• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• The Korean Journal of Physiology
• /
• v.1 no.1
• /
• pp.103-120
• /
• 1967

As pointed out by many previous investigators, the cardio-pulmonary system of well trained athletes is so adapted that they can perform a given physical exercise more efficiently as compared to non-trained persons. However, the time course of the development of these cardio-pulmonary adaptations has not been extensively studied in the past. Although the development of these training effects is undoubtedly related to the magnitude of an exercise load which is repeatedly given, it would be practical if one could maintain a good physical fitness with a minimal daily exercise. Hence, the present investigation was undertaken to study the time course of the development of cardio-pulmonary adaptations while a group of non-athletes was subjected to a daily 6 to 10 minutes running exercise for a period of 4 weeks. Six healthy male medical students (22 to 24 years old) were randomly selected as experimental subjects, and were equally divided into two groups (A and B). Both groups were subjected to the same daily running exercise (approximately 1,000 kg-m). 6 days a week for 4 weeks, but the rate of exercise was such that the group A ran on treadmill with 8.6% grade for 10 min daily at a speed of 127 m/min while the group B ran for 6 min at a speed of 200 m/min. In order to assess the effects of these physical trainings on the cardio-pulmonary system, the minute volume, the $O_2$ consumption, the $CO_2$ output and the heart rate were determined weekly while the subject was engaged in a given running exercise on treadmill (8.6% grade and 127 m/min) for a period of 5 min. In addition, the arterial blood pressure, the cardiac output, the acid-base state of arterial blood and the gas composition of arterial blood were also determined every other week in 4 subjects (2 from each group) while they were engaged in exercise on a bicycle ergometer at a rate of approximately 900 kg m/min until exhaustion. The maximal work capacity was also determined by asking the subject to engage in exercise on treadmill and ergometer until exhaustion. For the measurement of minute volume, the expired gas was collected in a Douglas bag. The $O_2$ consumption and the $CO_2$ output were subsequently computed by analysing the expired gas with a Scholander micro gas analyzer. The heart rate was calculated from the R-R interval of ECG tracings recorded by an Offner RS Dynograph. A 19 gauge Cournand needle was inserted into a brachial artery, through which arterial blood samples were taken. A Statham $P_{23}AA$ pressure transducer and a PR-7 Research Recorder were used for recording instantaneous arterial pressure. The cardiac output was measured by indicator (Cardiogreen) dilution method. The results may be summarized as follows: (1) The maximal running time on treadmill increased linearly during the 4 week training period at the end of which it increased by 2.8 to 4.6 times. In general, an increase in the maximal running time was greater when the speed was fixed at a level at which the subject was trained. The mammal exercise time on bicycle ergometer also increased linearly during the training period. (2) In carrying out a given running exercise on treadmill (8.6%grade, 127 m/min), the following changes in cardio·pulmonary functions were observed during the training period: (a) The minute volume as well as the $O_2$ consumption during steady state exercise tended to decrease progressively and showed significant reductions after 3 weeks of training. (b) The $CO_2$ production during steady state exercise showed a significant reduction within 1 week of training. (c) The heart rate during steady state exercise tended to decrease progressively and showed a significant reduction after 2 weeks of training. The reduction of heart rate following a given exercise tended to become faster by training and showed a significant change after 3 weeks. Although the resting heart rate also tended to decrease by training, no significant change was observed. (3) In rallying out a given exercise (900 kg-m/min) on a bicycle ergometer, the following change in cardio-vascular functions were observed during the training period: (3) The systolic blood pressure during steady state exercise was not affected while the diastolic blood Pressure was significantly lowered after 4 weeks of training. The resting diastolic pressure was also significantly lowered by the end of 4 weeks. (b) The cardiac output and the stroke volume during steady state exercise increased maximally within 2 weeks of training. However, the resting cardiac output was not altered while the resting stroke volume tended to increase somewhat by training. (c) The total peripheral resistance during steady state exercise was greatly lowered within 2 weeks of training. The mean circulation time during exorcise was also considerably shortened while the left heart work output during exercise increased significantly within 2 weeks. However, these functions_at rest were not altered by training. (d) Although both pH, $P_{co2}\;and\;(HCO_3-)$ of arterial plasma decreased during exercise, the magnitude of reductions became less by training. On the other hand, the $O_2$ content of arterial blood decreased during exercise before training while it tended to increase slightly after training. There was no significant alteration in these values at rest. These results indicate that cardio-pulmonary adaptations to physical training can be acquired by subjecting non-athletes to brief daily exercise routine for certain period of time. Although the time of appearance of various adaptive phenomena is not identical, it may be stated that one has to engage in daily exercise routine for at least 2 weeks for the development of significant adaptive changes.

• 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 Broadcast Engineering
• /
• v.5 no.2
• /
• pp.247-259
• /
• 2000

This paper introduces a new technique that reduces the search times and Improves the accuracy of motion estimation using high temporal and spatial correlation of motion vector. Instead of using the fixed first search Point of previously proposed search algorithms, the proposed method finds more accurate first search point as to compensating searching area using high temporal and spatial correlation of motion vector. Therefore, the main idea of proposed method is to find first search point to improve the performance of motion estimation and reduce the search times. The proposed method utilizes the direction of the same coordinate block of the previous frame compared with a block of the current frame to use temporal correlation and the direction of the adjacent blocks of the current frame to use spatial correlation. Based on these directions, we compute the first search point. We search the motion vector in the middle of computed first search point with two fixed search patterns. Using that idea, an efficient adaptive predicted direction search algorithm (APDSA) for block matching motion estimation is proposed. In the experimental results show that the PSNR values are improved up to the 3.6dB as depend on the Image sequences and advanced about 1.7dB on an average. The results of the comparison show that the performance of the proposed APDSA algorithm is better than those of other fast search algorithms whether the image sequence contains fast or slow motion, and is similar to the performance of the FS (Full Search) algorithm. Simulation results also show that the performance of the APDSA scheme gives better subjective picture quality than the other fast search algorithms and is closer to that of the FS algorithm.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.62 no.2
• /
• pp.124-133
• /
• 2017

This experiment was conducted to evaluate the effects of high temperature on the stem, leaf and grain of barley during the ripening period and to provide information for the development of high-temperature cultivation techniques and adaptive varieties. We used an artificial climate control facility, to provide a temperature $3^{\circ}C$ higher than the normal average temperature during the ripening stage. Although the maximum rate of starch synthesis was increased at high temperature by approximately 11%, the starch content was decreased, because the period of starch synthesis ended 4 days earlier. As in the case of starch synthesis, the expression of genes related to starch synthesis was increased at the early ripening stage in the high temperature treatment, however, the duration of expression tended to decrease rapidly. Furthermore, the partitioning rate of assimilation products in the panicle increased to a greater extent in the high temperature treatment than in the control. In contrast, for the stem and leaf, the partitioning rate of assimilation products decreased more rapidly in the high temperature treatment than in the control. On the basis of these results, it can be considered that the translocation rate of assimilation products increased to a greater extent in the high temperature treatment than in the control at the early ripening stage. These results indicate that the decrease in grain weight at high temperature during the ripening stage is attributable to an increase in the speed of starch synthesis at high temperature, but the increase in ripening speed does not compensate for the shortening of the ripening period. Finally to develop varieties and cultivation techniques suited to high temperature, we need to focus on physiological characteristics related to the duration of starch synthesis.