Real-time Monitoring Platform Research Articles

Calibration modeling of drilling fluid rheological parameters in variable temperature environment based on support vector machine.

Traditional measurement of drilling fluid rheological parameters suffers from significant lag due to the inability of the instruments to promptly capture real-time parameters of the drilling fluid. These measurement models are typically constructed based on fixed temperature conditions and empirical formulas, rendering them inadequate for complex temperature gradient environments. Consequently, this limitation results in increased prediction errors, severely compromising the precise monitoring of drilling fluid performance. Aiming at the problems of low accuracy and poor stability of drilling fluid measurements under variable temperature conditions, a support vector machine-based calibration model for drilling fluid rheological parameters in a variable temperature environment is proposed in this paper. First, the measurement principle of the double-tube differential pressure rheology real-time measurement device is analyzed. The relationship between shear stress and shear rate is then established using differential pressure sensor and flow rate data. Utilizing the gray wolf optimization algorithm to optimize the kernel function weights and parameters, an SVM-based calibration model for predicting drilling fluid rheology correction parameters is constructed. Finally, a real-time monitoring platform for drilling fluid is developed. Experimental results show that the maximum relative errors for the predictions of apparent viscosity, plastic viscosity, and yield point are within ±5%, with coefficients of determination (R2) all greater than 0.95. These results validate the effectiveness of the proposed method in accurately monitoring the rheological performance of drilling fluids.

Fluidic Interface for Surface-based DNA Origami Studies.

Traditionally, the use of DNA origami nanostructures (DONs) to study early cell signaling processes has been conducted using standard laboratory equipment with DONs typically utilized in solution. Surface-based technologies simplify the microscopic analysis of cells treated with DON agents by anchoring them to solid substrates, thus avoiding the complications of receptor-mediated endocytosis. A robust microfluidic platform for real-time monitoring and precise functionalization of surfaces with DONs was developed here. The combination of controlled flow conditions with an upright total internal reflection fluorescence microscope enabled the kinetic analysis of the immobilization of DONs on DNA-functionalized surfaces. The results revealed that DON morphology and binding tags influence the binding kinetics and that DON hybridization on surfaces is more effective in microfluidic devices with larger-than-standard dimensions, addressing the low diffusivity challenge of DONs. The platform enabled the decoration of DONs with protein-binding ligands and in situ investigation of ligand occupancy on DONs to produce high-quality bioactive surfaces. These surfaces were used to recruit and activate the epidermal growth factor receptor (EGFR) through clustering in the membranes of living cancer cells (MCF-7) using an antagonistic antibody (Panitumumab). The activation was quantified depending on the interligand distances of the EGFR-targeting antibody.

A novel fluorescence platform for portable and visual monitoring of meat freshness

Biogenic amines (BAs) are crucial markers of meat spoilage. Developing practical and effective BAs detection methods is essential for monitoring meat freshness and ensuring daily consumption safety. This study prepared several naphthalene-based fluorescent compounds to visually monitor meat freshness in real-time. These probes show a colorimetric fluorescence response to putrescine and cadaverine (typical spoilage indicators) through nucleophilic addition/elimination reaction. The detectability of these probes can be optimized by altering the electronegativity and substitution position of the recognition group. Among these compounds, 2-((6-(4-(diphenylamino)phenyl)naphthalen-2-yl)methylene)malono nitrile (TNMA) demonstrated exceptional sensing performance toward putrescine and cadaverine, including high-contrast fluorescence color transition (red to blue), rapid response times (∼30 s), high selectivity and sensitivity (detection limit for putrescine: 2.69 ppm, cadaverine: 6.11 ppm). Furthermore, the B/R values of TNMA test strips output by RGB analysis presented a linear correlation with total volatile basic nitrogen (TVBN, an international standard for evaluating food spoilage) values in pork. Based on this correlation, we utilized smartphone applications to construct an intelligent evaluation system, enabling visual monitoring of pork, chicken, and shrimp freshness under various storage conditions. The TNMA-based system offers a reliable platform for real-time, portable and visual monitoring of meat freshness for consumers and suppliers in the food industry.

Supervised classification and fault detection in grid-connected PV systems using 1D-CNN: Simulation and real-time validation

Photovoltaic (PV) systems are prone to various faults, including short-circuit, open-circuit, partial shading, and inverter bypass diode issues, which reduce power output and can damage components. This study presents an innovative fault detection and online monitoring technique for grid-connected PV (GCPV) systems, combining Internet of Things (IoT) technology with a one-dimensional convolutional neural network (1D-CNN) deep learning approach. The method involves developing a temperature-dependent PV system model using series resistance and ideality factor, capturing real-time data from a 15kWp GCPV system with optimally placed sensors to minimize sensor count while maintaining data accuracy, and validating the model through MATLAB/Simulink simulations and real-time experiments under various fault scenarios. The collected data is used to train the 1D-CNN model to classify different fault types. The model is then implemented on an IoT platform for real-time monitoring and fault detection, displaying system status and alerts via a dashboard. The proposed system achieves a high fault detection accuracy of 98.15 % and 93.12 % during cyberattacks, with an uncertainty of ±4 %, significantly enhancing fault detection reliability and efficiency compared to existing methods. The IoT dashboard provides an effective tool for monitoring system performance and issuing alerts under abnormal conditions.

Planar Disk μ-Aptasensors by Monolayer Assembly in a Dissolving Microdroplet.

Electrochemical aptamer-based sensors provide a highly modular platform for real-time monitoring of small molecules. Their ability to selectively recognize target molecules in complex environments like biological fluids makes them an attractive technology for the analysis of micro- and nanoscale systems. The signal-to-noise of the measurement depends on the electroactive surface (i.e., how many aptamers one can place), which has previously precluded miniaturization of aptamer-based sensors to planar disk ultramicroelectrodes (r ∼ 5-10 μm). Here, we employ a concentration enrichment strategy based on the active dissolution of an aqueous, aptamer-containing microdroplet on an ultramicroelectrode submerged in an organic continuous phase (1,2-dichloroethane). We show consistent voltammetric signal increase as a function of droplet lifetime, indicating the successful immobalization of the thiol-terminated aminoglycoside aptamers to the electrode surface. We observe a diagnostic methylene blue peak and 10-fold increase in current magnitude as compared to bare microelectrodes. We report robust sensor behavior with a linear dynamic range extending from milli- to micromolar concentrations of kanamycin in buffer. This research offers a successful method for optimized electrochemical aptamer-based sensor fabrication and miniaturization on ultramicroelectrodes without the need for electrode surface area enhancement.

Prototype smart integrated fire detection based on deep learning YOLO v8 and IoT (internet of things) to improve early fire detection

The high incidence of fires in Indonesia in 2018-2023 is 5,336 fire incidents have caused many deaths and enormous material losses. This system is designed to identify early signs of fire through object detection and sensor technology, which is integrated with the Blynk IoT platform for real-time sensor monitoring and Telegram for instant notifications to users. The waterfall prototype method was designed through observation, system design, program code creation, tool testing, and tool implementation. This research uses Deep Learning YOLOv8 technology and IoT using ESP 32 as a microcontroller. Based on the training datasets, it produces precision=0.95872; recall=0.91; mAP50=0.97; mAP50-95 =0.66. The system uses the integration of a multisensor KY-026 flame sensor, DHT 22 temperature and humidity sensor, and MQ-2 sensors can detect CO, LPG, and smoke gas. All these multisensors can be monitored on Blynk IoT and Telegrambot in real time.

A data platform for real-time monitoring and analysis of the brown marmorated stink bug in Northern Italy

The brown marmorated stink bug (Halyomorpha halys) is one of the main insect pest species causing economic damage to several agricultural commodities worldwide and one of the worst threats to tree fruit crops in northern Italy, especially in the Emilia-Romagna region. Previous efforts in implementing H. halys surveillance at the regional level were mainly focused on studying the H. halys phenology, but they were not designed to provide a public service. In this paper, we propose a data-driven approach to support the application of Integrated Pest Management strategies against H. halys. The proposal is based on the experience of a three-year project in which a network of monitoring traps has been deployed throughout the whole Emilia-Romagna region and a data platform has been implemented to enable the real-time tracking of H. halys occurrence and distribution, integrating these information with multiple data sources, and analytical capabilities through a public website. Besides the real-time pest surveillance, the data platform allowed us to increase our understanding about H. halys seasonal invasion dynamics and the main factors contributing to its spread. The results will help individual growers in protecting their crops and the whole region in promoting more efficient usage of insecticides and more sustainable and healthy agricultural productions.

A wearable microneedle patch incorporating reversible FRET-based hydrogel sensors for continuous glucose monitoring

Continuous glucose monitors are crucial for diabetes management, but invasive sampling, signal drift and frequent calibrations restrict their widespread usage. Microneedle sensors are emerging as a minimally-invasive platform for real-time monitoring of clinical parameters in interstitial fluid. Herein, a painless and flexible microneedle sensing patch is constructed by a mechanically-strong microneedle base and a thin layer of fluorescent hydrogel sensor for on-site, accurate, and continuous glucose monitoring. The Förster resonance energy transfer (FRET)-based hydrogel sensors are fabricated by facile photopolymerizations of acryloylated FRET pairs and glucose-specific phenylboronic acid. The optimized hydrogel sensor enables quantification of glucose with reversibility, high selectivity, and signal stability against photobleaching. Poly (ethylene glycol diacrylate)-co-polyacrylamide hydrogel is utilized as the microneedle base, facilitating effective skin piercing and biofluid extraction. The integrated microneedle sensor patch displays a sensitivity of 0.029 mM−1 in the (patho)physiological range, a low detection limit of 0.193 mM, and a response time of 7.7 min in human serum. Hypoglycemia, euglycemia and hyperglycemia are continuously monitored over 6 h simulated meal and rest activities in a porcine skin model. This microneedle sensor with high transdermal analytical performance offers a powerful tool for continuous diabetes monitoring at point-of-care settings.

Experiment-Based Determination of Optimal Parameters in Constant Temperature–Constant Voltage Charging Technique for Lithium-Ion Batteries Using Taguchi Method

Charging methods significantly affect the performance and lifespan of lithium-ion batteries. Investigating charging techniques is crucial for optimizing the charging time, charging efficiency, and cycle life of the battery cells. This study introduces a real-time charging monitoring platform based on LabVIEW, enabling observation of battery parameters such as voltage, current, and temperature. The proposed system allows the precise control of charging parameters via a user-friendly interface. Utilizing a programmable DC power supply, it delivers specific charging waveforms, while data acquisition instruments record temperature changes. Key performance metrics, including charging time, efficiency, and temperature rise, are analyzed. Moreover, this paper conducts in-depth research on the constant temperature–constant voltage (CT-CV) charging technique and applies the Taguchi method to identify key parameter configurations that achieve the objectives of the shortest charging time, highest charging efficiency, and lowest average temperature rise. A comprehensive evaluation compares the optimized CT-CV method with conventional constant current–constant voltage (CC-CV) charging. The results demonstrate a 10.7% reduction in charging time compared to the 1C CC-CV method, indicating the efficacy of CT-CV in shortening charging duration while managing temperature rise.

Robust Intelligent Monitoring and Measurement System toward Downhole Dynamic Liquid Level.

Dynamic liquid level monitoring and measurement in oil wells is essential in ensuring the safe and efficient operation of oil extraction machinery and formulating rational extraction policies that enhance the productivity of oilfields. This paper presents an intelligent infrasound-based measurement method for oil wells' dynamic liquid levels; it is designed to address the challenges of conventional measurement methods, including high costs, low precision, low robustness and inadequate real-time performance. Firstly, a novel noise reduction algorithm is introduced to effectively mitigate both periodic and stochastic noise, thereby significantly improving the accuracy of dynamic liquid level detection. Additionally, leveraging the PyQT framework, a software platform for real-time dynamic liquid level monitoring is engineered, capable of generating liquid level profiles, computing the sound velocity and liquid depth and visualizing the monitoring data. To bolster the data storage and analytical capabilities, the system incorporates an around-the-clock unattended monitoring approach, utilizing Internet of Things (IoT) technology to facilitate the transmission of the collected dynamic liquid level data and computed results to the oilfield's central data repository via LoRa and 4G communication modules. Field trials on dynamic liquid level monitoring and measurement in oil wells demonstrate a measurement range of 600 m to 3000 m, with consistent and reliable results, fulfilling the requirements for oil well dynamic liquid level monitoring and measurement. This innovative system offers a new perspective and methodology for the computation and surveillance of dynamic liquid level depths.

Hourly land surface temperature retrieval over the Tibetan Plateau using Geo-LightGBM framework: Fusion of Himawari-8 satellite, ERA5 and site observations

The Tibetan Plateau (TP) is highly sensitive to even minor fluctuations in land surface temperature (LST), which can result in permafrost melting and degradation of alpine grasslands, leading to serious ecological consequences. Therefore, it is crucial to have high-temporal-resolution and seamless hourly estimating and monitoring of LST for a better understanding of climate change on the TP. Here, we employed Himawari-8 satellite, Digital Elevation Model (DEM), ERA5 reanalysis and meteorological station observations data to develop a new LightGBM framework (called Geo-LightGBM) for estimating LST on the TP, and then analyzed the spatiotemporal variations of those LST. Geo-LightGBM demonstrated excellent LST estimation accuracy, with an R2 (coefficient of determination) of 0.971, RMSE (root-mean-square error) of 2.479 °C, and MAE (mean absolute error) of 1.510 °C. The estimated LST values for the year 2020 agreed well with observed values, with remarkable differences in hourly LST variations. Meanwhile, the estimated LST was more accurate than that from FY-4A. Spatially, there were two high LST centers, located in the Yarlung Zangbo River Basin and the Qaidam Basin, and a low LST center located in the central TP. The SHAP (SHapley Additive exPlanations) and correlation analyses revealed DSCS (the mean ground downward shortwave radiation under clear-sky conditions) to be the most importantly input variable for estimating LST. Spatiotemporal dummy variables (e.g., longitude, latitude, DEM) were also found to be crucial for model accuracy improvement. Our findings indicate the potential for constructing a high-precision and seamless 24-h LST real-time retrieval and monitoring platform for the TP by combining satellite and China's independently developed CLDAS (China Land Data Assimilation System) data in future.

Semiconducting Polymer Dots for Dual-Wavelength Differential Background-Suppressed Photoacoustic Imaging.

Photoacoustic imaging (PAI) can sensitively detect regions and substances with strong optical absorption, which means that diseased tissue can be imaged with high contrast in the presence of surrounding healthy tissue through the photoacoustic effect. However, its signal intensity and resolution may be limited by background signals generated by endogenous chromophores such as melanin and hemoglobin. A feasible method for practical application of this so-called background-suppressed PAI is still lacking. In this work, a dual-wavelength differential background noise-suppressed photoacoustic tomography is developed based on organic semiconducting polymer dots (Pdots). The Pdots have a strong absorption peak at 945nm, and then the absorption decreases sharply with the increase of wavelength, and the absorption intensity drops to only about a quarter of the original value at 1050nm. The present system significantly suppresses the strong background noise of blood through dual-wavelength differential PAI, enabling precise monitoring of the distribution information of theranostic agents in diseased tissues. The signal-to-noise ratio of the theranostic agent distribution map is increased by about 20dB. This work provides a platform for real-time and accurate monitoring of tumors and drugs, which helps avoid damage to healthy tissue during treatment and has clinical significance in cancer treatment.

Smartphone based wearable sweat glucose sensing device correlated with machine learning for real-time diabetes screening

BackgroundDiabetes is a significant health threat, with its prevalence and burden increasing worldwide indicating its challenge for global healthcare management. To decrease the disease severity, the diabetic patients are recommended to regularly check their blood glucose levels. The conventional finger-pricking test possesses some drawbacks, including painfulness and infection risk. Nowadays, smartphone has become a part of our lives offering an important benefit in self-health monitoring. Thus, non-invasive wearable sweat glucose sensor connected with a smartphone readout is of interest for real-time glucose detection. ResultsWearable sweat glucose sensing device is fabricated for self-monitoring of diabetes. This device is designed as a body strap consisting of a sensing strip and a portable potentiostat connected with a smartphone readout via Bluetooth. The sensing strip is modified by carbon nanotubes (CNTs)-cellulose nanofibers (CNFs), followed by electrodeposition of Prussian blue. To preserve the activity of glucose oxidase (GOx) immobilized on the modified sensing strip, chitosan is coated on the top layer of the electrode strip. Herein, machine learning is implemented to correlate between the electrochemical results and the nanomaterial content along with deposition cycle of prussian blue, which provide the highest current response signal. The optimized regression models provide an insight, establishing a robust framework for design of high-performance glucose sensor. SignificanceThis wearable glucose sensing device connected with a smartphone readout offers a user-friendly platform for real-time sweat glucose monitoring. This device provides a linear range of 0.1–1.5 mM with a detection limit of 0.1 mM that is sufficient enough for distinguishing between normal and diabetes patient with a cut-off level of 0.3 mM. This platform might be an alternative tool for improving health management for diabetes patients.

Women Safety System Using ARM Micro controller and Arduino

This abstract presents a comprehensive women's safety device leveraging modern technology for effective emergency response. The device integrates various components including the Neo6M GPS module, module, Arduino Nano microcontroller, push button for emergency alert, , pulse oximeter MAX30100, and temperature sensor LM35. The Arduino Nano serves as the central processing unit, orchestrating data collection, processing, and transmission.Incorporating a Python Flask WebApp and ThingSpeak platform, the device ensures real-time alerts and cloud storage capabilities. The Flask WebApp facilitates user interaction and customization, enabling users to set preferences and receive notifications. ThingSpeak enables seamless data logging and retrieval from the cloud, ensuring data integrity and accessibility.Upon activation, the device initiates location tracking via the GPS module and triggers an emergency alert through the module. Simultaneously, vital signs such as pulse rate and temperature are monitored using the MAX30100 pulse oximeter and LM35 temperature sensor respectively. These data are transmitted to the Flask WebApp and ThingSpeak platform for real-time monitoring and alert generation.This innovative solution aims to provide women with a reliable, multifunctional safety device capable of prompt emergency response and continuous monitoring, ultimately enhancing their safety and well-being in various settings. Key Words: Safety system, ARM micro-controller, Arduino, GPS, Alerting, Web-Application.

Paper-based humidity sensor for wearable based on near-field electrohydrodynamic direct writing

Flexible humidity sensors have been widely used in wearable electronics, owing to their flexibility and compatibility with electronic device substrates. This study fabricated a flexible paper-based humidity sensor with a grid-like sensing film using the near-field electrohydrodynamic direct writing (NFEDW) method. A grid-like sensing layer with a dense network of carbon nanotubes/cellulose nanofiber (CNTs/CNF) was prepared, and induced by a voltage field applied during printing. The effects of the substrates and pattern width on the performance of the sensor were systematically investigated. The prepared sensor exhibited high sensitivity of 101 % at 95 % relative humidity (RH). An interlocking structure formed between the CNTs/CNF composite and the paper substrate, endowing the sensor with outstanding bending (minimum diameter of 5 mm) and folding (up to 100 times) durability. Furthermore, the prepared sensor exhibited rapid response performance (17 % within 10 s). This addresses the issue of long response time, which is typically associated with CNTs-based sensors, making these sensors more suitable to practical applications. The above-mentioned advantages enable the sensor to be used for respiration monitoring and even for vocal recognition. Finally, a real-time respiration monitoring platform was developed to demonstrate the sensor’s potential in wearable devices.

Plant Information Management System Using OSIsoft PI System: A Case Study of Cilacap Power Plant Units 1 and 2

In the dynamic industrial sector, the ability to combine and manage data from various sources is essential. This study focuses on the utilization of the PI System to integrate operational data from multiple data sources at power plants, facilitating data driven decision making and enhancing operational efficiency. The application of the PI System in collecting data from Distributed Control Systems (DCS) and asset management systems like Maximo is examined, as well as its potential for integrating data from other power plant units. The study utilizes systems analysis methods to understand the potential of data integration in improving operational visibility and control. Findings from testing reveal that effective data integration can extend monitoring and management capabilities, indicating an overall improvement in operational performance. This study contributes to the literature on industrial data management by demonstrating the effective use of the PI System as a comprehensive tool for integrating data from various systems within power plants. It showcases the system's adaptability in enhancing operational decision-making and providing a cohesive platform for real-time performance monitoring. Additionally, the research offers insights into the practical application of systems analysis methods in the context of power plant operations, contributing to the ongoing discourse on digital transformation in the energy sector.

All-in-one strategy for the nano-engineering of paper-based bifunctional fluorescent platform for robustly-integrated real-time monitoring of food and drinking-water safety

Cu2+ contamination and food spoilage raise food and drinking water safety issues, posing a serious threat to human health. Besides, Cu2+ and H2S levels indicate excess Cu2+-caused diseases and protein-containing food spoilage. Herein, a coumarin-containing bifunctional paper-based fluorescent platform integrated with a straightforward smartphone color recognition app is developed by an all-in-one strategy. The proposed fluorescent materials can simultaneously detect Cu2+ and H2S for on-demand food and drinking water safety monitoring at home. Specifically, a coumarin-derived fluorescence sensor (referred to as CMIA) with a low detection limit (0.430 μM) and high-selectivity/-sensitivity for Cu2+ is synthesized through a simple one-step route and then loaded onto commercially used cellulose fiber filter paper to engineer a biomass-based fluorescent material (CMIA-FP). The CMIA-FP offers user-friendly, high-precision, fast-responsive, and real-time visual monitoring of Cu2+. Moreover, CMIA forms a chemically stable complex with Cu2+, loaded onto filter paper to prepare another biomass-based fluorescent platform (CMIA-CU-FP) for visual real-time monitoring of H2S. Based on the exquisite composition design, the proposed dual-function paper-based fluorescent materials equipped with a smartphone color recognition program concurrently realize fast, accurate, and easy real-time monitoring of Cu2+ in drinking water and H2S in chicken breast-/shrimp-spoilage, demonstrating an effective detection strategy for the Cu2+ and H2S monitoring and presenting the new type of biomass-based platforms for concentrated reflection of drinking water and food safety.

A Highly Integrated Lab-on-a-CMOS Platform for Real-Time Monitoring of E. Coli Growth Kinetics.

Existing miniaturized and cost-effective solutions for bacterial growth monitoring usually require offline incubators with constant temperature to culture the bio-samples prior to measurement. Such a separated sample preparation and detection scheme requires extensive human intervention, risks contamination, and suffers from poor temporal resolution. To achieve integrated sample preparation and real-time bacterial growth monitoring, this article presents a lab-on-a-CMOS platform incorporates an optical sensor array, temperature sensor array, micro-heaters, and readout circuits. Escherichia coli's (E. coli) optimum growth temperature of 37 °C is achieved through a heat regulation system consisting of two micro-heaters and an on-chip temperature sensor array. A photodiode array with an in-pixel capacitive trans-impedance amplifier to reduce inter-pixel cross-coupling is designed to extract the optical information during bacterial growth. To balance the footprint, power consumption, and quantization speed, a 10 b column successive-approximation register (SAR)/single-slope (SS) dual-mode analog-to-digital converter (ADC) is designed to digitize the temperature and optical signals. Fabricated in a standard 0.18 um CMOS process, the proposed platform can regulate the sample temperature to 37 +/- 0.2/0.3 °C within 32 mins. Enabled by an on-chip heat regulation system and photodetectors, the prototype demonstrates a real-time monitoring of bacterial growth kinetics and antibiotic responses. Minute-level temporal resolution is achieved as this proposed platform is free of extensive and time-consuming human intervention. The proposed platform can be viably used in contamination sensitive applications such as antibiotic tests, stem cell cultures, and organ-on-chips.

Portable ECG monitoring system with IOT analysis

This system is designed to calculate the heart rate of patients and transmit the data in beats per minute (bpm) to a cloud database. By using this system, doctors can analyze critical parameters remotely. The project involves interfacing the AD8232 ECG Sensor with the NodeMCU ESP8266 Board to monitor ECG waveforms on a Serial Plotter Screen and transmit the data to an IoT cloud platform for real-time monitoring. This innovation allows for remote monitoring of heart activity, reducing the need for hospital stays. Utilizing the Blynk IoT platform, the system ensures online access via PC or Smartphone, representing a significant advancement in patient health monitoring. This approach aims to improve early detection and prevention of heart diseases, enhancing patient care and reducing fatalities.

Preparation of multifunctional hydrogels based on co-pigment-polysaccharide complexes and establishment of a machine learning monitoring platform

Economic loss due to fish spoilage exceeds 25 billion euros every year. Accurate and real-time monitoring of the freshness of fish can effectively cut down economic loss and food wastage. In this study, a dual-functional hydrogel based on sodium alginate-co-pigment complex with volatile antibacterial and intelligent indication was prepared and characterized. The characterization results indicated that the sodium alginate-co-pigment complex successfully improved the stability and color development ability of blueberry anthocyanins and bilberry anthocyanins at different temperatures and pH. The double cross-linking network inside the hydrogel conferred it with excellent mechanical properties. During rainbow trout storage, the hydrogel indicated a color difference of 73.55 on the last day and successfully extended the shelf-life of rainbow trout by 2 days (4 °C). Additionally, four dual-channel monitoring models were constructed using machine learning. The validation error of the genetic algorithm back propagation model (GA–BP) was only 5.6e-3, indicating that GA-BP can accurately monitor the freshness of rainbow trout. The rainbow trout real-time monitoring platform built based on GA-BP model can monitor the freshness of rainbow trout in real time through the images uploaded by users. The results of this study have broad applicability in the food industry, environmental conservation, and economic sustainability.