Learning Accuracy Research Articles

The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types

When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a "rationality coefficient" capturing how much noise or entropy we expect to see in the human behavior. Prior work typically sets the rationality level to a constant value, regardless of the type, or quality, of human feedback. However, in many settings, giving one type of feedback (e.g. a demonstration) may be much more difficult than a different type of feedback (e.g. answering a comparison query). Thus, we expect to see more or less noise depending on the type of human feedback. In this work, we advocate that grounding the rationality coefficient in real data for each feedback type, rather than assuming a default value, has a significant positive effect on reward learning. We test this in both simulated experiments and in a user study with real human feedback. We find that overestimating human rationality can have dire effects on reward learning accuracy and regret. We also find that fitting the rationality coefficient to human data enables better reward learning, even when the human deviates significantly from the noisy-rational choice model due to systematic biases. Further, we find that the rationality level affects the informativeness of each feedback type: surprisingly, demonstrations are not always the most informative---when the human acts very suboptimally, comparisons actually become more informative, even when the rationality level is the same for both. Ultimately, our results emphasize the importance and advantage of paying attention to the assumed human-rationality-level, especially when agents actively learn from multiple types of human feedback.

Early Prediction of Response of Hepatocellular Carcinoma to Yttrium-90 Radiation Segmentectomy Using a Machine Learning MR Imaging Radiomic Approach

PurposeTo assess the accuracy of a machine learning (ML) approach based on magnetic resonance (MR) imaging radiomic quantification obtained before treatment and early after treatment for prediction of early hepatocellular carcinoma (HCC) response to yttrium-90 transarterial radioembolization (TARE). Materials and MethodsIn this retrospective single-center study of 76 patients with HCC, baseline and early (1–2 months) post-TARE MR images were collected. Semiautomated tumor segmentation facilitated extraction of shape, first-order histogram, and custom signal intensity–based radiomic features, which were then trained (n = 46) using a ML XGBoost model and validated on a separate cohort (n = 30) not used in training to predict treatment response assessed at 4–6 months (based on modified Response and Evaluation Criteria in Solid Tumors criteria). Performance of this ML radiomic model was compared with those of models comprising clinical parameters and standard imaging characteristics using area under the receiver operating curve (AUROC) analysis for prediction of complete response (CR). ResultsSeventy-six tumors with a mean (±SD) diameter of 2.6 cm ± 1.6 were included. Sixty, 12, 1, and 3 patients were classified as having CR, partial response, stable disease, and progressive disease, respectively, at 4–6 months posttreatment on the basis of MR images. In the validation cohort, the radiomic model showed good performance (AUROC, 0.89) for prediction of CR, compared with models comprising clinical and standard imaging criteria (AUROC, 0.58 and 0.59, respectively). Baseline imaging features appeared to be more heavily weighted in the radiomic model. ConclusionsThe use of ML modeling of radiomic data combining baseline and early follow-up MR imaging could predict HCC response to TARE. These models need to be investigated further in an independent cohort.

Diagnostic Accuracy of Machine Learning AI Architectures in Detection and Classification of Lung Cancer: A Systematic Review.

The application of artificial intelligence (AI) in diagnostic imaging has gained significant interest in recent years, particularly in lung cancer detection. This systematic review aims to assess the accuracy of machine learning (ML) AI algorithms in lung cancer detection, identify the ML architectures currently in use, and evaluate the clinical relevance of these diagnostic imaging methods. A systematic search of PubMed, Web of Science, Cochrane, and Scopus databases was conducted in February 2023, encompassing the literature published up until December 2022. The review included nine studies, comprising five case-control studies, three retrospective cohort studies, and one prospective cohort study. Various ML architectures were analyzed, including artificial neural network (ANN), entropy degradation method (EDM), probabilistic neural network (PNN), support vector machine (SVM), partially observable Markov decision process (POMDP), and random forest neural network (RFNN). The ML architectures demonstrated promising results in detecting and classifying lung cancer across different lesion types. The sensitivity of the ML algorithms ranged from 0.81 to 0.99, while the specificity varied from 0.46 to 1.00. The accuracy of the ML algorithms ranged from 77.8% to 100%. The AI architectures were successful in differentiating between malignant and benign lesions and detecting small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). This systematic review highlights the potential of ML AI architectures in the detection and classification of lung cancer, with varying levels of diagnostic accuracy. Further studies are needed to optimize and validate these AI algorithms, as well as to determine their clinical relevance and applicability in routine practice.

Proposal of a New System for Essential Oil Classification Based on Low-Cost Gas Sensor and Machine Learning Techniques.

Essential oils are valuable in various industries, but their easy adulteration can cause adverse health effects. Electronic nasal sensors offer a solution for adulteration detection. This article proposes a new system for characterising essential oils based on low-cost sensor networks and machine learning techniques. The sensors used belong to the MQ family (MQ-2, MQ-3, MQ-4, MQ-5, MQ-6, MQ-7, and MQ-8). Six essential oils were used, including Cistus ladanifer, Pinus pinaster, and Cistus ladanifer oil adulterated with Pinus pinaster, Melaleuca alternifolia, tea tree, and red fruits. A total of up to 7100 measurements were included, with more than 118 h of measurements of 33 different parameters. These data were used to train and compare five machine learning algorithms: discriminant analysis, support vector machine, k-nearest neighbours, neural network, and naive Bayesian when the data were used individually or when hourly mean values were included. To evaluate the performance of the included machine learning algorithms, accuracy, precision, recall, and F1-score were considered. The study found that using k-nearest neighbours, accuracy, recall, F1-score, and precision values were 1, 0.99, 0.99, and 1, respectively. The accuracy reached 100% with k-nearest neighbours using only 2 parameters for averaged data or 15 parameters for individual data.

Ordering taxa in image convolution networks improves microbiome-based machine learning accuracy

ABSTRACT The human gut microbiome is associated with a large number of disease etiologies. As such, it is a natural candidate for machine-learning-based biomarker development for multiple diseases and conditions. The microbiome is often analyzed using 16S rRNA gene sequencing or shotgun metagenomics. However, several properties of microbial sequence-based studies hinder machine learning (ML), including non-uniform representation, a small number of samples compared with the dimension of each sample, and sparsity of the data, with the majority of taxa present in a small subset of samples. We show here using a graph representation that the cladogram structure is as informative as the taxa frequency. We then suggest a novel method to combine information from different taxa and improve data representation for ML using microbial taxonomy. iMic (image microbiome) translates the microbiome to images through an iterative ordering scheme, and applies convolutional neural networks to the resulting image. We show that iMic has a higher precision in static microbiome gene sequence-based ML than state-of-the-art methods. iMic also facilitates the interpretation of the classifiers through an explainable artificial intelligence (AI) algorithm to iMic to detect taxa relevant to each condition. iMic is then extended to dynamic microbiome samples by translating them to movies.

Tensor product based 2-D correlation data preprocessing methods for Raman spectroscopy of Chinese handmade paper

The paper introduces two new methods, namely the cross correlation method (CCM) and two-dimensional correlation method (TDCM), for preprocessing Raman spectroscopy data for analyzing Chinese handmade paper samples. CCM expands the spectral dimension from 1×N to 1×2N-1 by taking cross-correlation between two spectral data of the same category. TDCM includes two-dimensional synchronous correlation method (TDSCM) and two-dimensional asynchronous correlation method (TDACM), which expand the spectral dimension from 1×N to N×N by taking tensor products between two spectral data and between one spectral data and the Hilbert transformation of the other spectral data of the same category, respectively. The experimental data were preprocessed using baseline removal, CCM, TDSCM, and TDACM methods. Four machine learning models were employed to evaluate the effects of these methods: principal component analysis (PCA) combined with linear regression (LR), support vector machine (SVM) combined with LR, k-Nearest Neighbors (KNN), and random forest (RF). The results show that the R-squared values for the PCA model were nearly 1 for all types of data, indicating high accuracy. However, for SVM-LR, KNN, and RF models, the R-squared values were sorted in the order of raw data, baseline removal data, CCM, TDSCM, and TDACM preprocessed data. The R-squared values of KNN and RF machine learning models for TDACM preprocessed data were approaching 1, indicating that the accuracy of machine learning was significantly improved by nearly 100%. This has led to a remarkable improvement in the accuracy of supervised models such as KNN and RF, bringing them closer to the level of unsupervised models such as PCA.

Machine Learning Based Electronic Structure Predictors in Single-Atom Alloys: A Model Study of CO Kink-Site Adsorption across Transition Metal Substrates

This work reports on a comprehensive analysis of the predictive capacity and underlying physicochemical trends provided by d-band based electronic structure features as applied to single-atom alloys (SAAs). Taking CO adsorption energies at kink sites as a model framework, SAA adsorption trends are examined across a range of substrates with vastly differing intrinsic CO adsorption trends. Through this approach, it is demonstrated that SAA adsorption properties can be highly transferable, often displaying atom-like behavior independent of the host substrate, particularly in groups 6 through 12 of the periodic table. The predictability of such SAA behavior is found, however, to be highly qualitative for single d-band based electronic structure features. Nevertheless, it is shown that predictive capacity can be greatly improved through the creation of a feature space comprised of as few as 8 electronic structure features. Intriguingly, following the framework of Hammer and Nørskov, the machine learning accuracy of d-band based electronic structure features is shown to be sensitive to the atomic configuration diversity present in the training ensemble with model accuracy systematically improving through restrictions in the configurational space. More directly, it is shown that elements to the far left of the transition metal block such as Zr and Hf may exhibit CO binding properties comparable to Cu in the CO2 reduction reaction. However, impurities from groups 6–10 are demonstrated to overbind in a highly transferable manner in line with established pure substrate trends and are likely to act as unwanted posing species concerning CO and the overall CO2 reduction reaction. The results of this work broadly lay out the predictive capabilities of d-band features as applied to SAAs, as well as their propensity for exhibiting transferable binding properties among d-band substrates.

Efficient Creation of Jettability Diagrams Using Active Machine Learning.

The ability to jet a wide variety of materials consistently from print heads remains a key technical challenge for inkjet-based additive manufacturing processes. Drop watching is the most direct method for testing new inks and print head designs but such experiments are also resource consuming. In this work, a data-efficient machine learning technique called active learning is used to construct detailed jettability diagrams that identify complex regions corresponding to "no jetting," "jetting," and "desired jetting," rather than only individually sampled points. Crucially, our active learning method has resolved challenges with model selection that previously limited the accuracy of active learning in practical settings with very small experimental budgets. In addition, the key "desired jetting" zone may be quite small which is a challenge for initializing active learning. We leverage the physical intuition that the "desired jetting" zone tends to exist between the "jetting" and "no jetting" zone, to improve the performance of this highly imbalanced classification problem by performing two binary classifications in sequence. The first binary classification aims to map out the "jetting" zone versus the "no jetting" zone, while the second binary classification targets identifying the "desired jetting" zone with primary drops only. Our experiments use a stroboscopic drop watcher to visualize the jetting behavior of two fluids from a piezoelectric print head with different jetting waveforms. The results obtained from active learning were compared to a grid search method, which involves running more than 200 experiments for each fluid. The active learning method significantly reduces the number of experiments by 80% while achieving a test accuracy of more than 95% in the "jetting" zone prediction for the test fluids. The ability to construct these jettability diagrams will further accelerate new ink and print head developments.

Fault diagnosis of pumping system based on multimodal attention learning (CBMA Learning)

Grasping the pumping system’s operational state in time is crucial to the petroleum extraction sector. Rapid and efficient identification of indicator diagrams is a direct method of determining the operating status of oil wells. A new method of multimodal attention learning model(CBMA Learning) using superimposed images of the indicator diagrams and its frequency domain maps combined with numerical data of the indicator diagram is proposed. By processing the specified type of data through each branch network of the model in this method, the model could extract the characteristics of various modal data, and the attention mechanism introduced can efficiently capture the detailed information of the data and increase the precision of fault diagnosis.The proposed method is validated by applying it to an actual dataset from an oil field in northwest China. The experimental results demonstrate that the average classification accuracy of CBMA Learning is increased by 1.17 percent compared to the simple multimodal learning model, and the average accuracy of CBMA Learning reaches 93.05 percent, which is 10.47 percent higher than other models.

Recurrent neural network architecture for forecasting banana prices in Gujarat, India.

The forecasting of horticulture commodity prices, such as bananas, has wide-ranging impacts on farmers, traders and end-users. The considerable volatility in horticultural commodities pricing estimates has allowed farmers to exploit various local marketplaces for profitable sales of their farm produce. Despite the demonstrated efficacy of machine learning models as a suitable substitute for conventional statistical approaches, their application for price forecasting in the context of Indian horticulture remains an area of contention. Past attempts to forecast agricultural commodity prices have relied on a wide variety of statistical models, each of which comes with its own set of limitations. Although machine learning models have emerged as formidable alternatives to more conventional statistical methods, there is still reluctance to use them for the purpose of predicting prices in India. In the present investigation, we have analysed and compared the efficacy of a variety of statistical and machine learning models in order to get accurate price forecast. Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average model (SARIMA), Autoregressive Conditional Heteroscedasticity model (ARCH), Generalized Autoregressive Conditional Heteroscedasticity model (GARCH), Artificial Neural Network (ANN) and Recurrent Neural Network (RNN) were fitted to generate reliable predictions of prices of banana in Gujarat, India from January 2009 to December 2019. Empirical comparisons have been made between the predictive accuracy of different machine learning (ML) models and the typical stochastic model and it is observed that ML approaches, especially RNN, surpassed all other models in the majority of situations. Mean Absolute Percent Error (MAPE), Root Mean Square Error (RMSE), symmetric mean absolute percentage error (SMAPE), mean absolute scaled error (MASE) and mean directional accuracy (MDA) are used to illustrate the superiority of the models and RNN resulted least in terms of all error accuracy measures. RNN outperforms other models in this study for predicting accurate prices when compared to various statistical and machine learning techniques. The accuracy of other methodologies like ARIMA, SARIMA, ARCH GARCH, and ANN falls short of expectations.

Fully Automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM

Background and objectiveThe sheer volume of data generated by population imaging studies is unparalleled by current capabilities to extract objective and quantitative cardiac phenotypes; subjective and time-consuming manual image analysis remains the gold standard. Automated image analytics to compute quantitative imaging biomarkers of cardiac function are desperately needed. Data volumes and their variability pose a challenge to most state-of-the-art methods for endo- and epicardial contours, which lack robustness when applied to very large datasets. Our aim is to develop an analysis pipeline for the automatic quantification of cardiac function from cine magnetic resonance imaging data. MethodThis work adopt 4,638 cardiac MRI cases coming from UK Biobank with ground truth available for left and RV contours. A hybrid and robust algorithm is proposed to improve the accuracy of automatic left and right ventricle segmentation by harnessing the localization accuracy of deep learning and the morphological accuracy of 3D-ASM (three-dimensional active shape models). The contributions of this paper are three-fold. First, a fully automatic method is proposed for left and right ventricle initialization and cardiac MRI segmentation by taking full advantage of spatiotemporal constraint. Second, a deeply supervised network is introduced to train and segment the heart. Third, the 3D-ASM image search procedure is improved by combining image intensity models with convolutional neural network (CNN) derived distance maps improving endo- and epicardial edge localization. ResultsThe proposed architecture outperformed the state of the art for cardiac MRI segmentation from UK Biobank. The statistics of RV landmarks detection errors for Triscuspid valve and RV apex are 4.17 mm and 5.58 mm separately. The overlap metric, mean contour distance, Hausdorff distance and cardiac functional parameters are calculated for the LV (Left Ventricle) and RV (Right Ventricle) contour segmentation. Bland–Altman analysis for clinical parameters shows that the results from our automated image analysis pipelines are in good agreement with results from expert manual analysis. ConclusionsOur hybrid scheme combines deep learning and statistical shape modeling for automatic segmentation of the LV/RV from cardiac MRI datasets is effective and robust and can compute cardiac functional indexes from population imaging.

A dynamic support ratio of selected feature-based information for feature selection

Feature selection aims to select crucial features to improve classification accuracy in machine learning and data mining. Existing methods concentrate on the classification information from candidate features while seldom considering the changing information supported by selected features. In this paper, we construct a dynamic support ratio (DSR), which employs the new information of selected features to support classification. DSR explicitly describes the dynamic interactions between selected features and candidate features. Simultaneously, the feature relevance and feature redundancy are treated adaptively. Thus, distinctive features can be noticed sensitively. Afterward, a novel feature selection method based on a dynamic support ratio (DSRFS) is proposed. The proposed method is established on 18 benchmark data sets with four different classifiers. Classification accuracy, standard deviation, recall and statistical validations are employed to measure the classification performance. Extensive experiments demonstrate that DSRFS not only reduces the dimension of the feature space effectively, but also obtains the best average classification accuracy.

Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives.

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a first-line screening and diagnostic tool for prostate cancer, aiding in treatment selection and noninvasive radiotherapy guidance. However, the manual interpretation of MRI data is challenging and time-consuming, which may impact sensitivity and specificity. With recent technological advances, artificial intelligence (AI) in the form of computer-aided diagnosis (CAD) based on MRI data has been applied to prostate cancer diagnosis and treatment. Among AI techniques, deep learning involving convolutional neural networks contributes to detection, segmentation, scoring, grading, and prognostic evaluation of prostate cancer. CAD systems have automatic operation, rapid processing, and accuracy, incorporating multiple sequences of multiparametric MRI data of the prostate gland into the deep learning model. Thus, they have become a research direction of great interest, especially in smart healthcare. This review highlights the current progress of deep learning technology in MRI-based diagnosis and treatment of prostate cancer. The key elements of deep learning-based MRI image processing in CAD systems and radiotherapy of prostate cancer are briefly described, making it understandable not only for radiologists but also for general physicians without specialized imaging interpretation training. Deep learning technology enables lesion identification, detection, and segmentation, grading and scoring of prostate cancer, and prediction of postoperative recurrence and prognostic outcomes. The diagnostic accuracy of deep learning can be improved by optimizing models and algorithms, expanding medical database resources, and combining multi-omics data and comprehensive analysis of various morphological data. Deep learning has the potential to become the key diagnostic method in prostate cancer diagnosis and treatment in the future.

Three-stage multi-objective feature selection with distributed ensemble machine and deep learning for processing of complex and large datasets

The need for analytical solutions using machine learning (ML) and deep learning (DL) has risen in this era of industry-wide informed decision-making. Data is now readily available and moving at fast speeds due to the maturation of data processing technologies and the development of new technologies in the Big Data, streaming, and IoT sectors. As a result, a transformation is required in how analytical systems handle data. A novel approach to learning, distributed learning, maybe a wise choice for managing huge and high-speed data while overcoming the difficulties presented by noisy and dynamic data sources. Data scientists can considerably increase their productivity using distributed learning by 1) distributing concurrent experiments across several devices and 2) significantly reducing training time by distributing a network's training across several devices. A learning strategy takes a long time, and the model's performance suffers in large datasets due to redundant features and the dimensionality curse. But most feature selection methods are unstable, selecting different subsets of features for different training datasets, resulting in varying levels of classification accuracy. A novel ensemble machine and deep learning technologies are also needed to improve accuracy in distributed learning. To analyze complex and large datasets, this paper proposed a three-stage multi-objective feature selection (TMFS) with distributed ensemble machine and deep learning (DEMDL). The proposed TMFS technique selects the best feature subset by combining multiple feature subsets. To achieve these goals, the TMFS technique employs 5 feature selection strategies in 3 stages: correlation coefficient, Fisher score, information gain, mean absolute deviation, and min-max normalization. SVM is used for machine learning, and Dl4jMlpCassifier is used for deep learning. This SVM and Dl4jMlpClassifier are combined in DEMDL using a stacking classifier. SVM and Dl4jMlpClassifier are utilized as base classifiers in this stacking classifier, and the RIPPER classifier is employed as the meta-classifier. The experimental finding demonstrates that compared to existing classification techniques, the TMFS with DEMDL technique offers higher accuracy, Precision, Recall, and F-measure.

Predictive value of machine learning for breast cancer recurrence: a systematic review and meta-analysis.

Recurrence of breast cancer leads to a high lifetime risk and a low 5year survival rate. Researchers have used machine learning to predict the risk of recurrence in patients with breast cancer, but the predictive performance of machine learning remains controversial. Hence, this study aimed to explore the accuracy of machine learning in predicting breast cancer recurrence risk and aggregate predictive variables to provide guidance for the development of subsequent risk scoring systems. We searched Pubmed, EMBASE, Cochrane, and Web of Science. The risk of bias in the included studies was evaluated using prediction model risk of bias assessment tool (PROBAST). Meta-regression was adopted to explore whether there was a significant difference in the recurrence time by machine learning. Thirty-four studies involving 67,560 subjects were included, among whom 8695 experienced breast cancer recurrence. The c-index of prediction models was 0.814 (95%CI 0.802-0.826) and 0.770 (95%CI 0.737-0.803) in the training and validation sets, respectively; the sensitivity and specificity were 0.69 (95% CI 0.64-0.74), 0.89 (95% CI 0.86-0.92) in the training, and 0.64 (95% CI 0.58-0.70), 0.88 (95% CI 0.82-0.92) in the validation, respectively. Age, histological grading, and lymph node status are the most commonly used variables in model construction. Attention should be paid to unhealthy lifestyles such as drinking, smoking and BMI as modeling variables. Risk prediction models based on machine learning have long-term monitoring value for breast cancer population, and subsequent studies should consider using large-sample and multi-center data to establish risk equations for verification. Machine learning may be used as a predictive tool for breast cancer recurrence. Currently, there is a lack of effective and universally applicable machine learning models in clinical practice. We expect to incorporate multi-center studies in the future and attempt to develop tools for predicting breast cancer recurrence risk, so as to effectively identify populations at high risk of recurrence and develop personalized follow-up strategies and prognostic interventions to reduce the risk of recurrence.

Deep attention fuzzy cognitive maps for interpretable multivariate time series prediction

Although time series prediction is widely used to estimate the future state of complex systems in various industries, accurate, interpretable and generalizable methods are still limited when used to make long-term nonstationary predictions. To this end, this article proposes deep attention fuzzy cognitive maps (DAFCM), which is composed of spatiotemporal fuzzy cognitive maps (STFCM), long short-term memory (LSTM) neural network, temporal fuzzy cognitive maps (TFCM) and residual structures. First, an improved attention mechanism is used to build spatiotemporal fuzzy cognitive maps that capture the spatial correlation in pairs of nodes and the temporal correlation of respective nodes. Second, the node state updated through the STFCM is input to the LSTM to capture the long-term trend of these series, and the TFCM with improved time attention is applied for the nonstationary problem in the time series. Finally, we add the state values of previous nodes into the DAFCM and build residual structures through linear transformation to prevent gradient explosion and gradient disappearance in long-term backpropagation. By combining the interpretability of fuzzy cognitive maps (FCM) and the high prediction accuracy of deep learning, the DAFCM can be used to accomplish tasks such as multivariate long-term nonstationary time series forecasting in multiple domains, and its efficiency is validated with 6 public datasets across 9 baselines.

Improving Efficiency and Accuracy in English Translation Learning: Investigating a Semantic Analysis Correction Algorithm

ABSTRACT Translation serves as a vital link in connecting individuals from diverse cultural backgrounds, assuming greater significance in the context of globalization. With the continued growth of international communication, the importance of effective translation in fostering mutual understanding, exploring new horizons, and building relationships cannot be overstated. However, the persistent language barrier necessitates improvements in translation accuracy and efficiency. In recent years, information technology has facilitated the development of innovative algorithms for English translation. This study aims to investigate correction algorithms for English translation learning, proposing a method that encompasses semantic word similarity calculations, a log-linear model construction, and the selection of appropriate translations using a dependency tree-to-string approach. Our research examines the performance of this system through comprehensive testing, showcasing noteworthy enhancements in the efficacy and precision of the translations in English. By addressing the users’ needs for English translation correction, this work contributes to bridging language gaps and fostering effective cross-cultural communication.

Student Perceptions of Glover/Curwen Hand Signs in the Elementary Music Classroom

Elementary music educators use a variety of strategies in classroom instruction. The purpose of this case study was to explore student perceptions of Curwen hand signs, a common instructional strategy in elementary music classrooms. Second- and third-grade students reported various challenges, benefits, and influential factors surrounding hand sign use. Results indicated that students enjoyed movement activities and benefited from visual and physical reminders of singing tasks during instruction. They described several challenges, including multitasking, required background knowledge, and distraction. Influential factors included a learning curve, accuracy, placement, pattern length and complexity, and enjoyment. The results of this study suggest that hand signs should be considered one instructional strategy in a toolbox of multiple approaches.

A TEDE Algorithm Studies the Effect of Dataset Grouping on Supervised Learning Accuracy

Datasets are the basis for research on deep learning methods in computer vision. The impact of the percentage of training sets in a dataset on the performance of neural network models needs to be further explored. In this paper, a twice equal difference enumeration (TEDE) algorithm is proposed to investigate the effect of different training set percentages in the dataset on the performance of the network model, and the optimal training set percentage is determined. By selecting the Pascal VOC dataset and dividing it into six different datasets from largest to smallest, and then dividing each dataset into the datasets to be analyzed according to five different training set percentages, the YOLOv5 convolutional neural network is used to train and test the 30 datasets to determine the optimal neural network model corresponding to the training set percentages. Finally, tests were conducted using the Udacity Self-Driving dataset with a self-made Tire Tread Defects (TTD) dataset. The results show that the network model performance is superior when the training set accounts for between 85% and 90% of the overall dataset. The results of dataset partitioning obtained by the TEDE algorithm can provide a reference for deep learning research.

An Exploration of Prediction Accuracy of Developmental Degrees of Music Expression in Early Childhood Based on A Simultaneous Analysis of Both Eye Movement and Full-Body Movement

This article explores validity to introduce eye movement of children in association with body movement as feature quantities of machine learning, in particular, to assess children’s maturity level of musical expression. There is a growing awareness of applying machine learning technique to yield practical benefit on predicting developmental degrees of music education by observing body movements with motion capture technology. From professional teaching perspective, it is believed only experienced teachers can evaluate children’s music achievement because coordinated functioning of body movements need carefully be observed in connection with various music factor such as rhythm, beat strength, tones, etc. If new teachers can take advantage of having objective results of evaluation of children’s expression level by machines, it will enhance educational efficiency to certain levels which experts could attain. The author aims to improve classification accuracy of machine learning by focusing on eye movements data simultaneously recorded with body movements. In this study, children (n=43) at two child facilities participated in the data capture of both eye movement and body movement during musical expression. Feature quantities were extracted from the results of a three-way of ANOVA, and applied to machine learning to improve the classification accuracy of developmental degree in musical expression. Specifically, when using several classifiers such as NN (Neural Network model), the classification accuracy of developmental degree of musical development was more precisely in the case of both body movement data and eye movement data included in feature quantities than in the case of only body movement data as feature quantities.