Predictive Clustering-based Collaborative Filtering Technique for Performance-Stability of Recommendation System (추천 시스템의 성능 안정성을 위한 예측적 군집화 기반 협업 필터링 기법)
-
- 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.
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
One of the most common feelings in everyday life is anger. Anger plays an important role in activating emotional energy and increasing intolerance when confronted with hardships, frustration and improper treatments. And it provides us with controlling interpersonal behavior, organizing internal, physiological, psychological process and various adaptive functions. If anger is not properly expressed, it brings about offensive attitude, leading to not only physical impairment but also anxiety in interpersonal relations and maladaptive to everyday life. For elementary school students, frequent quarrels, abusive words and defiant attitude toward adults are also caused by students' anger. Therefore, students' anger is one of the most difficult problems to be dealt with not only psychologically but also in elementary schools. In this respect, after investigating frequently experienced anger- inducing situations and inventing anger-inducing situation questionnaire, we postulated specific situations changing irrational belief into rational one. Based on these situations, we accounted for how to cope with anger inducing factors and change irrational belief into rational one, introducing several strategies needed to control anger, invented cognitive behavioral anger control program and tried to clarify the relationship between anger inducing experience and anger regulation ability. In order to derive usual anger-inducing situations, we made 180 students with fifth and sixth grade to record the reason why he/she got angry, mood, thought, behavior and result. Through this process, we could derive 47 situations bringing about anger and prepared anger-inducing situation questionnaire. It can be divided into 3 anger inducing situations by using factor analysis into 500 elementary students of fifth and sixth grade. Cognitive behavioral anger control program used in this study consists of 13 sessions. From first to fifth session, it is composed of 10 anger control methods to make students be aware of and control their anger. From sixth through thirteenth session, the relationship between irrational belief and anger inducing is introduced is focused on how irrational belief is changed into rational one. To examine the effects of the program, high anger students and the students lacking anger control are selected. Thirty students through pre-test using anger-inducing questionnaire and anger control ability questionnaire are taught the goals and procedures. Volunteer students and students with parents' consent allocated to experimental group (12 students) and the rest of the students are control group (12 students). Cognitive Behavioral Anger Control Program are applied every 50 minutes twice a week for 7 weeks and 4 weeks before and after this program, anger-inducing situation questionnaire and anger control ability questionnaire are practiced. Data collected in this study analyzed by SPSS and Kwakstat. In the middle of this program, quarterly reports and satisfaction measuratings were evaluated to examine whether there is verbal and non-verbal behavior change and students feel satisfied with the program. The results of this study are as follows: First, Cognitive-behavioral anger control program used in this study effectively reduced anger experience and lasted for 4 weeks. Second, cognitive behavioral anger control program increased students' ability to control anger inducing situations and also effective for 4 weeks. And its effect on verbal and non-verbal behaviour was very impressive Students come to realize that irrational belief is the cause of their anger and actively apply cognitive-behavioral anger control technique to themselves as well. Students became improved in their peer relations and felt confident in everyday life. The overall evaluation of this program can be listed as follows; "very satisfactory (91.67%)", "satisfactory (8.33%)", "very helpful (91.67%)", "helpful (8.33%). In this study we first investigated several anger-inducing situations and invented anger-inducing situation questionnaire and then applied cognitive behavioral anger control program in order to control their. anger and not to experience it. By creating workbooks and manuals this method can easily be used in school education settings.
In this paper, we propose a GNSS-based RF receiver, A high precision localization architecture, and a high sensitivity localization architecture in order to solve the satellite navigation system's problem mentioned above. The GNSS-based RF receiver model should have the structure to simultaneously receive both the conventional GPS and navigation information data of future-usable Galileo. As a result, it is constructed as the multi-band which can receive at the same time Ll band (1575.42MHz) of GPS and El band (1575.42MHz), E5A band (1207.1MHz), and E4B band (1176.45MHz) of Galileo This high precision localization architecture proposes a delay lock loop with the structure of Early_early code, Early_late code, Prompt code, Late_early code, and Late_late code other than Early code, Prompt code, and Late code which a previous delay lock loop structure has. As we suggest the delay lock loop structure of 1/4chips spacing, we successfully deal with the synchronization problem with the C/A code derived from inaccuracy of the signal received from the satellite navigation system. The synchronization problem with the C/A code causes an acquisition delay time problem of the vehicle navigation system and leads to performance reduction of the receiver. In addition, as this high sensitivity localization architecture is designed as an asymmetry structure using 20 correlators, maximizes reception amplification factor, and minimizes noise, it improves a reception rate. Satellite navigation system repeatedly transmits the same C/A code 20 times. Consequently, we propose a structure which can use all of the same C/A code. Since this has an adaptive structure and can limit(offer) the number of the correlator according to the nearby environment, it can reduce unnecessary delay time of the system. With the use of this structure, we can lower the acquisition delay time and guarantee the continuity of tracking.
In recent years dry direct-seeding of rice has been encouraged by the government and increasingly practiced by farmers in Korea. This has been bringing up an increased occurrence of weedy rites. Some farmers in the southern region dare to sow the rice before winter after harvest, while most farmers wish to sow as early as possible in the spring to secure the growing period, and to disperse the intensive labor in early May. The purpose of this study was to determine the feasibility of moving the sowing of rice to an earlier date under dry direct-seeding, and to elucidate the nature of emergence of an old strain of rice, weedy rites, and barnyardgrasses tinder this farming practice and their adaptive competence over present cultivate. The presently recommended rice cultivar, Dongjinbyo and an old rice strain, Dadajo which prevailed in early 1900s, almost could not emerge from soil deeper than 6cm and could emerge to only 5.3% at best from 1cm deep loamy soil field when the seeds were sown on Nov. 28. However, two strains of weedy rites being weedy for over 200 years emerged by 17.0 to 63.0% from the loamy and sandy clay loam field 1 to 6cm deep. Emergence of the weedy rites was greater in the loamy soil and at a shallow depth, and negligible from the soil depth of 9cm. Barnyardgrasses sown on Nov. 28 emerged by 13.4 to 51 % from the 1 to 3cm deep loamy soil, and 8.6 to 46.7% from the 1cm deep sandy clay loam. Echinochloa crus-galli var. crus-galli emerged more than var. praticola, and var. oryzicola least. Most of the non-emerged barnyardgrasses seem to have entered secondary dormancy. Seeding rice a month earlier than the season lowered the emergence of Dongjinbyo by ca. 10, 18, and 26%, respectively at 1, 3, and 6cm soil depths, indicating that moving the seeding date a month earlier is impractical. The old strain, Dadajo sown in the soil at a depth of 6cm responded similarly. However, the strain has shown a significantly higher ability in emergence from 9cm deep soil. Weedy rices sown a month earlier A month earlier sown weedy rices have shown very similar emergence rates at various soil depths to those sown on May 1. Barnyardgrasses have also shown similar emergence rates when sown between April 3 and May 1. Like barnyardgrasses, the old strain and weedy rices apparantly posessed a greater adaptability to emerge under lower temperatures, and from deeper soil ; Dongjinbyo
The wall shear stress in the vicinity of end-to end anastomoses under steady flow conditions was measured using a flush-mounted hot-film anemometer(FMHFA) probe. The experimental measurements were in good agreement with numerical results except in flow with low Reynolds numbers. The wall shear stress increased proximal to the anastomosis in flow from the Penrose tubing (simulating an artery) to the PTFE: graft. In flow from the PTFE graft to the Penrose tubing, low wall shear stress was observed distal to the anastomosis. Abnormal distributions of wall shear stress in the vicinity of the anastomosis, resulting from the compliance mismatch between the graft and the host artery, might be an important factor of ANFH formation and the graft failure. The present study suggests a correlation between regions of the low wall shear stress and the development of anastomotic neointimal fibrous hyperplasia(ANPH) in end-to-end anastomoses. 30523 T00401030523 ^x Air pressure decay(APD) rate and ultrafiltration rate(UFR) tests were performed on new and saline rinsed dialyzers as well as those roused in patients several times. C-DAK 4000 (Cordis Dow) and CF IS-11 (Baxter Travenol) reused dialyzers obtained from the dialysis clinic were used in the present study. The new dialyzers exhibited a relatively flat APD, whereas saline rinsed and reused dialyzers showed considerable amount of decay. C-DAH dialyzers had a larger APD(11.70
In this study, formation background of biodiversity and its changes in the process of geologic history, and effects of climate change on biodiversity and human were discussed and the alternatives to reduce the effects of climate change were suggested. Biodiversity is 'the variety of life' and refers collectively to variation at all levels of biological organization. That is, biodiversity encompasses the genes, species and ecosystems and their interactions. It provides the basis for ecosystems and the services on which all people fundamentally depend. Nevertheless, today, biodiversity is increasingly threatened, usually as the result of human activity. Diverse organisms on earth, which are estimated as 10 to 30 million species, are the result of adaptation and evolution to various environments through long history of four billion years since the birth of life. Countlessly many organisms composing biodiversity have specific characteristics, respectively and are interrelated with each other through diverse relationship. Environment of the earth, on which we live, has also created for long years through extensive relationship and interaction of those organisms. We mankind also live through interrelationship with the other organisms as an organism. The man cannot lives without the other organisms around him. Even though so, human beings accelerate mean extinction rate about 1,000 times compared with that of the past for recent several years. We have to conserve biodiversity for plentiful life of our future generation and are responsible for sustainable use of biodiversity. Korea has achieved faster economic growth than any other countries in the world. On the other hand, Korea had hold originally rich biodiversity as it is not only a peninsula country stretched lengthily from north to south but also three sides are surrounded by sea. But they disappeared increasingly in the process of fast economic growth. Korean people have created specific Korean culture by coexistence with nature through a long history of agriculture, forestry, and fishery. But in recent years, the relationship between Korean and nature became far in the processes of introduction of western culture and development of science and technology and specific natural feature born from harmonious combination between nature and culture disappears more and more. Population of Korea is expected to be reduced as contrasted with world population growing continuously. At this time, we need to restore biodiversity damaged in the processes of rapid population growth and economic development in concert with recovery of natural ecosystem due to population decrease. There were grand extinction events of five times since the birth of life on the earth. Modern extinction is very rapid and human activity is major causal factor. In these respects, it is distinguished from the past one. Climate change is real. Biodiversity is very vulnerable to climate change. If organisms did not find a survival method such as 'adaptation through evolution', 'movement to the other place where they can exist', and so on in the changed environment, they would extinct. In this respect, if climate change is continued, biodiversity should be damaged greatly. Furthermore, climate change would also influence on human life and socio-economic environment through change of biodiversity. Therefore, we need to grasp the effects that climate change influences on biodiversity more actively and further to prepare the alternatives to reduce the damage. Change of phenology, change of distribution range including vegetation shift, disharmony of interaction among organisms, reduction of reproduction and growth rates due to odd food chain, degradation of coral reef, and so on are emerged as the effects of climate change on biodiversity. Expansion of infectious disease, reduction of food production, change of cultivation range of crops, change of fishing ground and time, and so on appear as the effects on human. To solve climate change problem, first of all, we need to mitigate climate change by reducing discharge of warming gases. But even though we now stop discharge of warming gases, climate change is expected to be continued for the time being. In this respect, preparing adaptive strategy of climate change can be more realistic. Continuous monitoring to observe the effects of climate change on biodiversity and establishment of monitoring system have to be preceded over all others. Insurance of diverse ecological spaces where biodiversity can establish, assisted migration, and establishment of horizontal network from south to north and vertical one from lowland to upland ecological networks could be recommended as the alternatives to aid adaptation of biodiversity to the changing climate.