Recently, the use of reinforcement-learning algorithms has been proposed to create value and policy functions, and their effectiveness has been demonstrated using Go, Chess, and Shogi. In previous studies, the policy function is trained to predict the search probabilities of each move output by Monte Carlo Tree Search; thus, a number of simulations are required to obtain the search probabilities. We propose a reinforcement-learning algorithm with game of self-play to create value and policy functions such that the policy function is trained directly from the game results without the search probabilities. In this study, we use Hex, a board game developed by Piet Hein, to evaluate the proposed method. We demonstrate the effectiveness of the proposed learning algorithm in terms of the policy function accuracy, and play a tournament with the proposed computer Hex algorithm DeepEZO and 2017 world-champion programs. The tournament results demonstrate that DeepEZO outperforms all programs. DeepEZO achieved a winning percentage of 79.3% against the world-champion program MoHex2.0 under the same search conditions on 13x13 board. We also show that the highly accurate policy functions can be created by training the policy functions to increase the number of moves to be searched in the loser position.
A polarisation switchable microstrip array antenna is presented. This array consists of square patch antennas coupled in close proximity to a microstrip line. The polarisation state can be switched electrically by short- or open-circuiting the end of the feedline using a PIN diode. Fundamental characteristics of the proposed array are investigated by measurements performed at S-band to demonstrate the proposal.
Pain is a basic sensation associated with tissue injury. Although facial expression is a useful indicator of pain in mammals, its assessment in rodents requires expertise and experience. Here, we aimed to establish an automated pain assessment method using the facial images of free-moving mice. A convolutional neural network (CNN) was trained with the facial images of untreated mice and those subjected to acetic acid (AC)-induced pain. The trained CNN successfully predicted the faces of AC-, capsaicin-, and calcitonin gene-related peptide-induced pain that had not been used for CNN training. It also detected the analgesic effect of diclofenac, a nonsteroidal anti-inflammatory drug, against AC-induced pain. We used dimensionality reduction algorithms to select images with similar compositions and visualized the regions focused on by the CNN during predictions. The CNN focused on the head, forehead, ear, eye, cheek, and nose to predict pain or no pain. In conclusion, we established a method for automated pain assessment using the facial images of free-moving mice.
Compressed video action recognition classifies actions using multiple features stored in compressed videos to omit the decoding process for RGB frames and shorten the computation time. Previous methods mostly used multiple networks to process compressed video features and explored the use of lightweight networks without affecting accuracy to reduce the computational complexity further. We have focused on another approach that uses only one network to reduce computational complexity. Our previous study proposed the MussNet model, which consists of independent subnetworks within a single network instead of multiple networks. The subnetworks classify compressed video features independently with a feedforwarding step of a single network and achieved competitive accuracy against previous studies with lower computational complexity. The remaining issue of the MussNet model is howto fuse the independently processed compressed video features. The current MussNet model makes independent predictions from each input and only averages them to fuse the inputs. However, recent studies have shown that intermediate fusion, which fuses features inside the networks, improves accuracy. This study proposes the EFS module that extends the MussNet model into intermediate fusion by disentangling and aggregating the features of the same videos in the hidden vectors while keeping the individual subnetworks. Our experiments show that the EFS module improves the MussNet model’s accuracy by 0.4 points for UCF-101 and 1.0 points for HMDB-51, while the additional GFLOPs are only 1% of the MussNet model. These accuracy scores are also competitive against previous studies while keeping one of the lowest computational complexity.
Several researchers have proposed systems with high recognition rates for sign language recognition. Recently, there has also been an increase in research that uses multiple recognition methods and further fuses their results to improve recognition rates. The most recent of these studies, skeleton aware multi-modal SLR (SAM-SLR), achieved a recognition rate of 98.00% on the RGB video of the Turkish Sign Language dataset AUTSL. We investigated the unrecognized parts of this dataset and found that some signs where the fingers touch parts of the face were not correctly recognized. The proposed method is as follows: First, those with slight differences in top-1 and top-2 evaluation values in the SAM-SLR recognition results are extracted and re-evaluated. Then, we created heatmaps of the coordinates of the index finger in one-handed sign language in the face region of the recognition result in the top-1 to top-3 training data of the candidates based on the face part criteria, respectively. In addition, we extracted four index finger positions from the test data where the index finger stayed longer and obtained the product of the heatmap values of these positions. The highest value among them was used as the result of the re-evaluation. Finally, three evaluation methods were used: the absolute and relative evaluation with two heatmaps and an evaluation method integrating the absolute and relative evaluation results. As a result of applying the proposed method to the SAM-SLR and the previously proposed model, respectively, the best method achieved 98.24% for the highest recognition rate, an improvement of 0.30 points.