• 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.

• The Korean Journal of Physiology
• /
• v.5 no.1
• /
• pp.23-42
• /
• 1971

I. Chemical analysis A study was planned to see if administration of ginseng extract has any influence upon the adrenal, the hepatic, the splenic, and the pancreatic nucleic acid contents of rats, and to estimate the effect of ACTH administration as a substitute for stress reaction upon these nucleic acid contents of rats previously primed with ginseng. Ninety male rats$(body\;weight:\;150{\sim}200gm)$ were divided into the ginseng, the saline, and the normal control groups, which received for 5 days 0.5ml/100 gm body weight of ginseng extract solution (4 mg of ginseng alcohol extract in 1 ml of saline), same amount of saline, or no medication, respectively. On the 5th experimental day, each of the 3 groups was further divided into 2 subgroups yielding the ginseng, the ginseng-ACTIT, the saline, the saline-ACTH, the normal control, and the normal-ACTH subgroups. The ginseng, the saline, and the normal control subgroups were sacrificed 3 hours after the last medication, while the ginseng-ACTH, the saline·ACTH, and the normal-ACTH subgroups received ACTH(0.1 unit/subject) 1 hour after the last medication and were sacrificed after 1 more hour. The adrenal gland, the liver, the spleen and the pancreas of each rat were measured for RNA and DNA contents using the chemical method of Schmidt-Thannhauser-Schneider. Following results were obtained: 1. Adrenal RNA and DNA contents and RNA/DNA ratio were all significantly higher in the ginseng group compared with the values obtained from the normal control and the saline groups. Generally administration of ACTH reduced nucleic acid contents of the viscera examined. However, in the ginseng group the rate of decrease [(value of ginseng-ACTH subgroup-value of ginseng subgroup) x100/value of ginseng subgroup)] in adrenal RNA and DNA contents and in RNA/DNA ratio were more conspicuous than they were in the normal control and the saline groups. 2. Hepatic RNA and DNA contents and RNA/DNA ratio were all significantly less in the ginseng group than in the normal control and the saline groups. After ACTH, the rate of decrease in hepatic RNA, DNA, and RNA/DNA ratio of the ginseng· group was less conspicuous than those of the other 2 groups. 3. With regard to the splenic nucleic acid contents, the RNA and the RNA/DNA values of the ginseng group were higher than those of the normal control group but lower than those of the saline group, while the DNA value of the ginseng group was lower than that of the normal control group but higher than that of the saline group. Following administration of ACTH, the rate of decrease in RNA and DNA contents and in RNA/DNA ratio of the ginseng group was more conspicuous than that of the normal control group but less remarkable than that of the saline group. 4. Pancreatic RNA and DNA contents were notably lower in the ginseng group than in the normal control and the saline groups. However, the RNA/DNA ratio of the ginseng group was higher than that of the normal control and the saline groups.'After ACTH, the rate of decrease in pancreatic RNA and RNA/DNA ratio of the ginseng group was less than that of the normal. control group but more than that of the saline group, while the DNA content was actually increased in the ginseng group though it decreased in the normal control and the saline groups. Although the results are not clear enough for an accurate interpretation, they seem to indicate that ginseng exerts notable influence upon the RNA and DNA contents and the RNA/DNA ratio of the viscera stodied. On the whole the drug tends to increase the RNA and DNA contents and RNA/DNA ratio of the adrenal gland but seems to diminish the values of the other 3 viscera. In the early period following ACTH, ginseng facilitates the fall in RNA and DNA contents and RNA/DNA ratio of the adrenal gland, while it tends to reduce the fall in the values of the other viscera studied. II. Autoradiographic and histochemical analysis It was planned autoradiographically and histochemically to affirm and extend the results obtained in part I with regard to the chemically assessed change in the adrenal, the pancreatic, the hepatic and the splenic DNA and RNA contents under the influence of ginseng and ACTH. Fourty male mice (body weight: $18{\sim}20gm$) and 20 male rats were used. Each animal species was divided into the saline, the ginseng, the saline-ACTH, and the ginseng-ACTH groups according to the administered drugs. In the mice, the adrenal, the pancreatic, the splenic and the hepatic DNA-synthetic activity was assessed autoradiographically after administration of $^3H$-thymidine. In the rats, the RNA content of the above 4 organs was assessed histochemically after staining them with methylgreen pyronine. Following results were obtained: 1. Labeled cells were significantly more numerous in the adrenal cortex, the spleen and the liver of the ginseng group than in those of the saline group, although they were less numerous in the pancreas of the ginseng group than in the pancreas of the saline group. The adrenocortical, the pancreatic, the splenic and the hepatic tissues were stained with methylgreen pyronine more deeply in the ginseng group than in the saline group. 2. The adrenocortical, the pancreatic, the splenic and the hepatic tissues contained labeled cells less numerously in the saline-ACTH and the ginseng-ACTH group than in the saline and the ginseng groups. All these tissues were also stained with methylgreen pyronine less deeply in the saline-ACTH and the ginseng-ACTH groups than in the saline and the ginseng groups. 3. However, the adrenal cortex, the spleen, the pancreas, and the liver contained labeled cells more numerously in the ginseng-ACTH group than in the saline-ACTH group. the 4 tissues were stained with methylgreen pyronine more deeply in the ginseng-ACTH group than in the saline-ACTH group. It is inferred from the above results that though with exception, the ginseng mostly facilitates cellular synthesis of nucleic acids and mitigates reduction in nucleic acid content of tissues after administration of ACTH.