Reliable Model Research Articles

PersistVerify: Federated model ownership verification with spatial attention and boundary sampling

Federated learning, known for its emphasis on privacy and resource efficiency, has emerged as a transformative paradigm in the fields of artificial intelligence and industrial machine learning. However, with the advancement and widespread adoption of this technology, the concern of model theft in federated learning models becomes increasingly prominent. While current endeavors concentrate on protecting individual deep learning models, limited attention has been dedicated to those involved in federated learning, especially within decentralized environments. To fill this void, we introduce PersistVerify, an innovative approach for verifying model copyright within the federated learning framework. PersistVerify integrates boundary sample selection and spatial attention mechanisms, enhancing the robustness and confidentiality of neural network backdoor watermarks to ensure secure verification of model ownership. PersistVerify constructs a confidential and robust watermark dataset through three sequential steps: latent representation extraction, boundary sample selection, and spatial attention-based trigger embedding. Our research addresses the pervasive challenge of reliable model ownership verification in federated learning, demonstrating the efficacy of PersistVerify. This study provides valuable insights and methodologies to maintain the confidentiality and reliability of neural network backdoor watermarks in the domains of artificial intelligence and federated learning.

The Effect of Salt Concentration on Dielectric Permittivity and Interfacial Polarization in Carbonate Rocks with Complex Pore Structure

Summary Broadband dielectric dispersion measurements are attractive options for the assessment of water-filled porosity. Dielectric permittivity is influenced by salinity as well as other rock/fluid properties. However, the effect of salinity on Maxwell-Wagner polarization (i.e., interfacial polarization) and dielectric permittivity in rock samples with complex pore structures requires further investigation. The objectives of this work are (a) to perform frequency-domain dielectric permittivity numerical simulations on 3D pore-scale rock samples at different salt concentration levels, (b) to quantify the effect of salinity on dielectric permittivity and interfacial polarization in the frequency range between 20 MHz and 5 GHz, and (c) to quantify the critical frequency (i.e., the frequency at which the relative permittivity becomes frequency-independent). We first perform pore-scale frequency domain dielectric permittivity simulations in fully water-saturated carbonate samples with complex pore structures to obtain the complex dielectric permittivity in the frequency range of 0.01–5 GHz and at different salinity levels. Next, we numerically create partially water/hydrocarbon-saturated water-wet samples and perform simulations at different salinity and water saturation levels to investigate the combined effect of salinity and water saturation on dielectric permittivity. Finally, we investigate how reliable conventional mixing models, such as the complex refractive index model (CRIM) and Hanai-Bruggeman (HB), are in the assessment of water saturation at different salinity levels. We used 3D pore-scale rock samples with complex pore structures from Austin Chalk, Estaillades Limestone, and Happy Spraberry formations. The increase in salinity from 2 to 50 parts per thousand (PPT) resulted in the relative permittivity to increase by 18% at 20 MHz. Similarly, an increase in salinity from 2 PPT to 50 PPT resulted in electrical conductivity to increase by 15 times at 20 MHz. However, at 5 GHz, the difference between the relative permittivity of the samples at different salinities was negligible. We demonstrated that the critical frequency was above 1 GHz. Thus, if complex dielectric permittivity at 1 GHz is being used, an accurate salinity assumption is required in the interpretation of conventional dielectric mixture models in carbonate formations. Finally, we observed 52% and 42% average relative errors in water saturation quantification when applying CRIM and HB models at all the frequencies of interest, respectively. The results also indicated that conventional models should not be used in the presence of uncertainty in salinity at lower frequencies. The results of this work quantified the frequency at which the water-filled pore volume rather than the Maxwell-Wagner polarization controls the relative permittivity of rock samples saturated with a wide range of brine salinity. Moreover, the results demonstrated that the relative permittivity of the rock samples with complex pore structures may still be significantly affected by the interfacial polarization even at 1 GHz. Moreover, the results suggested that the conventional mixture methods cannot reliably take into account the salt concentration of formation water, and this can lead to significant errors in reserves assessment.

Reliability analysis method of competitive failure processes considering the coupling effect of multiple shock processes and degradation process

AbstractDuring the operational phase, complex systems are subject to various shocks, both random and continuous degradation. This coupling effect poses significant challenges for reliability assessment. The proposed method aims to provide a clear and objective evaluation of the system's reliability. In this paper, we propose a competitive failure reliability analysis method that considers the coupling effect of multiple shock processes and degradation processes. The random shocks are subdivided into external and internal shocks. The degradation increment is mainly influenced by external shocks, whereas internal shocks affect the degradation rate. The combined effect of these two shock processes accelerates the failure processes. Additionally, two different shock models are combined to create an extreme‐cumulative shock model to assess the impact of various shock processes and the degradation process on system reliability. The analysis examines the coupling effect between the degradation process and shock processes to explore the influence law between hard failure and soft failure. Subsequently, the reliability modeling of competitive failure processes is completed. Finally, practical case studies demonstrate the effectiveness and practicality of the proposed method.

Thrombosis in Acute Promyelocytic Leukemia: The Current Understanding.

Despite enormous improvement in the management of patients with acute promyelocytic leukemia (APL), the distinctive coagulopathy observed at presentation in affected patients is often life-threatening. While hemorrhagic manifestations are well known and described in this setting, APL-related thromboses are underappreciated. Data regarding this complication are scarce showing variable incidence. Furthermore, risk factors for thrombosis are inconsistent and unreliable; so, differentiation of increased risk of hemorrhage from an increased thrombotic risk is quite difficult in the absence of adequate predictive scores. Besides, prophylactic use of anticoagulants and recombinant thrombomodulin are a matter of ongoing debate. Also, due to the common feature of thrombocytopenia and other hemorrhagic risks, patients with APL are excluded from trials analyzing anticoagulant prophylaxis in cancers; so, data from prospective trials are lacking. A detailed analysis of thrombotic risks in APL with the development of a reliable risk stratification model is needed to further improve the care of APL patients.

Hydrological balance and runoff from a montane peat bog traced by water temperature

ABSTRACT Peatlands are hydrologically significant landscape units in mountain headwater catchments in Central Europe. In this study, the contribution of a peat bog to runoff and its annual water balance were analysed and compared with those of a forested mineral soil hillslope. A mixing model method using the water temperature as a tracer was applied, and the resulting ratio of peat bog water in streams was incorporated into a hydrological model. The mean peat bog contribution during baseflow ranged from 33.4% during the cold season to 48.9% during the warm season, while during runoff events, the contribution reached over 83%. The simulated water balance results showed a higher actual evapotranspiration on the mineral hillslope, which suggests a higher total runoff from the peat bog (1523 versus 1327 mm/year on the mineral hillslope). The results of this study enable more reliable modelling assessments of peatland reactions to climate change.

Modelling and optimizing microgrid systems with the utilization of real-time residential data: a case study for Palapye, Botswana

Microgrids are becoming a realistic choice for residential buildings due to the increasing need for affordable and sustainable energy solutions in developing nations. Through modeling and simulation, the main goal is to evaluate the viability and performance of a solar microgrid system. Residential load modeling is used, which is vital to developing an effective Energy Management System (EMS) for the microgrid. A residential household’s load metering data is examined using statistical methods, including time series and regression analysis. For the residential community load in this research, Proportional-Integral-Derivative (PID) controllers and Fuzzy Logic Controllers (FLC) are used to generate the necessary Direct Current (DC) microgrid voltage. The simulation research shows that FLC have benefits over PID controllers. The FLC technique performs better at reducing total harmonic distortion, which improves the microgrid system’s overall power quality. The Seasonal Autoregressive Integrated Moving Average (SARIMA) model was found to be the most appropriate and reliable model for the dataset after the performance of the models was evaluated using the metrics. The optimization results also showed that FLC optimization improves the microgrid system’s stability. The exponential Gaussian process regression (GPR) produced the highest R-squared measure of 0.49 and RSME measure of 7.9646, making it the best goodness fit for modeling the total daily energy usage and the peak daily usage.

Investigating the economic impact of climate change on agriculture in Iran: Spatial spillovers matter

AbstractIn this study, we enhance our understanding of the economic impacts of climate change on agriculture in Iran to provide further information for moving Iran's climate policy forward by linking farmland net revenue to novel climatic and non‐climatic variables. We take advantage of spatial panel econometrics to better circumvent omitted factors extraneous to the agricultural sector and to develop a more reliable and consistent model when data are inherently spatial. In contrast to conventional panel studies which relied on year‐to‐year weather observations, we exploit a hybrid approach to compromise between the disadvantages and advantages of longer‐term cross‐sectional analysis and shorter‐term panel models. We estimate the potential impacts of climate change on agriculture under several global warming scenarios based on the Sixth Phase of the Coupled Model Intercomparison Project (CMIP6). We find that (I) farmlands’ net revenues are projected to decline by 8%–19% and 14%–51% by 2050 and 2080; (II) the distributional impacts of climate change would highly depend on climate zones and geographical locations; (III) a few counties might benefit from climate changes; (IV) finally, failing to account for spatial spillovers when they are present leads to a misspecified model.

Combined advanced oxidation dye-wastewater treatment plant: design and development with data-driven predictive performance modeling

The recalcitrant nature of the industrial dyes poses a significant challenge to existing treatment technologies due to the stringent environmental regulations. This combined with the inefficiency of a single treatment method has led to the implementation of the combination of primary, secondary, and tertiary treatment processes, which fails during complex secondary aeration processes due to variable pH loads of industrial effluent wastewater. This article presents a modified design methodology of a pilot-scale micro-pre-treatment unit using a solar-triggered advanced oxidation process reactor that both effectively controls the influent variability at the source and mitigates textile effluents for making the discharge reusable for different industrial purposes. The proposed modified combination technique of controlled serial processes inclusive of primary, secondary, and tertiary treatment steps with ZnO/ZnO-GO NanoMat-based advanced oxidation process demonstrates complete remediation of industrial grade effluent with effective reuse of the discharge. Further, a reliable prediction model for estimating water quality parameter using machine learning models are proposed. Multi-linear regression and Artificial Neural network modeling provide simple, accurate, and robust prediction capabilities, which are evaluated for the efficiency of the processes. The generated prediction models capture the output parameters within an acceptable level of accuracy (Radj2>0.90)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$({{\\boldsymbol{R}}}_{{adj}}^{{\\bf{2}}}\\, >\\, 0.90)$$\\end{document} and allow compliance with the discharge Inland Water Discharge Standards (IWDS).

Navigating fertility dilemmas across the lifespan in girls with Turner syndrome-a scoping review.

Girls with Turner syndrome (TS) lack a partial or complete sex chromosome, which causes an accelerated decline of their ovarian reserve. Girls have to deal with several dilemmas related to their fertility, while only a limited number of them are referred to a fertility specialist and counselled about options of family planning on time. This scoping review provides an update of the literature on fertility in girls with TS throughout their lifespan and aims to propose a clinical practice guideline on fertility in TS. Databases of PubMed, Embase, and Web of science were searched using the following key terms: Turner syndrome, fertility, puberty, pregnancy, sex-hormones, karyotype, fertility preservation, assisted reproductive techniques, and counselling, alongside relevant subject headings and synonymous terms. English language articles published since 2007 were critically reviewed. Pregnancies after using donated oocytes and data about girls with TS with Y-chromosomal content were excluded. This search identified 1269 studies of which 120 were extracted for the review. The prevalence of natural conception ranged from 15% to 48% in women with 45,X/46,XX, 1% to 3% in women with 45,X, and 4% to 9% in women with other TS karyotypes. When assessing a girl's fertility potential, it was crucial to determine the karyotype in two cell lines, because hidden mosaicism may exist. In addition to karyotype, assessment of anti-Müllerian hormone (AMH) played a significant role in estimating ovarian function. Girls with AMH above the detection limit were most likely to experience spontaneous thelarche, menarche, and ongoing ovarian function during the reproductive lifespan. Fertility preservation became more routine practice: vitrification of oocytes was reported in 58 girls with TS and a median of five oocytes were preserved per stimulation. Ovarian tissue cryopreservation has demonstrated the presence of follicles in approximately 30% of girls with TS, mostly in girls with mosaic-TS, spontaneous puberty, and AMH above the detection limit. Although girls and their parents appreciated receiving counselling on fertility in TS, only one in ten girls with TS received specialized counselling. Unfamiliarity with fertility preservation techniques or uncertainties regarding the eligibility of a girl for fertility preservation constituted barriers for healthcare professionals when discussing fertility with girls with TS. There currently is a high demand for fertility preservation techniques in girls with TS. A reliable prognostic model to determine which girls with TS might benefit from fertility preservation is lacking. Only a minority of these girls received comprehensive fertility counselling on the full spectrum of fertility, including uncertainties of fertility preservation, pregnancy risks, and alternatives, such as adoption. Fertility preservation could be a viable option for girls with TS. However, the question remains whether enough oocytes can be obtained for a realistic prospect of a live birth. It is important that girls and parents are empowered with the necessary information to make a well-informed decision.

Reliability modeling of systems with random failure threshold subjected to cumulative shocks using machine learning method

AbstractModeling and evaluation of a system reliability is a key issue in shock model analysis. In cumulative shock model, a system fails when the total damages caused by shocks exceeds the system failure threshold level. The reliability of a system with random failure threshold level under cumulative shocks is investigated in this work, considering the general dependency between inter‐arrival times of shocks and their damages magnitudes. Clustering, as one of the unsupervised machine learning methods, is utilized here by applying a genetic algorithm (GA) and particle swarm optimization algorithm (PSO) for its implementation. Phase‐type (PH) distributions and their properties are also applied for finding a system failure distribution functions, determining the convolutions, evaluating the integrals, and ultimately modeling the system reliability. An illustrative example is provided to demonstrate the implementation and effectiveness of the proposed modeling procedure and the suggested approach for computing the system reliability and remaining useful lifetime (RUL). Also, an example case study of X‐ray machine in healthcare industry is provided to demonstrate the application of the proposed model. Applying other machine learning methods for patterns recognition is an area for future research.

Error‐controlled feature selection for ultrahigh‐dimensional and highly correlated feature space using deep learning

AbstractDeep learning has been at the center of analytics in recent years due to its impressive empirical success in analyzing complex data objects. Despite this success, most existing tools behave like black‐box machines, thus the increasing interest in interpretable, reliable, and robust deep learning models applicable to a broad class of applications. Feature‐selected deep learning has emerged as a promising tool in this realm. However, the recent developments do not accommodate ultrahigh‐dimensional and highly correlated features or high noise levels. In this article, we propose a novel screening and cleaning method with the aid of deep learning for a data‐adaptive multi‐resolutional discovery of highly correlated predictors with a controlled error rate. Extensive empirical evaluations over a wide range of simulated scenarios and several real datasets demonstrate the effectiveness of the proposed method in achieving high power while keeping the false discovery rate at a minimum.

Building initial model for seismic inversion based on semi‐supervised learning

AbstractSeismic inversion is an important tool for reservoir characterization. The inversion results are significantly impacted by a reliable initial model. Conventional well interpolation methods are not able to meet the needs of seismic inversion for lateral heterogeneous reservoirs. Inspired by the sequence modelling network and seismic inversion in the Laplace–Fourier domain, we propose an initial model‐building method using semi‐supervised learning strategy. The proposed method considers spatial information to ensure the horizontal continuity of the initial model. Based on the fact that the low‐frequency components of seismic signals in the Laplace–Fourier domain are easier to obtain, we use the forward model in the Laplace–Fourier domain to replace the time‐domain forward model. The proposed workflow was validated using the Marmousi II model. Although the training was carried out on a small number of low‐frequency impedance traces, the proposed workflow was able to build low‐frequency model for the entire Marmousi II model with a correlation of 98%. Field data examples demonstrate the feasibility and effectiveness of the proposed method. For lateral heterogeneous reservoirs, the proposed method performs better than the well interpolation method. By utilizing the model obtained by the proposed method as the initial low‐frequency model of the conventional inversion method, it is possible to estimate better inversion results. The results of different combinations of training sets demonstrate the stability of the proposed method. This method may still be a viable choice if there is lateral heterogeneity underground but not much well‐logging label data.

Reliability analysis of wind turbines considering seasonal weather effects

The failure rate of wind turbines shows obvious fluctuation due to seasonal environmental factors. However, few efforts have been devoted to modeling the seasonal failure rate. This paper develops a novel model that consists of a baseline failure rate function, seasonal indices, and a residual term to describe the monthly failure rate of wind turbines. A two-stage procedure is developed to estimate the 16 unknown parameters in the model. The first stage explores the relationship between the parameters in the baseline function and the monthly coefficients by maximum likelihood estimation and then integrates the properties into the genetic algorithm to estimate the main parameters. In the second stage, the variance of the residual term is estimated based on the analysis of the differences between the observed and predicted failure rates. The failure history of 48 months has been used to illustrate the proposed approach. The results show that the monthly failure rate function can well fit the real failure history of wind turbines, and it outperforms the traditional reliability model.

Deep Graph Learning-Based Surrogate Model for Inverse Modeling of Fractured Reservoirs

Inverse modeling can estimate uncertain parameters in subsurface reservoirs and provide reliable numerical models for reservoir development and management. The traditional simulation-based inversion method usually requires numerous numerical simulations, which is time-consuming. Recently, deep learning-based surrogate models have been widely studied as an alternative to numerical simulation, which can significantly improve the solving efficiency of inversion. However, for reservoirs with complex fracture distribution, constructing the surrogate model of numerical simulation presents a significant challenge. In this work, we present a deep graph learning-based surrogate model for inverse modeling of fractured reservoirs. Specifically, the proposed surrogate model integrates the graph attention mechanisms to extract features of fracture network in reservoirs. The graph learning can retain the discrete characteristics and structural information of the fracture network. The extracted features are subsequently integrated with a multi-layer recurrent neural network model to predict the production dynamics of wells. A surrogate-based inverse modeling workflow is then developed by combining the surrogate model with the differential evolutionary algorithm. Numerical studies performed on a synthetic naturally fractured reservoir model with multi-scale fractures illustrate the performance of the proposed methods. The results demonstrate that the proposed surrogate model exhibits promising generalization performance of production prediction. Compared with tens of thousands of numerical simulations required by the simulation-based inverse modeling method, the proposed surrogate-based method only requires 1000 to 1500 numerical simulations, and the solution efficiency can be improved by ten times.

MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants.

Despite the increasing availability of genomic data and enhanced data analysis procedures, predicting the severity of associated diseases remains elusive in the absence of clinical descriptors. To address this challenge, we have focused on the KV7.2 voltage-gated potassium channel gene (KCNQ2), known for its link to developmental delays and various epilepsies, including self-limited benign familial neonatal epilepsy and epileptic encephalopathy. Genome-wide tools often exhibit a tendency to overestimate deleterious mutations, frequently overlooking tolerated variants, and lack the capacity to discriminate variant severity. This study introduces a novel approach by evaluating multiple machine learning (ML) protocols and descriptors. The combination of genomic information with a novel Variant Frequency Index (VFI) builds a robust foundation for constructing reliable gene-specific ML models. The ensemble model, MLe-KCNQ2, formed through logistic regression, support vector machine, random forest and gradient boosting algorithms, achieves specificity and sensitivity values surpassing 0.95 (AUC-ROC > 0.98). The ensemble MLe-KCNQ2 model also categorizes pathogenic mutations as benign or severe, with an area under the receiver operating characteristic curve (AUC-ROC) above 0.67. This study not only presents a transferable methodology for accurately classifying KCNQ2 missense variants, but also provides valuable insights for clinical counseling and aids in the determination of variant severity. The research context emphasizes the necessity of precise variant classification, especially for genes like KCNQ2, contributing to the broader understanding of gene-specific challenges in the field of genomic research. The MLe-KCNQ2 model stands as a promising tool for enhancing clinical decision making and prognosis in the realm of KCNQ2-related pathologies.

Characterization, Analysis, and Modeling of Long-Term RF Reliability and Degradation of SiGe HBTs for High Power Density Applications

Characterization, Analysis, and Modeling of Long-Term RF Reliability and Degradation of SiGe HBTs for High Power Density Applications

Modeling Doxorubicin Pharmacokinetics in Multiple Myeloma Suggests Mechanism of Drug Resistance.

Multiple myeloma (MM) is a plasma cell malignancy often treated with chemotherapy drugs. Among these, doxorubicin (DOXO) is commonly employed, sometimes in combined-drug therapies, but it has to be optimally administered in order to maximize its efficacy and reduce possible side effects. To support DOXO studies and treatment optimization, here we propose an experimental/modeling approach to establish a model describing DOXO pharmacokinetics (PK) in MM cells. A series of in vitro experiments were performed in MM1R and MOLP-2 cells. DOXO was administered at two dosages (200 nM, 450 nM) at [Formula: see text] = 0 and removed at [Formula: see text] = 3 hrs. Intracellular DOXO concentration was measured via fluorescence microscopy during both drug uptake ([Formula: see text] = 0-3 hrs) and release phases ([Formula: see text] = 3-8 hrs). Four PK candidate models were identified, and were compared and selected based on their ability to describe DOXO data and numerical parameter identification. The most parsimonious model consists of three compartments describing DOXO distribution between the extracellular space, the cell cytoplasm and the nucleus, and defines the intracellular DOXO efflux rate through a Hill function, simulating a threshold/saturation drug resistance mechanism. This model predicted DOXO data well in all the experiments and provided precise parameter estimates (mean ± standard deviation coefficient of variation: 15.8 ± 12.2%). A reliable PK model describing DOXO uptake and release in MM cells has been successfully developed. The proposed PK model, once integrated with DOXO pharmacodynamics, has the potential of allowing the study and the optimization of DOXO treatment strategies in MM.

Abstract B014: Patient-derived organoid models for drug screening in molecular subtypes of endometrial cancer

Abstract Introduction: The lack of reliable pre-clinical models has significantly impeded the progress of drug discovery for specific molecular subtypes of endometrial cancer. This study aimed to develop patient-derived organoid models for use in preclinical screening of novel and repurposed therapies in endometrial cancer molecular subtypes. Method: Endometrial cancer tissue (n=27) and ascites fluid (n=1) were collected for this study (ethics approval SESLHD HREC 2021_ETH11975 and 19/001) from patients of various subtypes (17 endometrioid, 3 high grade serous, 2 carcinosarcoma, 2 clear cell, 3 mixed) undergoing treatment at the Royal Hospital for Women and Prince of Wales Private Hospital in Sydney, Australia. Tumor cells were isolated, embedded in 70% Matrigel and cultured in defined culture medium to form organoids. Molecular subtyping of organoids and matched parental tissue was undertaken by mismatch repair (MMR) and p53 immunohistochemistry (IHC), and sequencing of POLE exonuclease domain mutations (EDMs). A unique matched two-dimensional (2D) cell line and three-dimensional (3D) organoid culture derived from ascites isolated from a high grade serous endometrial cancer patient was established. These molecularly stratified pre-clinical models were then used to test drug activity. As a proof of principle, response to paclitaxel and carboplatin was undertaken. Result: 20 organoids representing all major molecular subtypes were established (71% success rate), including one derived from ascites fluid. Organoids are presented with either a cystic or solid structure that highly resembles the morphology of the original tissue. Organoid culture can faithfully retain key features including MMR, p53 status as well as POLE EDMs of the parental tissue. The drug screening results identified contrasting responses of 2D and 3D models obtained from the same patient tissue, highlighting the importance of selecting appropriate pre-clinical models for drug development and testing. Conclusion: This study demonstrated that patient-derived organoids can successfully recapitulate the molecular characterization of endometrial cancer. Molecularly defined organoids represent a promising preclinical resource for drug screening in endometrial cancer. In addition, the model structure should be taken into account while conducting drug screening. Citation Format: Dongli Liu, Elyse Powell, King Man Wan, Ramanand Athavale, Christine Loo, Caroline E. Ford. Patient-derived organoid models for drug screening in molecular subtypes of endometrial cancer [abstract]. In: Proceedings of the AACR Special Conference on Endometrial Cancer: Transforming Care through Science; 2023 Nov 16-18; Boston, Massachusetts. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(5_Suppl):Abstract nr B014.

Developing weather-based biomass prediction equation to assess the field pea yield under future climatic scenario

The present research focuses on the variation of field pea production under different prevailing weather parameters, aiming to develop a reliable forecasting model. For that a field experiment was conducted in New Alluvial Zone of West Bengal during 2018-19 and 2019-20 with three different varieties (VL42, Indrira Matar, Rachana) of this region. Biomass predicting equation based on maximum temperature, minimum temperature and solar radiation was developed to estimate field pea yield for 2040-2099 period under SSP 2-4.5 and SSP 5-8.5 scenarios. It reveals that solar radiation positively influences crop biomass, while high maximum and minimum temperatures have adverse effects on yield. The developed forecasting equation demonstrated its accuracy (nRMSE=17.37%) by aligning closely with historical data, showcasing its potential for reliable predictions. Furthermore, the study delves into future climate scenarios, showing that increasing temperatures are likely to impact field pea yield negatively. Both biomass and yield showed decreasing trend for the years from 2040 to 2099. SSP 5-8.5 scenario, which is more pessimistic one, foresees a substantial reduction in crop productivity. This weather parameter-based biomass prediction equation can be effectively utilized as a method to assess the impact of climate change on agriculture.
 Keywords: Field pea, weather parameters, crop yield prediction, New Alluvial Zone, nRMSE

Affective analysis in machine learning using AMIGOS with Gaussian expectation-maximization model

<p>Investigating human subjects is the goal of predicting human emotions in the stock market. A significant number of psychological effects require (feelings) to be produced, directly releasing human emotions. The development of effect theory leads one to believe that one must be aware of one's sentiments and emotions to forecast one's behavior. The proposed line of inquiry focuses on developing a reliable model incorporating neurophysiological data into actual feelings. Any change in emotional affect will directly elicit a response in the body's physiological systems. This approach is named after the notion of Gaussian mixture models (GMM). The statistical reaction following data processing, quantitative findings on emotion labels, and coincidental responses with training samples all directly impact the outcomes that are accomplished. In terms of statistical parameters such as population mean and standard deviation, the suggested method is evaluated compared to a technique considered to be state-of-the-art. The proposed system determines an individual's emotional state after a minimum of 6 iterative learning using the Gaussian expectation-maximization (GEM) statistical model, in which the iterations tend to continue to zero error. Perhaps each of these improves predictions while simultaneously increasing the amount of value extracted.</p>