• 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 Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.111-126
• /
• 2017

Recommender systems based on association rule mining significantly contribute to seller's sales by reducing consumers' time to search for products that they want. Recommendations based on the frequency of transactions such as orders can effectively screen out the products that are statistically marketable among multiple products. A product with a high possibility of sales, however, can be omitted from the recommendation if it records insufficient number of transactions at the beginning of the sale. Products missing from the associated recommendations may lose the chance of exposure to consumers, which leads to a decline in the number of transactions. In turn, diminished transactions may create a vicious circle of lost opportunity to be recommended. Thus, initial sales are likely to remain stagnant for a certain period of time. Products that are susceptible to fashion or seasonality, such as clothing, may be greatly affected. This study was aimed at expanding association rules to include into the list of recommendations those products whose initial trading frequency of transactions is low despite the possibility of high sales. The particular purpose is to predict the strength of the direct connection of two unconnected items through the properties of the paths located between them. An association between two items revealed in transactions can be interpreted as the interaction between them, which can be expressed as a link in a social network whose nodes are items. The first step calculates the centralities of the nodes in the middle of the paths that indirectly connect the two nodes without direct connection. The next step identifies the number of the paths and the shortest among them. These extracts are used as independent variables in the regression analysis to predict future connection strength between the nodes. The strength of the connection between the two nodes of the model, which is defined by the number of nodes between the two nodes, is measured after a certain period of time. The regression analysis results confirm that the number of paths between the two products, the distance of the shortest path, and the number of neighboring items connected to the products are significantly related to their potential strength. This study used actual order transaction data collected for three months from February to April in 2016 from an online commerce company. To reduce the complexity of analytics as the scale of the network grows, the analysis was performed only on miscellaneous goods. Two consecutively purchased items were chosen from each customer's transactions to obtain a pair of antecedent and consequent, which secures a link needed for constituting a social network. The direction of the link was determined in the order in which the goods were purchased. Except for the last ten days of the data collection period, the social network of associated items was built for the extraction of independent variables. The model predicts the number of links to be connected in the next ten days from the explanatory variables. Of the 5,711 previously unconnected links, 611 were newly connected for the last ten days. Through experiments, the proposed model demonstrated excellent predictions. Of the 571 links that the proposed model predicts, 269 were confirmed to have been connected. This is 4.4 times more than the average of 61, which can be found without any prediction model. This study is expected to be useful regarding industries whose new products launch quickly with short life cycles, since their exposure time is critical. Also, it can be used to detect diseases that are rarely found in the early stages of medical treatment because of the low incidence of outbreaks. Since the complexity of the social networking analysis is sensitive to the number of nodes and links that make up the network, this study was conducted in a particular category of miscellaneous goods. Future research should consider that this condition may limit the opportunity to detect unexpected associations between products belonging to different categories of classification.

• Clinical and Experimental Pediatrics
• /
• v.52 no.4
• /
• pp.481-487
• /
• 2009

Purpose : This study investigated the clinical course and prognostic factor of very low birth weight infants (VLBWI) with hemodynamically significant congenital heart defects (CHDs). Methods : Medical records of 1,098 VLBWI with birth weight <1,500 g who had been admitted to the neonatal intensive care unit of Samsung Medical Center from October 1994 to December 2007 were reviewed retrospectively. The data for these patients with hemodynamically significant CHD (n=33) were compared with those without CHD (n=1,065). Results : The incidence of CHD was 3.0% (33 patients) 7 patients (21%) had CHD combined with the congenital abnormalities or chromosomal disorders. The most common CHD was a ventricular septal defect. The incidence of intrauterine growth retardation was higher in patients with CHD than in patients without CHD (34% vs. 20%), but there were no significant differences in gestational age, birth weight, respiratory distress syndrome, bronchopulmonary dysplasia, necrotizing enterocolitis, severe intraventricular hemorrhage (${\geq}$Gr III), and periventricular leukomalacia. Cardiac surgery was performed on 13 patients (39%). Nine patients received staged operations, and 10 patients received early intervention. The overall mortality in patients who had CHD was higher than in the patients who did not have CHD (27% vs. 16%). In patients with CHD, congenital abnormalities or chromosomal disorders were more important factors for increased mortality (86% vs. 11%) than the degree of complexity of CHD (19% vs. 42%). Conclusion : The most important prognostic factors of VLBWI with CHD are the associated congenital abnormalities or chromosomal disorders.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.6
• /
• pp.3-14
• /
• 2016

Recently, researches for new waveforms have been carried in order to satisfy KPI for 5G mobile communication system. UFMC and FBMC are well known as ways to reduce OOB power. In this paper, we analyze spectrum of OFDM, UFMC, and FBMC system under nonlinear HPA environment. And then we evaluate and analyze performance of these systems under the same environment. As simulation results, OOB power of OFDM, UFMC, and FBMC increases with HPA nonlinearity increasement. Especially, OOB power of FBMC is the largest increase due to HPA nonlinearity. Also, BER performance of these systems is degraded by increasement of HPA nonlinearity. Therefore, In this paper, we can confirm that a system with low-complexity and high-speed processing is advantageous, because BER performance and OOB power characteristic of these systems are degraded to similar level, when these systems are implemented in real world.

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.10
• /
• pp.1388-1393
• /
• 2015

Genetic parameters of Berkshire pigs for reproduction, carcass and meat quality traits were estimated using the records from a breeding farm in Korea. For reproduction traits, 2,457 records of the total number of piglets born (TNB) and the number of piglets born alive (NBA) from 781 sows and 53 sires were used. For two carcass traits which are carcass weight (CW) and backfat thickness (BF) and for 10 meat quality traits which are pH value after 45 minutes (pH45m), pH value after 24 hours (pH24h), lightness in meat color (LMC), redness in meat color (RMC), yellowness in meat color (YMC), moisture holding capacity (MHC), drip loss (DL), cooking loss (CL), fat content (FC), and shear force value (SH), 1,942 pig records were used to estimate genetic parameters. The genetic parameters for each trait were estimated using VCE program with animal model. Heritability estimates for reproduction traits TNB and NBA were 0.07 and 0.06, respectively, for carcass traits CW and BF were 0.37 and 0.57, respectively and for meat traits pH45m, pH24h, LMC, RMC, YMC, MHC, DL, CL, FC, and SH were 0.48, 0.15, 0.19, 0.36, 0.28, 0.21, 0.33, 0.45, 0.43, and 0.39, respectively. The estimate for genetic correlation coefficient between CW and BF was 0.27. The Genetic correlation between pH24h and meat color traits were in the range of -0.51 to -0.33 and between pH24h and DL and SH were -0.41 and -0.32, respectively. The estimates for genetic correlation coefficients between reproductive and meat quality traits were very low or zero. However, the estimates for genetic correlation coefficients between reproductive traits and drip and cooking loss were in the range of 0.12 to 0.17 and -0.14 to -0.12, respectively. As the estimated heritability of meat quality traits showed medium to high heritability, these traits may be applicable for the genetic improvement by continuous measurement. However, since some of the meat quality traits showed negative genetic correlations with carcass traits, an appropriate breeding scheme is required that carefully considers the complexity of genetic parameters and applicability of data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.2
• /
• pp.129-137
• /
• 2001

Matching pursuit algorithm was successfully demonstrated useful in low bit-rate video coding, However, one of the practical concerns related to applying the matching pursuit algorithm to application is its massive computation required for finding bases whose weighted sum best approximates the given input image. The main contribution of this paper is that we provide a new method that can drastically reduce the computational load without any degradation of image quality. Its main idea is based on reducing the number of inner product calculation required for finding best bases because the complexity of matching pursuit algorithm is due to the exhaustive local inner product calculation. As the first step, we compute a matrix which is the 1-D inner product of the given motion-compensated error input image with the 1-D vertical Gabor functions using the separable property of Gabor bases. In the second step, we calculate length of each vector in the matrix that corresponds to 1-D horizontal Gabor function, and compare the length with the current maximum absolute inner product value so far. According to the result of this comparison, one can decide whether or not to calculate the inner product. Since most of them do not need to calculate the inner product value, one can significantly reduce the computational load. Experimental results show that proposed method reduces about 70% of inner product calculation compared to the Neff's fast algorithm without any degradation of image quality.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.5
• /
• pp.1325-1341
• /
• 1998

A conventional CBR channel is now capable of delivering several digitally compressed video programs due to recent advances in video compression, such as MPEG-2, and digital transmission technology. This paper presents a joint video coding scheme that is to maintain a constant sum of bit rates for all the programs but to allow the variable bit rate for individual program in the transimission environment mentioned above. Thus advantages of VBR video compression can be obtained. This paper contributes in two aspects. First, a rate-distortion estimation method for MPEG-2 video is proposed, which enavle us predict the amount of bits and the distortion generated from an encoded picture at a given quantization step size and vice versa. The most attractive features of the proposed rate-distortion estimation method are its accuracy and a computational complexity low enough to be applied to real-time video coding applications. Second, this paper presents an efficient and accurate joint rate control scheme using the rate-distortion estimation results and verifies its performance with experiments. The experimental results show that our coding scheme gives a significant gain even though a small number of video programs are coded jointly. For example, a stable picture quality is maintained among the video programs as well as within a program, and additional extra programs can be transmitted over the same channel bandwidth if the proposed joint video coding scheme is used.

• Health Policy and Management
• /
• v.5 no.2
• /
• pp.35-69
• /
• 1995

The managerial environment of hospitals in Korea characterized by low levels of medical insurance fees is worsening by increasing government regulations as to the utilization of medical services, rising costs of labor, material, and medical equipments, growing patient expectations concerning the quality of services, and escalating competitions among large hospitals in the market. Hospitals should seek for their survival strategies in this harsh environment and they should have information about costs of their products in doing so. However, it has not been available due to the complexity of the production process of hospital services. The objectives of this study were to develop a service-based cost accounting model and to apply the developed model to a study hospital to obtain cost information of hospital services. A model commonly used for the job-order product cost accounting in the manufacturing industry was modified for the use in hospitals in Korea. Actual costs, instead of standard costs, incurred to produce a unit of services during a given period of time were estimated in the model. Data required to implement the model included financial information, statistics for the allocation of supportive cost center costs to final cost centers, statistics for the allocation of final cost center costs to services, and the volume of each services charged to patients during a study period. The model was executed using data of a university teaching hospital located in Seoul for the fiscal year 1992. Data for financial information, allocation statistics fo supportive service costs, and the volume of services, most of them in electronic form, were available to the study. Data for allocation statistics of final cost center costs were collected in the study. There were 15 types of evaluation and management service, 2, 923 types of technical service, and 2, 608 types of drug and material service charged to patients in the study hospital during the fiscal year 1992. Labor costs of each of seven types of pesonnel, material costs of 611 types of drugs and materials, and depreciation costs of 212 types of medical equipments, miscellaneous costs, and indirect costs incurred in producing a unit of each services were estimated. Medical insurance fees for basic services such as evaluation and management of inpatients and outpatients, injection, and filling prescriptions, and for operating procedures were found to be set lower than costs. Infrequent services which use expensive medical equipments showed negative revenuse as well. On the other hand, fees for services not covered by the insurance such as CT, MRI and Sonogram, and for laboratory tests were higher than costs. This study has a significance in making it possible for a hospital to obtain cost information for all types of services which produced income based on all types of expenses incurred during a given period of time. This information can assist the management of a hospital in finding an effective cost reduction strategy, an efficient service-mix strategy under a given fee structure, and an optimum strategy for within-hospital resource allocations.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.630-637
• /
• 2018

Harmony search (HS) is a recently developed metaheuristic optimization algorithm. HS is inspired by the process of musical improvisation and repeatedly searches for the optimal solution using three operations: random selection, memory recall (or harmony memory consideration), and pitch adjustment. HS has been applied by many researchers in various fields. The increasing complexity of real-world optimization problems has created enormous challenges for the current technique, and improved techniques of optimization algorithms and HS are required. We propose an improved clustering harmony search (ICHS) that uses a clustering technique to group solutions in harmony memory based on their objective function values. The proposed ICHS performs modified harmony memory consideration in which decision variables of solutions in a high-ranked cluster have higher probability of being selected than those in a low-ranked cluster. The ICHS is demonstrated in various optimization problems, including mathematical benchmark functions and water distribution system pipe design problems. The results show that the proposed ICHS outperforms other improved versions of HS.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.12 no.4
• /
• pp.315-334
• /
• 2014

Wolsong Low- and Intermediate-level radioactive waste (LILW) disposal center has two different types of disposal facilities and interacts with the neighboring Wolsong nuclear power plant. These situations impose a high level of complexity which requires in-depth understanding of phenomena in the safety assessment of the disposal facility. In this context, multidimensional radionuclide transport model and hydraulic performance assessment model should be developed to identify more realistic performance of the complex system and reduce unnecessary conservatism in the conventional performance assessment models developed for the $1^{st}$ stage underground disposal. In addition, the advanced performance assessment model is required to calculate many cases to treat uncertainties or study parameter importance. To fulfill the requirements, this study introduces the development of two-dimensional integrated near-field performance assessment model combining near-field hydraulic performance assessment model and radionuclide transport model for the $2^{nd}$ stage near-surface disposal. The hydraulic and radionuclide transport behaviors were evaluated by PORFLOW and GoldSim. GoldSim radionuclide transport model was verified through benchmark calculations with PORFLOW radionuclide transport model. GoldSim model was shown to be computationally efficient and provided the better understanding of the radionuclide transport behavior than conventional model.