• 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.

• Journal of Korean Society for Atmospheric Environment
• /
• v.34 no.1
• /
• pp.16-37
• /
• 2018

In this study, difference in chemical composition of $PM_{2.5}$ observed between the year 2013 and 2015 at six air quality intensive monitoring stations (Bangryenogdo (BR), Seoul (SL), Daejeon (DJ), Gwangju (GJ), Ulsan (US), and Jeju (JJ)) was investigated and the possible factors causing their difference were also discussed. $PM_{2.5}$, organic and elemental carbon (OC and EC), and water-soluble ionic species concentrations were observed on a hourly basis in the six stations. The difference in chemical composition by regions was examined based on emissions of gaseous criteria pollutants (CO, $SO_2$, and $NO_2$), meteorological parameters (wind speed, temperature, and relative humidity), and origins and transport pathways of air masses. For the years 2013 and 2014, annual average $PM_{2.5}$ was in the order of SL ($${\sim_=}DJ$$)>GJ>BR>US>JJ, but the highest concentration in 2015 was found at DJ, following by GJ ($${\sim_=}SJ$$)>BR>US>JJ. Similar patterns were found in $SO{_4}^{2-}$, $NO_3{^-}$, and $NH_4{^+}$. Lower $PM_{2.5}$ at SL than at DJ and GJ was resulted from low concentrations of secondary ionic species. Annual average concentrations of OC and EC by regions had no big difference among the years, but their patterns were distinct from the $PM_{2.5}$, $SO{_4}^{2-}$, $NO_3{^-}$, and $NH_4{^+}$ concentrations by regions. 4-day air mass backward trajectory calculations indicated that in the event of daily average $PM_{2.5}$ exceeding the monthly average values, >70% of the air masses reaching the all stations were coming from northeastern Chinese polluted regions, indicating the long-range transportation (LTP) was an important contributor to $PM_{2.5}$ and its chemical composition at the stations. Lower concentrations of secondary ionic species and $PM_{2.5}$ at SL in 2015 than those at DJ and GJ sites were due to the decrease in impact by LTP from polluted Chinese regions, rather than the difference in local emissions of criteria gas pollutants ($SO_2$, $NO_2$, and $NH_3$) among the SL, DJ, and GJ sites. The difference in annual average $SO{_4}^{2-}$ by regions was resulted from combination of the difference in local $SO_2$ emissions and chemical conversion of $SO_2$ to $SO{_4}^{2-}$, and LTP from China. However, the $SO{_4}^{2-}$ at the sites were more influenced by LTP than the formation by chemical transformation of locally emitted $SO_2$. The $NO_3{^-}$ increase was closely associated with the increase in local emissions of nitrogen oxides at four urban sites except for the BR and JJ, as well as the LTP with a small contribution. Among the meterological parameters (wind speed, temperature, and relative humidity), the ambient temperature was most important factor to control the variation of $PM_{2.5}$ and its major chemical components concentrations. In other words, as the average temperature increases, the $PM_{2.5}$, OC, EC, and $NO_3{^-}$ concentrations showed a decreasing tendency, especially with a prominent feature in $NO_3{^-}$. Results from a case study that examined the $PM_{2.5}$ and its major chemical data observed between February 19 and March 2, 2014 at the all stations suggest that ambient $SO{_4}^{2-}$ and $NO_3{^-}$ concentrations are not necessarily proportional to the concentrations of their precursor emissions because the rates at which they form and their gas/particle partitioning may be controlled by factors (e.g., long range transportation) other than the concentration of the precursor gases.