dnabarcoder: an open-source software package for analyzing and predicting DNA sequence similarity cut-offs for fungal sequence identification

The accuracy and precision of fungal molecular identification and classification are challenging, particularly in environmental metabarcoding approaches as these often trade accuracy for efficiency given the large data volumes at hand. In most ecological studies, only a single similarity cut-off value is used for sequence identification. This is not sufficient since the most commonly used DNA markers are known to vary widely in terms of inter- and intra-specific variability. We address this problem by presenting a new tool, dnabarcoder, to analyze and predict different local similarity cut-offs for sequence identification for different clades of fungi. For each similarity cut-off in a clade, a confidence measure is computed to evaluate the resolving power of the genetic marker in that clade. Experimental results showed that when analyzing a recently released filamentous fungal ITS DNA barcode dataset of CBS strains from the Westerdijk Fungal Biodiversity Institute, the predicted local similarity cut-offs varied immensely between the clades of the dataset. In addition, most of them had a higher confidence measure than the global similarity cut-off predicted for the whole dataset. When classifying a large public fungal ITS dataset – the UNITE database - against the barcode dataset, the local similarity cut-offs assigned fewer sequences than the traditional cut-offs used in metabarcoding studies. However, the obtained accuracy and precision were significantly improved.

The Development and Validation of the Planning to Make Meals Performance Measure

The Planning to Make Meals Performance Measure (PMMPM) was initially created as an outcome measure for an occupation-based program dedicated to helping individuals living in poverty maximize their food resources. This article briefly describes the PMMPM and the results of a cross-sectional study examining construct validity. Forty-two participants completed the PMMPM, Food Skills Confidence Measure (FSCM), and Cooking Skills Confidence Measure (CSCM). Analysis using Spearman’s correlations revealed that one or more PMMPM score significantly correlated with the FSCM ( r = .37–.50, p ≤ .05) and the CSCM ( r = .44–.49, p = .01). These findings add to the psychometric properties of the PMMPM, promoting its usefulness as an alternative to self-report measures for programs seeking to enhance food, cooking, or resource management skills. Creating authentic and direct performance measures that assess complex constructs or skills is another way occupational therapy can contribute to health and well-being.

Psychometric evaluation of the 8-item Altarum Consumer Engagement (ACE) Measure™ in community-dwelling adults in Singapore

Background A valid and reliable measure is essential to assess patient engagement and its impact on health outcomes. This study aimed to examine the psychometric properties of the 8-item Altarum Consumer Engagement Measure™ (ACE Measure) among English-speaking community-dwelling adults in Singapore. Methods This cross-sectional study involved 400 randomly selected community-dwelling adults (mean age: 49.7 years, 50.0% were female, 72.3% were Chinese) who completed the English version of the 8-item ACE Measure independently. The item-level statistics were described. The internal consistency of the measure was measured by Cronbach alpha and item-rest correlations. Validity of the tool was assessed by 1) factorial validity using confirmatory factor analysis (CFA), 2) hypothesis-testing validity by correlating ACE subscales (Commitment and Navigation) with health-related outcomes, and 3) criterion validity against the Patient Activation Measure and Health Confidence Measure. Results There was no floor or ceiling effect for Commitment and Navigation subscales, and the Cronbach alpha for each subscale was 0.76 and 0.54, respectively. The two-factor structure was confirmed by CFA. In general, Commitment and Navigation subscales were positively correlated with frequency of activity participation (rho = 0.30 - 0.33) and EQ-5D visual analog scale (rho = 0.15 - 0.30). Individuals who perceived better health than peers had higher subscale scores (p < 0.01). Each subscale score had moderate and positive correlations with activation score (rho = 0.48 - 0.55) and health confidence score (rho = 0.35 - 0.47). Conclusions The two-subscale ACE Measure demonstrated good construct validity in English-speaking Singapore community-dwelling adults. Evidence in internal consistency was mixed, indicating further investigation.

Multimatcher Model to Enhance Ontology Matching Using Background Knowledge

Ontology matching is a rapidly emerging topic crucial for semantic web effort, data integration, and interoperability. Semantic heterogeneity is one of the most challenging aspects of ontology matching. Consequently, background knowledge (BK) resources are utilized to bridge the semantic gap between the ontologies. Generic BK approaches use a single matcher to discover correspondences between entities from different ontologies. However, the Ontology Alignment Evaluation Initiative (OAEI) results show that not all matchers identify the same correct mappings. Moreover, none of the matchers can obtain good results across all matching tasks. This study proposes a novel BK multimatcher approach for improving ontology matching by effectively generating and combining mappings from biomedical ontologies. Aggregation strategies to create more effective mappings are discussed. Then, a matcher path confidence measure that helps select the most promising paths using the final mapping selection algorithm is proposed. The proposed model performance is tested using the Anatomy and Large Biomed tracks offered by the OAEI 2020. Results show that higher recall levels have been obtained. Moreover, the F-measure values achieved with our model are comparable with those obtained by the state of the art matchers.

Music Segmentation Algorithm Based on Self-Adaptive Update of Confidence Measure

To improve the accuracy of music segmentation and enhance segmentation effect, an algorithm based on the adaptive update of confidence measure is proposed. According to the theory of compressed sensing, the music fragments are denoised, and thus the denoised signals are subjected to short-term correlation analysis. Then, the pitch frequency is extracted, and the music fragments are roughly classified by wavelet transform to realize the preprocessing of the music fragments. In order to calculate the confidence measure of the music segment, the SVM method is used, whereas the adaptive update of the confidence measure is studied using reliable data selection algorithm. The dynamic threshold notes are segmented according to the update result to realize music segmentation. Experimental results show that the recall and precision values of the algorithm reach 97.5% and 93.8%, respectively, the segmentation error rate is low, and it can achieve effective segmentation of music fragments, indicating that the algorithm is effective.

Self-Learning Pipeline for Low-Energy Resource-Constrained Devices

The trend of bringing machine learning (ML) to the Internet of Things (IoT) field devices is becoming ever more relevant, also reducing the overall energy need of the applications. ML models are usually trained in the cloud and then deployed on edge devices. Most IoT devices generate large amounts of unlabeled data, which are expensive and challenging to annotate. This paper introduces the self-learning autonomous edge learning and inferencing pipeline (AEP), deployable in a resource-constrained embedded system, which can be used for unsupervised local training and classification. AEP uses two complementary approaches: pseudo-label generation with a confidence measure using k-means clustering and periodic training of one of the supported classifiers, namely decision tree (DT) and k-nearest neighbor (k-NN), exploiting the pseudo-labels. We tested the proposed system on two IoT datasets. The AEP, running on the STM NUCLEO-H743ZI2 microcontroller, achieves comparable accuracy levels as same-type models trained on actual labels. The paper makes an in-depth performance analysis of the system, particularly addressing the limited memory footprint of embedded devices and the need to support remote training robustness.

Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study

Acute intestinal ischemia is a life-threatening condition. The current gold standard, with evaluation based on visual and tactile sensation, has low specificity. In this study, we explore the feasibility of using machine learning models on images of the intestine, to assess small intestinal viability. A digital microscope was used to acquire images of the jejunum in 10 pigs. Ischemic segments were created by local clamping (approximately 30 cm in width) of small arteries and veins in the mesentery and reperfusion was initiated by releasing the clamps. A series of images were acquired once an hour on the surface of each of the segments. The convolutional neural network (CNN) has previously been used to classify medical images, while knowledge is lacking whether CNNs have potential to classify ischemia-reperfusion injury on the small intestine. We compared how different deep learning models perform for this task. Moreover, the Shapley additive explanations (SHAP) method within explainable artificial intelligence (AI) was used to identify features that the model utilizes as important in classification of different ischemic injury degrees. To be able to assess to what extent we can trust our deep learning model decisions is critical in a clinical setting. A probabilistic model Bayesian CNN was implemented to estimate the model uncertainty which provides a confidence measure of our model decisions.

Stable Median Centre Clustering for Unsupervised Domain Adaptation Person Re-Identification

The current unsupervised domain adaptation person re-identification (re-ID) method aims to solve the domain shift problem and applies prior knowledge learned from labelled data in the source domain to unlabelled data in the target domain for person re-ID. At present, the unsupervised domain adaptation person re-ID method based on pseudolabels has obtained state-of-the-art performance. This method obtains pseudolabels via a clustering algorithm and uses these pseudolabels to optimize a CNN model. Although it achieves optimal performance, the model cannot be further optimized due to the existence of noisy labels in the clustering process. In this paper, we propose a stable median centre clustering (SMCC) for the unsupervised domain adaptation person re-ID method. SMCC adaptively mines credible samples for optimization purposes and reduces the impact of label noise and outliers on training to improve the performance of the resulting model. In particular, we use the intracluster distance confidence measure of the sample and its K-reciprocal nearest neighbour cluster proportion in the clustering process to select credible samples and assign different weights according to the intracluster sample distance confidence of samples to measure the distances between different clusters, thereby making the clustering results more robust. The experiments show that our SMCC method can select credible and stable samples for training and improve performance of the unsupervised domain adaptation model. Our code is available at https://github.com/sunburst792/SMCC-method/tree/master.