach enhances agricultural productivity, conserves resources, and promotes eco-friendly farming practices. Keywords: IoT, automatic irrigation, solar panels, Amazon Alexa, smart agriculture, sustainable farming, automation, renewable energy.

Oil Pollution Sensing Based on Light Detection and Ranging

We have developed a system for oil pollution detection using Light Detection and Ranging (LiDAR) technology. The system utilizes a TFmini-S LiDAR sensor and an ESP32 microcontroller to detect the presence of oil in freshwater. The LiDAR sensor emits laser pulses and records the reflection patterns from the water surface. The sensor identifies changes in reflected light intensity due to the presence of oil, distinguishing between clear water and oil-contaminated water. Experiments were conducted in controlled laboratory conditions using two types of oil samples: new gasoline oil and used gasoline oil. These samples were mixed with water to simulate oil pollution scenarios. The sensor readings were continuously monitored, and the data was analysed to assess the effectiveness of the system. Results show that the system could detect changes in surface properties caused by oil, with distinct patterns observed for new and used oil samples. New oil demonstrated more stable sensor readings due to its uniform surface properties, while used oil exhibited fluctuations, likely due to impurities and varied surface textures. This research confirms the feasibility of using LiDAR technology to detect oil in freshwater environments. The system offers a non-invasive and real-time method for monitoring water quality and detecting oil pollution. Future work will involve optimizing the system for field deployment, including testing under varying environmental conditions such as temperature, light, and water movement. This study contributes to the development of LiDAR-based environmental sensing systems for pollution monitoring, providing a potential tool for environmental agencies and water management organizations to detect and manage oil spills effectively.

Industrial IoT Based Health Monitoring System of Motor or Transformer

This research introduces an Industrial IoT-based health monitoring system specifically designed for motor and transformer components within industrial environments. By integrating advanced sensors, microcontrollers, and the local web server for data visualization, the system enables real-time monitoring and predictive maintenance. The precise measurement of critical parameters, combined with effective anomaly detection algorithms, empowers operators to proactively address potential equipment failures. The system's reliability and effectiveness in enhancing equipment dependability and minimizing downtime present a promising solution for industrial maintenance challenges. The system comprises a network of sensors strategically positioned on motor and transformer components to collect essential operating data. Additionally, a relay-based feedback system is incorporated to execute protection actions when abnormal conditions are detected, ensuring improved equipment safety and reliability. These sensors interface with microcontrollers, which then use the web-based interface to transmit and display the processed and analyzed data to a central monitoring station. The efficiency and user-friendly nature of the web interface ensure the timely delivery of critical information, enabling operators to make quick decisions. Key Words: Industrial IoT, Health Monitoring System, Motor Components, Transformer Components, ESP32, ACS758, ADXL345, DHT11, Web-Based Interface, Predictive Maintenance, Relay based Feedback

Reconstruction of Missing Vibration Data for Long-Span Bridges by Fusing Multiple-Frequency Information Utilizing LSTM with Bayesian Optimization

Effective monitoring of bridge structural health relies heavily on continuous and accurate data acquisition. However, sensor failures, communication disruptions, and environmental factors often lead to missing data, challenging the reliability of monitoring systems. Given the intricate features and nonlinear characteristics of vibration data, traditional full-band reconstruction methods based on machine learning may encounter difficulties in feature selection and extraction and are notably sensitive to data quality, especially when data loss occurs in parts of a single measurement. To address this challenge, this paper proposes an LSTM-based reconstruction method for missing vibration data by splitting band to fuse multi-frequency information. Bayesian optimization complements LSTM to improve the accuracy and robustness of reconstruction by systematically optimizing network hyperparameters. The reconstructed effectiveness is verified using acceleration data from both a numerical-simulated three-span continuous beam bridge and a full-scale long-span suspension bridge. The results provide a thorough comparison between the performance and advantages of full-band reconstruction and the proposed split-band reconstruction approaches. Through comparative analyses, the efficacy and practicality of the split-band reconstruction approach based on LSTM with Bayesian optimization is underscored. This research aims to provide a theoretical basis for improving the resilience and service life of civil infrastructure by improving the reconstruction of missing data from vibration signals.

Monitoring bands during the Norwegian national day parade: a case study on urban distributed acoustic sensing

Existing networks of fiber optic telecommunication infrastructure can be used to measure acoustic events. For this purpose, a laser instrumentation is attached to a “dark fiber” turning it into a Distributed Acoustic Sensing (DAS) device. In May 2023, a DAS test was conducted to measure acoustic activity in Oslo, Norway. The main purpose was to measure the “pulse” of the Oslo city center during the Norwegian National Day parade. Additionally, five days before and after the National Day were recorded for reference to daily acoustic background noise conditions in Oslo. Data during the National Day captured the yearly parade in which schools and bands participate. Using this data, it was possible to detect the participating bands, analyze their frequency content, and estimate their walking speed and step length. High-order harmonics were recognized in the frequency response for the bands. A total of 88 bands participated in the parade and 87 were detected using the harmonic characteristics. While one individual band could be tracked before the main parade over separate streets, it was challenging to continue the track for other bands within the parade. The test revealed that DAS can be used as part of decision support systems for crowd monitoring.

Automated System Design for Sending Arrival Messages at Backup Facilities in Jakarta Air Traffic Service Center

This research is urgent to ensure that the Arrival Message Engine, which is separate from the Main ATC System, can send ATS Messages automatically. This was deemed necessary to do immediately to back up a bug in the Main ATC System, which caused several Arrival Messages not to be sent. The method used is the research and development method, meaning it is a scientific way to research, design, and test the validity of the product that has been created. Research and development has four levels: researching without testing, testing without researching, researching and testing to develop existing products, and researching and testing to create new products. A product has been produced in the form of an arrival message delivery automation system that automatically sends arrival message data to the AFTN message network and can run well per the user needs assessment in this research. It was proven from the design validation results that the test results were 100% and categorized as very feasible, as well as from the system test results using the Black Box method. As a continuation of this research, a warning and monitoring system for sending ATS messages is needed when a failure or anomaly occurs in the main system. It is hoped that this research can be considered for use in operations as an alternative facility so that it can support activities related to handling ATS messages or flight data processing systems in flight navigation operations.

Malicious Traffic Detection Method for Power Monitoring Systems Based on Multi-Model Fusion Stacking Ensemble Learning

With the rapid development of the internet, the increasing amount of malicious traffic poses a significant challenge to the network security of critical infrastructures, including power monitoring systems. As the core part of the power grid operation, the network security of power monitoring systems directly affects the stability of the power system and the safety of electricity supply. Nowadays, network attacks are complex and diverse, and traditional rule-based detection methods are no longer adequate. With the advancement of machine learning technologies, researchers have introduced them into the field of traffic detection to address this issue. Current malicious traffic detection methods mostly rely on single machine learning models, which face problems such as poor generalization, low detection accuracy, and instability. To solve these issues, this paper proposes a malicious traffic detection method based on multi-model fusion, using the stacking strategy to integrate models. Compared to single models, stacking enhances the model’s generalization and stability, improving detection accuracy. Experimental results show that the accuracy of the stacking model on the NSL-KDD test set is 96.5%, with an F1 score of 96.6% and a false-positive rate of 1.8%, demonstrating a significant improvement over single models and validating the advantages of multi-model fusion in malicious traffic detection.

INTELLIGENCE THREAT ANALYSIS AND MALWARE DETECTION

Malware Detection entails the process of identifying and classifying malicious software (malware) that can potentially damage devices, networks, or data. It consists of signature-based detection, heuristic analysis, behavioral analysis, and even machine learning. There is great concern for the impact of malware on digital security due to the possibility of exposing sensitive information and damaging the system. The aim of this particular project is to develop an efficient malware detection system with advanced machine learning techniques, behavioral analysis, and signature-based detection. Characterizing files, network traffic, and monitoring systems enables the model to identify threats in real time and neutralize them. This project is designed to improve cybersecurity by increasing detection accuracy, lowering false alarms, and offering proactive response to threats. This solution enables systems to withs the continuous changes in cyber threats and creates a better environment on the internet. Nowadays, with the advances in technology, digital systems make our life easier and more complicated at the same time. This also includes an increase in the potential for cyber threats which is one of the most significant challenges we face today. Malware comes on top of the list. My project aims at developing and integrating an efficient malware detection application that relies on pattern recognition to find malware and contains advanced detection algorithms. It employs machine learning and both static and dynamic analysis techniques.

Virtual MOS Sensor Array Design for Ammonia Monitoring in Pig Barns

Animal welfare in barns is strongly influenced by air quality, with gaseous emissions like ammonia posing significant respiratory health risks. However, current state-of-the-art ammonia monitoring systems are labor-intensive and expensive. Metal Oxide Semiconductor (MOS) sensors offer a promising alternative due to their compatibility with sensor networks, enabling high-resolution ammonia monitoring across spatial and temporal scales. While MOS sensors exhibit high sensitivity to various volatile compounds, temperature-cycled operation is commonly employed to enhance selectivity, effectively creating virtual sensor arrays. This study aims to improve ammonia detection by designing a virtual sensor array through a cyclic data-driven approach, integrating machine learning with solid-state sensor modeling. The results of a two-week dataset with measurements of four different pig barns demonstrate ammonia sensing with a sampling rate of about 2/min and a range of 1–30 ppm. The method is robust and exhibits a 10 increase in normalized RMSE when comparing testing results of an unseen sensor module with results of the training dataset. A filter membrane boosts accuracy and prevents data loss due to contamination, such as flyspecks. Overall, the used MOS sensor BME688 is effective and economical for widespread continuous ammonia monitoring and localization of ammonia sources in pig barns.

Model Updating of Bridges Using Measured Influence Lines

In developing a digital twin of a real structure, finite element model updating (FEMU) is essential for refining the model’s response based on measured data, enabling the detection of structural damage or hidden reserves over time. This case study focused on a 40-year-old multi-span concrete roadway bridge, equipped with permanent bridge weigh-in-motion (B-WIM) and structural health monitoring (SHM) systems. Bridge responses from two calibration vehicles were used to derive strain influence lines (ILs) from mid-span B-WIM strain transducers mounted on the main girders. The error-domain model falsification (EDMF) methodology was applied to perform strain IL-based FEMU and the more conventional frequency-based, MAC-based, and combined frequency and MAC-based FEMU. Boundary conditions and three Young’s modulus adjustment factors, representing different groups of structural elements, were updated. The strain IL-based updated FE model, with averages of 35% and 50% stiffness increases for the two main girders, showed strong agreement with independently measured mid-span vertical displacements. Maximum values deviated not more than 5%. In contrast, the frequency and MAC-based updated FE model underestimated displacements by 25–30%. These findings highlight the potential of using B-WIM for FEMU and SHM on such types of bridges, particularly when the response under traffic load is of interest.

An Image-Based Intelligent System for Addressing Risk in Construction Site Safety Monitoring Within Civil Engineering Projects

In the construction industry, safety is of paramount importance given the complex and dynamic nature of construction sites, which are prone to various hazards, like falls from heights, being hit by falling objects, and structural collapses. Traditional safety management strategies, such as manual inspections and safety training, have shown significant limitations. This study presents an intelligent monitoring and analysis system for construction site safety based on an image dataset. A specifically designed Construction Site Safety Image Dataset, comprising 10 distinct classes of objects, is utilized and divided into training, validation, and test subsets. InceptionV3 and MobileNetV2 are chosen as pre-trained models for feature extraction and are modified through truncation and compression to better suit the task. A novel feature fusion architecture is introduced, integrating these modified models, along with a Squeeze-and-Excitation block. Experimental results demonstrate that the proposed model achieves a mean average precision (mAP) of 0.90 at an IoU threshold of 0.5, with high accuracies for classes like “Safety Cone” (91%) and “Machinery” (93%) but relatively lower accuracy for “Vehicle” (57%). The training process exhibits smooth convergence, and compared to prior methods, such as YOLOv4 and SSD, the proposed framework shows superiority in regard to precision and recall. Despite its achievements, the system has limitations, including reliance on visual data and dataset imbalance. Future research directions involve incorporating multi-modal data, conducting real-world deployments, and optimizing for edge deployment, aiming to further enhance construction site safety.

Intelligent Clustering and Adaptive Energy Management in Wireless Sensor Networks with KDE-Based Deployment

Wireless sensor networks (WSNs) are widely used in IoT, environmental monitoring, and industrial systems, but ensuring energy efficiency, extended network lifetime, and reliable communication under real-world constraints remains challenging. This work proposes a novel clustering framework that integrates kernel density estimation (KDE)-based adaptive node deployment, silhouette-optimized K-means clustering, Bayesian cluster head (CH) selection with Gaussian noise-based energy uncertainty modeling, energy-efficient coverage control, and carrier sense multiple access with collision avoidance-based data transmission. Unlike conventional approaches that rely on fixed clustering and uniform deployments, our framework supports terrain-aware node placement and dynamic CH selection based on residual energy and distance under imperfect sensing conditions. Simulation results demonstrate significant improvements in performance, including over 35% extension in network lifetime and higher coverage retention under energy constraints, compared to baseline methods such as LEACH and K-LEACH. While detailed metrics vary per run due to adaptive parameters and stochastic node behavior, these outcomes validate the scalability, robustness, and practical relevance of the proposed method for real-world WSN deployments.

Anomaly Detection in Financial Transactions Using Convolutional Neural Networks

The rise of digital financial systems has brought unprecedented convenience but has also exposed users and institutions to various fraudulent activities. Anomaly detection plays a critical role in ensuring financial security by identifying unusual transaction patterns that may indicate fraud or other irregularities. Traditional statistical and rule-based approaches, though effective to some extent, often fall short when dealing with the increasing volume and complexity of financial data. This study proposes a novel approach to anomaly detection in financial transactions using Convolutional Neural Networks (CNNs), a class of deep learning models primarily known for their success in image processing tasks. In this work, transactional data are preprocessed and transformed into structured formats suitable for CNN input. By treating sequences of financial transactions as temporal-spatial matrices, the CNN model learns intricate patterns that distinguish normal from anomalous behavior. Our methodology includes a comprehensive pipeline involving data normalization, feature engineering, and the construction of multi-channel representations to exploit CNNs' strength in hierarchical feature learning. We evaluate our model on benchmark financial datasets and compare its performance against traditional machine learning algorithms such as Support Vector Machines (SVM), Random Forest, and Logistic Regression. The CNN-based model demonstrates superior performance in terms of accuracy, precision, recall, and F1-score. Additionally, it shows robustness in detecting rare anomalies while minimizing false positives, a critical requirement in real-time financial fraud detection systems. The results indicate that CNNs can effectively capture both local and global dependencies within financial transaction sequences, making them suitable for large-scale and high-dimensional data environments. This study contributes to the growing body of research advocating for the adoption of deep learning techniques in financial anomaly detection and opens up possibilities for integrating CNNs with real-time monitoring systems for enhanced financial security. Future research may focus on hybrid models combining CNNs with recurrent layers to capture long-term dependencies more effectively.

Digital Twin-Driven Stability Optimization Framework for Large Underground Caverns

With rapid urbanization, the utilization of underground space has become an important part of infrastructure. However, the stability of underground spaces such as large caverns remains a key challenge in civil engineering throughout the lifecycle of a project. Traditional methods of stability assessment rely on static models and periodic monitoring and often fail to capture real-time changes in rock behavior, leading to potential safety risks and, in severe cases, even the collapse of underground infrastructure. To address this challenge, this study introduces a digital twin (DT) framework to improve stability assessments and monitor deformations in underground structures. The framework enables the continuous monitoring and adaptive optimization of rock support systems by combining real-time sensor data with virtual simulations. A five-dimensional DT framework comprises physical objects, virtual objects, service systems, DT data, and their interconnections. It incorporates six key modules, which are structure, geology, material, behavior, performance, and environment, to enhance the understanding of cavern stability. The framework is based on Industry Foundation Classes standards to ensure seamless data exchange, interoperability, and the standardized representation of geotechnical and structural data. A seven-step methodology is developed for this framework, encompassing geological assessment, virtual modeling, Building Information Modeling (BIM)-based design, construction processes, real-time monitoring, and optimization strategies. To evaluate its effectiveness, the framework is applied to a case study, demonstrating improvements in deformation monitoring and rock support efficiency. The findings highlight the potential of integrating DT with BIM to enhance safety, reliability, and long-term stability in underground construction projects.

Effect of nutrient concentrations and vermiwash on bottle gourd productivity in automated IoT-based hydroponic systems

ABSTRACT This study examines the effect of different concentrations of nitrogen, phosphorus, and potassium in a modified Hoagland solution supplemented with vermiwash on the growth and productivity of bottle gourd plants (Lagenaria siceraria L) grown in nutrient film technique and wick hydroponic systems. The experiment was conducted in a controlled greenhouse at Lovely Professional University, India, during the summer seasons of 2022–2024. Three nutrient levels – 100:60:60 (recommended dose), a 20% increase (120:72:72), and a 30% increase (130:78:78) – were tested using two hydroponic systems: the nutrient film technique (NFT) and the wick system. An automated monitoring system that consisted of programmed microcontrollers regulated the delivery of nutrients in real-time with pH, electrical conductivity, and environmental conditions.Sensors continuously measure the efficiency of nutrient uptake, temperature, relative humidity, and plant growth parameters. Optimal performance was achieved by the nutrient film technique system at 20% nutrient increase with plant height recorded as 103.26 cm, 15.9 flowers, 8 fruits, and 20.73 grams of dry matter content. Hydroponic automated systems may be employed in growth and yield improvement; however, among all systems studied, the nutrient film technique has proven to be the optimal method for sustainable bottle gourd production as compared to the wick system.

Ultrasensitive Room-Temperature NO2 Gas Sensor Based on MXene-Cu2O Composites.

The development of real-time trace-level NO2 quantification platforms that can be operated at room temperature constitutes a critical advancement for occupational safety and public health monitoring systems. This study demonstrates a room-temperature NO2 sensor using MXene-Cu2O composites prepared via a hydrothermal method. Systematic evaluation of MXene-introduced effects identified the 0.84 wt % MXene-Cu2O composite as optimal, exhibiting 4-fold enhanced sensitivity and shorter response (55 s)/recovery (35 s) time compared to pure Cu2O. Additionally, the sensor exhibits a low detection limit (10 ppb), high selectivity, great reversibility, and long-term stability. The enhanced sensing performance originates from precisely engineered interfacial architectures between MXene and Cu2O, which effectively adjust the charge-transfer behavior through the conduction tunnel in the sensing material. Furthermore, oxygen vacancy engineering creates defect-mediated adsorption centers that promote selective NO2 chemisorption through charge polarization effects. This research offers a novel strategy for designing optimized structures to enhance the sensitivity of MOS-based materials for NO2 gas detection.

Acute Effects of Daily Life Spontaneous and Structured Physical Activity on Glycemia in Children with Type 1 Diabetes.

In type 1 diabetes, glycemia management is rendered complex through the confounding influence of spontaneous physical activity (PA), particularly frequent in children. We aim to understand the glycemic effects of self-reported PA and cumulative spontaneous PA in their everyday life, controlling for carbohydrate intake and insulin. In this 7-day observational study, 45 children/adolescents (21 females, 11‧7 ± 3‧4 years) wore a continuous glucose monitoring system and accelerometer, completing diaries about PA, diet, insulin. Types of PA included (i) self-reported PA and its characteristics (duration, subjective intensity) and conditions (previous sessions, timing and pre-exercise carbohydrate intake, insulin-on-board, glycemia), (ii) spontaneous cumulative PA (accelerometry) adjusted for sedentary time. Linear mixed models were used with results expressed as the estimated coefficient 'e'. In cases of skewed continuous dependent outcomes containing a preponderance of zero % values, random-intercept binary logistic regressions were used with results expressed as odds ratios (OR). Accumulating moderate-to-vigorous PA during the late afternoon (e = -0‧32, P = 0‧039) was associated with decreased concomitant time spent >13‧9 mmol.L-1. Time spent >10‧0 mmol.L-1 during self-reported PA was lower when children consumed less high-glycemic-index carbohydrates the previous hour (e = +0‧49, P = 0‧034; albeit found only in one model out of two) or were physically active before the session (tendency: e = -11‧58, P < 0‧07). PA conditions were not significantly associated with hypoglycemia. Risk of spending some time < 3‧9 mmol.L-1 during sessions was higher in the case of longer PA duration (OR = 1‧02, P = 0‧008). Risk of nocturnal time < 3‧0 mmol.L-1 was greater when children performed longer duration structured PA (OR = 1‧02, P = 0‧054) or accumulated more afternoon vigorous-intensity PA (OR = 1‧06, P = 0‧04). Increasing spontaneous active behavior during the late afternoon could help reduce day-time spent >13‧9 mmol.L-1. There is a possibility that hyperglycemia during exercise could be limited by multiplying daily PA sessions or avoiding excessive pre-exercise carbohydrate intake. However, as only sessions characteristics, especially duration, predicted time < 3‧9 mmol.L-1 during PA and < 3‧0 mmol.L-1 the following night, simplified guidelines (not considering PA conditions) on hypoglycemic risk could be developed.

Five years of high-frequency data of phytoplankton zooplankton and limnology from a temperate eutrophic lake

This study presents a comprehensive dataset from Lake Greifen, Switzerland, collected between April 2018 and June 2023, using high-frequency automated monitoring systems. The dataset integrates meteorological data, nutrient chemistry, water column profiles for water physics, and plankton underwater imaging, offering insights into the lake’s physical and biological processes. A dual-magnification dark field underwater microscope captured hourly plankton dynamics at 3 m depth, providing size, shape, and taxonomic information. A profiler with a multiparametric probe monitored water temperature, oxygen, and other key parameters from 1 to 17 m depth, while weekly nutrient sampling complemented the measurements. Data processing involved rigorous cleaning protocols to remove technical artefacts, ensuring data quality. Our dataset showcases the utility of integrating different approaches for high-frequency monitoring to detect lake temporal processes, from phytoplankton blooms to zooplankton vertical migration and seasonal shifts in water column stability. This dataset provides a unique resource for studying limnology and plankton community ecology. All data and related processing codes are publicly available for further research, supporting interdisciplinary studies.

AI-Enhanced Attention Monitoring System for Effective Learning

There are numerous studies in which researchers have attempted to attract college students' attention. Many of these approximations lack quantitative evaluation and are primarily based on qualitative evaluation. This artistic creation thus targets to connect the distance among subjective and quantitative methodologies to developing understudy commitment. This study therefore routinely divides college students into attentive and inattentive RGB-D sensor statistics using machine learning algorithms (K-manner and SVM). The National Academy of Engineering has done a lot of research on this topic, and the findings of this study can be used to inform and support teaching methods for teachers of all levels. The ability of teachers to implement individualized learning methods is a major goal of their work. In this view, contraption learning calculations are utilized for educational purposes.