Confidence Measure Research Articles

Spatial uncertainty in herbarium data: simulated displacement but not error distance alters estimates of phenological sensitivity to climate in a widespread California wildflower

Herbarium records provide a broad spatial and temporal range with which to investigate plant responses to environmental change. Research on plant phenology and its sensitivity to climate has advanced with the increasing availability of digitized herbarium specimens, but limitations of specimen‐derived data can undermine the inferences derived from such research. One issue that has received little attention is collection site uncertainty (i.e. error distance), a measure of confidence in the location from which a specimen was collected. We conducted comparative analyses of phenoclimatic models to determine whether spatial deviations of 2, 5, 15 or 25 km between recorded and simulated collection sites, as well as the error distance reported in digitized records, affect estimates of the phenological sensitivity of flowering time to annual temperature and precipitation in a widespread annual California wildflower. In this approach, we considered both spatial and interannual variation in climatic conditions. Simulated site displacements led to increasingly weak estimates of phenological sensitivity to temperature and precipitation anomalies with increasing distances. However, we found no significant effect of reported error distance magnitude on estimates of phenological sensitivity to climate normals or anomalies. These findings suggest that the spatial uncertainty of collection sites among specimens of widely collected plant species may not adversely affect estimates of phenological sensitivity to climate, even though real discrepancies and georeferencing inaccuracy can negatively impact such estimates. Collection site uncertainty merits further attention as a potential source of noise in herbarium data, especially for research on how plant traits respond to spatial and interannual climatic variation.

Evidence for subdominant multipole moments and precession in merging black-hole-binaries from GWTC-2.1

The LIGO--Virgo--KAGRA collaborations (LVK) produced a catalogue containing gravitational-wave (GW) observations from the first half of the third GW observing run (O3a). This catalogue, GWTC-2.1, includes for the first time a number of \emph{exceptional} GW candidates produced from merging black-hole-binaries with unequivocally unequal component masses. Since subdominant multipole moments and spin-induced orbital precession are more likely to leave measurable imprints on the emitted GW from unequal component mass binaries, these general relativistic phenomena may now be measurable. Indeed, both GW190412 and GW190814 have already shown conclusive evidence for subdominant multipole moments. This provides valuable insights into the dynamics of the binary. We calculate the evidence for subdominant multipole moments and spin-induced orbital precession for all merging black-hole-binaries in GWTC-2.1 that were observed during O3a and show that (a) no gravitational-wave candidate has measurable higher order multipole content beyond $\ell = 3$, (b) in addition to the confident subdominant multipole measurements in GW190412 and GW190814, GW190519\_153544 and GW190929\_012149 show marginal evidence for the $(\ell, |m|) = (3, 3)$ subdominant multipole, (c) GW190521 may have measurable subdominant multipole content and (d) GW190412 may show evidence for spin-induced orbital precession.

Care of the dying – medical student confidence and preparedness: mixed-methods simulation study

ObjectivesOf all doctors, Foundation Year 1 trainees spend the most time caring for dying patients yet report poor preparation and low confidence in providing this care. Despite documented effectiveness of...

Development, implementation, and evaluation of a trauma-informed simulation-based training program for graduate nurses: A single arm feasibility and pilot study

BackgroundThe chance of hospital staff encountering a patient with a trauma history is high. The way health services are offered and carried out are important when engaging with people who have experienced trauma. Implementing training in trauma-informed care (TIC) is part of a cultural change of benefit to both patients and staff. Simulation-based training is a well-accepted method to reduce staff fear and anxiety when working with individuals in distress and to address issues relating to bias and stigma. ObjectivesTo provide simulation-based TIC training to graduate nurses. DesignA three-phase process was undertaken to i) create the intervention, ii) determine feasibility, and iii) evaluate the developed training. SettingA 600-bed inner-city tertiary hospital in Melbourne, Victoria. ParticipantsGraduate nurses undertaking their first year of employment (n = 23). MethodsThe content of the training was created using evidence derived from a literature review, a scoping study of available resources, and expert consensus. A pre/post-test within-groups design to assess the safety, acceptability, and effectiveness of the training was undertaken. ResultsThe Trauma Informed–Simulation Based Training (TI-SBT) aims to increase TIC knowledge and promote TIC behaviours. It is delivered face-to-face over one day and encompasses an education component followed by three immersive patient simulations using professional actors. Analysis found significant improvement in TIC knowledge (p ≤ 0.001, 95% CI = −3.53, −0.47) and behaviours (p = 0.013, 95% CI = −8.88, −5.03). No significant differences were found in measures of anxiety and confidence. Satisfaction with all aspects of the training was high. Qualitatively, participants provided concrete examples of changes to their practice to facilitate TIC. ConclusionsThe developed and novel TI-SBT is a feasible (safe, acceptable, and effective) way of introducing TIC to graduate nurses. These findings provide strong evidence to support a more rigorous evaluation of the training by randomised controlled trial. The TI-SBT has the capacity to not only improve patient care but the experience of hospital staff.

Robust Assessment of EEG Connectivity Patterns in Mild Cognitive Impairment and Alzheimer's Disease.

The prevalence of dementia, including Alzheimer's disease (AD), is on the rise globally with screening and intervention of particular importance and benefit to those with limited access to healthcare. Electroencephalogram (EEG) is an inexpensive, scalable, and portable brain imaging technology that could deliver AD screening to those without local tertiary healthcare infrastructure. We study EEG recordings of subjects with sporadic mild cognitive impairment (MCI) and prodromal familial, early-onset, AD for the same working memory tasks using high- and low-density EEG, respectively. A challenge in detecting electrophysiological changes from EEG recordings is that noise and volume conduction effects are common and disruptive. It is known that the imaginary part of coherency (iCOH) can generate functional connectivity networks that mitigate against volume conduction, while also erasing true instantaneous activity (zero or π-phase). We aim to expose topological differences in these iCOH connectivity networks using a global network measure, eigenvector alignment (EA), shown to be robust to network alterations that emulate the erasure of connectivities by iCOH. Alignments assessed by EA capture the relationship between a pair of EEG channels from the similarity of their connectivity patterns. Significant alignments-from comparison with random null models-are seen to be consistent across frequency ranges (delta, theta, alpha, and beta) for the working memory tasks, where consistency of iCOH connectivities is also noted. For high-density EEG recordings, stark differences in the control and sporadic MCI results are observed with the control group demonstrating far more consistent alignments. Differences between the control and pre-dementia groupings are detected for significant correlation and iCOH connectivities, but only EA suggests a notable difference in network topology when comparing between subjects with sporadic MCI and prodromal familial AD. The consistency of alignments, across frequency ranges, provides a measure of confidence in EA's detection of topological structure, an important aspect that marks this approach as a promising direction for developing a reliable test for early onset AD.

Image-Level Uncertainty in Pseudo-Label Selection for Semi-Supervised Segmentation.

Advancements in deep learning techniques have proved useful in biomedical image segmentation. However, the large amount of unlabeled data inherent in biomedical imagery, particularly in digital pathology, creates a semi-supervised learning paradigm. Specifically, because of the time consuming nature of producing pixel-wise annotations and the high cost of having a pathologist dedicate time to labeling, there is a large amount of unlabeled data that we wish to utilize in training segmentation algorithms. Pseudo-labeling is one method to leverage the unlabeled data to increase overall model performance. We adapt a method used for image classification pseudo-labeling to select images for segmentation pseudo-labeling and apply it to 3 digital pathology datasets. To select images for pseudo-labeling, we create and explore different thresholds for confidence and uncertainty on an image level basis. Furthermore, we study the relationship between image-level uncertainty and confidence with model performance. We find that the certainty metrics do not consistently correlate with performance intuitively, and abnormal correlations serve as an indicator of a model's ability to produce pseudo-labels that are useful in training. Clinical relevance - The proposed approach adapts image-level confidence and uncertainty measures for segmentation pseudo-labeling on digital pathology datasets. Increased model performance enables better disease quantification for histopathology.

WisRule: First cognitive algorithm of wise association rule mining

This article proposes a new algorithm for a newly emerging domain wisdom mining that claims to extract wisdom from data. Association rule mining is one of the dominant data mining techniques based on which a new algorithm called WisRule is proposed that generates both positive and negative association rules. These rules can be used for decision-making with less influence from a specialist. The existing algorithms of association rule extraction are based on the frequency of an itemset, which was introduced into the Apriori algorithm for the first time. In these algorithms, those itemsets are converted to the rules of the form Antecedent ⇒ Consequent that qualify the threshold of support, confidence and similar other measures. WisRule is proposed as an extension to the CBPNARM algorithm. WisRule produces both positive and negative association rules based on their frequency evaluated in a certain context (C), utility (U), time (T) and location (L). Rules that are valid in a given context, have high utility and are valid across multiple time intervals and locations become part of the final ruleset. The evaluation of a rule in these four dimensions is claimed as mining wisdom from the given data that is currently used as a hypothetical basis for a domain expert’s decision. WisRule is compared with the Apriori, PNARM and CBPNARM algorithms in terms of precision, recall, number of rules, average confidence, F-measure and execution time.

Self-assessment: With all its limitations, why are we still measuring and teaching it? Lessons from a scoping review

Introduction Self-Assessment (SA) is often assumed to be essential for learning, however, this assumption has been extensively rebutted. Research shows SA has significant limitations, including its lack of correlation with competence. Method We undertook a scoping review of SA in medical education (2011–2021) and surprisingly discovered substantial research where SA was erroneously assumed to be a valid measure of successful learning, or a skill needing to be taught. Although the initial intent of our scoping review was to explore where SA is being effectively used to advance lifelong learning, we paused to explore the extent of the problem of its misuse and resulting in wasted research, by examining excluded studies. Results From 1151 articles, we identified 207 which ignored the documented limitations of SA. Thirty-nine studies explored SA of learning. This research has limited utility: increasing the accuracy of SA does not improve performance or lifelong learning. One hundred and sixty-eight used SA as an outcome measure to assess a program or intervention, including 63 where self-assessed improvement in knowledge/skills was the sole measure. SA of self-confidence was measured in 62 studies. When confidence was compared with an objective measure of performance, both invariably increased, but confidence did not always align with competence when measured. Discussion Many researchers mistakenly assume the ability to accurately self-assess is essential for learning, so focus on teaching self-calibration rather than evidence-based methods of advancing learning. Other researchers incorrectly suppose that self-reported improvements in knowledge/skills provide evidence of the efficacy of a program/intervention. This is particularly troubling with regards to novices, who may believe that because they self-assess to have improved/gained confidence, they are now competent. Conclusion Our findings highlight the significant volume of research being done where SA is misunderstood and/or misused as a measurement. We posit reasons that such research continues to take place and suggest solutions moving forward.

Quantitative predictions from chemical read-across and their confidence measures

In silico modeling new approach methodologies (NAMs) are viewed as a promising starting point for filling the existing gaps in safety and ecosafety data. Read-across is one of the most widely used alternative tools for hazard assessment, aimed at filling data gaps. However, there are no systematic studies or recommendations on the measures to identify the quality of read-across predictions for the data points without any experimental response data. Recently, we have reported a new similarity-based read-across algorithm for the prediction of toxicity (biological activity in general) of untested compounds from structural analogues (the tool available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home). Three similarity estimation techniques such as, Euclidean distance-based similarity, Gaussian kernel function similarity, and Laplacian kernel function similarity are used in this algorithm. As the confidence of predictions for untested compounds is important information, we have addressed this issue here by consideration of several similarity and error – based criteria. The role of these measures in discriminating high and low residual query compounds is studied in three different approaches: (a) comparison of means of a measure for high and low residual groups; (b) development of classification models for absolute residuals to identify the contributing measures; (c) application of the sum of ranking differences (SRD) approach to identify the measures closer to the reference rank defined by the absolute residuals. Finally, the frequency of occurrences of different measures in the three approaches is compared. The results from three data sets with 10 divisions of source and target compounds in each case indicate that weighted standard deviation of the predicted response values appear to be the most deterministic feature for the reliability of predictions followed by different similarity-based features. The derived reliability measures will provide a greater confidence to the quality of quantitative predictions from the chemical read-across tool for new query compounds.

Estimation of household characteristics with uncertainties from smart meter data

The knowledge of household characteristics can help energy providers carry out more personalized demand-side management programs. Obtaining such information through surveys is costly and time-consuming in practice. This paper proposes a novel estimation method for household characteristics with uncertainties using the residential electricity consumption data. To alleviate the class imbalance problem in the dataset, a dynamic time warping sampling (DTWS) method is proposed to generate synthetic data for the minority class. To overcome the problem that the existing methods for identifying household characteristics cannot provide the confidence level of the results, a Bayesian convolutional neural network (BCNN) model is developed for feature extraction and characteristic identification with uncertainties. These quantified uncertainties can be regarded as a measure of confidence and can be used to target customers more effectively for energy efficiency and demand response programs. The effectiveness of the proposed model is validated by experiments on ground truth data.

Unifying Knowledge Base Completion with PU Learning to Mitigate the Observation Bias

Methods for Knowledge Base Completion (KBC) reason about a knowledge base (KB) in order to derive new facts that should be included in the KB. This is challenging for two reasons. First, KBs only contain positive examples. This complicates model evaluation which needs both positive and negative examples. Second, those facts that were selected to be included in the knowledge base, are most likely not an i.i.d. sample of the true facts, due to the way knowledge bases are constructed. In this paper, we focus on rule-based approaches, which traditionally address the first challenge by making assumptions that enable identifying negative examples, which in turn makes it possible to compute a rule's confidence or precision. However, they largely ignore the second challenge, which means that their estimates of a rule's confidence can be biased. This paper approaches rule-based KBC through the lens of PU-learning, which can cope with both challenges. We make three contributions.: (1) We provide a unifying view that formalizes the relationship between multiple existing confidences measures based on (i) what assumption they make about and (ii) how their accuracy depends on the selection mechanism. (2) We introduce two new confidence measures that can mitigate known biases by using propensity scores that quantify how likely a fact is to be included the KB. (3) We show through theoretical and empirical analysis that taking the bias into account improves the confidence estimates, even when the propensity scores are not known exactly.

The threshold of an intra oral scanner to measure lesion depth on natural unpolished teeth

ObjectivesTo investigate the threshold and accuracy of intraoral scanning in measuring freeform human enamel surfaces. MethodsSoftware softgauges, ranging between 20 and 160 µm depth, were used to compare four workflow analysis techniques to measure step height on a freeform surface; with or without reference areas and in combination with surface-subtraction to establish which combination produced the most accurate outcome. Having established the optimum combination, 1.5 mm diameter, individual depths ranging from 11 to 81 µm were created separately on 14 unpolished human enamel samples and then scanned with gold standard laboratory optical profilometry (NCLP, TaiCaan Technologies™, XYRIS2000CL, UK) and a clinical intraoral scanner (TrueDefinition™, Midmark Corp., USA). The sequence of surface registration and subtraction determined from the softgauges was used to measure step height on natural human enamel surfaces. Step heights (μm) were compared using two-way ANOVA with post-hoc Bonferroni (p < 0.05) and Bland-Altman analyses. ResultsSoftware differences were significantly reduced from − 29.7 to − 32.5% without, to − 2.4 to − 3.6% with reference areas (p < 0.0001) and the addition of surface-subtraction after registration reduced this further to 0.0 to − 0.3% (p < 0.0001). The intraoral scanner had a depth discrimination threshold of 73 µm on unpolished natural enamel and significant differences (p < 0.05) were observed compared to NCLP below this level. SignificanceThe workflow of combining surface-registration and subtraction of surface profiles taken from intraoral scans of freeform unpolished enamel enabled confident measurement of step height above 73 µm. The limits of the scanner is related to data capture and these results provide opportunities for clinical measurement.

Measuring Palliative Care-Related Knowledge, Attitudes, and Confidence in Home Health Care Clinicians, Patients, and Caregivers: A Systematic Review.

Background: Integrating palliative care services in the home health care (HHC) setting is an important strategy to provide care for seriously ill adults and improve symptom burden, quality of life, and caregiver burden. Routine palliative care in HHC is only possible if clinicians who provide this care are prepared and patients and caregivers are well equipped with the knowledge to receive this care. A key first step in integrating palliative care services within HHC is to measure preparedness of clinicians and readiness of patients and caregivers to receive it. Objective: The objective of this systematic review was to review existing literature related to the measurement of palliative care-related knowledge, attitudes, and confidence among HHC clinicians, patients, and caregivers. Methods: We searched PubMed, CINAHL, Web of Science, and Cochrane for relevant articles between 2000 and 2021. Articles were included in the final analysis if they (1) reported specifically on palliative care knowledge, attitudes, or confidence, (2) presented measurement tools, instruments, scales, or questionnaires, (3) were conducted in the HHC setting, (4) and included HHC clinicians, patients, or caregivers. Results: Seventeen articles were included. While knowledge, attitudes, and confidence have been studied in HHC clinicians, patients, and caregivers, results varied significantly across countries and health care systems. No study captured knowledge, attitudes, and confidence of the full HHC workforce; notably, home health aides were not included in the studies. Conclusion: Existing instruments did not comprehensively contain elements of the eight domains of palliative care outlined by the National Consensus Project (NCP) for Quality Palliative Care. A comprehensive psychometrically tested instrument to measure palliative care-related knowledge, attitudes, and confidence in the HHC setting is needed.

Learning from crowds with sparse and imbalanced annotations

Traditional supervised learning requires ground truth labels for training, whose collection however is difficult in many cases. Recently, crowdsourcing has established itself as an efficient labeling solution by resorting to non-expert crowds. To reduce the labeling error effects, one common practice is to distribute each instance to multiple workers, whereas each worker only annotates a subset of data, resulting in the sparse annotation phenomenon. In this paper, we show that when meeting with class-imbalance, i.e., even when the groundtruth labels are slightly imbalanced, the sparse annotations are prone to be skewly distributed and would bias the learning algorithm severely. To combat this issue, we propose one Distribution Aware Self-training based Crowdsourcing learning (DASC) approach, which supplements the sparse annotations by adding confident pseudo-annotations and at the same time re-balancing the annotation distribution. Specifically, we propose one distribution aware confidence measure to select the most confident pseudo-annotations, with minority/majority classes selected more/less frequently. As a universal framework, DASC is applicable to various crowdsourcing methods for consistent performance gains. We conduct extensive experiments over real-world crowdsourcing benchmarks, from slight to heavy imbalance ratio, with various annotation sparsity levels, and show that DASC substantially improves previous crowdsourcing models by \(2\%\)-\(20\%\) absolute test accuracy, and yields much more balanced annotations.

Robust sparse Bayesian learning for broad learning with application to high-speed railway track monitoring

In this study, we focus on non-parametric probabilistic modeling for general regression analysis with large amounts of data and present an algorithm called the robust sparse Bayesian broad learning system. Robust sparse Bayesian learning is employed to infer the posterior distribution of the sparse connecting weight parameters in broad learning system. Regardless of the number of candidate features, our algorithm can always produce a compact subset of hidden-layer neurons of almost the same size learned from the data, which allows the algorithm to automatically adjust the model complexity of the network. This algorithm not only solves the regression problem of large amounts of data robustly but also possesses high computational efficiency and low requirements for computing hardware. Moreover, as a Bayesian probabilistic algorithm, it can provide the posterior uncertainty quantification of the predicted output, giving a measure of prediction confidence. The proposed algorithm is verified using simulated data generated by a benchmark function and also applied in non-parametric probabilistic modeling using high-speed railway track monitoring data. The results show that compared with several existing neural network algorithms, our proposed algorithm has strong model robustness, excellent prediction accuracy, and computational efficiency for regression analysis with large amounts of data, and has the potential to be widely used in general regression problems in science and engineering.

Complex ontology alignment for autonomous systems via the Compact Co-Evolutionary Brain Storm Optimization algorithm

Autonomous Systems (ASs) that work in the open, dynamic environment are required to share their data entities and semantics to implement the co-operations. Typically, AS’s data schemas and semantics are described via ontology. Since ASs need to maintain their autonomy and conceptual specificity, their ontologies might define one concept with different terms or in different contexts, which yields the heterogeneity issue and hampers their co-operations. An effective solution is to establish a set of data entity’s correspondences through the Ontology Alignment (OA). Sine the simple correspondence of one-to-one style lacks expressiveness and cannot completely cover different types of heterogeneity, ASs’ co-operations require using the complex correspondence of one-to-many or many-to-may style. Inspired by the success of applying the Brain Storm Optimization algorithm (BSO) to solve diverse complex optimization problems, this work proposes a Compact Co-Evolutionary BSO (CCBSO) to face the challenge of aligning AS ontologies. In particular, the AS ontology aligning problem is formally defined, a hybrid confidence measure for distinguishing the simple and complex correspondences is proposed, and a problem-specific CCBSO is presented. The experiment tests CCBSO’s performance on different AS ontology aligning tasks, which consist of two simple ontology aligning tasks and one complex ontology aligning track. The experimental results show that CCBSO outperforms the state-of-the-art ontology aligning techniques on all simple and complex ontology aligning tasks.

Brain health correlates of mobility-related confidence.

Mobility is important for independence in older age. While brain health correlates of objectively measured mobility-related features like gait and balance have been reported, we aimed to test neuroimaging and cognitive correlates of subjective measures of mobility-related confidence. We carried out a cross-sectional observational study comprised of N=29 cognitively unimpaired older adult participants, mean age 75.8±5.8, 52% female, 24% non-white. We measured cognition, hippocampal volume, white matter hyperintensities, cerebral amyloid-β (Aβ), and gait and balance confidence. We tested associations using unadjusted Spearman correlations and correlations partialling out covariates of interest one at a time. Greater gait confidence was associated with better attention (unadjusted ρ=0.37, p=0.05; partially attenuated by adjustment for age, APOE4, anxiety, motivation, gait speed, or Aβ); executive performance (unadjusted ρ=0.35, p=0.06; partially attenuated by adjustment for age, APOE4, gait speed, or Aβ); and lower Aβ levels (unadjusted ρ=-0.40, p=0.04; partially attenuated by adjustment for age, depressive symptoms, motivation, or gait speed). Greater balance confidence was associated with better global cognition (unadjusted ρ=0.41, p=0.03; partially attenuated by adjustment for APOE4, gait speed, or Aβ); attention (unadjusted ρ=0.46, p=0.01; robust to adjustment); and lower Aβ levels (unadjusted ρ=-0.35, p=0.07; partially attenuated by adjustment for age, education, APOE4, depressive symptoms, anxiety, motivation, or gait speed). Self-reported mobility-related confidence is associated with neuroimaging and cognitive measures and would be easy for providers to use in clinical evaluations. These associations should be further evaluated in larger samples, and longitudinal studies can help determine temporality of declines.

Standardizing protocols for determining the cause of mortality in wildlife studies.

Mortality site investigations of telemetered wildlife are important for cause‐specific survival analyses and understanding underlying causes of observed population dynamics. Yet, eroding ecoliteracy and a lack of quality control in data collection can lead researchers to make incorrect conclusions, which may negatively impact management decisions for wildlife populations. We reviewed a random sample of 50 peer‐reviewed studies published between 2000 and 2019 on survival and cause‐specific mortality of ungulates monitored with telemetry devices. This concise review revealed extensive variation in reporting of field procedures, with many studies omitting critical information for the cause of mortality inference. Field protocols used to investigate mortality sites and ascertain the cause of mortality are often minimally described and frequently fail to address how investigators dealt with uncertainty. We outline a step‐by‐step procedure for mortality site investigations of telemetered ungulates, including evidence that should be documented in the field. Specifically, we highlight data that can be useful to differentiate predation from scavenging and more conclusively identify the predator species that killed the ungulate. We also outline how uncertainty in identifying the cause of mortality could be acknowledged and reported. We demonstrate the importance of rigorous protocols and prompt site investigations using data from our 5‐year study on survival and cause‐specific mortality of telemetered mule deer (Odocoileus hemionus) in northern California. Over the course of our study, we visited mortality sites of neonates (n = 91) and adults (n = 23) to ascertain the cause of mortality. Rapid site visitations significantly improved the successful identification of the cause of mortality and confidence levels for neonates. We discuss the need for rigorous and standardized protocols that include measures of confidence for mortality site investigations. We invite reviewers and journal editors to encourage authors to provide supportive information associated with the identification of causes of mortality, including uncertainty.

Comparison of Water Sensitive Paper and Glass Strip Sampling Approaches to Access Spray Deposit by UAV Sprayers

Target and off-target spray depositions determine the spray’s effectiveness and impact on the environment. A decisive stage in the measurement of spray deposition and drift is selecting an appropriate sampling approach under field conditions. There are various approaches available for sampling spray deposition and drift, during the evaluation of ground sprayers used for the UAV sprayer assessment, under field conditions. In this study, two sampling approaches (water-sensitive paper, and glass strip collectors) were compared to analyze spray deposition in target and off-target zones. The results showed a variation in the estimation of the spray deposits among the two applied sampling methods. The results showed that the water-sensitive paper recorded the droplet deposition in the target zone with a range from 0.049 to 4.866 µLcm−2, whereas the glass strip recorded from 0.11 to 0.793 µLcm−2. The results also showed the water sensitive paper recorded an 80.3% higher deposition than that of the glass strip at zero position during the driving flight height 2 m and flight speed 2 ms−1 (T1 treatment). It can be concluded that variation in recorded depositing is due to the sampling material. It is recommended that the confident deposition results, measurement methods and sampling approaches must be standardized for UAV sprayers according to the field conditions and controlled within artificial assessments.

An empirical study of scoring functions for learning Bayesian networks in model averaging

Scoring functions for Bayesian network (BN) structure learning can conflict in their rankings and previous work has empirically studied their effectiveness with an aim to provide recommendations on their use. However, previous studies on scoring functions are limited by the small number and scale of the instances used in the evaluation and by a focus on learning a single network. Often, a better alternative to committing to a single network is to learn multiple networks and perform model averaging as this method provides confidence measures for knowledge discovery and improved accuracy for density estimation. In this paper, we empirically study a selection of widely used and also recently proposed scoring functions. We address design limitations of previous empirical studies by scaling our experiments to larger BNs, comparing on an extensive set of both ground truth BNs and real-world datasets, considering alternative performance metrics, and comparing scoring functions on two model averaging frameworks: the bootstrap and the credible set. Contrary to previous recommendations based on finding a single structure, we find that for model averaging the BDeu scoring function is the preferred choice in most scenarios for the bootstrap framework and a recent score called quotient normalized maximum likelihood (qNML) is the preferred choice for the credible set framework.