Fanconi Anemia: Examining Guidelines for Testing All Patients with Hand Anomalies Using a Machine Learning Approach

Background: This study investigated the questionable necessity of genetic testing for Fanconi anemia in children with hand anomalies. The current UK guidelines suggest that every child with radial ray dysplasia or a thumb anomaly should undergo further cost intensive investigation for Fanconi anemia. In this study we reviewed the numbers of patients and referral patterns, as well as the financial and service provision implications UK guidelines provide. Methods: Over three years, every patient with thumb or radial ray anomaly referred to our service was tested for Fanconi Anemia. CART Analysis and machine learning techniques using Waikato Environment for Knowledge Analysis were applied to evaluate single clinical features predicting Fanconi anemia. Results: Youden Index and Predictive Summary Index (PSI) scores suggested no clinical significance of hand anomalies associated with Fanconi anemia. CART Analysis and attribute evaluation with Waikato Environment for Knowledge Analysis (WEKA) showed no single feature predictive for Fanconi anemia. Furthermore, none of the positive Fanconi anemia patients in this study had an isolated upper limb anomaly without presenting other features of Fanconi anemia. Conclusion: As a conclusion, this study does not support Fanconi anemia testing for isolated hand abnormalities in the absence of other features associated with this blood disease.

Double Feature Extraction Method of Ship-Radiated Noise Signal Based on Slope Entropy and Permutation Entropy

In order to accurately identify various types of ships and develop coastal defenses, a single feature extraction method based on slope entropy (SlEn) and a double feature extraction method based on SlEn combined with permutation entropy (SlEn&PE) are proposed. Firstly, SlEn is used for the feature extraction of ship-radiated noise signal (SNS) compared with permutation entropy (PE), dispersion entropy (DE), fluctuation dispersion entropy (FDE), and reverse dispersion entropy (RDE), so that the effectiveness of SlEn is verified, and SlEn has the highest recognition rate calculated by the k-Nearest Neighbor (KNN) algorithm. Secondly, SlEn is combined with PE, DE, FDE, and RDE, respectively, to extract the feature of SNS for a higher recognition rate, and SlEn&PE has the highest recognition rate after the calculation of the KNN algorithm. Lastly, the recognition rates of SlEn and SlEn&PE are compared, and the recognition rates of SlEn&PE are higher than SlEn by 4.22%. Therefore, the double feature extraction method proposed in this paper is more effective in the application of ship type recognition.

Physical Activity Classification with Wearable Sensor Data in an eCoach Recommendation System (Preprint)

UNSTRUCTURED Leading a sedentary lifestyle may cause numerous health problems. Therefore, sedentary lifestyle changes should be given priority to avoid severe damage. Research in eHealth can provide methods to enrich personal healthcare with Information and Communication Technologies (ICTs). An eCoach system may allow people to manage a healthy lifestyle with health state monitoring and personalized recommendations. Using machine learning (ML) techniques, this study investigated the possibility of classifying daily physical activity for adults into the following classes - sedentary, low active, active, active, highly active, and rigorous active. The daily total step count, total daily minutes of sedentary time, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) served as input for the classification models. We first used publicly available Fitbit data to build the classification models. Second, using the transfer learning approach, we re-used the top five best-performing models on a real dataset as collected from the MOX2-5 wearable medical-grade activity sensor. We found that ensemble ExtraTreesClassifier with an estimator value of 150 outperformed other classifiers with a mean accuracy score of 99.72% for single feature and support vector classifier (SVC) with “linear” kernel outpaced other classifiers with a mean accuracy score of 99.14% for five features, for the public Fitbit datasets. To demonstrate the practical usefulness of the classifiers, we conceptualized how the classifier model can be used in an eCoach prototype system to attain personalized activity goals (e.g., stay active for the entire week). After transfer learning, K-Nearest-Neighbor (KNN) outpaced the other four classifiers for a single feature, and SVC with a “linear” kernel outdid the other four classifiers for multiple features.

A Novel Adaptive Feature Fusion Strategy for Image Retrieval

In the era of big data, it is challenging to efficiently retrieve the required images from the vast amount of data. Therefore, a content-based image retrieval system is an important research direction to address this problem. Furthermore, a multi-feature-based image retrieval system can compensate for the shortage of a single feature to a certain extent, which is essential for improving retrieval system performance. Feature selection and feature fusion strategies are critical in the study of multi-feature fusion image retrieval. This paper proposes a multi-feature fusion image retrieval strategy with adaptive features based on information entropy theory. Firstly, we extract the image features, construct the distance function to calculate the similarity using the information entropy proposed in this paper, and obtain the initial retrieval results. Then, we obtain the precision of single feature retrieval based on the correlation feedback as the retrieval trust and use the retrieval trust to select the effective features automatically. After that, we initialize the weights of selected features using the average weights, construct the probability transfer matrix, and use the PageRank algorithm to update the initialized feature weights to obtain the final weights. Finally, we calculate the comprehensive similarity based on the final weights and output the detection results. This has two advantages: (1) the proposed strategy uses multiple features for image retrieval, which has better performance and more substantial generalization than the retrieval strategy based on a single feature; (2) compared with the fixed-feature retrieval strategy, our method selects the best features for fusion in each query, which takes full advantages of each feature. The experimental results show that our proposed method outperforms other methods. In the datasets of Corel1k, UC Merced Land-Use, and RSSCN7, the top10 retrieval precision is 99.55%, 88.02%, and 88.28%, respectively. In the Holidays dataset, the mean average precision (mAP) was 92.46%.

Face Manipulation Detection Based on Supervised Multi-Feature Fusion Attention Network

Nowadays, faces in videos can be easily replaced with the development of deep learning, and these manipulated videos are realistic and cannot be distinguished by human eyes. Some people maliciously use the technology to attack others, especially celebrities and politicians, causing destructive social impacts. Therefore, it is imperative to design an accurate method for detecting face manipulation. However, most of the existing methods adopt single convolutional neural network as the feature extraction module, causing the extracted features to be inconsistent with the human visual mechanism. Moreover, the rich details and semantic information cannot be reflected with single feature, limiting the detection performance. Therefore, this paper tackles the above problems by proposing a novel face manipulation detection method based on a supervised multi-feature fusion attention network (SMFAN). Specifically, the capsule network is used for face manipulation detection, and the SMFAN is added to the original capsule network to extract details of the fake face image. Further, the focal loss is used to realize hard example mining. Finally, the experimental results on the public dataset FaceForensics++ show that the proposed method has better performance.

Application of Partial Differential Equation Image Classification Methods to the Aesthetic Evaluation of Images

The average accuracy of the fusion of color harmony and composition features is 75.17%, which is higher than that of a single feature. The classification accuracy of NP-DP-DCNN structure is about 1% higher than that of other methods and 1.77% higher than that of NP-DCNN. Traditional image aesthetic evaluation methods are only effective for specific image sets or specific style images and are not suitable for all types of images. Based on the introduction of the partial differential equation image filtering method, through the parallel supervised learning of aesthetic attribute labels, this paper extracts the global aesthetic depth features, adopts the partial differential equation to evolve the contour C constant, and constructs a convolution neural network. The structure of a convolution kernel learned by using parallel network structure achieves better classification performance. Through the aesthetic evaluation experiment, the overall test accuracy is improved by 0.58% and the average accuracy of the integration of color harmony and composition features is 75.17%, which is higher than that of a single feature. The classification accuracy of NP-DP-DCNN structure is about 1% higher than that of other methods and 1.83% higher than that of NP-DCNN. It has achieved better test accuracy than before in the seven subcategories with discrimination between high aesthetic and low aesthetic images. It has achieved better classification performance than the traditional feature extraction methods in the public dataset CUHK database, and it has excellent aesthetic reference value.

European VLBI Network Observations of the Proposed Dual AGN SDSS J101022.95+141300.9

During galaxy merger events, the supermassive black holes in the center of the galaxies may form a pair of active galactic nuclei (AGN) with kiloparsec-scale or even parsec-scale separation. Recently, optical observations revealed a promising dual-AGN candidate at the center of the galaxy SDSS J101022.95+141300.9 (hereafter J1010+1413). The presence of two distinct [O iii]-emitting point sources with a projected separation of ∼430 pc indicates a dual-AGN system. To search for AGN-dominated radio emission originating from the Hubble Space Telescope (HST) point sources, we carried out very long baseline interferometry observations. We resolved the radio structure of J1010+1413 and detected a single feature offset from the HST point sources and also from the Gaia optical position of the object. Our multiwavelength analysis of J1010+1413 inferred two possible interpretations of the observed properties challenging its proposed dual-AGN classification.

Buzz Tweet Classification Based on Text and Image Features of Tweets Using Multi-Task Learning

This study investigates social media trends and proposes a buzz tweet classification method to explore the factors causing the buzz phenomenon on Twitter. It is difficult to identify the causes of the buzz phenomenon based solely on texts posted on Twitter. It is expected that by limiting the tweets to those with attached images and using the characteristics of the images and the relationships between the text and images, a more detailed analysis than that of with text-only tweets can be conducted. Therefore, an analysis method was devised based on a multi-task neural network that uses both the features extracted from the image and text as input and the buzz class (buzz/non-buzz) and the number of “likes (favorites)” and “retweets (RTs)” as output. The predictions made using a single feature of the text and image were compared with the predictions using a combination of multiple features. The differences between buzz and non-buzz features were analyzed based on the cosine similarity between the text and the image. The buzz class was correctly identified with a correctness rate of approximately 80% for all combinations of image and text features, with the combination of BERT and VGG16 providing the highest correctness rate.

Strategy Development and Feedback Processing During Complex Category Learning

In this study, 38 young adults participated in a probabilistic A/B prototype category learning task under observational and feedback-based conditions. The study compared learning success (testing accuracy) and strategy use (multi-cue vs. single feature vs. random pattern) between training conditions. The feedback-related negativity (FRN) and P3a event related potentials were measured to explore the relationships between feedback processing and strategy use under a probabilistic paradigm. A greater number of participants were found to utilize an optimal, multi-cue strategy following feedback-based training than observational training, adding to the body of research suggesting that feedback can influence learning approach. There was a significant interaction between training phase and strategy on FRN amplitude. Specifically, participants who used a strategy in which category membership was determined by a single feature (single feature strategy) exhibited a significant decrease in FRN amplitude from early training to late training, perhaps due to reduced utilization of feedback or reduced prediction error. There were no significant main or interaction effects between valence, training phase, or strategy on P3a amplitude. Findings are consistent with prior research suggesting that learners vary in their approach to learning and that training method influences learning. Findings also suggest that measures of feedback processing during probabilistic category learning may reflect changes in feedback utilization and may further illuminate differences among individual learners.