Reliable Monitoring Research Articles

Statistical analysis of regional STEC gradient trends for midlatitude ionosphere

In this study, the gradients of Total Electron Content (TEC) for a midlatitude region are estimated and grouped with respect to the distance between neighboring stations, time periods within a day, and satellite directions. Annual medians of these gradients for quiet days are computed as templates. The metric distances (L2N) and Symmetric Kullback-Leibler Distances (SKLD) are obtained between the templates and the daily gradient series. The grouped histograms are fitted to the prospective Probability Density Functions (PDF). The method is applied to the Slant Total Electron Content (STEC) estimates from the Turkish National Permanent GPS Network (TNPGN-Active) for 2015. The highest gradients are observed in the east-west axis with a maximum of 25 mm/km during a geomagnetic storm. The maximum differences from the gradient templates occur for neighboring stations within 100–130 km distance away from each other, during night hours, and for regions bordering the Black Sea and the Mediterranean in the northeast and southeast of Turkey. The empirical PDFs of the station-pair gradients are predominantly Weibull-distributed. The mean values of Weibull PDFs in all station groups are between 1.2 and 1.8 mm/km, with an increase during noon and afternoon hours. The standard deviations of the gradient PDFs generally increase during night hours. The algorithm will form a basis for quantifying the stochastic variations of the spatial rate of change of TEC trends in midlatitude regions, thus supplementing reliable and accurate regional monitoring of ionospheric variability.

Rapid determination of hippuric acid as an exposure biomarker of toluene using a colorimetric assay and comparison with high-performance liquid chromatography

Occupational exposure to toluene is associated with health risks that require reliable monitoring methods. Hippuric acid (HA), a urinary metabolite of toluene, serves as a valuable biomarker for such exposure. Colorimetric methods for the quantitative determination of HA have gained prominence due to their simplicity, cost-effectiveness, and suitability for field application. In the present study, a simple colorimetric technique was optimized for the determination of HA in the urine sample, and compared with a usual HPLC technique. The central composite design (CCD) was applied to examine the effective parameters on the colorimetric determination of HA. The calibration curve for HA was established within the concentration range of 6 to 100 mg L−1 with R2 = 0.97. The detection limit (LOD) and quantification limit (LOQ) were determined to be 1.8 mg L−1 and 6 mg L−1 respectively. The relative standard deviation (RSD%) was less than 5%, and the recovery% (R%) was 90.5–100.1. The overall results showed good agreement between the colorimetric and HPLC results. There was a significant relationship between the results obtained from HPLC and colorimetric methods especially for higher concentration levels of HA (≥ 500 mg/g creatinine). In conclusion, our optimized colorimetric method is a simple, cost-effective, and rapid method for determination of HA in occupational exposure, which is comparable with the HPLC technique.

Smart and Intelligent Prayer System for Elderly Muslim with IoT

An assistive and monitoring prayer system has been designed to help elderly Muslims in performing their daily prayers. However, the system has several limitations in the aspect of efficiency, cost, size, complexity, security and usability. In this paper, several enhancements have been proposed to improve the existing smart prayer system including a better approach to retrieve exact prayer times, efficient way to retrieve current date/time, two different sensors used to detect the physical movements, smaller microcontroller with a built-in Wi-Fi module and the fabrication of PCB board. On the monitoring system, this project offers a more user’s friendly mobile application with several enhanced features. Reminder and authentication features are added to the mobile application for increased security and usability. The mobile application only allowed authorized or registered users to use the mobile application to view prayer performance of the elderly and send a prayer reminder to the elderly. The proposed system implements Internet of Things (IoT) technology, with a microcontroller communicating with the database through Wi-Fi, and data is modified before being displayed via the mobile application. Experimental testing shows a high level of support for the system's commercialization due to its ability to assist and monitor the elderly with their daily prayers. This new smart prayer system offers a more reliable assistive and monitoring system for elderly Muslim.

Improving mean water lake surface elevation estimates using dense lidar measurements from the GEDI satellite mission

Lakes are an essential component of the global water cycle and are considered as sentinels of climate change. An accurate estimate of lake's water levels is necessary for reliable continuous monitoring of their water balance. Due to their huge number worldwide, satellite altimetry has been identified as an efficient tool for measuring their temporal variations of water level. This technique can reach an accuracy of a few centimeters for water level estimates over large lakes. Due to the coarse across-track spatial resolution of the radar altimetry missions, their spatial sampling only covers a small part of the lakes surface. To obtain an accurate estimate of the lake water level, it is necessary to apply a correction to account for the small-scale orthometric height undulations occurring on the lake area and not present in the current global geoid models. In this study, the high-density lidar measurements from GEDI are used to estimate the mean lake surface. From the 1,366,211 GEDI data over 1239 tracks acquired over more than 6000 km2 of the surface of Lake Issy-Kul (Kyrgyzstan, Central Asia) between May 2019 and mid-November 2021, 654,592 shots over 843 tracks were selected after a multi-step quality-check and processed to generate a mean lake surface of Lake Issyk-Kul. Comparison between the GEDI-based mean lake surface and GNSS kinematic surveys corrected from the lake level variations exhibit an RMSE of 0.065 m. The principal objective of performing such mean lake surface is to further use it in the framework of the calibration/validation of the Surface Water and Ocean Topography (SWOT) mission.

Reliable ratiometric colorimetric monitoring of dopamine in practice based on the catalytic signal amplification of nano CeO2/CuO modified carboxylated chitosan

To reliably monitor dopamine (DA), a common neurotransmitter, a kind of nano CeO2/CuO modified carboxylated chitosan nanozyme (CeO2/CuO@CC) was constructed under microwave-assisted conditions. The proposed CeO2/CuO@CC exhibited superior synergistic- enhancement oxidase-like activity, with high specific surface area and superior stability. It could accelerate the oxidization of colorless 3,3′,5,5′-tetramethylbenzidine (TMB) into blue oxTMB in the air. What’s more, the presence of trace DA could exclusively change the enzyme-like activity of CeO2/CuO@CC, accompanied with visual color changes from blue to colorless. Under the optimized conditions, there expressed double ratiometric linear relationships between lg(A652/A285)/lg(A370/A285) and cDA, with a large linear range between 6.0 × 10−9 and 1.0 × 10−5 M of DA. When applied for visual detection of DA in real samples, the detection limit was low to 2.0 × 10−9 M with RSD % less than 4.14 %. The mechanisms for enhanced oxidase-mimic activity of CeO2/CuO@CC and its selective detection of DA were proposed. This work will offer an insight to design efficient nanozyme for visual detection of bio-analytes in practice.

IoT-Driven solutions for VANET trustworthiness: Examining misconduct and position security challenges

Vehicular ad hoc networks (VANETs) improve the traffic management and road safety by exchanging real-time data between automobiles and roadside infrastructure. Reliable Intelligent Transport Systems (ITS) solutions tend to boost VANET data security, integrity and dependability. These systems communicate VANET data between infrastructure and automobiles using sensors, Internet of Things (IoT) devices and communication technologies. IoT-driven includes a Real-Time Traffic Observation optimizes VANET route design. Traffic management and safety improve with ITS-connected cars and infrastructure. Remote communication technologies enhance traffic management and decision-making by sending a real-time data between cars and infrastructure. Smart parking systems use real-time parking availability data from IoT sensors and devices to maximize space use and reduce congestion. Security and misbehavior are dependable problems in 40 IoT-driven VANET studies. Miscommunication and unstandardized are the main security issues which pose hazards. This review shows VANETs that requires authentication, encryption and anomaly detection to prevent attacks and IoT for transportation sector. This extensive review covers VANET reliability and IoT-driven real-time traffic monitoring, ITS, remote communication and intelligent parking systems. This review analyzes the metrics to assess the many detection techniques which includes, misconduct-Aware On-Demand Collaborative Intrusion Detection System (MACIDS) and Collision-Induced Dissociation Spectroscopy (CIDS), (i) Accuracy (ii) False Positive Rate, (iii) precision, (iv) recall (v) False Negative Rate and (vi) F1-Score in VANET security in Attack Detection Rates (ADR), misbehavior detection, evaluation metrics and detection algorithms were studied using CIC-IDS data. Due to misconduct and security issues, a strong IoT-driven solutions are required to improve VANET trustworthiness and offers a secure and reliable vehicular communication networks for safer and more efficient transportation systems.

Experimental Study on Enhanced Methane Detection Using an MEMS-Pyroelectric Sensor Integrated with a Wavelet Algorithm.

An optical sensing approach that balances portability with cost efficiency has been designed for the reliable monitoring of fugitive methane (CH4) emissions. Employing a LiTaO3-based pyroelectric detector integrated with micro-electro-mechanical systems and a broad infrared source, the developed gas sensor adeptly measured CH4 concentrations with a low limit of detection of about 5.6 ppmv and showed rapid response times with t90 consistently under 3 s. Notably, the novelty of our method lies in its precise control and reduction of CH4 levels, enhanced by wavelet denoising. This technique, optimized through meticulous grid search, effectively mitigated noise interference noticeable at CH4 levels below 10 ppmv. Postdenoising, nonlinear regression analyses based on the modified Beer-Lambert equation returned R2 values of 0.985 and 0.982 for the training and validation sets, respectively. In conclusion, this gas sensor has been shown to be able to meet the requirements for early warning of CH4 leakage on the surface in various carbon capture, utilization, and storage projects such as enhanced oil or gas recovery projects using CO2 injection.

Denaturing mass photometry for rapid optimization of chemical protein-protein cross-linking reactions

Chemical cross-linking reactions (XL) are an important strategy for studying protein-protein interactions (PPIs), including low abundant sub-complexes, in structural biology. However, choosing XL reagents and conditions is laborious and mostly limited to analysis of protein assemblies that can be resolved using SDS-PAGE. To overcome these limitations, we develop here a denaturing mass photometry (dMP) method for fast, reliable and user-friendly optimization and monitoring of chemical XL reactions. The dMP is a robust 2-step protocol that ensures 95% of irreversible denaturation within only 5 min. We show that dMP provides accurate mass identification across a broad mass range (30 kDa–5 MDa) along with direct label-free relative quantification of all coexisting XL species (sub-complexes and aggregates). We compare dMP with SDS-PAGE and observe that, unlike the benchmark, dMP is time-efficient (3 min/triplicate), requires significantly less material (20–100×) and affords single molecule sensitivity. To illustrate its utility for routine structural biology applications, we show that dMP affords screening of 20 XL conditions in 1 h, accurately identifying and quantifying all coexisting species. Taken together, we anticipate that dMP will have an impact on ability to structurally characterize more PPIs and macromolecular assemblies, expected final complexes but also sub-complexes that form en route.

Ultra-sensitive and rapid detection of Salmonella enterica and Staphylococcus aureus to single-cell level by aptamer-functionalized carbon nanotube field-effect transistor biosensors

Foodborne diseases caused by Salmonella enterica (S. enterica) and Staphylococcus aureus (S. aureus) significantly impact public health, underscoring the imperative for highly sensitive, rapid, and accurate detection technologies to ensure food safety and prevent human diseases. Nanomaterials hold great promise in the development of high-sensitivity transistor biosensors. In this work, field-effect transistor (FET) comprising high-purity carbon nanotubes (CNTs) were fabricated and modified with corresponding nucleic acid aptamers for the high-affinity and selective capture of S. enterica and S. aureus. The aptamer-functionalized CNT-FET biosensor demonstrated ultra-sensitive and rapid detection of these foodborne pathogens. Experimental results indicated that the biosensor could detect S. enterica at a limit of detection (LOD) as low as 1 CFU in PBS buffer, and S. aureus at an LOD of 1.2 CFUs, achieving single-cell level detection accuracy with exceptional specificity. The biosensor exhibited a rapid response time, completing single detections within 200 s. Even in the presence of interference from six complex food matrices, the biosensor maintained its ultra-sensitive (3.1 CFUs) and rapid response (within 200 s) characteristics for both pathogens. The developed aptamer-functionalized CNT-FET biosensor demonstrates a capability for low-cost, ultra-sensitive, label-free, and rapid detection of low-abundance S. enterica and S. aureus in both buffer solutions and complex environments. This innovation holds significant potential for applying this detection technology to on-site rapid testing scenarios, offering a promising solution to the pressing need for efficient and reliable pathogen monitoring in various settings.

MelSPPNET—A self-explainable recognition model for emerald ash borer vibrational signals

IntroductionThis study aims to achieve early and reliable monitoring of wood-boring pests, which are often highly concealed, have long lag times, and cause significant damage to forests. Specifically, the research focuses on the larval feeding vibration signal of the emerald ash borer as a representative pest. Given the crucial importance of such pest monitoring for the protection of forestry resources, developing a method that can accurately identify and interpret their vibration signals is paramount.MethodsWe introduce MelSPPNET, a self-explaining model designed to extract prototypes from input vibration signals and obtain the most representative audio segments as the basis for model recognition. The study collected feeding vibration signals of emerald ash borer larvae using detectors, along with typical outdoor noises. The design of MelSPPNET considers both model accuracy and interpretability.ResultsExperimental results demonstrate that MelSPPNET compares favorably in accuracy with its similar non-interpretable counterparts, while providing interpretability that these networks lack. To evaluate the interpretability of the case-based self-explaining model, we designed an interpretability evaluation metric and proved that MelSPPNET exhibits good interpretability. This provides accurate and reliable technical support for the identification of emerald ash borer larvae.DiscussionWhile the work in this study is limited to one pest type, future experiments will focus on the applicability of this network in identifying other vibration signals. With further research and optimization, MelSPPNET has the potential to provide broader and deeper pest monitoring solutions for forestry resource protection. Additionally, this study demonstrates the potential of self-explaining models in the field of signal processing, offering new ideas and methods for addressing similar problems.

Harnessing the power of artificial intelligence: A new door for quick surgery in Pakistan.

Artificial intelligence (AI) has the potential to transform surgery in Pakistan, improving results, reducing complications, and increasing patient safety. Deep learning, a branch of machine learning, can assist surgeons in making wise judgments. Pubmed and Research Gate discuss the promise of AI in surgery. Incorporating AI in healthcare systems can expedite diagnosis and management while avoiding injudicious resource allocation. AI-based techniques in cardiology, nephrology, and neurology enable high-accuracy detection of cardiovascular disease risks, kidney disease treatment, and epileptic episode identification. Neurological devices like bispectral index monitor (BIS) and Near-infrared spectroscopy (NIRS) utilize advanced technology for reliable monitoring and objective diagnosis of neurological issues (Ahmed, 2022). AI uses electronic data and neural network methods to evaluate operating room logistics, time management, and anesthesiologist activities using electronic data and neural network methods (Khan F. H., 2019). AI algorithms are effectively detect minute differences for accurate diagnosis, with studies showing high specificity, sensitivity, and inter-operator repeatability. AI can be used to train and assess neurosurgical residents and early mid-career surgeons, improving diagnosis and 3D simulation labs (Shlobin, 2022). Surgeons play a crucial role in adopting AI-based technologies for surgical care by partnering with data scientists to capture novel clinical data and generate meaningful interpretations. They should demand transparency and interpretability in algorithms to hold AI accountable for its predictions and recommendations.AI advancements in plastic surgery practice, research, and education offer opportunities for improvement. Combining AI-enabled decision-making tools with predictive analytics and human intuition, surgeons can make real-time decisions based on 3D planning, anatomical localization, and navigation (Rasteau, 2022). While current AI tools cannot perform complex surgical procedures, advancements may enable them to perform more complex tasks in the future. Pakistan is a significant market for AI-based solutions, utilizing technology in various industries to address challenges and boost demand. The country has enhanced its self-security systems, including AI-powered missiles, cyber security, and effective cameras (Khan, 2022). AI allows tasks to be completed more precisely and efficiently, with machine learning and deep learning being advanced subtypes. In developing countries like Pakistan, AI tools are needed for patient-centred diagnosis and treatment assistance, especially in emergency surgery such as cardiac illnesses or life threatening bleeding caused road traffic accident. Hence insuring patient receive care timely. An appropriate budget should be allocated for AI technologies in the health sector.

Hybrid Random Forest Regression and Artificial Neural Networks for Modelling and Monitoring the State of Health of Li-Ion Battery

Lithium-ion batteries play a significant role in modern energy storage systems for a number of applications, including renewable energy installations, electric cars, and portable devices. In order to guarantee the long-term dependability and safety of these battery packs, comprehensive modelling and monitoring approaches are required for accurate State of Health (SoH) evaluation. This research suggests an innovative strategy that combines the strengths of Random Forest Regression (RFR) and Artificial Neural Networks (ANN) for reliable Li-ion battery SoH modelling and monitoring. The research starts with the collection of thorough Li-ion battery data, which includes voltage, current, temperature, and cycling characteristics. The battery dataset's nonlinear relationships are captured utilising RFR as the main modelling method. In terms of feature selection and prediction precision, RFR's ensemble of decision trees shines, making it a strong contender for modelling complex battery behaviour. The SoH prediction is then enhanced by the use of ANN, a deep learning framework renowned for its ability to extract detailed patterns from data. The characteristics of RFR are complemented by ANN's capacity to discover hidden features and nonlinear correlations, improving the overall prediction performance. The suggested hybrid approach, that combines RFR and ANN, is trained and verified utilising a diverse database acquired from Li-ion battery sources under operational circumstances. To assess the prediction accuracy of a suggested framework measures like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values are employed. The outcomes show that the hybrid RFR-ANN model works better than the individual RFR and ANN models, producing better SoH predictions. A viable solution for real-time Li-ion battery health monitoring is provided by this combination of conventional ML and deep learning approaches, which demonstrates the synergy among complexity and interpretability. This research advances battery SoH assessment and paves the way for the practical incorporation of precise monitoring systems into applications like electric vehicles, where timely and accurate SoH data is essential for maximising battery performance and extending operational lifespan.

Development and Research of Safety Video Monitoring System for Loading and Unloading of Chemical Products in Railway Transportation

As the important position of chemical railroad transportation in modern logistics is becoming more and more prominent, its safety problem has attracted wide attention. To improve the safety of transporting chemicals by rail, this paper strives to develop an advanced safety monitoring system. The main background of this paper is the serious potential results of chemical products railroad transportation accidents which require an effective monitoring method to prevent. The purpose of this research is to design and realize an efficient and reliable video monitoring system to monitor the loading and unloading of chemicals transported by railroads in real-time. To achieve this goal, we adopted comprehensive methods, including video image recognition technology, data analysis technology, communication network technology, etc., which have significant meaning in preventing railroad accidents of chemical product transportation and safeguarding people’s life and property.

Fast-Response and Low-Power Self-Heating Gas Sensor Using Metal/Metal Oxide/Metal (MMOM) Structured Nanowires.

With the escalating global awareness of air quality management, the need for continuous and reliable monitoring of toxic gases by using low-power operating systems has become increasingly important. One of which, semiconductor metal oxide gas sensors have received great attention due to their high/fast response and simple working mechanism. More specifically, self-heating metal oxide gas sensors, wherein direct thermal activation in the sensing material, have been sought for their low power-consuming characteristics. However, previous works have neglected to address the temperature distribution within the sensing material, resulting in inefficient gas response and prolonged response/recovery times, particularly due to the low-temperature regions. Here, we present a unique metal/metal oxide/metal (MMOM) nanowire architecture that conductively confines heat to the sensing material, achieving high uniformity in the temperature distribution. The proposed structure enables uniform thermal activation within the sensing material, allowing the sensor to efficiently react with the toxic gas. As a result, the proposed MMOM gas sensor showed significantly enhanced gas response (from 6.7 to 20.1% at 30 ppm), response time (from 195 to 17 s at 30 ppm), and limit of detection (∼1 ppm) when compared to those of conventional single-material structures upon exposure to carbon monoxide. Furthermore, the proposed work demonstrated low power consumption (2.36 mW) and high thermal durability (1500 on/off cycles), demonstrating its potential for practical applications in reliable and low-power operating gas sensor systems. These results propose a new paradigm for power-efficient and robust self-heating metal oxide gas sensors with potential implications for other fields requiring thermal engineering.

A novel albumin-based supramolecular biosensor for ratiometric on-site determination of buprofezin

Buprofezin (BUP) is an effective insecticide against Homopteran and Thysanoptera pests. However, exposure to BUP may result in several harmful effects on the non-target organism including human body, such as hepatotoxicity and DNA damage. Therefore, development of a reliable analytical method for BUP holds paramount importance. This study presents a novel albumin-based supramolecular biosensor, DPP@ALB, designed for the sensitive detection of BUP in environmental matrices, including water, soil, and real food samples. The features of this biosensor include a fast response, high sensitivity, and visually detectable fluorescence color change, enabling on-site detection of BUP based on the portable paper strips and 3D-printed miniaturized testing system. Overcoming challenges associated with the low chemical reactivity of BUP, this supramolecular biosensor emerges as the very first fluorescent sensor for efficient and reliable monitoring of BUP with applications in broader areas of environmental analysis and food safety.

Sweat and Deformation‐Resistance Graphite/PVDF/PANI‐Based Temperature Sensor for Real‐Time Body Temperature Monitoring

AbstractBody temperature is critical indicator of human health, and its real‐time monitoring is crucial for assessing body status and disease diagnosis. In this work, a flexible temperature sensor is presented that employs a graphite/polyvinylidene fluoride (PVDF)/polyaniline composite and demonstrates a negative temperature coefficient (NTC). This sensor exhibits high sensitivity (−0.832%/ °C), rapid response time (11.05 s), and excellent linearity (R2 = 0.98). Its integration with a self‐adhesion PDMS‐PEG substrate layer ensures close skin contact, enhancing the accuracy of temperature measurements. Notably, the sensor's stability and resistance to sweat and deformation ensure continuous, reliable temperature monitoring, even during extensive exercise. This sensor thus represents a significant advancement in flexible and waterproof temperature sensing technologies.

Single cell analysis of Chinese hamster ovary cells during a bioprocess using a novel dynamic imaging system.

Reliable monitoring of mammalian cells in bioreactors is essential to biopharmaceutical production. Trypan blue exclusion is a method of determining cell density and viability that has been used for over one hundred years to monitor cells in culture and is the current standard method in biomanufacturing. This method has many disadvantages however and there is a growing demand for more detailed and in-line measurements of cell growth in bioreactors. This article assesses a novel dynamic imaging system for single cell analysis. This data shows that comparable total cell density, viable cell density and percentage viability data shown here, generated by the imaging system, aligned well with conventional trypan blue counting methods for an industrially relevant Chinese Hamster Ovary (CHO) cell line. Furthermore, detailed statistical analysis shows that the classification system used by the PharmaFlow system can reveal trends of interest in monitoring the health of mammalian cells over a 6-day bioreactor culture. The system is also capable of sampling at-line, removing the necessity for taking samples off-line and enabling real time monitoring of cells in a bioreactor culture.

Acquisition Devices for Fetal Phonocardiography: A Scoping Review.

Timely and reliable fetal monitoring is crucial to prevent adverse events during pregnancy and delivery. Fetal phonocardiography, i.e., the recording of fetal heart sounds, is emerging as a novel possibility to monitor fetal health status. Indeed, due to its passive nature and its noninvasiveness, the technique is suitable for long-term monitoring and for telemonitoring applications. Despite the high share of literature focusing on signal processing, no previous work has reviewed the technological hardware solutions devoted to the recording of fetal heart sounds. Thus, the aim of this scoping review is to collect information regarding the acquisition devices for fetal phonocardiography (FPCG), focusing on technical specifications and clinical use. Overall, PRISMA-guidelines-based analysis selected 57 studies that described 26 research prototypes and eight commercial devices for FPCG acquisition. Results of our review study reveal that no commercial devices were designed for fetal-specific purposes, that the latest advances involve the use of multiple microphones and sensors, and that no quantitative validation was usually performed. By highlighting the past and future trends and the most relevant innovations from both a technical and clinical perspective, this review will represent a useful reference for the evaluation of different acquisition devices and for the development of new FPCG-based systems for fetal monitoring.

Online monitoring of protein refolding in inclusion body processing using intrinsic fluorescence

Inclusion bodies (IBs) are protein aggregates formed as a result of overexpression of recombinant protein in E. coli. The formation of IBs is a valuable strategy of recombinant protein production despite the need for additional processing steps, i.e., isolation, solubilization and refolding. Industrial process development of protein refolding is a labor-intensive task based largely on empirical approaches rather than knowledge-driven strategies. A prerequisite for knowledge-driven process development is a reliable monitoring strategy. This work explores the potential of intrinsic tryptophan and tyrosine fluorescence for real-time and in situ monitoring of protein refolding. In contrast to commonly established process analytical technology (PAT), this technique showed high sensitivity with reproducible measurements for protein concentrations down to 0.01 g L-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{-1}$$\\end{document}. The change of protein conformation during refolding is reflected as a shift in the position of the maxima of the tryptophan and tyrosine fluorescence spectra as well as change in the signal intensity. The shift in the peak position, expressed as average emission wavelength of a spectrum, was correlated to the amount of folding intermediates whereas the intensity integral correlates to the extent of aggregation. These correlations were implemented as an observation function into a mechanistic model. The versatility and transferability of the technique were demonstrated on the refolding of three different proteins with varying structural complexity. The technique was also successfully applied to detect the effect of additives and process mode on the refolding process efficiency. Thus, the methodology presented poses a generic and reliable PAT tool enabling real-time process monitoring of protein refolding.Graphical abstractReal-time intrinsic fluorescence monitoring in protein refolding

Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective

AbstractIn the rapidly evolving landscape of manufacturing, the ability to make accurate predictions is crucial for optimizing processes. This study introduces a novel framework that combines predictive uncertainty with explanatory mechanisms to enhance decision-making in complex systems. The approach leverages Quantile Regression Forests for reliable predictive process monitoring and incorporates Shapley Additive Explanations (SHAP) to identify the drivers of predictive uncertainty. This dual-faceted strategy serves as a valuable tool for domain experts engaged in process planning activities. Supported by a real-world case study involving a medium-sized German manufacturing firm, the article validates the model’s effectiveness through rigorous evaluations, including sensitivity analyses and tests for statistical significance. By seamlessly integrating uncertainty quantification with explainable artificial intelligence, this research makes a novel contribution to the evolving discourse on intelligent decision-making in complex systems.