Mean Absolute Deviation Research Articles

Recycling of Waste PET Plastic on Asphalt, by Using Application of Response Surface Methodology: Effect of Production Process Parameters

Plastic, polymers of variable compositions have become object of common use and difficult to digest by micro-organisms, especially single-use plastic waste, such as polyethylene terephthalate (PET) water canisters. These polymers are source of environmental pollution. Therefore, it is important to manage theme in the good way to protect environment. In this study, different conditions of waste plastic PET (Polyethylene Terephthalate) recycling on asphalt were optimized. Response Surface Methodology (RSM) using the Doehlert experimental design has been employed in the optimization. The independent variables considered were bitumen (5-8%), PET (0-12%), Mixing temperature (150-160°C) and Mixing time (20-30min). Four-second order polynomial models were generated. The responses obtained by the models were well described as: specific density (Y.<SUB>SD</SUB>), penetrability (Y.<SUB>P</SUB>), softening point (Y.<SUB>SP</SUB>), and flash point (Y.<SUB>FP</SUB>) of the process with satisfactory fits in terms of absolute average deviation, bias factor and accuracy factor. The optimum responses were 1,04 as specificity gravity (Y.<SUB>SG</SUB>), 60*(1/10mm) as penetrability at 25°C, 100g and 5sec (Y.<SUB>P</SUB>), 50°C as softening point (Y.<SUB>SP</SUB>), and 242°C as flash point (Y.<SUB>FP</SUB>). The statistical relation between the four independent variables and the process responses were well described.

Predictive energy control for grid-connected industrial PV-battery systems using GEP-ANFIS

Rising energy costs in Uganda's industrial sector have significantly increased manufacturing expenses and led to the closure of potential enterprises, underscoring the urgent need for efficient energy management solutions. The study presents an optimization-based predictive energy control model that integrates Gene Expression Programming (GEP) and Adaptive Network-based Fuzzy Inference Systems (ANFIS) for grid-connected solar PV-battery systems. The hybrid GEP-ANFIS model leverages GEP's strength in complex pattern recognition and ANFIS's adaptive learning capability to manage nonlinear data, resulting in more accurate and reliable energy predictions. The model utilizes historical load patterns, grid data, and solar PV/battery inputs to forecast load demand and solar power generation, optimizing energy usage based on Time of Use (TOU) pricing. The approach addresses the limitations of existing energy management techniques by enhancing predictive accuracy and ensuring seamless integration with industrial applications. The present work demonstrates that the proposed GEP-ANFIS double diode model consistently outperforms its counterparts, achieving a mean absolute percentage error (MAPE) of 7.25 %, a mean absolute deviation (MAD) of 2.95 %, and a root mean square error (RMSE) of 8.42 %. Moreover, the model exhibits superior accuracy in predicting short-term load demand, with a MAPE of 2.24 %, a MAD of 0.13 %, and an RMSE of 0.18 %. Additionally, the model results in an average energy cost reduction of 6.7 % for hybrid grid-connected solar PV/battery configurations, highlighting its economic benefits. The study's key contributions include the creation of a novel hybrid predictive model, significant cost savings, improved load prediction accuracy, and the integration of renewable energy sources into industrial energy management. The model's inferences can effectively address the challenges of rising energy costs, providing a robust framework for sustainable and efficient energy management in industrial settings.

Machine Learning model for the prediction of self-diffusion coefficients in liquids, compressed gases and supercritical fluids

Machine Learning (ML) models were developed in this work to predict self-diffusion coefficients (D11) of dense fluids using four training algorithms: Gradient Boosting, k-Nearest Neighbors, Decision Tree, and Random Forest. A database of 7931 experimental points from 223 substances, at different pressures and temperatures, was used to train the models. From an initial set of 34 input features (variables/properties), the eight most important ones, ranked by decreasing relevance, were: density, acentric factor, temperature, critical temperature, critical volume, number of NH and/or OH bonds, pressure, and number of rotatable bonds. The best performance was achieved by models using the first 5 and 8 input features (ML5-D11 and ML8-D11) using the Gradient Boosting algorithm, for which the average absolute relative deviations (AARDglobal) were 9.06 % and 7.14 %, for the test set. The performance of the ML5-D11 and ML8-D11 models was compared with four phenomenological models – the predictive Zhu et al. equation, the 2-parameters Dymond-Hildebrand-Batschinski correlation, and the 1-parameter and 4-parameters Lennard-Jones correlations (LJ1 and LJ4) – which showed AARDglobal of 104.05 %, 82.94 %, 16.92 % and 7.97 %, respectively, for the same test set. Despite the good results of LJ4 equation, it is worth noting it embodies 4 substance-specific parameters that must be fitted to experimental data in advance. The new ML5-D11 and ML8-D11 models are purely predictive and can be applied to polar/nonpolar, spherical/non-spherical, and even hydrogen-bonding molecules in liquids, compressed gases or supercritical fluids. The ML5-D11 and ML8-D11 are provided for use as a Python program.

The M-Estimator and S-Estimator in Robust Improved Geographically and Temporally Weighted Regression for Modelling GRDP in West Java, Indonesia

The success of development in a region in Indonesia can be measured by economic growth, especially in the financial sector using the Gross Regional Domestic Product (GRDP) growth rate. The GRDP figure at the Regency and City level in West Java is one of Indonesia's highest and most diverse. This is due to various factors, including the geographical location of West Java, which is directly adjacent to DKI Jakarta, which is the center of the national economy. Although classified as high, the diversity of GRDP values between regions in West Java needs attention to equalize economic growth. The diversity of GRDP values can be modeled by the Improved Geographically and Temporally Weighted Regression (I-GTWR) method by taking samples in 2018-2022. The I-GTWR modeling method considers the influence of spatial heterogeneity and spatial-temporal interaction, which has been proven to produce better results than the GTWR method in modeling GRDP in Central Java in 2011-2015. This study also adds M-estimators and S-estimators to improve the model's performance and make it robust to outliers. The explanatory variables we use are Regional Original Revenue, General Allocation Fund, Foreign Investment, Regional Minimum Wage, Domestic Investment, Poverty, Per-Capita Expenditure, and Number of Job Vacancies. The analysis shows that the Robust I-GTWR model, especially the M-estimator, produces better model performance than the I-GTWR model in modeling West Java GRDP. The coefficient of determination made by the Robust I-GTWR method using the M-estimator is 94.62% with a mean absolute deviation value of 0.1491 and an Akaike Information Criterion value of 110.4899.

Omni-directional attitude detection of advanced hydraulic support relative to roadway based on visual measurement principle

In order to address the challenge of detecting the attitude of advanced hydraulic support in a harsh mine environment, this study proposes a binocular vision technology that accurately measures the omni-directional attitude of advanced hydraulic support relative to the roadway in real-time. The first step involves constructing a visual measurement system and optimizing the software development platform based on the actual motion conditions. Next, an innovative algorithm for space point reconstruction and omni-directional attitude is proposed. Finally, an indoor ground experimental platform is built to demonstrate the feasibility and effectiveness of the method by comparing it with high-precision experiments. The results show that the average absolute deviation of the measured attitude angle is within 0.4° and the average absolute deviation of the measured distance is within 6 mm, which meets the accuracy requirements of the fully mechanized mining equipment under the mine. This method has high measurement accuracy and sufficient visibility, which has important practical significance for ensuring the support efficiency of advanced hydraulic support and the intelligent production of working faces.

Optimizing pantograph fractional differential equations: A Haar wavelet operational matrix method

In this study, we developed an operational matrix method of integration using Haar wavelets to solve both linear and nonlinear pantograph fractional differential equations by taking Atangana's beta derivative. The proposed method utilizes an operational matrix and truncated Haar wavelet series to transform linear and nonlinear problems into objective functions. These objective functions are then minimized using differential evolution optimization. Illustrative examples demonstrate convergence and validation of the proposed method. The proposed method yields exceptional numerical outcomes in terms of competitiveness and accuracy when compared to exact solutions. In addition, performance metrics, including the mean absolute deviation, root mean squared error, P2norm, P∞ norm, Theil's inequality coefficient, variance account for, coefficient of determination, and Nash-Sutcliffe efficiency, were calculated for a varying number of collocation points. The results indicate that the Haar wavelet operational matrix method is a straightforward and efficient method for solving pantograph fractional differential equations.

An accurate handheld device to measure log diameter and volume using machine vision technique

Log diameter and volume measurements are crucial processes in the wood supply chain. Conventionally, the measurement mainly focuses on diameters and lengths. Despite the clear definition of conventional measurement methods, obtaining exact diameters is challenging due to the complexity of the measuring process and variability in the organic nature of logs. In this study, a smart handheld device, mainly composed of a single industrial camera, laser projectors, and a small embedded processor, is developed to capture and process log end images. Additionally, a measuring method is proposed, which consists of instance segmentation, contour fitting, and pose estimation, to automatically measure the diameters and estimate the volumes of cut-to-length (CTL) logs by using formulae. Specifically, instance segmentation is used to identify the salient object as a contour in the image space. Contour fitting is then applied to fit the contour into an ellipse, where the major and minor axes represent the long and short diameters of the object, respectively. Pose estimation is utilized to establish the relationship between the image space and physical space. Subsequently, several groups of comparative experiments are conducted with manual measurements as a reference. The experimental results indicate that, for log diameter measurement, approximately 97.33 % of the deviations between device measurement and conventional measurement can be expected to fall within a range of −0.54 cm and 0.61 cm, with mean absolute deviation (MAD) and mean relative deviation (MRD) of 0.25 cm and 0.78 %, respectively. In terms of volume estimations, MAD and MRD are found to be 0.23 and 0.56 %, respectively. The results imply that the device contributes to substantial improvements in accuracy, reliability, and traceability, and it shows promising potential to replace manual measurements.

Utilization of XGBoost algorithm to predict dryout incipience quality for saturated flow boiling in mini/micro-channels

Critical heat flux (CHF) is arguably the most important design parameter for applications involving cooling of high heat flux devices. Despite prior limited successes, developing accurate predictive tools for CHF remains quite challenging, but key identifiable trigger mechanisms for CHF are intermittent liquid film dryout, complete liquid film dryout, and departure from nucleate boiling (DNB). For saturated flow boiling in mini/micro-channels, dryout incipience is a necessary condition for commencement of liquid film dryout, which is marked by a substantial deterioration in the heat transfer coefficient. The primary objective of this study is to predict system parameters for dryout incipience quality using machine learning, relying on a massive database for this parameter. Predictions are achieved using eXtreme Gradient Boosting (XGBoost), one of the supervised ensemble machine learning methods. This technique is applied to the Purdue University Boiling and Two-Phase Flow Laboratory (PU-BTPFL) consolidated database for dryout incipience quality for saturated flow boiling in mini/micro-channels. This database comprises 997 datapoints amassed from 26 sources and encompasses 13 different working fluids, hydraulic diameters from 0.51 to 6.0 mm, mass velocities from 29 to 2303 kg/m2s, liquid-only Reynolds numbers from 125 to 53,770, boiling numbers from 0.31×104 to 44.3×104, and reduced pressures from 0.005 to 0.78. Optuna, a supervised automated hyper-parameter optimization software, is used to set the best hyper-parameters in the learning process based on the consolidated database. A part of consolidated database is used to train the XGBoost algorithm, and the XGBoost machine, consisting of specific input parameters, is developed with appropriately determined hyper-parameter set after optimization. The trained XGBoost machine is shown to provide remarkable accuracy in predicting the dryout incipience quality, evidenced by a mean absolute error (MAE) of 2.45% and mean absolute deviation (MAD) of 3.57×10−2.

Solubility of oxazepam in supercritical carbon dioxide: Experimental and modeling

This study thoroughly investigates the solubility of oxazepam in supercritical carbon dioxide (SC-CO2) at temperatures of 308, 318, 328, and 338 K and pressures ranging from 12 to 30 MPa. The solubility measurements revealed a mole fraction of oxazepam ranging from 2.50 × 10−6 to 7.13 × 10−5, with the highest solubility observed at 338 K and 30 MPa. The solubility data were effectively modeled using semi-empirical density-based models (Mendez-Santiago and Teja (MST), Chrastil, Bartle et al., Kumar and Johnston (K-J), and Alwi-Garlapati), two equations of state (Peng-Robinson and modified-Pazuki) and regular solution models. The K-J model emerged as the best fit for the experimental data, boasting the lowest Average Absolute Relative Deviation (AARD) value of 7.73 %. The Peng-Robinson equation of state outperformed the modified-Pazuki equation, with AARD values of 15.71 % and 18.15 %, respectively. The study's key finding is the low solubility of oxazepam in SC-CO2, which suggests that supercritical antisolvent techniques could be effectively employed for synthesizing nanoparticles of this pharmaceutical compound. These findings have practical implications as they provide valuable insights for optimizing drug formulation processes and demonstrate the potential of SC-CO2 in pharmaceutical applications.

A Modified Model of Micro-Scale Gas Seepage in Rock Porous Media

It is of significance to study the micro-scale gas seepage mechanism in rock porous media due to shale gas exploitation and prevention of tunnel gas explosion. However, current microscale seepage models have problems, such as poor accuracy or small computational domain. In this work, a representative volume element scale microscopic seepage model with high precision and large computational domain is established using the lattice Boltzamnn method. In the representative volume element scale model, micro-scale effect is considered by the Beskok-Karniadakis correction relationship. Then the accuracy of the representative volume element scale model is improved by proposing an equivalent resistance correction coefficient. The correction coefficient value is obtained by comparing the calculated result for the flow rate at a representative volume element scale and more precise pore scale. For example, when the porosity is 0.9 and the dimensionless specific surface area is 30, the corrected model can reduce the average deviation from 34.38 to 0.14%. Finally, to expand the applicability of the proposed model, a correlation for the correction coefficient is introduced as a function of the Knudsen number, porosity of porous media, and dimensionless specific surface area. The mean absolute percentage deviation of the correction coefficient correlation is 9.25%.

Intraoral ultrasonography image registration for evaluation of partial edentulous ridge: A methodology and validation study

ObjectivesUltrasound (US) reveals details for diagnosing soft- and hard-tissue dimensions around teeth, implants, and the edentulous ridge, not seen in 2D radiographs. Co-registering free-hand US scans with other 3D modalities presents reliability challenges. This study first aims to develop and validate a registration method to longitudinally reproduce US images of the jawbone on a simulator. In addition, it also evaluates the degree of the anatomical match in humans between US images acquired by the proposed registration method and the commonly used freehand acquisitions in comparison to cone beam computed tomography (CBCT) and intra-oral optical scan (IOS), used as references. MethodsA previously introduced ultrasound phantom was employed as a CBCT-US hybrid, suitable for training and technique development of US guides in edentulous ridges. After establishing feasibility in the phantom, the methodology was validated in a cohort of 24 human subjects (26 cases). Soft tissues were delineated on US and IOS, and hard tissues on US and CBCT. US accuracy and repeatability from both guided and freehand scans (non-guided) was assessed as the average distance between US and the references. ResultsGuided US images resembled the references more closely than freehand (non-guided) scans. Notably, delineation of soft and hard tissues was significantly more accurate when employing guides. In the phantom, guided scans exhibited an absolute mean deviation of 81.8 µm for gingiva and 90.4 µm for bone, whereas non-guided scans showed deviations of 150.4 µm and 177.2 µm, respectively. Similarly, in vivo, guided US outperformed non-guided US, with gingiva deviations of 125 µm and 196 µm, and bone deviations of 354 µm and 554 µm, respectively. ConclusionsBy using a registration method, guided US scans improved repeatability and accuracy of mapping hard and soft tissue of the edentulous ridge when compared to non-guided scans. Clinical relevanceThis guided US imaging method could lay the foundation for longitudinal evaluation of tissue behavior and dimensional changes with improved accuracy.

A hybrid algorithm for estimating total nitrogen from a large eutrophic plateau lake using Orbita hyperspectral (OHS) satellite imagery

Total nitrogen concentration (CTN) enrichment is the primary cause of natural water eutrophication. Accurately estimating CTN and its spatiotemporal dynamics is crucial for formulating monitoring and control measures to alleviate lake eutrophication. A hybrid model was proposed for estimating CTN in optically complex inland waters by incorporating the relationship between CTN and water optical active components for Zhuhai-1 Orbita hyperspectral (OHS) imagery. Compared with other semi-analytical algorithms, the re-adjusted reference wavelength QAA716 shows the best performance in aph(λ) retrieval. The hybrid model for CTN estimation achieves an root mean square deviation (RMSD) of 0.20 mg/L, a mean absolute percentage deviation (MAPD) of 6.96 %, and a unbiased mean absolute percentage deviation (UMAPD) of 6.96 %, with aph(569) accuracy exerting the greatest influence. Ground-satellite synchronous validation demonstrates robust performance, with an RMSD of 0.28 mg/L, a MAPD of 14.49 %, and a UMAPD of 14.92 %. The hybrid model was applied to OHS observations of Lake Dianchi from April 2019 to September 2021. The analysis revealed a generally decreasing trend in CTN during this timeframe. The above results demonstrate that the robustness and applicability of the proposed CTN hybrid model for inland waters with complex optical properties. Furthermore, satellite-based data products provide valuable information for formulating lake management strategies.

Experimental study of hollow fiber membrane contactor process using aqueous amino acid salt-based absorbents for efficient CO2 capture

Gas–liquid membrane contactors are a promising alternative to packed columns that suffer from channeling, bubble formation, and flooding problems. In this study, potassium serinate + piperazine (PSZ) and potassium alaninate + piperazine (PAZ), which are amino acid salts with good CO2 absorption performances and high surface tensions, are investigated to determine the effects of the operating parameters on the CO2 removal efficiency, CO2 absorption flux, CO2 loading, and overall mass-transfer coefficient in the membrane contactor process. The experimental results demonstrate that the 2.5 M PSZ and 2.5 M PAZ absorbents outperform 2.5 M monoethanolamine (MEA) under various operating conditions, including the gas flow rate, liquid flow rate, CO2 concentration, and CO2-loaded absorbent. Based on these results, an expression for predicting the CO2 loading from the pH is proposed. The amount of cross-over confirmed that amino acids with high surface tension have better resistance to membrane wetting than 2.5 M MEA. In addition, empirical correlation expressions were established from the results of several operating parameters. The absolute average deviation (AAD) values were 6.50 %, 2.95 %, and 4.71 % for 2.5 M MEA, 2.5 M PSZ, and 2.5 M PAZ, respectively, suggesting good agreement between the theoretical and experimental results.

Short-term forecasting of rooftop retrofitted photovoltaic power generation using machine learning

This paper explores short-term forecasting of rooftop retrofitted photovoltaic (PV) power generation using a Neural Networks (NN) model, highlighting its importance for energy management and grid integration. The study used data from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) of the Faculty of Electrical & Electronics Engineering Technology (FTKEE), capturing a 570.4 kWp rooftop PV system. The data, collected at 15-min intervals from January 29 to February 4, 2024, included thirty-three input features such as ambient temperature, horizontal irradiation, AC voltages, AC currents, and Maximum Power Point Trackers (MPPTs). The target was the total active power in kilowatts. The methodology involved partitioning the data into a training set covering the first five days and a testing set for the last two days. The NN model was compared with other machine learning approaches, including Long Short-Term Memory Networks (LSTM), Gated Recurrent Units (GRU), Random Forest (RF), and k-Nearest Neighbors (k-NN). Performance metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Maximum Error, and Standard Deviation were used to evaluate the models. The results showed that the NN model outperformed all other models, achieving an RMSE of 0.7098, an MAE of 0.3629, a Maximum Error of 3.901, and a Standard Deviation of 0.7076. These findings suggest that NN effectively capture complex patterns in rooftop PV system data, contributing to enhanced reliability and efficiency in short-term solar power forecasting. The study's implications extend to improved grid management and energy efficiency, underlining the significance of advanced machine learning techniques in renewable energy forecasting.

Lower bounds for the trade-off between bias and mean absolute deviation

In nonparametric statistics, rate-optimal estimators typically balance bias and stochastic error. The recent work on overparametrization raises the question whether rate-optimal estimators exist that do not obey this trade-off. In this work we consider pointwise estimation in the Gaussian white noise model with regression function f in a class of β-Hölder smooth functions. Let ’worst-case’ refer to the supremum over all functions f in the Hölder class. It is shown that any estimator with worst-case bias ≲n−β/(2β+1)≕ψn must necessarily also have a worst-case mean absolute deviation that is lower bounded by ≳ψn. To derive the result, we establish abstract inequalities relating the change of expectation for two probability measures to the mean absolute deviation.

Raman spectroscopy for the determination of hydrogen concentration in liquid organic hydrogen carrier systems

This work reports on the development of a calibration approach of Raman spectroscopy for the determination of the concentration of dissolved hydrogen (H2) in representative compounds and mixtures of liquid organic hydrogen carrier (LOHC) systems based on diphenylmethane and ortho-benzyltoluene (o-BT). Hydrogen solubility data are measured by the isochoric-saturation method at temperatures and pressures up to 473 K and 7 MPa where Raman spectra of the saturated liquid phase are recorded in parallel. By selecting an appropriate frequency range attributed to the LOHC signatures in isotropic spectra, a calibration which is independent of the LOHC system, the degree of hydrogenation of the LOHC samples, and temperature can be found. The transfer of the calibration to another setup is successfully tested up to 523 K and 6 MPa, where H2 solubilities in the fully hydrogenated o-BT can be determined with an average absolute deviation of 0.009 from theoretically calculated data.

Solubility of lumiracoxib in supercritical carbon dioxide

This study aims to use a static-based solubility method for measuring the solubility of lumiracoxib at a temperature of 308–338 K and pressure of 120–400 bar for the first time. The obtained solubility data for lumiracoxib is between 4.74 × 10−5 and 3.46 × 10−4 (mole fraction) for the studied ranges of pressure and temperature. The solubility values reveal that the lumiracoxib experiences a crossover pressure of about 160 bar. Moreover, the measured solubility data of these two drugs are correlated with density-based semi-empirical correlations namely Bartle et al., Mendez-Santiago-Teja, Kumar and Johnstone, Chrastil and modified Chrastil models with an average absolute relative deviation of 10.7%, 9.5%, 9.8%, 7.8%, and 8.7% respectively for lumiracoxib. According to these findings, it is obvious that all of the examined models are rather accurate and there is no superiority between these models for both examined drugs although the Chrastil model is slightly better in the overall view.

Experimental and modeling investigations on CH4 hydrate phase equilibria in multi-ion “Haima” cold seep environment

CH4 hydrate formation represents a primary pathway for CH4 transformation within the deep-sea CH4 seepage environment, holding utmost significance for global carbon budget and marine hydrate resources distribution. As a typical active CH4 seeping, however, the influence characteristics of various ions in in-situ “Haima” cold seep on CH4 hydrate stability remains unclear. In this study, founded on the multiple ion components from the seawater of the “Haima” cold seep, the effects of salt ion categories and concentrations on CH4 hydrate phase equilibrium were investigated, and a thermodynamic model suitable for high-salinity deep-sea environment was proposed. Results indicated that, in higher concentration salt solutions (>3.45 wt%), hydrate stability was no longer solely governed by salinity, and significant differences among ion types were observed. The inhibitory strength of the ions on CH4 hydrate stability followed the order of Mg2+>Na+>Ca2+>Mn2+≈K+>Sr2+>Ba2+. The predicted CH4 hydrate phase equilibrium conditions from the proposed model exhibited strong agreement with both experimental results and data reported in the literature. The average absolute deviation of pressure (AADP) from the model prediction was 2.7% and 4.3% compared to the experimental and published literature data, respectively, which outperformed those of the CSMHYD model, Chen-Guo model and Hu-Lee-Sum correlation (4.7%–6.2%). In light of the marine temperature gradient and prediction results, it is estimated that CH4 hydrate could maintain stably below 600 m depth of the seawater in the cold seep area.

Techno-economic analysis of AMP/PZ solvent for CO2 capture in a biomass CHP plant: towards net negative emissions

Compared to conventional monoethanolamine (MEA), alternative solvents are expected to substantially contribute to reduce the energy demand of post-combustion CO2 capture from flue gases. This study presents a comprehensive techno-economic analysis of a 27 wt% 2-amino-2-methyl-1-propanol (AMP) + 13 wt% piperazine (PZ) aqueous solution for CO2 capture, compared to a 30 wt% MEA solution. The study addresses the retrofit of a carbon capture unit to a biomass-fired combined heat and power (CHP) plant, effectively making it a bioenergy with a carbon capture and storage (BECCS) system. The treated flue gas has a flow rate of 23 tons/hour (t/h) with 11.54 vol% CO2 and a 90% capture rate is aimed for. Aspen Plus V14 was employed for process simulations. Initially, binary interaction parameters for AMP/PZ, AMP/H2O, and PZ/H2O are regressed using vapor-liquid equilibrium (VLE) data, which were retrieved from literature along with reaction kinetics. Validation of parameters from available experimental literature yields an average absolute relative deviation (AARD) of only 5.9%. Afterwards, a process simulation model is developed and validated against experimental data from a reference pilot plant, using a similar AMP/PZ blend, resulting in 5% AARD. Next, a sensitivity analysis optimizes operating conditions, including solvent rate, absorber/stripper packing heights, and stripper pressure, based on regeneration energy impact. Optimized results, compared to MEA, reveal that AMP/PZ reduces the energy consumption from 3.61 to 2.86 GJ/tCO2. The retrofitting of the capture unit onto the selected CHP plant is examined through the development of a dedicated model. Two control strategies are compared to address energy unavailability for supplying the capture unit. The analysis spans 4 months, selected to account for seasonal variations. At nominal capacity, CO2 emissions, rendered negative by biomass combustion and CO2 capture, reach a maximum of −3.4 tCO2/h compared to 0.36 tCO2/h before retrofitting. Depending on the control strategy and CHP plant operating point, the Specific Primary Energy Consumption for CO2 Avoided (SPECCA) ranges from 4.91 MJ/kgCO2 to 1.76 MJ/kgCO2. Finally, an economic comparison based on systematic methodology reveals a 7.87% reduction in capture cost favoring the AMP/PZ blend. Together, these findings highlight AMP/PZ as a highly favorable alternative solvent.

Towards interactive AI-authoring with prototypical few-shot classifiers in histopathology

A vast multitude of tasks in histopathology could potentially benefit from the support of artificial intelligence (AI). Many examples have been shown in the literature and first commercial products with FDA or CE-IVDR clearance are available. However, two key challenges remain: (1) a scarcity of thoroughly annotated images, respectively the laboriousness of this task, and (2) the creation of robust models that can cope with the data heterogeneity in the field (domain generalization). In this work, we investigate how the combination of prototypical few-shot classification models and data augmentation can address both of these challenges. Based on annotated data sets that include multiple centers, multiple scanners, and two tumor entities, we examine the robustness and the adaptability of few-shot classifiers in multiple scenarios. We demonstrate that data from one scanner and one site are sufficient to train robust few-shot classification models by applying domain-specific data augmentation. The models achieved classification performance of around 90% on a multiscanner and multicenter database, which is on par with the accuracy achieved on the primary single-center single-scanner data. Various convolutional neural network (CNN) architectures can be used for feature extraction in the few-shot model. A comparison of nine state-of-the-art architectures yielded that EfficientNet B0 provides the best trade-off between accuracy and inference time. The classification of prototypical few-shot models directly relies on class prototypes derived from example images of each class. Therefore, we investigated the influence of prototypes originating from images from different scanners and evaluated their performance also on the multiscanner database. Again, our few-shot model showed a stable performance with an average absolute deviation in accuracy compared to the primary prototypes of 1.8% points. Finally, we examined the adaptability to a new tumor entity: classification of tissue sections containing urothelial carcinoma into normal, tumor, and necrotic regions. Only three annotations per subclass (e.g., muscle and adipose tissue are subclasses of normal tissue) were provided to adapt the few-shot model, which obtained an overall accuracy of 93.6%. These results demonstrate that prototypical few-shot classification is an ideal technology for realizing an interactive AI authoring system as it only requires few annotations and can be adapted to new tasks without involving retraining of the underlying feature extraction CNN, which would in turn require a selection of hyper-parameters based on data science expert knowledge. Similarly, it can be regarded as a guided annotation system. To this end, we realized a workflow and user interface that targets non-technical users.