• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• MISULJARYO - National Museum of Korea Art Journal
• /
• v.104
• /
• pp.102-142
• /
• 2023

The Bronze Bell of Wongaksa Temple, also known as the Bosingak Bell, was produced in 1468 during the reign of King Sejo for dedication at Wongaksa Temple in the middle of the capital Hanyang in celebration of the tenth anniversary of his accession to the throne. It is currently heavily damaged and cannot be struck. This paper focuses on the man-made damage inflicted on the Bosingak Bell and explores when, why, and by whom the bell was damaged along with the historical significance of this damage. In the first section, the relevant literature is reviewed and the problems concerned, research perspective, and methodology are presented. The history of related theories is investigated focusing on the relationship between Bosingak Bell and Wongaksa Bell. The perspective that Bosingak Bell and Wongaksa Bell are the same is introduced. My discussion will be developed from this perspective. In the second section, the background to King Sejo's construction of Wongaksa Bell is examined. Specifically, the bells commissioned by the kings of the early Joseon era are divided into court bells (jojong) and Buddhist bells (beomjong). They total four court bells and three Buddhist bells. The former are the Jongnu Tower Bell commissioned by King Taejo, Donhwamun Gate Bell by King Taejong, Gwanghwamun Gate Bell by King Sejong, and Sajeongjeon Hall Bell by King Sejo. The latter are the bells of Yongmunsa, Heungcheonsa (or Jeongneungsa) and Wongaksa Temples, all of which were made during the reign of King Sejo. Sejo also made Wongaksa Bell and gave it the meaning that the monarch and the Buddha both wish to enlighten the people through the sound of the bells. In the third section, traces of the man-made damage done to Bosingak Bell are closely examined. By observing the current condition of Bosingak Bell and comparing it with the contemporaneous Heungcheongsa Bell (1462) and Bongseonsa Bell (1469), the components of Bosingak Bell that were damaged can be identified. The damaged parts are again divided into Buddhist elements and non-Buddhist elements. The former includes the reversed lotus petals on the shoulder band, four standing bodhisattvas, and the inscription of the bell composed by Choe Hang. The latter includes lists of chief supervisors (dojejo). I describe the phenomenon of deliberately damaging Buddhist elements on bells as "effacement of Buddhism," meaning Buddhist images and inscriptions are eliminated, and I note the prevailing rejection of Buddhism theory among Neo-Confucianists as its ideological root. The erasure of non-Buddhist images was probably caused by political conflicts such as Yeonsangun's purge in 1504. Since both ideological and political factors played a role in the changes made to Bosingak Bell, the damage was possibly done between the Purge of 1504 and the abdication of Yeonsangun in 1506. Chapter four traces the transformation of the Buddhist bell of Wongaksa Temple into the Bosingak court bell. Finally completed in 1468, the Wongaksa Bell only served its role as a Buddhist bell at related services for a relatively brief period of 36 years (until 1504). Wongaksa Temple was closed down and the bell lost its Buddhist function. In 1536, it was moved from Wongaksa Temple to Namdaemun Gate, where it remained silent for the next 90 years until it was struck again in November 1594. However, after the destruction of the Jongnu Bell in a fire during the Japanese Invasions of Korea (1592-1598), the Buddhist bell from Wongaksa Temple became a court bell. The Wongaksa Temple bell was relocated to Jongnu Tower in 1619, traveling through Myeongdong Pass. From then on, as the official Jongnu Bell (later renamed Bosingak Bell), it was regularly rung at dawn and dusk every day for nearly 300 years until 1908, when Japanese authorities halted the ritual. The transformation of the Wongaksa Bell (a Buddhist bell) to Bosingak Bell (a court bell) means that the voice of the Buddha was changed to the voice of the king. The concept of "effacement of Buddhism," evident in the transformation of Wongaksa Bell to Bosingak Bell, was practiced widely on almost every manifestation of Buddhism throughout the Joseon period. In short, the damage evident in Bosingak Bell underscores the debuddhismization in Korean society during the Joseon Dynasty.