Use Of Prior Knowledge Research Articles

Knowledge-slanted random forest method for high-dimensional data and small sample size with a feature selection application for gene expression data

The use of prior knowledge in the machine learning framework has been considered a potential tool to handle the curse of dimensionality in genetic and genomics data. Although random forest (RF) represents a flexible non-parametric approach with several advantages, it can provide poor accuracy in high-dimensional settings, mainly in scenarios with small sample sizes. We propose a knowledge-slanted RF that integrates biological networks as prior knowledge into the model to improve its performance and explainability, exemplifying its use for selecting and identifying relevant genes. knowledge-slanted RF is a combination of two stages. First, prior knowledge represented by graphs is translated by running a random walk with restart algorithm to determine the relevance of each gene based on its connection and localization on a protein-protein interaction network. Then, each relevance is used to modify the selection probability to draw a gene as a candidate split-feature in the conventional RF. Experiments in simulated datasets with very small sample sizes (n≤30)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$(n \\le 30)$$\\end{document} comparing knowledge-slanted RF against conventional RF and logistic lasso regression, suggest an improved precision in outcome prediction compared to the other methods. The knowledge-slanted RF was completed with the introduction of a modified version of the Boruta feature selection algorithm. Finally, knowledge-slanted RF identified more relevant biological genes, offering a higher level of explainability for users than conventional RF. These findings were corroborated in one real case to identify relevant genes to calcific aortic valve stenosis.

Use of prior knowledge to discover causal additive models with unobserved variables and its application to time series data

Use of prior knowledge to discover causal additive models with unobserved variables and its application to time series data

Explicit coordinated signal control using soft actor–critic for cycle length determination

AbstractExplicit signal coordination carries prior knowledge of traffic engineering and is widely accepted for global implementation. With the recent popularity of reinforcement learning, numerous researchers have turned to implicit signal coordination. However, these methods inevitably require learning coordination from scratch. To maximize the use of prior knowledge, this study proposes an explicit coordinated signal control (ECSC) method using a soft actor–critic for cycle length determination. This method can fundamentally solve the challenges encountered by traditional methods in determining the cycle length. Soft actor–critic was selected among various reinforcement learning methods. A single agent was administered to the arterials. An action is defined as the selection of a cycle length from among the candidates. The state is represented as a feature vector, including the cycle length and features of each leg at every intersection. The reward is defined as departures that indirectly minimize system vehicle delays. Simulation results indicate that ECSC significantly outperforms the baseline methods, as evident in system vehicle delay across nearly all demand scenarios and throughput in high demand scenarios. The ECSC revitalizes explicit signal coordination and introduces new perspectives on the application of reinforcement learning methods in signal coordination.

Implementation a Different Segmentation Method as a Joint Prior Model to Reconstruction the Bayesian Image analysis

The basic concepts in the application of Bayesian approaches to image analysis have been introduced as advanced method. The Bayesian approach contains benefits in respect to image analysis and interpretation because it permits the use of prior knowledge concerning the situation under study. This paper use to investigate the application of some of the well-known procedures (determines number labels of image under several conditions like noise of image, resolution of image) for the Bayesian image analysis with segmentation as a joint prior model in order to estimate the Maximum Likelihood (ML). Markov random field with segmentation which resulted by mean of posterior (MP). This paper contains several sections. Firstly, includes introduction about the image analysis with, Bayes frame work and statistical background to Markov's random field and its relationship through Markov Chain Monte Carlo. Secondly, section, which directly addresses solutions by using a principle of segmentation, which is a representation in threshold, is simply type introduced. Thirdly, presents the description of Experiment of Segmentation by depend on histogram also study of the factor (one prior) and the same model by adding segmentation (joint prior) based on techniques presented in the previously section are discussed . Fourthly, this section contains on the second prior implementation and simulation by using phantom data (Castle from south East Asia) also steps of estimation. Finally, result of experiment as well as estimation and summary.

Analytical quality by design based on knowledge organization: A case study of developing an ultrahigh-performance liquid chromatography method for the detection of phenolic compounds.

Despite numerous successful cases, there are still some challenges in using analytical quality by design (AQbD) for the development of analytical methods. Knowledge organization helps to enhance the objectivity of risk assessment, reduce the number of preliminary exploratory experiments, identify potential critical method parameters (CMPs) and their scope. In the present study, we aimed to develop a simple, rapid, and robust analytical method for detecting phenolic compounds in Xiaochaihu capsule intermediates utilizing knowledge organization. Knowledge organization and AQbD were combined to obtain the initial analytical conditions through knowledge collection, extraction, reorganization, and analysis. The quantitative relationship between critical method attributes (CMAs) and CMPs was then established by a definitive screening design. The method operable design region was calculated using an exhaustive Monte Carlo approach based on the probability of reaching the standard. Robustness investigation and methodological validation were finally performed. Analytical target profiles, CMAs, potential CMPs, and initial analytical conditions were initially identified, and the optimized ranges of operating parameters were obtained. A UHPLC method was successfully established for the analysis of phenolic compounds in ginger-ginger pinellia percolate, and the method validation outcomes were also satisfactory. The developed method can be a reliable means to detect the phenolic compounds of Xiaochaihu capsule intermediates. Knowledge organization provides a new approach for making better use of prior knowledge, significantly enhancing the efficiency of analytical method development. The approach is versatile and can be similarly applied to the development of other methods.

Proceedings of the 2023 Viral Clearance Symposium, Session 1: Regulatory Updates.

At the time of the 2023 Viral Clearance Symposium in Vienna, the ongoing revision of ICH Guideline Q5A(R1) Viral Safety Evaluation of Biotechnology Products Derived from Cell Lines of Human or Animal Origin clearly was the dominant regulatory topic. At the symposium, the changes expected for Q5A(R2) to mirror advances of scientific knowledge, for example, the inclusion of new products, including viral-vector-derived ones, that can be subject to virus clearance, deliberations around continuous manufacturing processes, the use of prior knowledge to supplement or in part replace virus validation studies, and new molecular methods for detection of adventitious viruses, were discussed by a European and a US regulator as well as representatives from industry associations that had been involved with the drafting process.

Can Students without Prior Knowledge Use ChatGPT to Answer Test Questions? An Empirical Study

With the immense interest in ChatGPT worldwide, education has seen a mix of both excitement and skepticism. To properly evaluate its impact on education, it is crucial to understand how far it can help students without prior knowledge answer assessment questions. This study aims to address this question as well as the impact of the question type. We conducted multiple experiments with computer engineering students (experiment group: n =41 to 56), who were asked to use ChatGPT to answer previous test questions before learning about the related topics. Their scores were then compared with the scores of previous-term students who answered the same questions in a quiz or exam setting (control group: n =24 to 61). The results showed a wide range of effect sizes, from -2.55 to 1.23, depending on the question type and content. The experiment group performed best answering code analysis and conceptual questions but struggled with code completion and questions that involved images. However, the performance in code generation tasks was inconsistent. Overall, the ChatGPT group’s answers lagged slightly behind the control group’s answers with an effect size of -0.16. We conclude that ChatGPT, at least in the field of this study, is not yet ready to rely on by students who do not have sufficient background to evaluate generated answers. We suggest that educators try using ChatGPT and educate students on effective questioning techniques and how to assess the generated responses. This study provides insights into the capabilities and limitations of ChatGPT in education and informs future research and development.

Exploring numeracy teaching and learning by using ethnomathematics

The purpose of this study was to explore the impact that the cultural or everyday practices of ethnomathematics of a particular cultural group will have if they are used in teaching and learning of numeracy concepts related to geometrical shapes. It explored cultural practices, artefacts, written, verbal or visual communication messages reflecting mathematics in order to see how they could best eliminate the problems learners encounter in the acquisition of numeracy language. Data was generated using observations, brainstorming and interviews. Based on this research, the impact of using ethnomathematics in numeracy teaching and learning brings in innumerable benefits. These include promoting deep learning and allows teachers to maka use of prior knowledge in the classroom. This allows learners to recall and relate to the concepts learnt and employ them in their daily activities so that they do not to remain inert. Another impact of interest was the reclaiming of names of geometrical shapes from certain languages which currently teachers are not aware of as they are overlooked. For instance when geometrical shapes were first discussed using local terminology, it made more meaning than when taught using English used as a medium of teaching and learning in the research area.

Bayesian inference of the impulse-response model of athlete training and performance

ABSTRACT The Banister impulse-response (IR) model was designed to predict an athlete’s performance ability from their past training. Despite its long history, the model’s usefulness remains limited due to difficulties in obtaining precise parameter estimates and performance predictions. To help address these challenges, we developed a Bayesian implementation of the IR model, which formalises the combined use of prior knowledge and data. We report the following methodological contributions: 1) we reformulated the model to facilitate the specification of informative priors, 2) we derived the IR model in Bayesian terms, and 3) we developed a method that enabled the JAGS software to be used while enforcing parameter constraints. To demonstrate proof-of-principle, we applied the model to the data of a national-class middle-distance runner. We specified the priors from published values of IR model parameters, followed by estimating the posterior distributions from the priors and the athlete’s data. The Bayesian approach led to more precise and plausible parameter estimates than nonlinear least squares. We conclude that the Bayesian implementation of the IR model shows promise in addressing a primary challenge to its usefulness for athlete monitoring.

Prior knowledge and active learning enable hybrid method for estimating leaf chlorophyll content from multi-scale canopy reflectance

Real-time and accurate assessment of leaf chlorophyll content (Cab) will be significant for monitoring plant physiological status. Development of hybrid methods advances the assessment of Cab with the advantages of both physical mechanism and calculation capability, while the estimation accuracies were constrained by the lacking of prior knowledge and representative real samples. This study explored the use of prior knowledge and active learning to enable the development of efficient hybrid methods for assessing Cab from multi-scale canopy reflectance. The hybrid method was established by using the simulated dataset from the PROSAIL model to train the Gaussian process regression (GPR) model. We used two measured crop datasets and three publicly-available grassland, herbaceous, and tree species datasets collected from near-ground, unmanned aerial vehicle, and airborne platforms to examine the model performances. Prior knowledge for model parameters was obtained from ground measurements, and an active learning method, namely improved Greedy sampling (iGS), was employed to select new representative samples. The results showed that performance of the hybrid method in Cab estimations varied with leaf structure parameter, carotenoid content, anthocyanin content, carbon-based constituents, average leaf angle, leaf area index, and hot-spot size parameter. When prior knowledge for the ranges of model parameters was available, the hybrid method better estimated Cab with the root mean square error (RMSE) reduced by 7.59%–65.96%. Compared with the random selection, iGS was able to select representative samples to update the estimation models with only 10% of the measured samples, and a higher ratio (e.g., 20%) may be needed for small datasets. The hybrid method coupled with prior knowledge and active learning obtained satisfied estimations of Cab across different datasets with the relative RMSE of 12.30%–27.24%. The proposed method will contribute to improving the applicability and robustness of hybrid modeling for multi-scale monitoring of leaf biochemical traits.

Knowledge Enhanced Semantic Communication Receiver

In recent years, with the rapid development of deep learning and natural language processing technologies, semantic communication has become a topic of great interest in the field of communication. Although existing deep learning-based semantic communication approaches have shown many advantages, they still do not make sufficient use of prior knowledge. Moreover, most existing semantic communication methods focus on the semantic encoding at the transmitter side, while we believe that the semantic decoding capability of the receiver should also be concerned. In this paper, we propose a knowledge enhanced semantic communication framework in which the receiver can more actively utilize the facts in the knowledge base for semantic reasoning and decoding, on the basis of only affecting the parameters rather than the structure of the neural networks at the transmitter side. Specifically, we design a transformer-based knowledge extractor to find relevant factual triples for the received noisy signal. Extensive simulation results on the WebNLG dataset demonstrate that the proposed receiver yields superior performance on top of the knowledge graph enhanced decoding.

Hierarchical Bayesian modeling to quantify fracture limit uncertainty of high-burnup advanced fuel cladding tubes under loss-of-coolant accident conditions

For realizing a highly reliable fracture limit evaluation of fuel cladding tubes during loss-of-coolant accidents (LOCAs) in light-water reactors, we developed a method to quantify the fracture limit uncertainty of high-burnup advanced fuel cladding tubes. This method employs a hierarchical Bayesian model that can quantify uncertainty even with limited experimental data. The hierarchical Bayesian model was an extended version of the fracture probability estimation model developed in our previous study. The fracture limit uncertainty was quantified as a probability using the amount of oxidation (Equivalent cladding reacted: ECR) and the initial hydrogen concentration (the hydrogen concentration in the fuel cladding tubes before the LOCA-simulated tests) as explanatory variables. We divided the regression coefficients of this model into a hierarchical structure with an overall average term common to all types of fuel cladding tubes and a term representing differences among various types of fuel cladding tubes. This hierarchical structure enabled us to quantify the fracture limit uncertainty through the effective use of prior knowledge and data, even for high-burnup advanced fuel cladding tubes with a small number of data points. The fracture limits representing a 5% fracture probability with 95% confidence of the high-burnup advanced fuel cladding tubes evaluated by the hierarchical Bayesian model were higher than 15% ECR for the initial hydrogen concentrations of up to 700–900wtppm and restraint loads below 535N. These fracture limits were comparable to the limit of the unirradiated Zircaloy-4 cladding tube, indicating that the burnup extension and use of the advanced fuel cladding tubes do not significantly lower the fracture limit of fuel cladding tubes. Further, we proposed a method to reduce the fracture limit uncertainty by using non-binary data, instead of the binary data, depending on the condition of the fuel cladding tube specimens after performing the LOCA-simulated test, thereby increasing the amount of information in the data.

Noise-aware Local Model Training Mechanism for Federated Learning

As a new paradigm in training intelligent models, federated learning is widely used to train a global model without requiring local data to be uploaded from end devices. However, there are often mislabeled samples (i.e., noisy samples) in the dataset, which will cause the model update to deviate from the correct direction during the training process, thus reducing the convergence accuracy of the global model. Existing works employ noisy label correction techniques to reduce the impact of noisy samples on model updates by correcting labels; however, such methods necessitate the use of prior knowledge and additional communication costs, which cannot be directly applied to federated learning due to data privacy concerns and limited communication resources. Therefore, this paper proposes a noise-aware local model training method that corrects the noisy labels directly at the end device under the constraints of federated learning. By constructing a label correction model, a joint optimization problem is formally defined for optimizing both the label correction model and the client-side local training model (e.g., classification model). As a solution to this optimization problem, we propose a robustness training algorithm using label correction, along with a cross-validation data sampling algorithm that updates both models simultaneously. It is verified through experiments that the mechanism can effectively improve the model convergence accuracy on noisy datasets in federated learning scenarios.

Design, implementation and assessment of a targeting mechanism in a college savings program

Percorsi is a matched savings program aimed at helping students from low-income households attend college. Previous experimental re-search has demonstrated the positive effects of the program on college enrollment and persistence. This paper investigates the extent to which these experimental results are attributable to the applied targeting strategy: students were admitted to the study through a targeting mechanism based on household income and on a predictive model of university enrollment probability. Applicants with a very high predicted universi-ty enrollment probability and those who revealed no intention of going to university were excluded from the program. The authors assess the performance of this approach by comparing cost-effectiveness esti-mates against simulated scenarios, showing that both the implemented and a simplified targeting yield a cost-effectiveness gain over a no tar-geting scenario. The study makes the case for an increased use of prior knowledge and collaboration between researchers and program manag-ers to enhance programs' cost-effectiveness.

Abundance Determination of Large Mammals with Distance Sampling Perspective, the Case of Elephants of the Mole National Park (MNP) of Ghana

Distance sampling with line transect method has been applied by many researchers to monitor and observe varied animals and plants with the aim of determining the population density and or abundance of animals. The application of this method has not received the needed attention in Ghana, in particular to monitor, observe, and estimate the densities and abundance of animals and plants in the game reserves of the Mole National Park (MNP) is not without exception and the statistics of these are always reported based on guesses and without any scientific proof. This study has seen the application of line transect methodology in the MNP in which the abundance estimates are statistically determined with both the classical and Bayesian philosophies of statistical approaches. An alternative means of detectability estimation using the total probability concept has been established to enhance the probability of detection of a rare and elusive population of large mammals. In performing statistical investigations on rare and elusive population, it appears insufficient to model from the classical perspective, the use of PRIOR knowledge as seen in the Bayesian context cannot be underestimated. This study proposed that the concept of Total Probability with prior knowledge of animals and plants in line transect surveys must be well embraced, Periodic censuss must be conducted regularly to help in establishing the rate of extinction of units of interest in wildlife and Distance sampling data with line transect sampling methodology need not be analysed using only the classical reasoning. Attention must be given to the existence and availability of prior knowledge of the units under study.

Rotationally equivariant super-resolution of velocity fields in two-dimensional flows using convolutional neural networks

This paper investigates the super-resolution of velocity fields in two-dimensional flows from the viewpoint of rotational equivariance. Super-resolution refers to techniques that enhance the resolution of an image from low to high resolution, and it has recently been applied in fluid mechanics. Rotational equivariance of super-resolution models is defined as the property by which the super-resolved velocity field is rotated according to a rotation of the input, leading to inferences that are covariant with the orientation of fluid systems. In physics, covariance is often related to symmetries. To better understand the connection with symmetries, the notion of rotational consistency of datasets is introduced within the framework of supervised learning, which is defined as the invariance of pairs of low- and high-resolution velocity fields with respect to rotation. This consistency is sufficient and necessary for super-resolution models to learn rotational equivariance from large datasets. Such a large dataset is not required when rotational equivariance is imposed on super-resolution models through the use of prior knowledge in the form of equivariant kernel patterns. Nonetheless, even if a fluid system has rotational symmetry, this symmetry may not carry over to a velocity dataset, which is not rotationally consistent. This inconsistency can arise when the rotation does not commute with the generation of low-resolution velocity fields. These theoretical assertions are supported by the results of numerical experiments, where two existing convolutional neural networks (CNNs) are converted into rotationally equivariant CNNs and the inferences of these CNNs are compared after the supervised training.

A Comprehensive Overview of RNA Deconvolution Methods and Their Application.

Tumors are surrounded by a variety of tumor microenvironmental cells. Profiling individual cells within the tumor tissues is crucial to characterize the tumor microenvironment and its therapeutic implications. Since single-cell technologies are still not cost-effective, scientists have developed many statistical deconvolution methods to delineate cellular characteristics from bulk transcriptome data. Here, we present an overview of 20 deconvolution techniques, including cutting-edge techniques recently established. We categorized deconvolution techniques by three primary criteria: characteristics of methodology, use of prior knowledge of cell types and outcome of the methods. We highlighted the advantage of the recent deconvolution tools that are based on probabilistic models. Moreover, we illustrated two scenarios of the common application of deconvolution methods to study tumor microenvironments. This comprehensive review will serve as a guideline for the researchers to select the appropriate method for their application of deconvolution.

Evaluating the effects of the analogical learning approach on eighth graders’ learning outcomes: the role of metacognition

Teaching with analogies is an important pedagogy that helps learners construct abstract conceptions through reasoning with something familiar. Heat concepts were chosen for this study because they have an intangible nature and involve complex mechanisms that often challenge school-aged learners. Learning this kind of complex concept with analogies involves complicated mental processes that could demand learners’ metacognitive abilities; yet, to date, the influence of metacognition has been left unexamined. This study therefore investigated how metacognition differentially affected adolescents’ processes and outcomes of analogical learning about abstract heat concepts. Eighty-three eighth graders participated in the study and attended two units of Teaching-With-Analogies on specific heat and heat transfer. This study adopted a mixed-method approach along with within-group comparisons. Among them, eight individuals from each of the high-, moderate- and low-metacognitive groups were interviewed to explore the utilized metacognitive activities and their relation with the ability to reason with analogies. The quantitative findings revealed that analogies benefited the moderate metacognitive learners, and yet did not alter the conceptual understanding of the high and low metacognitive cohorts. A unique explanatory power of metacognition was also observed on the learners’ post conceptual understanding, in addition to on their prior knowledge. Verbal process data illustrated that metacognitive abilities substantially influenced every stage of solving heat problems with analogies. The differential outcomes of the analogical learning approach were explained by in-depth case analyses considering the use of prior knowledge and the absence of metacognition during analogical reasoning. Metacognitive characteristics of the dynamic analogy-inferring process for different metacognitive groups were synthesized. The associated implications for the analogical learning approach and accommodations for adolescents of different levels of metacognition are also discussed.

Semi-supervised clustering of quaternion time series: Application to gait analysis in multiple sclerosis using motion sensor data.

Recent approaches in gait analysis involve the use of wearable motion sensors to extract spatio-temporal parameters that characterize multiple aspects of an individual's gait. In particular, the medical community could largely benefit from this type of devices as they could provide the clinicians with a valuable tool for assessing gait impairment. Motion sensor data are however complex and there is an urgent unmet need to develop sound statistical methods for analyzing such data and extracting clinically relevant information. In this article, we measure gait by following the hip rotation over time and the resulting statistical unit is a time series of unit quaternions. We explore the possibility to form groups of patients with similar walking impairment by taking into account their walking data and their global decease severity with semi-supervised clustering. We generalize a compromise-based method named hclustcompro to unit quaternion time series by combining it with the proper dissimilarity quaternion dynamic time warping. We apply this method on patients diagnosed with multiple sclerosis to form groups of patients with similar walking deficiencies while accounting for the clinical assessment of their overall disability. We also compare the compromise-based clustering approach with the method mergeTrees that falls into a sub-class of ensemble clustering named collaborative clustering. The results provide a first proof of both the interest of using wearable motion sensors for assessing gait impairment and the use of prior knowledge to guide the clustering process. It also demonstrates that compromise-based clustering is a more appropriate approach in this context.

Bayesian updating with two-step parallel Bayesian optimization and quadrature

This work proposes a Bayesian updating approach, called parallel Bayesian optimization and quadrature (PBOQ). It is rooted in Bayesian updating with structural reliability methods (BUS) and offers a coherent Bayesian approach for the BUS analysis by assuming Gaussian process priors. The first step of the method, i.e., parallel Bayesian optimization, effectively explores a constant c in BUS by a novel parallel infill sampling strategy. The second step (parallel Bayesian quadrature) then infers the posterior distribution by another parallel infill sampling strategy using subset simulation. The proposed approach enables to make the fullest use of prior knowledge and parallel computing, resulting in a substantial reduction of the computational burden of model updating. Four numerical examples with varying complexity are investigated for demonstrating the proposed method against several existing methods. The results show the potential benefits by advocating a coherent Bayesian fashion to the BUS analysis.