Recent Advances in General Game Playing.

The goal of General Game Playing (GGP) has been to develop computer programs that can perform well across various game types. It is natural for human game players to transfer knowledge from games they already know how to play to other similar games. GGP research attempts to design systems that work well across different game types, including unknown new games. In this review, we present a survey of recent advances (2011 to 2014) in GGP for both traditional games and video games. It is notable that research on GGP has been expanding into modern video games. Monte-Carlo Tree Search and its enhancements have been the most influential techniques in GGP for both research domains. Additionally, international competitions have become important events that promote and increase GGP research. Recently, a video GGP competition was launched. In this survey, we review recent progress in the most challenging research areas of Artificial Intelligence (AI) related to universal game playing.

Engagnition: A multi-dimensional dataset for engagement recognition of children with autism spectrum disorder.

Engagement plays a key role in improving the cognitive and motor development of children with autism spectrum disorder (ASD). Sensing and recognizing their engagement is crucial before sustaining and improving the engagement. Engaging technologies involving interactive and multi-sensory stimuli have improved engagement and alleviated hyperactive and stereotyped behaviors. However, due to the scarcity of data on engagement recognition for children with ASD, limited access to and small pools of participants, and the prohibitive application requirements such as robots, high cost, and expertise, implementation in real world is challenging. However, serious games have the potential to overcome those drawbacks and are suitable for practical use in the field. This study proposes Engagnition, a dataset for engagement recognition of children with ASD (N = 57) using a serious game, "Defeat the Monster," based on enhancing recognition and classification skills. The dataset consists of physiological and behavioral responses, annotated by experts. For technical validation, we report the distributions of engagement and intervention, and the signal-to-noise ratio of physiological signals.

A Machine Learning-Based Initial Difficulty Level Adjustment Method for Balance Exercise on a Trunk Rehabilitation Robot.

Trunk rehabilitation exercises such as those for remediating core stability can help improve the seated balance of patients with weakness or loss of proprioception caused by diseases such as stroke, and aid the recovery of other functions such as gait. However, there has not yet been any reported method for automatically determining the parameters that define exercise difficulty on a trunk rehabilitation robot (TRR) based on data such as the patient's demographic information, balancing ability, and training sequence, etc. We have proposed a machine learning (ML)-based difficulty adjustment method to determine an appropriate virtual damping gain (Dvirtual) of the controller for the TRR's unstable training mode. Training data for the proposed system is obtained from 37 healthy young adults, and the trained ML model thus obtained is tested through experiments with a separate population of 25 healthy young adults. The leave-one-out cross validation results (37 subjects) from the training group for validation of the designed ML model showed 80.90% average accuracy (R2 score) for using the given information to predict the desired difficulty levels, which are represented by the level of balance performance quantified as Mean Velocity Displacement (MVD) of the center of pressure. Statistical analysis (Repeated measures analysis of variance) of subject performance also showed that ground truth difficulty levels from the training data and predicted difficulty levels did not differ significantly under any of the three exercise modes used in this study (Hard, Medium, and Easy), and the standard deviations were reduced by 16.39, 41.39, and 25.68%, respectively. Moreover, the Planar Deviation (PD) of the center of pressure, which was not the target parameter here, also showed results similar to the MVD, which indicates that the predicted Dvirtual affected the difficulty level of balance performance. Therefore, the proposed ML model-based difficulty adjustment method has potential for use with people who have varied balancing abilities.

Current Status of Amebic Liver Abscess in Korea Comparing with Pyogenic Liver Abscess.

Backgrounds/Aims: With the improvement of hygiene, the incidence of amebic liver abscess is decreasing in South Korea. On the other hand, there is little data on the status of amebic liver abscess compared to pyogenic liver abscess. Methods: Patients with an amebic liver abscess, in whom Entamoeba histolytica (E. histolytica) IgG was positive, were identified retrospectively in a university hospital. The clinical, laboratory, and radiological characteristics of amebic liver abscess were compared with those of pyogenic liver abscess in the same period. Results: Between March 2010 and October 2016, 413 patients with a liver abscess were identified. Among them, the serologic test for E. histolytica was performed in 209 patients. Fifteen (7.2%) were classified as an amebic liver abscess, and the remainder were diagnosed with a pyogenic liver abscess. The age, gender, white blood cell, and CRP was comparable between the two groups. Procalcitonin was lower in amebic liver abscess than the pyogenic one. On CT, peripheral rim enhancement was more frequent, but cluster signs were not observed in amebic liver abscess compared to pyogenic liver abscess. None of the patients with amebic liver abscess died. In contrast, the mortality of pyogenic liver abscess was 4.7%. Conclusions: Amebic liver abscess should still be considered as one of the causes of liver abscess in Korea. It is difficult to discriminate an amebic liver abscess from a pyogenic liver abscess only according to the clinical, laboratory, and radiologic findings. Therefore, it is necessary to perform a serologic test for E. histolytica for a precise evaluation of liver abscess in a high-risk group.

[Intussusception Caused by Colon Cancer in Pregnancy].

Intussusception is a common in pediatric age group. But it is rare in adults. And intussusception caused by tumor account for 1% of bowel obstructions in adult. Intussusception is an extremely rare cause of abdominal pain in pregnancy. In particular, cases of Intussusception due to colorectal cancer during pregnancy have never been reported in Korea. Our patient is a 34 years old woman who presented at 14 weeks of her second pregnancy. She presented with right lower abdominal discomfort and intermittent palpable mass which was usually spontaneously resolved. In the MRI study, pathologic asymmetric wall thickening was still noted and ileocolic intussusception was noted, and in colonoscopy, there was ulcerofungating mass around ileocecal valve which may be a leading point of intussusception. Biopsy was done. Pathologic finding was poorly differentiated adenocarcinoma. Under the patient agreement, we performed dilatation and curettage and laparoscopic right hemicolectomy and lymph node dissection. Now she is receiving a FOLFOX chemotherapy.

Active Player Modeling in the Iterated Prisoner's Dilemma.

The iterated prisoner's dilemma (IPD) is well known within the domain of game theory. Although it is relatively simple, it can also elucidate important problems related to cooperation and trust. Generally, players can predict their opponents' actions when they are able to build a precise model of their behavior based on their game playing experience. However, it is difficult to make such predictions based on a limited number of games. The creation of a precise model requires the use of not only an appropriate learning algorithm and framework but also a good dataset. Active learning approaches have recently been introduced to machine learning communities. The approach can usually produce informative datasets with relatively little effort. Therefore, we have proposed an active modeling technique to predict the behavior of IPD players. The proposed method can model the opponent player's behavior while taking advantage of interactive game environments. This experiment used twelve representative types of players as opponents, and an observer used an active modeling algorithm to model these opponents. This observer actively collected data and modeled the opponent's behavior online. Most of our data showed that the observer was able to build, through direct actions, a more accurate model of an opponent's behavior than when the data were collected through random actions.

Well-Tolerated and Undiscovered Common Atrium until Late Adulthood.

Common atrium is a rare congenital heart disease characterized by complete absence of the interatrial septum, and is commonly accompanied by malformation of the atrioventricular valve. Most patients with common atrium experience symptoms during childhood. Here, we describe a patient with common atrium who experienced his first obvious symptom at 48 years of age.

Inference of other's internal neural models from active observation.

Recently, there have been several attempts to replicate theory of mind, which explains how humans infer the mental states of other people using multiple sensory input, with artificial systems. One example of this is a robot that observes the behavior of other artificial systems and infers their internal models, mapping sensory inputs to the actuator's control signals. In this paper, we present the internal model as an artificial neural network, similar to biological systems. During inference, an observer can use an active incremental learning algorithm to guess an actor's internal neural model. This could significantly reduce the effort needed to guess other people's internal models. We apply an algorithm to the actor-observer robot scenarios with/without prior knowledge of the internal models. To validate our approach, we use a physics-based simulator with virtual robots. A series of experiments reveal that the observer robot can construct an "other's self-model", validating the possibility that a neural-based approach can be used as a platform for learning cognitive functions.

Amplitude death of coupled hair bundles with stochastic channel noise.

Hair cells conduct auditory transduction in vertebrates. In lower vertebrates such as frogs and turtles, due to the active mechanism in hair cells, hair bundles (stereocilia) can be spontaneously oscillating or quiescent. Recently an amplitude death phenomenon has been proposed [K.-H. Ahn, J. R. Soc. Interface, 10, 20130525 (2013)] as a mechanism for auditory transduction in frog hair-cell bundles, where sudden cessation of the oscillations arises due to the coupling between nonidentical hair bundles. The gating of the ion channel is intrinsically stochastic due to the stochastic nature of the configuration change of the channel. The strength of the noise due to the channel gating can be comparable to the thermal Brownian noise of hair bundles. Thus, we perform stochastic simulations of the elastically coupled hair bundles. In spite of stray noisy fluctuations due to its stochastic dynamics, our simulation shows the transition from collective oscillation to amplitude death as interbundle coupling strength increases. In its stochastic dynamics, the formation of the amplitude death state of coupled hair bundles can be seen as a sudden suppression of the displacement fluctuation of the hair bundles as the coupling strength increases. The enhancement of the signal-to-noise ratio through the amplitude death phenomenon is clearly seen in the stochastic dynamics. Our numerical results demonstrate that the multiple number of transduction channels per hair bundle is an important factor to the amplitude death phenomenon, because the phenomenon may disappear for a small number of transduction channels due to strong gating noise.

A comprehensive overview of the applications of artificial life.

We review the applications of artificial life (ALife), the creation of synthetic life on computers to study, simulate, and understand living systems. The definition and features of ALife are shown by application studies. ALife application fields treated include robot control, robot manufacturing, practical robots, computer graphics, natural phenomenon modeling, entertainment, games, music, economics, Internet, information processing, industrial design, simulation software, electronics, security, data mining, and telecommunications. In order to show the status of ALife application research, this review primarily features a survey of about 180 ALife application articles rather than a selected representation of a few articles. Evolutionary computation is the most popular method for designing such applications, but recently swarm intelligence, artificial immune network, and agent-based modeling have also produced results. Applications were initially restricted to the robotics and computer graphics, but presently, many different applications in engineering areas are of interest.