Regulating Grip Forces through EMG-Controlled Protheses for Transradial Amputees

This study aims to evaluate different combinations of features and algorithms to be used in the control of a prosthetic hand wherein both the configuration of the fingers and the gripping forces can be controlled. This requires identifying machine learning algorithms and feature sets to detect both intended force variation and hand gestures in EMG signals recorded from upper-limb amputees. However, despite the decades of research into pattern recognition techniques, each new problem requires researchers to find a suitable classification algorithm, as there is no such thing as a universal ’best’ solution. Consideration of different techniques and data representation represents a fundamental practice in order to achieve maximally effective results. To this end, we employ a publicly-available database recorded from amputees to evaluate different combinations of features and classifiers. Analysis of data from 9 different individuals shows that both for classic features and for time-dependent power spectrum descriptors (TD-PSD) the proposed logarithmically scaled version of the current window plus previous window achieves the highest classification accuracy. Using linear discriminant analysis (LDA) as a classifier and applying a majority-voting strategy to stabilize the individual window classification, we obtain 88% accuracy with classic features and 89% with TD-PSD features.

Classifying microscopic images as acute lymphoblastic leukemia by Resnet ensemble model and Taguchi method

Background Researchers have attempted to apply deep learning methods of artificial intelligence for rapidly and accurately detecting acute lymphoblastic leukemia (ALL) in microscopic images. Results A Resnet101-9 ensemble model was developed for classifying ALL in microscopic images. The proposed Resnet101-9 ensemble model combined the use of the nine trained Resnet-101 models with a majority voting strategy. Each trained Resnet-101 model integrated the well-known pre-trained Resnet-101 model and its algorithm hyperparameters by using transfer learning method to classify ALL in microscopic images. The best combination of algorithm hyperparameters for the pre-trained Resnet-101 model was determined by Taguchi experimental method. The microscopic images used for training of the pre-trained Resnet-101 model and for performance tests of the trained Resnet-101 model were obtained from the C-NMC dataset. In experimental tests of performance, the Resnet101-9 ensemble model achieved an accuracy of 85.11% and an F1-score of 88.94 in classifying ALL in microscopic images. The accuracy of the Resnet101-9 ensemble model was superior to that of the nine trained Resnet-101 individual models. All other performance measures (i.e., precision, recall, and specificity) for the Resnet101-9 ensemble model exceeded those for the nine trained Resnet-101 individual models. Conclusion Compared to the nine trained Resnet-101 individual models, the Resnet101-9 ensemble model had superior accuracy in classifying ALL in microscopic images obtained from the C-NMC dataset.

Continuous Stress Detection of Hospital Staff Using Smartwatch Sensors and Classifier Ensemble

High stress levels among hospital workers could be harmful to both workers and the institution. Enabling the workers to monitor their stress level has many advantages. Knowing their own stress level can help them to stay aware and feel more in control of their response to situations and know when it is time to relax or take some actions to treat it properly. This monitoring task can be enabled by using wearable devices to measure physiological responses related to stress. In this work, we propose a smartwatch sensors based continuous stress detection method using some individual classifiers and classifier ensembles. The experiment results show that all of the classifiers work quite well to detect stress with an accuracy of more than 70%. The results also show that the ensemble method obtained higher accuracy and F1-measure compared to all of the individual classifiers. The best accuracy was obtained by the ensemble with soft voting strategy (ES) with 87.10% while the hard voting strategy (EH) achieved the best F1-measure with 77.45%.

An improved D-S evidence theory based neighborhood rough classification approach

Neighborhood classifier, a common classification method, is applied in pattern recognition and data mining. The neighborhood classifier mainly relies on the majority voting strategy to judge each category. This strategy only considers the number of samples in the neighborhood but ignores the distribution of samples, which leads to a decreased classification accuracy. To overcome the shortcomings and improve the classification performance, D-S evidence theory is applied to represent the evidence information support of other samples in the neighborhood, and the distance between samples in the neighborhood is taken into account. In this paper, a novel attribute reduction method of neighborhood rough set with a dynamic updating strategy is developed. Different from the traditional heuristic algorithm, the termination threshold of the proposed reduction algorithm is dynamically optimized. Therefore, when the attribute significance is not monotonic, this method can retrieve a better value, in contrast to the traditional method. Moreover, a new classification approach based on D-S evidence theory is proposed. Compared with the classical neighborhood classifier, this method considers the distribution of samples in the neighborhood, and evidence theory is applied to describe the closeness between samples. Finally, datasets from the UCI database are used to indicate that the improved reduction can achieve a lower neighborhood decision error rate than classical heuristic reduction. In addition, the improved classifier acquires higher classification performance in contrast to the traditional neighborhood classifier. This research provides a new direction for improving the accuracy of neighborhood classification.

A Two-Round Weight Voting Strategy-Based Ensemble Learning Method for Sea Ice Classification of Sentinel-1 Imagery

Sea ice information in the Arctic region is essential for climatic change monitoring and ship navigation. Although many sea ice classification methods have been put forward, the accuracy and usability of classification systems can still be improved. In this paper, a two-round weight voting strategy-based ensemble learning method is proposed for refining sea ice classification. The proposed method includes three main steps. (1) The preferable features of sea ice are constituted by polarization features (HH, HV, HH/HV) and the top six GLCM-derived texture features via a random forest. (2) The initial classification maps can then be generated by an ensemble learning method, which includes six base classifiers (NB, DT, KNN, LR, ANN, and SVM). The tuned voting weights by a genetic algorithm are employed to obtain the category score matrix and, further, the first coarse classification result. (3) Some pixels may be misclassified due to their corresponding numerically close score value. By introducing an experiential score threshold, each pixel is identified as a fuzzy or an explicit pixel. The fuzzy pixels can then be further rectified based on the local similarity of the neighboring explicit pixels, thereby yielding the final precise classification result. The proposed method was examined on 18 Sentinel-1 EW images, which were captured in the Northeast Passage from November 2019 to April 2020. The experiments show that the proposed method can effectively maintain the edge profile of sea ice and restrain noise from SAR. It is superior to the current mainstream ensemble learning algorithms with the overall accuracy reaching 97%. The main contribution of this study is proposing a superior weight voting strategy in the ensemble learning method for sea ice classification of Sentinel-1 imagery, which is of great significance for guiding secure ship navigation and ice hazard forecasting in winter.

Multiscale Object Detection from Drone Imagery Using Ensemble Transfer Learning

Object detection in uncrewed aerial vehicle (UAV) images has been a longstanding challenge in the field of computer vision. Specifically, object detection in drone images is a complex task due to objects of various scales such as humans, buildings, water bodies, and hills. In this paper, we present an implementation of ensemble transfer learning to enhance the performance of the base models for multiscale object detection in drone imagery. Combined with a test-time augmentation pipeline, the algorithm combines different models and applies voting strategies to detect objects of various scales in UAV images. The data augmentation also presents a solution to the deficiency of drone image datasets. We experimented with two specific datasets in the open domain: the VisDrone dataset and the AU-AIR Dataset. Our approach is more practical and efficient due to the use of transfer learning and two-level voting strategy ensemble instead of training custom models on entire datasets. The experimentation shows significant improvement in the mAP for both VisDrone and AU-AIR datasets by employing the ensemble transfer learning method. Furthermore, the utilization of voting strategies further increases the 3reliability of the ensemble as the end-user can select and trace the effects of the mechanism for bounding box predictions.

An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making

Background The increasing prevalence of childhood obesity makes it essential to study the risk factors with a sample representative of the population covering more health topics for better preventive policies and interventions. It is aimed to develop an ensemble feature selection framework for large-scale data to identify risk factors of childhood obesity with good interpretability and clinical relevance. Methods We analyzed the data collected from 426,813 children under 18 during 2000–2019. A BMI above the 90th percentile for the children of the same age and gender was defined as overweight. An ensemble feature selection framework, Bagging-based Feature Selection framework integrating MapReduce (BFSMR), was proposed to identify risk factors. The framework comprises 5 models (filter with mutual information/SVM-RFE/Lasso/Ridge/Random Forest) from filter, wrapper, and embedded feature selection methods. Each feature selection model identified 10 variables based on variable importance. Considering accuracy, F-score, and model characteristics, the models were classified into 3 levels with different weights: Lasso/Ridge, Filter/SVM-RFE, and Random Forest. The voting strategy was applied to aggregate the selected features, with both feature weights and model weights taken into consideration. We compared our voting strategy with another two for selecting top-ranked features in terms of 6 dimensions of interpretability. Results Our method performed the best to select the features with good interpretability and clinical relevance. The top 10 features selected by BFSMR are age, sex, birth year, breastfeeding type, smoking habit and diet-related knowledge of both children and mothers, exercise, and Mother’s systolic blood pressure. Conclusion Our framework provides a solution for identifying a diverse and interpretable feature set without model bias from large-scale data, which can help identify risk factors of childhood obesity and potentially some other diseases for future interventions or policies.

Improving Human Happiness Analysis based on Transfer Learning：Algorithm Development and Validation (Preprint)

BACKGROUND Happiness refers to the joyful and pleasant emotions that humans produce subjectively. It is the positive part of emotions, and it affects the quality of human life. Therefore, understanding human happiness is a meaningful task in sentiment analysis. We mainly discuss two facets (Agency/Sociality) of happiness in this study. Through analysis and research on happiness, we can expand on new concepts that define happiness and enrich our understanding of emotions. OBJECTIVE In this paper, we treated each happy moment as a sequence of short sentences, then proposed a short happiness detection model based on transfer learning to analyze the Agency and Sociality aspects of happiness. METHODS Happiness analysis is a novel and challenging research task. However, the current dataset in the field of happiness is small. To solve this problem，we utilized the unlabeled training set and transfer learning to train a semantically enhanced language model in the target domain. Then, the trained language model with domain characteristics was further combined with other deep learning models to obtain various models. Finally, we used the improved voting strategy to further improve the experimental results. RESULTS The proposed approach was evaluated on the public dataset. Experimental results showed that our approach significantly outperforms the baselines. When predicting the Agency aspect of happiness, our approach achieved an accuracy of 0.8574 and an F1 score of 0.90, repectively. When predicting Sociality, our approach achieved an accuracy of 0.928 and an F1 score of 0.9360, respectively. CONCLUSIONS Through the evaluation of the dataset, the comparison results demonstrated the effectiveness of our approach for happiness analysis. Experimental results confirmed that our method achieved state-of-the-art performance and transfer learning effectively improved happiness analysis.