• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.109-131
• /
• 2014

As the demand of nuclear power plant equipment is continuously growing worldwide, the importance of handling nuclear strategic materials is also increasing. While the number of cases submitted for the exports of nuclear-power commodity and technology is dramatically increasing, preadjudication (or prescreening to be simple) of strategic materials has been done so far by experts of a long-time experience and extensive field knowledge. However, there is severe shortage of experts in this domain, not to mention that it takes a long time to develop an expert. Because human experts must manually evaluate all the documents submitted for export permission, the current practice of nuclear material export is neither time-efficient nor cost-effective. Toward alleviating the problem of relying on costly human experts only, our research proposes a new system designed to help field experts make their decisions more effectively and efficiently. The proposed system is built upon case-based reasoning, which in essence extracts key features from the existing cases, compares the features with the features of a new case, and derives a solution for the new case by referencing similar cases and their solutions. Our research proposes a framework of case-based reasoning system, designs a case-based reasoning system for the control of nuclear material exports, and evaluates the performance of alternative keyword extraction methods (full automatic, full manual, and semi-automatic). A keyword extraction method is an essential component of the case-based reasoning system as it is used to extract key features of the cases. The full automatic method was conducted using TF-IDF, which is a widely used de facto standard method for representative keyword extraction in text mining. TF (Term Frequency) is based on the frequency count of the term within a document, showing how important the term is within a document while IDF (Inverted Document Frequency) is based on the infrequency of the term within a document set, showing how uniquely the term represents the document. The results show that the semi-automatic approach, which is based on the collaboration of machine and human, is the most effective solution regardless of whether the human is a field expert or a student who majors in nuclear engineering. Moreover, we propose a new approach of computing nuclear document similarity along with a new framework of document analysis. The proposed algorithm of nuclear document similarity considers both document-to-document similarity (${\alpha}$) and document-to-nuclear system similarity (${\beta}$), in order to derive the final score (${\gamma}$) for the decision of whether the presented case is of strategic material or not. The final score (${\gamma}$) represents a document similarity between the past cases and the new case. The score is induced by not only exploiting conventional TF-IDF, but utilizing a nuclear system similarity score, which takes the context of nuclear system domain into account. Finally, the system retrieves top-3 documents stored in the case base that are considered as the most similar cases with regard to the new case, and provides them with the degree of credibility. With this final score and the credibility score, it becomes easier for a user to see which documents in the case base are more worthy of looking up so that the user can make a proper decision with relatively lower cost. The evaluation of the system has been conducted by developing a prototype and testing with field data. The system workflows and outcomes have been verified by the field experts. This research is expected to contribute the growth of knowledge service industry by proposing a new system that can effectively reduce the burden of relying on costly human experts for the export control of nuclear materials and that can be considered as a meaningful example of knowledge service application.

• Journal of Distribution Science
• /
• v.8 no.3
• /
• pp.27-35
• /
• 2010

As the population, buying power, and intensity of self-expression of the elderly generation increase, its importance as a market segment is also growing. Therefore, the mass marketing strategy for the elderly generation must be changed to a micro-marketing strategy based on the results of sub-segmentation that suitably captures the characteristics of this generation. Furthermore, as a customer access strategy is decided by sub-segmentation, proper segmentation is one of the key success factors for micro-marketing. Segments or sub-segments are different from sectors, because segmentation or sub-segmentation for micro-marketing is based on the homogeneity of customer needs. Theoretically, complete segmentation would reveal a single voice. However, it is impossible to achieve complete segmentation because of economic factors, factors that affect effectiveness, etc. To obtain a single voice from a segment, we sometimes need to divide it into many individual cases. In such a case, there would be a many segments to deal with. On the other hand, to maximize market access performance, fewer segments are preferred. In this paper, we use the term "sub-segmentation" instead of "segmentation," because we divide a specific segment into more detailed segments. To sub-segment the elderly generation, this paper takes their lifestyles and life stages into consideration. In order to reflect these aspects, various surveys and several rounds of expert interviews and focused group interviews (FGIs) were performed. Using the results of these qualitative surveys, we can define six sub-segments of the elderly generation. This paper uses five rules to divide the elderly generation. The five rules are (1) mutually exclusive and collectively exhaustive (MECE) sub-segmentation, (2) important life stages, (3) notable lifestyles, (4) minimum number of and easy classifiable sub-segments, and (5) significant difference in voices among the sub-segments. The most critical point for dividing the elderly market is whether children are married. The other points are source of income, gender, and occupation. In this paper, the elderly market is divided into six sub-segments. As mentioned, the number of sub-segments is a very key point for a successful marketing approach. Too many sub-segments would lead to narrow substantiality or lack of actionability. On the other hand, too few sub-segments would have no effects. Therefore, the creation of the optimum number of sub-segments is a critical problem faced by marketers. This paper presents a method of evaluating the fitness of sub-segments that was deduced from the preceding surveys. The presented method uses the degree of homogeneity (DoH) to measure the adequacy of sub-segments. This measure uses quantitative survey questions to calculate adequacy. The ratio of significantly homogeneous questions to the total numbers of survey questions indicates the DoH. A significantly homogeneous question is defined as a question in which one case is selected significantly more often than others. To show whether a case is selected significantly more often than others, we use a hypothesis test. In this case, the null hypothesis (H0) would be that there is no significant difference between the selection of one case and that of the others. Thus, the total number of significantly homogeneous questions is the total number of cases in which the null hypothesis is rejected. To calculate the DoH, we conducted a quantitative survey (total sample size was 400, 60 questions, 4~5 cases for each question). The sample size of the first sub-segment-has no unmarried offspring and earns a living independently-is 113. The sample size of the second sub-segment-has no unmarried offspring and is economically supported by its offspring-is 57. The sample size of the third sub-segment-has unmarried offspring and is employed and male-is 70. The sample size of the fourth sub-segment-has unmarried offspring and is not employed and male-is 45. The sample size of the fifth sub-segment-has unmarried offspring and is female and employed (either the female herself or her husband)-is 63. The sample size of the last sub-segment-has unmarried offspring and is female and not employed (not even the husband)-is 52. Statistically, the sample size of each sub-segment is sufficiently large. Therefore, we use the z-test for testing hypotheses. When the significance level is 0.05, the DoHs of the six sub-segments are 1.00, 0.95, 0.95, 0.87, 0.93, and 1.00, respectively. When the significance level is 0.01, the DoHs of the six sub-segments are 0.95, 0.87, 0.85, 0.80, 0.88, and 0.87, respectively. These results show that the first sub-segment is the most homogeneous category, while the fourth has more variety in terms of its needs. If the sample size is sufficiently large, more segmentation would be better in a given sub-segment. However, as the fourth sub-segment is smaller than the others, more detailed segmentation is not proceeded. A very critical point for a successful micro-marketing strategy is measuring the fit of a sub-segment. However, until now, there have been no robust rules for measuring fit. This paper presents a method of evaluating the fit of sub-segments. This method will be very helpful for deciding the adequacy of sub-segmentation. However, it has some limitations that prevent it from being robust. These limitations include the following: (1) the method is restricted to only quantitative questions; (2) the type of questions that must be involved in calculation pose difficulties; (3) DoH values depend on content formation. Despite these limitations, this paper has presented a useful method for conducting adequate sub-segmentation. We believe that the present method can be applied widely in many areas. Furthermore, the results of the sub-segmentation of the elderly generation can serve as a reference for mature marketing.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.123-132
• /
• 2013

As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.