Search

Demand for perishable food is sensitive to product prices and is affected by the prices of similar or alternative products. While brand loyalty influences the demand for products, determining a reasonable price requires a precise pricing strategy. In this paper, a pricing model for perishable food is presented in which the brand value of the product and the price of other manufacturers as competitors are considered. To this end, this study first predicts the price of competitors using a combination of optimized Neural Networks and presents an optimized model using a Genetic Algorithm. This algorithm combines a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a Genetic Algorithm (GA). The proposed model is then used to merge with a game-theory model for the pricing of perishable foods. In this game-theory model, pricing approaches are developed based on identified prices of competitors. In the coordination contract game-theory model, Multi Retailer- one Supplier and Price-sensitive demand of Perishable product are developed with and without quantity discount contract. Obtained results indicate that independent procurement provides retailers with higher profit, while lower profit will be presented when coordination is not considered. Also, with coordination, the ordering cycle increases, and the ordering frequency decrease. [ABSTRACT FROM AUTHOR]

[Display omitted] Electrochemical carbon dioxide reduction reaction (CO 2 RR) is a promising technology to establish an artificial carbon cycle. Two-dimensional conjugated metal–organic frameworks (2D c-MOFs) with high electrical conductivity have great potential as catalysts. Herein, we designed a range of 2D c-MOFs with different transition metal atoms and organic ligands, TMN x O 4-x -HDQ (TM = Cr∼Cu, Mo, Ru∼Ag, W∼Au; x = 0, 2, 4; HDQ = hexadipyrazinoquinoxaline), and systematically studied their catalytic performance using density functional theory (DFT). Calculation results indicated that all of TMN x O 4-x -HDQ structures possess good thermodynamic and electrochemical stability. Notably, among the examined 37 MOFs, 6 catalysts outperformed the Cu(2 1 1) surface in terms of catalytic activity and product selectivity. Specifically, NiN 4 -HDQ emerged as an exceptional electrocatalyst for CO production in CO 2 RR, yielding a remarkable low limiting potential (U L) of −0.04 V. CuN 4 -HDQ, NiN 2 O 2 -HDQ, and PtN 2 O 2 -HDQ also exhibited high activity for HCOOH production, with U L values of −0.27, −0.29, and −0.27 V, respectively, while MnN 4 -HDQ, and NiO 4 -HDQ mainly produced CH 4 with U L values of −0.58 and −0.24 V, respectively. Furthermore, these 6 catalysts efficiently suppressed the competitive hydrogen evolution reaction. Machine learning (ML) analysis revealed that the key intrinsic factors influencing CO 2 RR performance of these 2D c-MOFs include electron affinity (E A), electronegativity (χ), the first ionization energy (I e), p-band center of the coordinated N/O atom (ε p), the radius of metal atom (r), and d-band center (ε d). Our findings may provide valuable insights for the exploration of highly active and selective CO 2 RR electrocatalysts. [ABSTRACT FROM AUTHOR]

Full waveform inversion (FWI) is a technique widely used in geophysics to obtain high-resolution subsurface velocity models from waveform seismic data. Due to its large computation cost, most flavours of FWI rely only on the computation of the gradient of the loss function to estimate the update direction, therefore ignoring the contribution of the Hessian. Depending on the level of computational resources one can afford, an approximate of the inverse of the Hessian can be calculated and used to speed up the convergence of FWI towards the global (or a plausible local) minimum. In this work, we propose to use an approximate Hessian computed from a linearization of the wave equation as commonly done in least-squares migration. More precisely, we rely on the link between a migrated image and a doubly migrated image (i.e. an image obtained by demigration–migration of the migrated image) to estimate the inverse of the Hessian. However, instead of using non-stationary compact filters to link the two images and approximate the Hessian, we propose to use a deep neural network to directly learn the mapping between the FWI gradient (output) and its Hessian (blurred) counterpart (input). By doing so, the network learns to act as an approximate inverse Hessian: as such, when the trained network is applied to the FWI gradient, an enhanced update direction is obtained, which is shown to be beneficial for the convergence of FWI. The weights of the trained (deblurring) network are then transferred to the next FWI iteration to expedite convergence. We demonstrate the effectiveness of the proposed approach on two synthetic data sets and a field data set. [ABSTRACT FROM AUTHOR]

In order to effectively model data online, a learning model must not only have the high adaptability of dynamic data but also keep the low complexity to meet the online computing requirements. In this paper, a novel multi-innovation online sequential extreme learning machine (MIOSELM) and its kernel version called multi-innovation kernel online sequential extreme learning machine (MIKOSELM) are proposed to establish the online estimation models based on p latest samples using the multi-innovation theory. Besides, a modified whale optimization algorithm (MWOA) is introduced to optimize the execution parameters of our algorithms and is capable of automatically searching a proper p as the practical need, which can further improve the adaptability performance of the online learning models. Finally, two different datasets (the UCI dataset and KDD99 dataset) are used to evaluate the superiority of our methods. Experimental results show that the accuracy, F-score, and G-mean of MIKOSELM are 98.25%, 98.11% and 98.63% on WDBC from the UCI dataset, and are 83.61%, 75.96% and 70.97% on the KDD99 dataset respectively. Besides, our MIKOSELM based on MWOA achieves F-score of 94.28% and 76.73% on Musk from the UCI dataset and the KDD99 dataset. These results validate the effectiveness of our proposed methods. • A multi-innovation OSELM and its kernel version are proposed. • A modified whale optimization algorithm is developed for MIOSELM and MIKOSELM. • Experiments show the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In this study, a framework for predicting the gas‐sensitive properties of gas‐sensitive materials by combining machine learning and density functional theory (DFT) has been proposed. The framework rapidly predicts the gas response of materials by establishing relationships between multisource physical parameters and gas‐sensitive properties. In order to prove its effectiveness, the perovskite Cs3Cu2I5 has been selected as the representative material. The physical parameters before and after the adsorption of various gases have been calculated using DFT, and then a machine learning model has been trained based on these parameters. Previous studies have shown that a single physical parameter alone is not enough to accurately predict the gas sensitivity of materials. Therefore, a variety of physical parameters have been selected for machine learning, and the final machine learning model achieved 92% accuracy in predicting gas sensitivity. It is important to note that although there have been no previous reports on the response of Cs3Cu2I5 to hydrogen sulfide, the resulting model predicts the gas response of H2S; it is subsequently confirmed experimentally. This method not only enhances the understanding of the gas sensing mechanism, but also has a universal nature, making it suitable for the development of various new gas‐sensitive materials. [ABSTRACT FROM AUTHOR]

Some of the required characteristics for a true machine theory of mind (MToM) include the ability to (1) reproduce the full diversity of human thought and behavior, (2) develop a personalized model of an individual with very limited data, and (3) provide an explanation for behavioral predictions grounded in the cognitive processes of the individual. We propose that a certain class of cognitive models provide an approach that is well suited to meeting those requirements. Being grounded in a mechanistic framework like a cognitive architecture such as ACT‐R naturally fulfills the third requirement by mapping behavior to cognitive mechanisms. Exploiting a modeling paradigm such as instance‐based learning accounts for the first requirement by reflecting variations in individual experience into a diversity of behavior. Mechanisms such as knowledge tracing and model tracing allow a specific run of the cognitive model to be aligned with a given individual behavior trace, fulfilling the second requirement. We illustrate these principles with a cognitive model of decision‐making in a search and rescue task in the Minecraft simulation environment. We demonstrate that cognitive models personalized to individual human players can provide the MToM capability to optimize artificial intelligence agents by diagnosing the underlying causes of observed human behavior, projecting the future effects of potential interventions, and managing the adaptive process of shaping human behavior. Examples of the inputs provided by such analytic cognitive agents include predictions of cognitive load, probability of error, estimates of player self‐efficacy, and trust calibration. Finally, we discuss implications for future research and applications to collective human–machine intelligence. [ABSTRACT FROM AUTHOR]

Two trajectories underway transform human systems. Processes of growth/complexification have accelerated as stakeholders seek advantage from advances in connectivity/autonomy/sensing. Surprising empirical patterns also arise—puzzling collapses of critical valued services occur against a background of growth. In parallel, new scientific foundations have arisen from diverse directions explaining the observed anomalies and breakdowns, highlighting basic weaknesses of automata regardless of technology. Conceptual growth provides laws, theorems, and comprehensive theories that encompass the interplay of autonomy/people and complexity/adaptation across scales. One danger for synchronizing the trajectories is conceptual lag as researchers remain stuck in stale frames unable to keep pace with transformative change. Any approach that does not either build on the new conceptual advances—or provide alternative foundations—is no longer credible to match the scale and stakes of modern distributed layered systems and overcome the limits of automata. The paper examines longstanding challenges by contrasting progress then as the trajectories gathered steam, to situation now as change has accelerated. [ABSTRACT FROM AUTHOR]

The cutting characteristics of Inconel 718 alloy are high hardness and surface hardening, causing fast tool wear, severe chipping, and inadequate machining accuracy. In order to overcome the existing challenges, this study proposes a method to enhance the cutting performance by injecting fullerene C60 nanoparticle cutting fluid with minimum quantity lubrication (MQL) into the cutting zone. Leveraging the Johnson–Cook constitutive model and the imaginary heat source method, this study simulates the cooling effect and friction reduction characteristics of the cutting contact interface under minimum quantity lubrication conditions, and assessment of cutting energy consumption using predicted and measured specific cutting energy (SCE). Through friction wear tests, the friction coefficient changes under various lubrication conditions are measured. The impact of lubrication conditions on friction and wear mechanism is analyzed. The cutting test results demonstrate that variations in cutting parameters significantly influence energy efficiency, with specific cutting energy exhibiting a downward trend as the material removal rate (MRR) increases. Notably, C60 nanoparticle minimum quantity lubrication (NMQL) stands out excellent friction reduction and cooling effects among other lubrication methods. Experimental data indicate that NMQL compared with dry cutting, flood cutting, and pure MQL, the specific cutting energy is reduced by 31.3%, 19.13%, and 17.37%, respectively, and that the cutting energy performance is significantly improved. The maximum error of the SCE prediction model is 17.5%, and the prediction results align well with the experimental findings. Moreover, this study provides novel insights for advancing machining theory and exploring sustainable green machining of nickel-based alloys. [ABSTRACT FROM AUTHOR]

Copyright of HMD: Praxis der Wirtschaftsinformatik is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This perspective article presents the density functional theory and traces its evolution. With the advancement in density functional theory-based computations and the efforts to collate the data generated through density functional theory, the field now has a good repository/database of materials and their properties. This repository, though not as substantial as generally used for machine learning, has nonetheless made it possible to combine density functional theory and machine learning. This article highlights current research challenges and presents an optimistic outlook for the future of "Density Functional Theory with Machine Learning" by discussing some specific examples. [ABSTRACT FROM AUTHOR]

The complex compositional space of high entropy alloys (HEAs) has shown a great potential to reduce the cost and further increase the catalytic activity for hydrogen evolution reaction (HER) by compositional optimization. Without uncovering the specifics of the HER mechanism on a given HEA surface, it is unfeasible to apply compositional modifications to enhance the performance and save costs. In this work, a combination of density functional theory and Bayesian machine learning is used to demonstrate the unique catalytic mechanism of IrPdPtRhRu HEA catalysts for HER. At high coverage of underpotential‐deposited hydrogen, a d‐band investigation of the active sites of the HEA surface is conducted to elucidate the superior catalytic performance through electronic interactions between elements. At low coverage, a novel Bayesian learning with oversampling approach is then outlined to optimize the HEA composition for performance improvement and cost reduction. This approach proves more efficacious and efficient and yields higher‐quality structures with less training set bias compared with neural‐network optimization. The proposed HEA optimization theoretically outperforms benchmark Pt catalysts’ overpotential by ≈40% at a 15% reduced synthesis cost comparing to the equiatomic ratio HEA. [ABSTRACT FROM AUTHOR]

Macrophages induce the expression of hundreds of genes in response to immune threats. However, current technology limits our ability to capture single-cell inducible gene expression dynamics. Here, we generated high-resolution time series single-cell RNA sequencing (scRNA-seq) data from mouse macrophages responding to six stimuli, and imputed ensembles of real-time single-cell gene expression trajectories (scGETs). We found that dynamic information contained in scGETs substantially contributes to macrophage stimulus-response specificity (SRS). Dynamic information also identified correlations between immune response genes, indicating biological coordination. Furthermore, we showed that the microenvironmental context of polarizing cytokines profoundly affects scGETs, such that measuring response dynamics offered clearer discrimination of the polarization state of individual macrophage cells than single time-point measurements. Our findings highlight the important contribution of dynamic information contained in the single-cell expression responses of immune genes in characterizing the SRS and functional states of macrophages. [Display omitted] • Imputation of stimulus-induced single-cell gene expression trajectories (scGETs) • Trajectory features reveal unexpected stimulus specificity in macrophage responses • Expression integrals identify cell-cell correlations and co-regulated gene sets • Stimulus-response expression trajectories readily characterize cell functional states Because RNA measurements are cell destructive, it is unclear how variable stimulus-induced dynamic gene expression trajectories (GETs) are. Sheu et al. developed a method to assess single-cell gene expression trajectories (scGETs) in macrophages responding to stimuli and found scGETs to be much more informative than any single time-point measurement. [ABSTRACT FROM AUTHOR]

ABSTRACT Machine learning methods were shown to improve the prediction accuracies of genomic prediction of resistance scores compared to methods like RR‐BLUP, which were originally designed for metric rather than ordinal response values. We conducted a cross‐validation study with 361 wheat genotypes evaluated for five fungal diseases. Our objective was to compare the prediction accuracy and the ability to identify the most resistant genotypes of 19 genomic prediction approaches. Each approach consisted of a different combination of prediction method (RR‐BLUP, an alternative method with heterogeneous marker variances, Bayesian generalized linear regression with an ordinal response, support vector machine, gradient boosting machine and random forest), predictor (single SNP markers, LD‐based haplotype blocks, 250 variables generated with an autoencoder and SNPs identified with incremental feature selection) and response value (untransformed and logit‐transformed resistance scores). In our dataset, RR‐BLUP was consistently among the methods with the largest prediction accuracies and the best abilities to identify resistant genotypes in four of five investigated traits. However, in P. triticina, using gradient boosting machine and random forest instead of RR‐BLUP increased the prediction accuracy from 0.64 to 0.71, indicating that machine learning methods may have an advantage over linear models in genomic prediction. We also found that even though there was a positive correlation between the prediction accuracy and Cohen's κ$$ \kappa $$, a measure to judge how well the most resistant genotypes can be identified, the correlation is not perfect and a large value for the prediction accuracy does not necessarily translate into an equally large κ$$ \kappa $$ value. [ABSTRACT FROM AUTHOR]

Background: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance. Methods: This paper presents an entire pipeline how to use natural language processing techniques to make the titles and abstracts usable for machine learning and how to apply machine learning algorithms to adequately predict whether or not a publication should be forwarded to full text screening. Guidance for the practical use of the methodology is given. Results: The appealing performance of the approach is demonstrated by means of two real-world systematic reviews with meta analysis. Conclusions: Natural language processing and machine learning can help to semi-automatize title-abstract screening. Different project-specific considerations have to be made for applying them in practice. [ABSTRACT FROM AUTHOR]

The animation-effect of the movement-image constitutes not only a form of life but also a machinic analogue for Husserl's and Kant's accounts of temporality, engendering what Bernard Stiegler calls 'a cinematography of consciousness'. If autonomous movement is the hallmark of the living being as well as the inanimate mechanism, the movement-image likewise subtends scenes of human and artificial intelligence. Pairing a cybernetic reading of Lacan's mirror stage essay with reflections on the self-recognition dance of Machina Speculatrix (an early example of a biomimetic robot), this essay considers how exosomatic feedback loops enable a kind of ipseity for machinic life as well as the human being as technical being. Despite adopting Derrida's ideas of originary prostheticity and automaticity, rendering living beings as always-already machinic life, Stiegler sets arche-cinema against arche-writing. [ABSTRACT FROM AUTHOR]

In the future ten years, the mining depths of more than 30% metal mines will exceed 1000 m. Deep metal mining is confronted with complex geological conditions such as high in-situ stress, high ground temperature, highly-changeable grounds and strong mining disturbance, which bring severe challenges to roadway construction. Due to the shortcomings of noncontinuous operation, low construction rate and frequent disaster occurrence, traditional drilling-and-blasting method cannot meet the construction requirement, therefore the use of tunnel boring machine (TBM)for continuous mechanical tunnelling becomes the future development direction of deep metal mine roadway construction. However, due to the distinctive engineering geological features and roadway construction requirements, the application of TBM tunnelling technology in deep metal mine roadway construction still suffers from some technological problems and challenges. First, this paper summarizes the three main application difficulties for TBM tunnelling technology in deep metal mine roadway construction; 1) the lack of adaptative TBM type selection and machine design theory; 2) the lack of high efficient TBM tunnelling technology; 3) the lack of prewarning, prevention and control technology for engineering disasters. Then, this paper introduces the current research progresses for TBM tunnelling technology in deep metal mine roadway construction from six aspects, i. e., efficient rock breakage theory for cutterhead and cutters, adaptative TBM type selection and machine design technology, accurate tunnelling performance prediction and evaluation methodology, tunnelling technology for small turning radius or highly-inclined roadways, intelligent prewarning, prevention and control technology for engineering disasters, intelligent decision-making and assisted-driving technology. The above research progresses primarily indicate the development direction for the extensive application of TBM tunnelling technology for rapid roadway construction in deep metal mines. [ABSTRACT FROM AUTHOR]

Investment risk forecasting is challenging when the stock market is characterized by non-linearity and extremes. Under these conditions, VaR estimation based on the assumption of distribution normality becomes less accurate. Combining extreme value theory (EVT) with machine learning (ML) produces a model that detects and learns heavy tail patterns in data distributions containing extreme values while being effective in non-linear systems. We aimed to develop an investment risk forecasting model in the capital market with non-linear and extreme characteristics using the VaR method of the EVT approach combined with ML (VaRGPD-ML(α)). The combination of methods used is a multivariate time series forecasting model with RNN, LSTM, and GRU algorithms to obtain ML-based returns. The EVT method of the POT approach was used to model extremes. The VaR method was used for investment risk estimation. The backtesting method was used to validate the model. Our results showed that determining the threshold based on the normal distribution will identify extreme values with the ideal number, minimum bias, and distribution of extreme data following GPD. The VaRGPD-ML(α) model was valid in all samples based on backtesting at α = 0.95 and α = 0.99. Generally, this model produces a greater estimated value of investment risk than the VaRGPD(α) model at the 95% confidence level. [ABSTRACT FROM AUTHOR]

Due to enormous applications of large-area graphene with high quality, the epitaxial growth strategies have drawn a plethora of attention. However, the bottleneck in the production of graphene has caused delayed development in recent years, which is owing to the poor understanding of interaction mechanisms between graphene and the underlying metallic and non-metallic substrate. To understand the thermodynamics of graphene–substrate interface and growth kinetics, accurate density functional theory (DFT) calculations have been proved as an effective way, in terms of cost and time, compared with traditional experimental methods, which can calculate the interaction between graphene and substrates, helping us to better understand the practical phenomena. Here, we show the use of DFT methods to evaluate both van der Waals interaction and covalent bonding. Many of computational results fit well with the experimental observations. To address the relative low accuracy and small computation capacity (number of atoms) of common DFT models, we suggest that the machine learning (ML) methods will be a fresh impetus for epitaxial growth strategy of graphene, which put forward effective interpretations for complicated interconnections and correlations among the properties, thereby enabling ML a promising strategy for understanding, design, and synthesis of graphene over other 2D materials. [ABSTRACT FROM AUTHOR]

Response to pharmacotherapy varies considerably among youths with bipolar disorder (BD) and is poorly predicted by clinical or demographic features. It can take several weeks to determine whether medication for BD is clinically effective. Although neuroimaging biomarkers are promising predictors, few studies examined the predictive value of the brain connectomic topology. BD-I youth (N = 121) with no prior psychopharmacotherapy were randomized to 6-weeks of double-blind quetiapine or lithium. Structural magnetic resonance imaging (MRI) was performed before medication and at one week after medication initiation. Brain structural connectome was established from the MRI scans, and topological metrics were calculated for each patient. Deep learning-based prediction model was built using baseline and one-week connectome topology to predict medication response at week 6. Both baseline topological metrics and one-week topological changes could predict treatment response with significant accuracy (73.8 % - 86.8 %). A longitudinally joint model combining baseline and one-week topology provided the highest accuracy (91.3 %). The transferability between models for quetiapine and lithium was relatively poor. In addition, predictions for the two drugs were driven by similar baseline but distinct one-week salient topological patterns. Independent replication is needed to validate our preliminary findings. Brain structural connectomic topology at baseline and its acute changes within the first week enable accurate BD medication response prediction. The most contributive brain regions differed between prediction models for quetiapine and lithium after one week. These findings provide preliminary evidence for the development of neuroimaging-based biomarkers for guiding therapeutic interventions in youth with BD. • An MR imaging-based randomized clinical trial with over 100 BD youth • Both baseline and one-week connectomic topological characteristics could predict medication response at week 6. • Longitudinally combining baseline and one-week features enabled the highest prediction accuracy. • Neural patterns driving the medication prediction differed between lithium and quetiapine groups after one week. [ABSTRACT FROM AUTHOR]

The construction of metro tunnels in response to global urban traffic congestion presents challenges such as face stability, excessive cutter wear, cutter head clogging, and groundwater ingress during excavation. Surface settlement (SS) resulting from tunneling is a common issue that can lead to cracks in existing structures. Existing empirical and numerical solutions have limitations, including low accuracy and time-consuming calculations. To overcome these challenges, this study proposes the use of a combination of well-established theories and machine learning (ML), specifically theory-guided machine learning (TGML), to predict SS caused by twin tunnels. The TGML strategy incorporates data verification from a case study in Malaysia and data generation from numerical analysis. Within the realm of SS, tree-based techniques—including random forest, adaptive boost, gradient boosting tree, extreme gradient boost, light gradient boosting, and categorical boosting (CatBoost)—were employed in this study. The tree-based ML algorithms consistently demonstrated robust predictive performance, with coefficient of determination (R2) values consistently exceeding 0.9 and low root mean square error (RMSE) and mean absolute error (MAE) with high variance accounted for (VAF). Among these algorithms, CatBoost exhibited the highest R2 showcasing the lowest errors and highest explanatory power on both training and testing data which outperformed its counterparts. This observation highlights CatBoost's superior predictive capabilities compared to other tree-based algorithms, emphasizing its efficiency in capturing underlying patterns in the data set. TGML emerges as an effective, easy-to-apply, and practical solution for predicting SS induced by twin tunnels in future projects. [ABSTRACT FROM AUTHOR]

Abstract This paper investigates the benefits and challenges of the multi‐MW direct‐drive offshore wind Vernier generators. It is worth noting that the comparison of generator topologies presented in ref. [1] was for the same power level and therefore a reduced machine volume for the surface‐mounted permanent magnet Vernier (SPM‐V) generators. This would mainly impact the capital expenditure (CAPEX) cost between the different investigated machines. Whereas in this paper, the performance is compared for the same machine volume that allows the Vernier generators to produce a much higher energy yield than a conventional SPM generator. As the extra energy yield would be beneficial over the lifetime of the turbine, this will have a bigger impact than the CAPEX cost savings with a reduced machine volume. In addition, a novel Vernier machine with magnets on both the stator and rotor has been proposed to further improve the energy yield. In addition to the basic electromagnetic performance, the levelised cost of energy (LCOE) of the three generator topologies, that is, the conventional SPM, SPM‐V and the proposed Vernier machines, has been compared. The direct‐drive powertrain systems with SPM‐V and the proposed Vernier generators can achieve LCOE of 12.3% and 24% lower than that of the conventional SPM generators, indicating their huge potential as an alternative to reduce the overall cost of energy.

ABSTRACT Machine vision has had a substantial impact on human‐computer interaction and psychological research. The ability of robots to generate realistic facial expressions has been enhanced by advancements in artificial intelligence, neural networks, and deep learning, thereby nurturing more profound emotive connections between humans and machines. This paper offers an in‐depth look of the most recent developments in emotion classification technologies, with a specific focus on the period from 2019 to 2023. This research addresses the integration of facial and body gesture analysis into emotion detection, emphasising the development of methods such as partial transfer learning, sign‐based measurement systems, and lightweight convolutional neural networks. By analysing the most recent research, the paper not only provides a comprehensive overview of the most advanced methods, but also emphasises their superiority over previous approaches in terms of efficiency, and applicability. The integration of gestures into emotion analysis is underscored as a critical area for further investigation, providing novel opportunities for comprehending and interpreting the intricate layers of nonverbal communication. The objective of this survey is to provide a resource for researchers and practitioners who are interested in advancing the field of emotion classification by utilising innovative methodologies. [ABSTRACT FROM AUTHOR]

\nHIGHLIGHTSActivity schedule results from a complex decision-making process characterized by several interrelated decisions. Different facets of an activity schedule such as activity type, timing, duration, etc. influence each other and this makes modeling activity schedules a complex task. This complexity has compelled researchers to explore different approaches for modeling activity schedules, among which two predominant approaches can be identified: the utility-maximization theory based econometric approach and the computational process modeling approach. Despite their advantages and a few successful practical applications, challenges still remain leaving avenues for exploration of new approaches. This paper contributes in this direction by reviewing the relationship between language, grammar, and machines in the context of sequence analysis for activity sequence generation. Following that, the paper presents a stochastic Finite State Machine that can generate activity sequences to match the frequency distribution of sequences from a given data set. Our results show that the proposed algorithm can not only generate activity sequences with a distribution similar to that of original data but can also efficiently generate new patterns not in the original data. Presents the language, grammar, and machine framework for use in activity sequence generationDevelops a stochastic version of sequence generator with a case study to show the details of sequence generation techniquePresents the language, grammar, and machine framework for use in activity sequence generationDevelops a stochastic version of sequence generator with a case study to show the details of sequence generation technique [ABSTRACT FROM AUTHOR]

This review spotlights the role of atomic‐level modeling in research on metal‐organic frameworks (MOFs), especially the key methodologies of density functional theory (DFT), Monte Carlo (MC) simulations, and molecular dynamics (MD) simulations. The discussion focuses on how periodic and cluster‐based DFT calculations can provide novel insights into MOF properties, with a focus on predicting structural transformations, understanding thermodynamic properties and catalysis, and providing information or properties that are fed into classical simulations such as force field parameters or partial charges. Classical simulation methods, highlighting force field selection, databases of MOFs for high‐throughput screening, and the synergistic nature of MC and MD simulations, are described. By predicting equilibrium thermodynamic and dynamic properties, these methods offer a wide perspective on MOF behavior and mechanisms. Additionally, the incorporation of machine learning (ML) techniques into quantum and classical simulations is discussed. These methods can enhance accuracy, expedite simulation setup, reduce computational costs, as well as predict key parameters, optimize geometries, and estimate MOF stability. By charting the growth and promise of computational research in the MOF field, the aim is to provide insights and recommendations to facilitate the incorporation of computational modeling more broadly into MOF research. [ABSTRACT FROM AUTHOR]

The step-down DC/DC converter is characterized by the parametric uncertainty of its model and its high sensitivity to external disturbances identified by variations in the input voltage, load and output reference voltage. To overcome these limitations, this paper proposes the experimental evaluation of a new adaptive synergetic control law based on the M5P model tree for efficient output voltage control of the step-down type DC/DC converter. A combination of the synergetic technique, the fuzzy logic theory and the machine learning has been used for the first time to develop this advanced control law. The synergetic strategy is exploited to overcome the chattering problem arising from the use of the sliding mode approach which has been applied in previous research. Furthermore, the novel machine learning M5P tree-based approximator was designed and applied to approximate the unknown and imprecise dynamics of the studied converter. The learning data comes from the smart approximator, which is based on fuzzy logic, with the aim of extracting its own advantages and offering them to the new tree-based approximator M5P. This action will make it possible to improve the operation of the fuzzy approximator, which has already been studied in some research. Finally, the developed control strategy was successfully evaluated in the laboratory using the dSPACE 1104 board and compared with the fuzzy adaptive synergetic approach under different conditions of load variations and imposed references. The practical results show that the proposed tree adaptive synergetic approach is competitive with the fuzzy adaptive strategy in terms of ease of practical implementation, fast control execution and better output voltage regulation quality. [ABSTRACT FROM AUTHOR]

Lung cancer is the most diagnosed malignant neoplasm worldwide and it is associated with great mortality. Currently, developing antineoplastic agents is a challenging, time-consuming, and costly process. Computational methods can speed up the early discovery of anti-lung-cancer chemicals. Here, we report a perturbation theory machine learning model based on a multilayer perceptron (PTML-MLP) model for phenotypic early antineoplastic drug discovery, enabling the rational design and prediction of new molecules as virtual versatile inhibitors of multiple lung cancer cell lines. The PTML-MLP model achieved an accuracy above 80%. We applied the fragment-based topological design (FBTD) approach to physicochemically and structurally interpret the PTML-MLP model. This enabled the extraction of suitable fragments with a positive influence on anti-lung-cancer activity against the different lung cancer cell lines. By following the aforementioned interpretations, we could assemble several suitable fragments to design four novel molecules, which were predicted by the PTML-MLP model as versatile anti-lung-cancer agents. Such predictions of potent multi-cellular anticancer activity against diverse lung cancer cell lines were rigorously confirmed by a well-established virtual screening tool reported in the literature. The present work envisages new opportunities for the application of PTML models to accelerate early antineoplastic discovery from phenotypic assays. [ABSTRACT FROM AUTHOR]

We study the instantaneous inference of an unbounded planar flow from sparse noisy pressure measurements. The true flow field comprises one or more regularized point vortices of various strength and size. We interpret the true flow's measurements with a vortex estimator, also consisting of regularized vortices, and attempt to infer the positions and strengths of this estimator assuming little prior knowledge. The problem often has several possible solutions, many due to a variety of symmetries. To deal with this ill posedness and to quantify the uncertainty, we develop the vortex estimator in a Bayesian setting. We use Markov-chain Monte Carlo and a Gaussian mixture model to sample and categorize the probable vortex states in the posterior distribution, tailoring the prior to avoid spurious solutions. Through experiments with one or more true vortices, we reveal many aspects of the vortex inference problem. With fewer sensors than states, the estimator infers a manifold of equally possible states. Using one more sensor than states ensures that no cases of rank deficiency arise. Uncertainty grows rapidly with distance when a vortex lies outside of the vicinity of the sensors. Vortex size cannot be reliably inferred, but the position and strength of a larger vortex can be estimated with a much smaller one. In estimates of multiple vortices their individual signs are discernible because of the nonlinear coupling in the pressure. When the true vortex state is inferred from an estimator of fewer vortices, the estimate approximately aggregates the true vortices where possible. [ABSTRACT FROM AUTHOR]

Astrophysics to physical oceanography. String theory to machine learning. High energy theory to biophysics. Such leaps in research focus can be challenging—and rewarding. [ABSTRACT FROM AUTHOR]

Copyright of Gümüshane Üniversitesi Saglik Bilimleri Dergisi is the property of Gumushane University, Faculty of Health Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper investigates the benefits and challenges of the multi‐MW direct‐drive offshore wind Vernier generators. It is worth noting that the comparison of generator topologies presented in ref. [1] was for the same power level and therefore a reduced machine volume for the surface‐mounted permanent magnet Vernier (SPM‐V) generators. This would mainly impact the capital expenditure (CAPEX) cost between the different investigated machines. Whereas in this paper, the performance is compared for the same machine volume that allows the Vernier generators to produce a much higher energy yield than a conventional SPM generator. As the extra energy yield would be beneficial over the lifetime of the turbine, this will have a bigger impact than the CAPEX cost savings with a reduced machine volume. In addition, a novel Vernier machine with magnets on both the stator and rotor has been proposed to further improve the energy yield. In addition to the basic electromagnetic performance, the levelised cost of energy (LCOE) of the three generator topologies, that is, the conventional SPM, SPM‐V and the proposed Vernier machines, has been compared. The direct‐drive powertrain systems with SPM‐V and the proposed Vernier generators can achieve LCOE of 12.3% and 24% lower than that of the conventional SPM generators, indicating their huge potential as an alternative to reduce the overall cost of energy. [ABSTRACT FROM AUTHOR]

Purpose: By combining the notion of prospect theory with advanced machine learning algorithms, this study aims to predict whether financial institutions (FIs) adopt a reactive stance when they perceive climate change as a risk, consequently leading to the adoption of environmental, social and governance (ESG) practices to avoid this risk. Prospect theory assumes that decision-makers react quickly when decisions are framed as a risk or threat rather than as an opportunity. Design/methodology/approach: We used a sample of 168 FIs across 27 countries and seven regions over the period 2003–2020. To conduct our empirical investigation, we compared the prediction accuracy of various machine learning algorithms. Findings: Our findings suggest that out of 12 machine learning algorithms, AdaBoost, Gradient Boosting and XGBoost have the most precision in predicting whether FIs react to climate change risk in adopting ESG practices. This study also tested the overall climate change risk and risks associated with physical, opportunity and regulatory shocks of climate change. We observed that risks associated with physical and regulatory shocks significantly impact the adoption of ESG practices, supporting prospect theory predictions. Practical implications: The insights of this study provide important implications for policymakers. Specifically, policymakers must take into account the risk posed by climate change in the corporate decision-making process, as it directly influences a firm's adoption of corporate actions (ESG practices). Originality/value: To the best of our knowledge, this is the first study to investigate the firm-level climate change risk and adoption of ESG practices from a prospect theory perspective using novel machine learning algorithms. [ABSTRACT FROM AUTHOR]

This paper presents four state-of-art methods for the finite-state automaton inference based on a sample of labeled strings. The first algorithm is Exbar, and the next three are mathematical models based on ASP, SAT and SMT theories. The potentiality of using multiprocessor computers in the context of automata inference was our research's primary goal. In a series of experiments, we showed that our parallelization of the exbar algorithm is the best choice when a multiprocessor system is available. Furthermore, we obtained a superlinear speedup for some of the prepared datasets, achieving almost a 5-fold speedup on the median, using 12 and 24 processes. [ABSTRACT FROM AUTHOR]

We study the equivalence between eval-readback and eval-apply big-step evaluators in the general setting of the pure lambda calculus. We study 'one-step' equivalence (same strategy) and also discuss 'big-step' equivalence (same final result). One-step equivalence extends for free to evaluators in other settings (calculi, programming languages, proof assistants, etc.) by restricting the terms (closed, convergent) while maintaining the strategy. We present a proof that one-step equivalence holds when (1) the 'readback' stage satisfies straightforward well-formedness provisos, (2) the 'eval' stage implements a 'uniform' strategy, and (3) the eval-apply evaluator implements a 'balanced hybrid' strategy that has 'eval' as a subsidiary strategy. The proof proceeds by the 'lightweight fusion by fixed-point promotion' program transformation on evaluator implementations to fuse readback and eval into the balanced hybrid. The proof can be followed with no previous knowledge of the transformation. We use Haskell 2010 as the implementation language, with all evaluators written in monadic style to guarantee semantics (strategy) preservation, but the choice of implementation language is immaterial. To illustrate the large scope of the equivalence, we provide an extensive survey of the strategy space using canonical eval-apply evaluators in code and big-step 'natural' operational semantics. We discuss the strategies' properties, some of their uses, and their abstract machines. We improve the formal definition of uniform and hybrid strategy, use it to structure the strategy space, and to obtain generic higher-order evaluators which are used in the equivalence proof. We introduce a systematic notation for both evaluator styles and use it to summarise strategy and evaluator equivalences, including (non-)equivalences within a style and (non-)equivalences between styles not proven by the transformation. [ABSTRACT FROM AUTHOR]

Can the γ-calculus be considered a reasonable computational model? Can we use it for measuring the time and space consumption of algorithms? While the literature contains positive answers about time, much less is known about space. This paper presents a new reasonable space cost model for the γ-calculus, based on a variant over the Krivine abstract machine. For the first time, this cost model is able to accommodate logarithmic space. Moreover, we study the time behavior of our machine, which is unreasonable but it can be turned into a reasonable one using known techniques. Finally, we show how to transport our results to the call-by-value γ-calculus. [ABSTRACT FROM AUTHOR]

The growing urgency for low-carbon lifestyles necessitates developing effective strategies to promote sustainable consumer choices. This study investigates key dimensions of information quality that shape consumer behavior within digital marketing to achieve this goal. Employing a mixed-methods approach that integrates grounded theory and machine learning, this study identifies three core dimensions of low-carbon information quality: matching quality, presentation quality, and interpretability quality. These dimensions underscore the importance of aligning information with consumer needs, ensuring clear and accurate presentation, and fostering transparency for trustworthiness. A Random Forest algorithm-based evaluation model is constructed to assess low-carbon information quality, demonstrating its effectiveness in identifying high-quality, sustainable content. This research provides a practical tool for digital marketers to enhance their strategies, raise consumer awareness of sustainable options, and ultimately contribute to the growth of the low-carbon consumption market. [ABSTRACT FROM AUTHOR]

Surface integrity is a critical factor that affects the fatigue resistance of materials. A surface mechanical rolling treatment (SMRT) process can effectively improve the surface integrity of the material, thus enhancing the fatigue property. In this paper, an analysis of variance (ANOVA) and signal-to-noise ratio (SNR) are performed by orthogonal experimental design with SMRT parameters as variables and surface integrity indicators as optimization objectives, and the support vector machine-active learning (SVM-AL) model is proposed based on machine learning theory. The entire model includes three rounds of AL processes. In each round of the AL process, the SMRT parameters with relative average deviation and high output values from cross-validation are selected for the additional experimental supplement. The results show that the prediction accuracy and generalization ability of the SVM-AL model are significantly improved compared to the support vector machine (SVM) model. A fatigue test was also carried out, and the fatigue property of the SMRT specimens predicted by the SVM-AL model is also higher than that of the other specimens. [ABSTRACT FROM AUTHOR]

Knowing the rate at which particle radiation releases energy in a material, the "stopping power," is key to designing nuclear reactors, medical treatments, semiconductor and quantum materials, and many other technologies. While the nuclear contribution to stopping power, i.e., elastic scattering between atoms, is well understood in the literature, the route for gathering data on the electronic contribution has for decades remained costly and reliant on many simplifying assumptions, including that materials are isotropic. We establish a method that combines time-dependent density functional theory (TDDFT) and machine learning to reduce the time to assess new materials to hours on a supercomputer and provide valuable data on how atomic details influence electronic stopping. Our approach uses TDDFT to compute the electronic stopping from first principles in several directions and then machine learning to interpolate to other directions at a cost of 10 million times fewer core-hours. We demonstrate the combined approach in a study of proton irradiation in aluminum and employ it to predict how the depth of maximum energy deposition, the "Bragg Peak," varies depending on the incident angle—a quantity otherwise inaccessible to modelers and far outside the scales of quantum mechanical simulations. The lack of any experimental information requirement makes our method applicable to most materials, and its speed makes it a prime candidate for enabling quantum-to-continuum models of radiation damage. The prospect of reusing valuable TDDFT data for training the model makes our approach appealing for applications in the age of materials data science. [ABSTRACT FROM AUTHOR]

Online health communities (OHCs) are able to facilitate social support exchange among people with similar health concerns, and the relationship between self-disclosure and social support exchange has been widely discussed. Build upon the previous studies, we extend the seminal theory of reasoned action (TRA) in this research, through the adoption of an salient but understudied construct, user role, which captures user inclination toward providing or seeking social support, and further explore how it impacts OHC users' self-disclosure intention. We adopt a mixed methods approach including manual coding, machine learning algorithms, and econometric analyses, and investigate over 4 million posts over 17 years from a well-developed breast cancer OHC to uncover both direct and indirect effects of user role on OHC users' intention of future self-disclosure intention. The results reveal both the main and moderating effects of user roles regarding users' self-disclosure intention. First, user with a more clear intention of social support seeking or providing are more likely to disclose personal information. Second, the relative tendency of support provision magnifies the positive effects of attitudinal and normative factors toward future disclosure. We also discuss the findings and implications of the extended TRA framework to generate some actionable insights of OHC design. [ABSTRACT FROM AUTHOR]

In the dynamic world of cloud computing, auto-scaling stands as a beacon of efficiency, dynamically aligning resources with fluctuating demands. This paper presents a comprehensive review of auto-scaling techniques, highlighting significant advancements and persisting challenges in the field. First, we overview the fundamental principles and mechanisms of auto-scaling, including its role in improving cost efficiency, performance, and energy consumption in cloud services. We then discuss various strategies employed in auto-scaling, ranging from threshold-based rules and queuing theory to sophisticated machine learning and time series analysis approaches. After that, we explore the critical issues in auto-scaling practices and review several studies that demonstrate how these challenges can be addressed. We then conclude by offering insights into several promising research directions, emphasizing the development of predictive scaling mechanisms and the integration of advanced machine learning techniques to achieve more effective and efficient auto-scaling solutions. [ABSTRACT FROM AUTHOR]

Background: Essential tremor (ET) and Parkinson's disease (PD) are the two most prevalent movement disorders, sharing several overlapping tremor clinical features. Although growing evidence pointed out that changes in similar brain network nodes are associated with these two diseases, the brain network topological properties are still not very clear. Objective: The combination of graph theory analysis with machine learning (ML) algorithms provides a promising way to reveal the topological pathogenesis in ET and tremor-dominant PD (tPD). Methods: Topological metrics were extracted from Resting-state functional images of 86 ET patients, 86 tPD patients, and 86 age- and sex-matched healthy controls (HCs). Three steps were conducted to feature dimensionality reduction and four frequently used classifiers were adopted to discriminate ET, tPD, and HCs. Results: A support vector machine classifier achieved the best classification performance of four classifiers for discriminating ET, tPD, and HCs with 89.0% mean accuracy (mACC) and was used for binary classification. Particularly, the binary classification performances among ET vs. tPD, ET vs. HCs, and tPD vs. HCs were with 94.2% mACC, 86.0% mACC, and 86.3% mACC, respectively. The most power discriminative features were mainly located in the default, frontal-parietal, cingulo-opercular, sensorimotor, and cerebellum networks. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with clinical characteristics. Conclusions: These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET, tPD, and HCs but also help to reveal the potential brain topological network pathogenesis in ET and tPD. [ABSTRACT FROM AUTHOR]

We continue the investigation on the relations of QCDCL and QBF resolution systems. In particular, we introduce QCDCL versions that tightly characterise QUResolution and (a slight variant of) long-distance Q-Resolution. We show that most QCDCL variants – parameterised by different policies for decisions, unit propagations and reductions – lead to incomparable systems for almost all choices of these policies. [ABSTRACT FROM AUTHOR]

Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features, it allows us to summarize and privatize the data distribution once, which we can repeatedly use during generator training without further privacy loss. An important question in this framework is, then, what features are useful to distinguish between real and synthetic data distributions, and whether those enable us to generate quality synthetic data. This work considers using the features of neural tangent kernels (NTKs), more precisely empirical NTKs (e-NTKs). We find that, perhaps surprisingly, the expressiveness of the untrained e-NTK features is comparable to that of the features taken from pre-trained perceptual features using public data. As a result, our method improves the privacy-accuracy trade-off compared to other state-of-the-art methods, without relying on any public data, as demonstrated on several tabular and image benchmark datasets. [ABSTRACT FROM AUTHOR]

Background: Lately, the reproducibility of scientific results has become an increasing worry in the scientific community. Several studies show that artificial intelligence research is not spared from reproducibility issues. Objectives: As a pioneer in open and transparent research published on the Internet, the Journal of Artificial Intelligence Research (JAIR) seeks to promote good research practices and close the feedback loop between the original researchers and those reproducing their research. Methods: Four different mechanisms will be adopted immediately by JAIR. These are: 1) reproducibility checklists, 2) structured abstracts, 3) reproducibility badges and 4) reproducibility reports. Results: All authors submitting articles to JAIR fill out a reproducibility checklist and are encouraged to use structured abstracts. Articles that fulfill certain criteria will receive reproducibility badges, and reproducibility reports can be submitted by anyone for any article published in JAIR. Conclusions: We believe that adopting the four mechanisms outlined in this paper will improve the reproducibility of research published in JAIR and thus make a contribution to addressing the broader reproducibility issue in artificial intelligence. We hope that JAIR’s reproducibility initiative will inspire similar efforts at other top-tier journals. [ABSTRACT FROM AUTHOR]

As algorithmic decision-making systems (ADMS) are increasingly deployed across various sectors, the importance of research on fairness in Artificial Intelligence (AI) continues to grow. In this paper we highlight a number of significant practical limitations and regulatory compliance issues associated with the application of existing bias mitigation methods to ADMS. We present an example of an algorithmic system used in recruitment to illustrate these limitations. Our analysis of existing methods indicates a pressing need for a change in the approach to the development of new methods. In order to address the limitations, we provide recommendations for key factors to consider in the development of new bias mitigation methods that aim to be effective in real-world scenarios and comply with legal requirements in the European Union, United Kingdom and United States, such as non-discrimination, data protection and sector-specific regulations. Further, we suggest a checklist relating to these recommendations that should be included with the development of new bias mitigation methods. [ABSTRACT FROM AUTHOR]

Existing algorithms for ensuring fairness in AI use a single-shot training strategy, where an AI model is trained on an annotated training dataset with sensitive attributes and then fielded for utilization. This training strategy is effective in problems with stationary distributions, where both the training and testing data are drawn from the same distribution. However, it is vulnerable with respect to distributional shifts in the input space that may occur after the initial training phase. As a result, the time-dependent nature of data can introduce biases and performance degradation into the model predictions, even if the model is initially fair. Model retraining from scratch using a new annotated dataset is a naive solution that is expensive and time-consuming. We develop an algorithm to adapt a fair model to remain fair and generalizable under domain shift using solely new unannotated data points. We recast this learning setting as an unsupervised domain adaptation (UDA) problem. Our algorithm is based on updating the model such that the internal representation of data remains unbiased despite distributional shifts in the input space. We provide empirical validation on three common fairness datasets to show that the challenge exists in practical setting and to demonstrate the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

Despite significant efforts to democratize artificial intelligence (AI), computer vision which is a sub-field of AI, still lags in Africa. A significant factor to this, is the limited access to computing resources, datasets, and collaborations. As a result, Africa’s contribution to top-tier publications in this field has only been 0.06% over the past decade. Towards improving the computer vision field and making it more accessible and inclusive, this study analyzes 63,000 Scopus-indexed computer vision publications from Africa. We utilize large language models to automatically parse their abstracts, to identify and categorize topics and datasets. This resulted in listing more than 100 African datasets. Our objective is to provide a comprehensive taxonomy of dataset categories to facilitate better understanding and utilization of these resources. We also analyze collaboration trends of researchers within and outside the continent. Additionally, we conduct a large-scale questionnaire among African computer vision researchers to identify the structural barriers they believe require urgent attention. In conclusion, our study offers a comprehensive overview of the current state of computer vision research in Africa, to empower marginalized communities to participate in the design and development of computer vision systems. [ABSTRACT FROM AUTHOR]