Active Learning is an essential method for label-efficient deep learning. As a Bayesian active learning method, Bayesian Active Learning by Disagreement (BALD) successfully selects the most representative samples by maximizing the mutual information between the model prediction and model parameters. However, when applied to a batch acquisition mode, like batch construction with greedy search, BALD suffers from poor performance, especially with noises of near-duplicate data. To address this shortcoming, we propose a diverse beam search optimized batch active learning method, which explores a graph for every batch construction by expanding the highest-scored samples of a predetermined number. To avoid near duplicate beam branches (very similar beams generated from the same root and similar samples), which is undesirable for lacking diverse representations in the feature space, we design a self-adapted constraint within candidate beams. The proposed method is able to acquire data that can better represent the distribution of the unlabeled pool, and at the same time, be significantly different from existing beams. We observe that the proposed method achieves higher batch performance than the baseline methods on three benchmark datasets.

Cardiopulmonary function and power as well as efficient motion skill are extremely important for athletes. Thanks to the latest sensing technology and smart devices, many researchers have focused on sports-skill analysis. Electromyography (EMG), in particular, is gaining attention as a method of understanding the power-generating process in motions. However, most existing applications using EMG have remained being one-time measurement. This is because athletes do not know how to use the results and how to measure their improvement. We propose a sports-skill-training framework with muscle-usage indicators based on EMG and an EMG live visualization system. With this framework, athletes can determine the skill they need to improve by focusing on skills whose indicators are poor, activate their muscles with live feedback to overcome weaknesses, and quantitatively measure their improvement as the improvement of the indicators during the activation training. We also verified the effect of coaching in this framework on cycling athletes. The experimental results quantitatively indicate the effectiveness of continuous skill training with our framework.

Effective training without risk of injury based on quantitative data is important for all athletes. In bicycle racing, pedaling skill analysis with electromyography (EMG) is gaining attention as a technique to use in addition to power training and heart rate training, which already have effective measuring devices. However, EMG is not easy for non-specialists to use because of the difficulties in analysis and interpretation. We, therefore, propose a multilateral pedaling skill evaluation technique to quantitatively and practically analyze with surface EMG wear for non-specialists. This technique can extract strong and weak pedaling skill items that are difficult to detect through visual observation. It also removes the need to acquire additional data only for preprocessing and is well adapted for measurement in an actual environment over a long period. We verify the technique's expressiveness and feasibility through experiments involving 14 participants. The results indicate its potential for pedaling skill training.

RSSI-based indoor localization is getting much attention. Thanks to a number of researchers, the localization accuracy has already reached a sufficient level. However, it is still not easy-to-use technology because of its heavy installation cost. When an indoor localization system is installed, it needs to collect RSSI data for training classifiers. Existing techniques need to collect enough data at each location. This is why the installation cost is very heavy. We propose a technique to gather data efficiently by using machine learning techniques. Our proposed algorithm is based on multi-task learning and Bayesian optimization. This algorithm can remove the need to collect data of all location labels and select location labels to acquire new data efficiently. We verify this algorithm by using a Wi-Fi RSSI dataset collected in a building. The empirical results suggest that the algorithm is superior to an existing algorithm applying single-task learning and Active Class Selection.