Integration Of Prior Knowledge Research Articles

Noisecut: a python package for noise-tolerant classification of binary data using prior knowledge integration and max-cut solutions

BackgroundClassification of binary data arises naturally in many clinical applications, such as patient risk stratification through ICD codes. One of the key practical challenges in data classification using machine learning is to avoid overfitting. Overfitting in supervised learning primarily occurs when a model learns random variations from noisy labels in training data rather than the underlying patterns. While traditional methods such as regularization and early stopping have demonstrated effectiveness in interpolation tasks, addressing overfitting in the classification of binary data, in which predictions always amount to extrapolation, demands extrapolation-enhanced strategies. One such approach is hybrid mechanistic/data-driven modeling, which integrates prior knowledge on input features into the learning process, enhancing the model’s ability to extrapolate.ResultsWe present NoiseCut, a Python package for noise-tolerant classification of binary data by employing a hybrid modeling approach that leverages solutions of defined max-cut problems. In a comparative analysis conducted on synthetically generated binary datasets, NoiseCut exhibits better overfitting prevention compared to the early stopping technique employed by different supervised machine learning algorithms. The noise tolerance of NoiseCut stems from a dropout strategy that leverages prior knowledge of input features and is further enhanced by the integration of max-cut problems into the learning process.ConclusionsNoiseCut is a Python package for the implementation of hybrid modeling for the classification of binary data. It facilitates the integration of mechanistic knowledge on the input features into learning from data in a structured manner and proves to be a valuable classification tool when the available training data is noisy and/or limited in size. This advantage is especially prominent in medical and biomedical applications where data scarcity and noise are common challenges. The codebase, illustrations, and documentation for NoiseCut are accessible for download at https://pypi.org/project/noisecut/. The implementation detailed in this paper corresponds to the version 0.2.1 release of the software.

Utilizing domain knowledge: Robust machine learning for building energy performance prediction with small, inconsistent datasets

Machine learning (ML) applications often require large datasets, a requirement that can pose a major challenge in fields where data is sparse or inconsistent. To address this issue, we propose a novel approach that combines prior knowledge with data-driven methods to significantly reduce data dependency. This study represents a disentangled system compositionality knowledge by the method of Component-Based Machine Learning (CBML) in the context of energy-efficient building engineering. In this way, CBML incorporates semantic domain knowledge within the structure of a data-driven model. To understand the advantage of CBML, we conducted a case experiment to assess the effectiveness of this knowledge-encoded ML approach in scenarios with sparse data input (1 % - 0.0125 % sampling rate) and several typical ML methods. Our findings reveal three key advantages of this approach over traditional ML methods: 1) It significantly improves the robustness of ML models when dealing with extremely small and inconsistent datasets; 2) It allows for efficient utilization of data from diverse record collections; 3) It can handle incomplete data while maintaining high interpretability and reducing training time. These features offer a promising solution to the challenges associated with deploying data-intensive methods and contribute to more efficient real-world data usage. Additionally, we outline four essential prerequisites to ensure the successful integration of prior knowledge and ML generalization in target scenarios and open-sourced the code and dataset for community reproduction.

Direct prediction for oceanic mesoscale eddy geospatial distribution through prior statistical deep learning

Mesoscale Eddy (ME) is a widely recognized and significant oceanic phenomenon characterized by extensive energy exchange. Accurate predictions of the future geospatial distribution of ME are crucial for maritime activities. Deep learning (DL) methods for ME prediction have consistently outperformed classical mathematical models and numerical modeling approaches. However, current DL methods based on two-dimensional gridded data suffer from error accumulation issues due to their indirect prediction approach, which involves first predicting the future environmental field and then identifying the ME patterns within it. Additionally, these models ignore the potential influence of prior knowledge related to ME on prediction outcomes. To address these issues, this paper proposes a direct prediction DL network called ES-ConvGRU, which incorporates historical prior statistics. First, we conduct an analysis of ME data from the Northwest Pacific region, extracting prior statistical knowledge such as interannual variations and seasonal characteristics. Second, mining patterns for the spatiotemporal features of both ME sequence and sea surface environmental field sequence are established. Furthermore, a nonlinear approach for mapping prior statistical knowledge and a multi-step autoregressive prediction model are designed, facilitating the integration of prior knowledge with multidimensional spatiotemporal features for ME prediction. Finally, the performance and effectiveness of ES-ConvGRU are evaluated. It achieves an average pixel accuracy of 93.21%, a mean intersection over union of 81.48%, and a frequency-weighted intersection over union of 87.55% for the 7-day distribution prediction. The results show that ES-ConvGRU exhibits notable advantages compared to the existing indirect and direct prediction methods.

ProMvSD: Towards unsupervised knowledge graph anomaly detection via prior knowledge integration and multi-view semantic-driven estimation

Knowledge graphs (KGs) have found extensive applications within intelligent systems, such as information retrieval. Much of the research has predominantly focused on completing missing knowledge, with little consideration given to examining errors. Unfortunately, during customizing KGs, diverse unpredictable errors are virtually unavoidable to be introduced, and these anomalies significantly impact the performance of applications. Detecting erroneous knowledge presents a formidable challenge due to the costly acquisition of ground-truth labels. In this work, we develop an unsupervised anomaly detection framework named ProMvSD, aiming to adapt KGs of varying scales via serialization components. To overcome the insufficient contextual information provided by the topological structure, we introduce the large language model as a reasoner to extract prior knowledge from extensive pre-trained textual data, thereby enhancing the understanding of KGs. Anomalous triple may result in a larger semantic gap between the head and tail neighborhoods. To uncover latent anomalies effectively, we propose a multi-view semantic-driven model (MvSD) based on the assumptions of self-consistency and information stability. MvSD jointly estimates the suspiciousness of triples from three hyperviews: node-view semantic contradiction, triple-view semantic gap, and pathway-view semantic gap. Extensive experiments on three English benchmark KGs and a Chinese medical KG demonstrate that, for the top 1% of the most suspicious triples, we can detect real anomalies with at most 99.9% accuracy. Furthermore, ProMvSD significantly outperforms state-of-the-art representation learning baselines, achieving a 29.2% improvement in detecting all anomalies.

Variable linear transformation improved physics-informed neural networks to solve thin-layer flow problems

Physics-informed neural networks (PINNs) have attracted wide attention due to their ability to seamlessly embed the learning process with physical laws and their considerable success in solving forward and inverse differential equation (DE) problems. While most studies are improving the learning process and network architecture of PINNs, less attention has been paid to the modification of the DE system, which may play an important role in addressing some limitations of PINNs. One of the simplest modifications that can be implemented to all DE systems is the variable linear transformation (VLT). Therefore, in this work, we propose the VLT-PINNs that solve the DE systems of the linear-transformed variables instead of the original ones. To clearly illustrate the importance of prior knowledge in determining the VLT parameters, we choose the thin-layer flow problems as our focus. Ten related cases were tested, including the jet flows, wake flows, mixing layers, boundary layers and Kovasznay flows. Based on the principle of normalization and for a better match of the DE system to the preference of NNs, we identify three principles for determining the VLT parameters: magnitude normalization for dependent variables (principle 1), local normalization for independent variables (principle 2), and appropriate scaling for physics-related parameters in inverse problems (principle 3). The VLT-PINNs with the VLT parameters suggested by the proposed principles show excellent performance over all the test cases, while the results are quite poor with the VLT parameters suggested by traditional linear transformations, such as nondimensionalization and global normalization. Comparison studies also show that only under the constraints of the VLT principles can we obtain satisfactory results. Besides, we find tanh is more appropriate as the activation function than sin for thin-layer flow problems, from both posteriori results and priori analyses with physical intuition. We highlight that our VLT method is an attempt to combine the three advantages of accuracy, universality and simplicity, and hope that it can provide new insights into the better integration of prior knowledge, physical intuition and the nature of NNs. The code for this paper is available on https://github.com/CAME-THU/VLT-PINN.

6D Pose Estimation on Point Cloud Data through Prior Knowledge Integration: A Case Study in Autonomous Disassembly

The accurate estimation of 6D pose remains a challenging task within the computer vision domain, even when utilizing 3D point cloud data. Conversely, in the manufacturing domain, instances arise where leveraging prior knowledge can yield advancements in this endeavor. This study focuses on the disassembly of starter motors to augment the engineering of product life cycles. A pivotal objective in this context involves the identification and 6D pose estimation of bolts affixed to the motors, facilitating automated disassembly within the manufacturing workflow. Complicating matters, the presence of occlusions and the limitations of single-view data acquisition, notably when motors are placed in a clamping system, obscure certain portions and render some bolts imperceptible. Consequently, the development of a comprehensive pipeline capable of acquiring complete bolt information is imperative to avoid oversight in bolt detection. In this paper, employing the task of bolt detection within the scope of our project as a pertinent use case, we introduce a meticulously devised pipeline. This multi-stage pipeline effectively captures the 6D information with regard to all bolts on the motor, thereby showcasing the effective utilization of prior knowledge in handling this challenging task. The proposed methodology not only contributes to the field of 6D pose estimation but also underscores the viability of integrating domain-specific insights to tackle complex problems in manufacturing and automation.

Mechanisms for handling uncertainty in sensorimotor control in sports: a scoping review

ABSTRACT In complex naturalistic sensorimotor behaviour, uncertainty arises from ambiguities and delays in sensory inputs as well as noise in sensory detection and motor execution. In sports, where human capacity reaches its limits, handling uncertainty is crucial. In fundamental motor-control research, five mechanisms for handling uncertainty – multisensory integration, prior-knowledge integration, risk optimisation, redundancy exploitation, and impedance control – have been proposed based on a rich body of evidence, mostly investigating simple arm and hand movement tasks. Here we review the literature investigating more complex tasks and examine to what extent these mechanisms explain handling uncertainty in sensorimotor control in sports. A systematic search following the PRISMA guidelines resulted in the consideration of 82 studies. These studies provide robust empirical evidence for the mechanisms of multisensory integration, prior-knowledge integration, and redundancy exploitation in complex naturalistic behaviour, whilst only a few publications focused on the other two mechanisms. Furthermore, only a few studies test model-based predictions that can be derived from the theoretical frameworks to a satisfactory extent. Finally, beyond discussing these explanatory mechanisms in isolation, we propose a unifying model that builds upon the theory of optimal feedback control, in which the mechanisms can be related to each other coherently.

Modular response analysis reformulated as a multilinear regression problem.

Modular response analysis (MRA) is a well-established method to infer biological networks from perturbation data. Classically, MRA requires the solution of a linear system, and results are sensitive to noise in the data and perturbation intensities. Due to noise propagation, applications to networks of 10 nodes or more are difficult. We propose a new formulation of MRA as a multilinear regression problem. This enables to integrate all the replicates and potential additional perturbations in a larger, over-determined, and more stable system of equations. More relevant confidence intervals on network parameters can be obtained, and we show competitive performance for networks of size up to 1000. Prior knowledge integration in the form of known null edges further improves these results. The R code used to obtain the presented results is available from GitHub: https://github.com/J-P-Borg/BioInformatics.

Application of orthogonal sparse joint non-negative matrix factorization based on connectivity in Alzheimer's disease research.

Based on the mining of micro- and macro-relationships of genetic variation and brain imaging data, imaging genetics has been widely applied in the early diagnosis of Alzheimer's disease (AD). However, effective integration of prior knowledge remains a barrier to determining the biological mechanism of AD. This paper proposes a new connectivity-based orthogonal sparse joint non-negative matrix factorization (OSJNMF-C) method based on integrating the structural magnetic resonance image, single nucleotide polymorphism and gene expression data of AD patients; the correlation information, sparseness, orthogonal constraint and brain connectivity information between the brain image data and genetic data are designed as constraints in the proposed algorithm, which efficiently improved the accuracy and convergence through multiple iterative experiments. Compared with the competitive algorithm, OSJNMF-C has significantly smaller related errors and objective function values than the competitive algorithm, showing its good anti-noise performance. From the biological point of view, we have identified some biomarkers and statistically significant relationship pairs of AD/mild cognitive impairment (MCI), such as rs75277622 and BCL7A, which may affect the function and structure of multiple brain regions. These findings will promote the prediction of AD/MCI.

The Importance of Semantic Network Brain Regions in Integrating Prior Knowledge with an Ongoing Dialogue.

To understand a dialogue, we need to know the topics that are being discussed. This enables us to integrate our knowledge of what was said previously to interpret the current dialogue. This study involved a large-scale behavioral experiment conducted online and a separate fMRI experiment, both testing human participants. In both, we selectively manipulated knowledge about the narrative content of dialogues presented in short videos. The clips were scenes from situation comedies that were split into two parts. The speech in the part 1 clips could either be presented normally or spectrally rotated to render it unintelligible. The part 2 clips that concluded the scenes were always presented normally. The behavioral experiment showed that knowledge of the preceding narrative boosted memory for the part 2 clips as well as increased the intersubject semantic similarity of recalled descriptions of the dialogues. The fMRI experiment replicated the finding that prior knowledge improved memory for the conclusions of the dialogues. Furthermore, prior knowledge strengthened temporal intersubject correlations in brain regions including the left angular gyrus and inferior frontal gyrus. Together, these findings show that (1) prior knowledge constrains the interpretation of a dialogue to be more similar across individuals; and (2), consistent with this, the activation of brain regions involved in semantic control processing is also more similar between individuals who share the same prior knowledge. Processing in these regions likely supports the activation and integration of prior knowledge, which helps people to better understand and remember dialogues as they unfold.

Capability as a concept in advanced practice nursing and education: a scoping review protocol.

The objective of this scoping review is to identify and map how the concept of capability in advanced practice nursing and education is described in the literature. Advanced practice nursing and education is often described in terms of the achievement of competencies. The concept of capability has been proposed as a more accurate description of the attributes of advanced practice nursing. Definitions of capability in advanced practice nursing vary, but often focus on the integration of prior knowledge, skills, resources, judgment, and experience when solving unanticipated problems or working in new situations. This review will consider studies addressing the concept of individual capability in any setting related to advanced practice nursing education and practice. The working definition of capability in this review is a combination of knowledge, skills, experience, and competencies that enables advanced practice nurses to provide appropriate care for patients in both familiar and unfamiliar clinical settings. Advanced practice nurses will include nurses with both graduate education and an expanded scope of practice. Eight academic databases will be searched for qualitative, quantitative, and mixed methods study designs. The gray literature search will include policy and practice documents from nursing and health organization websites. Two reviewers will independently complete title and abstract screening prior to full-text review and data extraction. Articles published in English from 1975 to the present will be included. Other languages will be included if translations are available.

The Combination of Internet of Things Technology Based on Probability Model Network and Mass Education

With the continuous development of the Internet of things, educational informatization has become a hot spot in the application of education. Internet of things technology, combined with various subject fields of education, can better achieve subject teaching objectives and teaching assistance. In the multimode teaching optimization model, weight distribution is a complex multiobjective decision-making problem. In this paper, a Bayesian network based on probability model is proposed, which is combined with the large entropy criterion to determine the comprehensive weight. The combination of Bayesian network and Bayesian statistics can make full use of the information of domain knowledge and sample data. Bayesian network uses arc to represent the dependence between variables and probability distribution table to represent the strength of dependence. It organically combines prior information with sample knowledge to promote the integration of prior knowledge and data, which is particularly effective when sample data is sparse or difficult to obtain. Bayesian network is used to associate objective attributes and influencing factors to self-study the target weight. By grasping the characteristics of information technology and the nature of university citizenship curriculum, this paper further analyzes the internal relationship between them, promotes the deep integration of the two, and improves the effectiveness of university citizenship curriculum teaching. By grasping the characteristics of information technology and the nature of the school civics curriculum, we promote a deeper integration of the two. It is my education that is more advanced.

Network Approaches for Precision Oncology.

The growth of multi-omic tumour profile datasets along with knowledge of genome regulatory networks has created an unprecedented opportunity to advance precision oncology. Achieving this goal requires computational methods that can make sense of and combine heterogeneous data sources. Interpretability and integration of prior knowledge is of particular relevance for genomic models to minimize ungeneralizable models, promote rational treatment design, and make use of sparse genetic mutation data. While networks have long been used to capture genomic interactions at the levels of genes, proteins, and pathways, the use of networks in precision oncology is relatively new. In this chapter, I provide an introduction to network-based approaches used to integrate multi-modal data sources for patient stratification and patient classification. There is a particular emphasis on methods using patient similarity networks (PSNs) as part of the design. I separately discuss strategies for inferring driver mutations from individual patient mutation data. Finally, I discuss challenges and opportunities the field will need to overcome to achieve its full potential, with an outlook towards a clinic of the future.

Simplified and Hybrid Remote Sensing-Based Delineation of Management Zones for Nitrogen Variable Rate Application in Wheat

Enhancing digital and precision agriculture is currently inevitable to overcome the economic and environmental challenges of the agriculture in the 21st century. The purpose of this study was to generate and compare management zones (MZ) based on the Sentinel-2 satellite data for variable rate application of mineral nitrogen in wheat production, calculated using different remote sensing (RS)-based models under varied soil, yield and crop data availability. Three models were applied, including (1) a modified “RS- and threshold-based clustering”, (2) a “hybrid-based, unsupervised clustering”, in which data from different sources were combined for MZ delineation, and (3) a “RS-based, unsupervised clustering”. Various data processing methods including machine learning were used in the model development. Statistical tests such as the Paired Sample T-test, Kruskal–Wallis H-test and Wilcoxon signed-rank test were applied to evaluate the final delineated MZ maps. Additionally, a procedure for improving models based on information about phenological phases and the occurrence of agricultural drought was implemented. The results showed that information on agronomy and climate enables improving and optimizing MZ delineation. The integration of prior knowledge on new climate conditions (drought) in image selection was tested for effective use of the models. Lack of this information led to the infeasibility of obtaining optimal results. Models that solely rely on remote sensing information are comparatively less expensive than hybrid models. Additionally, remote sensing-based models enable delineating MZ for fertilizer recommendations that are temporally closer to fertilization times.

Technological Diversification to Green Domains: Technological Relatedness, Invention Impact and Knowledge Integration Capabilities

Climate changes and ecological challenges often motivate firms to diversify into environmental domains. However, this does not guarantee impactful inventions. Therefore, this study investigates how firms can create impactful environmental inventions based on their technological relatedness and prior knowledge integration capabilities. Using a unique dataset of 1,990 high-tech Chinese firms between 2006 and 2016, our results reveal that diversifying firms’ green technological relatedness has an inverted U-shaped relationship with invention impact. While the depth of firms’ knowledge integration capabilities steepens this relationship, the breadth flattens it. Higher levels of depth capability result in a greater impact, while greater breadth leads to an early attainment of peak invention impact at a lower degree of green technological relatedness. Theoretical and policy implications are discussed.

No increased circular inference in adults with high levels of autistic traits or autism.

Autism spectrum disorders have been proposed to arise from impairments in the probabilistic integration of prior knowledge with sensory inputs. Circular inference is one such possible impairment, in which excitation-to-inhibition imbalances in the cerebral cortex cause the reverberation and amplification of prior beliefs and sensory information. Recent empirical work has associated circular inference with the clinical dimensions of schizophrenia. Inhibition impairments have also been observed in autism, suggesting that signal reverberation might be present in that condition as well. In this study, we collected data from 21 participants with self-reported diagnoses of autism spectrum disorders and 155 participants with a broad range of autistic traits in an online probabilistic decision-making task (the fisher task). We used previously established Bayesian models to investigate possible associations between autistic traits or autism and circular inference. There was no correlation between prior or likelihood reverberation and autistic traits across the whole sample. Similarly, no differences in any of the circular inference model parameters were found between autistic participants and those with no diagnosis. Furthermore, participants incorporated information from both priors and likelihoods in their decisions, with no relationship between their weights and psychiatric traits, contrary to what common theories for both autism and schizophrenia would suggest. These findings suggest that there is no increased signal reverberation in autism, despite the known presence of excitation-to-inhibition imbalances. They can be used to further contrast and refine the Bayesian theories of schizophrenia and autism, revealing a divergence in the computational mechanisms underlying the two conditions.

Identifying homogeneous subgroups of patients and important features: a topological machine learning approach

BackgroundThis paper exploits recent developments in topological data analysis to present a pipeline for clustering based on Mapper, an algorithm that reduces complex data into a one-dimensional graph.ResultsWe present a pipeline to identify and summarise clusters based on statistically significant topological features from a point cloud using Mapper.ConclusionsKey strengths of this pipeline include the integration of prior knowledge to inform the clustering process and the selection of optimal clusters; the use of the bootstrap to restrict the search to robust topological features; the use of machine learning to inspect clusters; and the ability to incorporate mixed data types. Our pipeline can be downloaded under the GNU GPLv3 license at https://github.com/kcl-bhi/mapper-pipeline.

Big data does not equal big knowledge. A need for causal insights

BACKGROUND AND AIM: There is hope that the bigger the data, the bigger the knowledge will become. Very large data are or will be made available and shall bring robust and replicable effect estimates in exposome research. While larger data and complementary sources of data will, with little doubt, bring robust effect sizes to estimate how environmental, toxic, social, and biological exposures are associated with health outcomes. We may also expect that larger (and precise) data will allow us to go beyond common effects (as an analogy to common genetic variants) and detect rare or small effects. Moving on into the paradigm of big data, it may be wise to remind each other that correlation is not proof of causality. METHODS: Although bigger (observational) data will bring confidence on the strength of some association, relationships in large data are similarly affected by important selection and structural biases, confounding effects, and measurement errors. One strength of the European Human Exposome Network is to bring multiple study designs and dynamic longitudinal analytical strategies to help to triangulate the evidence. RESULTS:We shall, for example, use negative control, quasi-experimental designs, interventions, and instrumental variables (e.g. Mendelian randomization or instrument based on exogenous factors, i.e. environmental policies) to infer causation and identify causative pathways. CONCLUSIONS:These causal designs and approaches however are not always applicable or available. One should also seek for additional ways to gain confidence on the plausibility of causal insights through replication, triangulation, and integration of prior knowledge which is made available in the European Human Exposome Network. KEYWORDS: European Human Exposome Network, Big data, big knowledge, causal insights

High-level prior-based loss functions for medical image segmentation: A survey

Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions.

Single-cell classification using graph convolutional networks

BackgroundAnalyzing single-cell RNA sequencing (scRNAseq) data plays an important role in understanding the intrinsic and extrinsic cellular processes in biological and biomedical research. One significant effort in this area is the identification of cell types. With the availability of a huge amount of single cell sequencing data and discovering more and more cell types, classifying cells into known cell types has become a priority nowadays. Several methods have been introduced to classify cells utilizing gene expression data. However, incorporating biological gene interaction networks has been proved valuable in cell classification procedures.ResultsIn this study, we propose a multimodal end-to-end deep learning model, named sigGCN, for cell classification that combines a graph convolutional network (GCN) and a neural network to exploit gene interaction networks. We used standard classification metrics to evaluate the performance of the proposed method on the within-dataset classification and the cross-dataset classification. We compared the performance of the proposed method with those of the existing cell classification tools and traditional machine learning classification methods.ConclusionsResults indicate that the proposed method outperforms other commonly used methods in terms of classification accuracy and F1 scores. This study shows that the integration of prior knowledge about gene interactions with gene expressions using GCN methodologies can extract effective features improving the performance of cell classification.