• Journal of agriculture & life science
• /
• v.45 no.5
• /
• pp.57-62
• /
• 2011

This study was conducted to determine the distribution of nitrogenous compounds to various tree parts and the extent of reserve accumulation in persimmon (Diospyros kaki) under various fruit-loads. This study also ascertained the proportion of storage nitrogen made available for the new growth the following year. On June 15, the fruit-load was adjusted to a leaf-fruit (L/F) ratio of 10, 20, and 30, and some trees were completely defruited. Between June 15 and November 11, the increase of total amino acids were greater with a high L/F ratio. The amino acids increased in the root were negligible at the 10-L/F ratio. Of the total amino acids increased during this period, the proportion distributed to the root was 64% in the 20-L/F, 18.5% in the 30-L/F, and 81% in the defruited trees, and the distribution to the fruits was 81% in 10-L/F, 12% in 20-L/F, and 35% in the 30-L/F trees. Leaf amino acids decreased in the 10-L/F trees. Total proteins increased in autumn were greater as the L/F ratio was higher. Total proteins were in the fruits the most, and the distribution to the permanent parts was decreased as the L/F ratio was decreased. At the L/F ratio of 30, 59% of the total proteins increased in the autumn was distributed to the fruits and 40% to the root. Leaf proteins decreased at 10 and 20 L/F ratios. During the new growth from April 10 to June 10 the following year, amino acids decreased in the old wood and 1-yr-old shoot, whereas proteins decreased only in the 1-year-old shoots. Amino acids and protein decreased by 540 mg and 610 mg, respectively, in the roots of the defruited trees. Total amino acid and proteins in the newly-grown parts were the most at 730 mg and 1290 mg, respectively, when defruited the previous year. They were the least at the 10-L/F ratio, being 120 mg and 400 mg, respectively.

• 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.

• The Korean Journal of Nuclear Medicine
• /
• v.1 no.1
• /
• pp.55-66
• /
• 1967

In view of its prevalence in the Far East area, a more detailed knowledge on the hookworm infection is one of the very important medical problems. The present study was aimed to; determine the infectivity of the artificially hatched ancylostoma duodenale larvae in man after its oral administration, evaluate the clinical symptomatology of such infection, determine the date of first appearance of the ova in the stool, calculate the blood loss per worm per day, assess the relation-ships between the ova count, infectivity(worm load), blood loss and severity of anemia. An erythrokinetic study was also done to analyse the characteristics of hookworm anemia by means of $^{59}Fe\;and\;^{51}Cr$. Materials and Methods Ten healthy male volunteers(doctors, medical students and laboratory technicians) with the ages ranging from 21 to 40 years were selected as the experimental materials. They had no history of hookworm infection for preceding several years, and care was taken not to be exposed to reinfection. A baseline study including a through physical examinations and laboratory investigations such as complete blood counts, stool examination and estimation of the serum iron levels was done, and a vermifuge, bephenium hydroxynaphoate, was given 10 days prior to the main experiment. The ancylostoma duodenale filariform larvae were obtained in the following manner; The pure ancylostoma duodenale ova were obtained from the hookworm anemia patients and a modified filter paper method was adopted to harvest larger number of infective larvae, which were washed several times with saline. The actively moving mature larvae were put into the gelatine capsules, 150 in each, and were given to the volunteers in the fasting state with 300ml. of water. The volunteers were previously treated with intramuscular injection of 15mg. of chlorpromazine in order to prevent the eventual nausea and vomiting after the larvae intake. The clinical symptoms and signs mainly of the respiratory and gastrointestinal tracts, appearance of the ova and occult blood in the stool etc. were checked every day for the first 20 days and then twice weekly until the end of the experiment, which usually lasted for about 3 months. Roentgenological survey of the lungs was also done. The hematological changes such as the red blood cell, white blood cell and eosinophil cell counts, hemoglobin content and serum iron levels were studied. The appearance of the ova in the stool was examined by the formalin ether method and the ova were counted in triplicate on two successive days using the Stoll's dilution method. The ferrokinetic data were calculated by the modified Huff's method and the apparent half survival time of the red blood cells by the modified Gray's method. The isotopes were simultaneously tagged and injected intravenously, and then the stool and blood samples were collected as was described by Roche et al., namely, three separate 4-day stool samples with the blood sample drawing before each 4-day stool collection. The radio-activities of the stools ashfied and the blood were separately measured by the pulse-height analyser. The daily blood loss was calculated with the following formula; daily blood loss in $ml.=\frac{cpm/g\;stool{\times}weight\;in\;g\;of\;4-day\;stool}{cpm/ml\;blood{\times}4}$ The average of these three 4-day periods was given as the daily blood loss in each patient. The blood loss per day per worm was calculated by simply dividing the daily blood loss by the number of the hookworm recovered after the vermifuge given twice a week at the termination of the experiment. The iron loss in mg. through the gastrointestinal tract was estimated with the daily iron loss in $mg=\frac{g\;Hgb/100ml{\times}ml\;daily\;blood\;loss{\times}3.40}{100}$ 3.40=mg of iron per g Hgb following formula; Results 1. The respiratory symptoms such as cough and sputum were noted in almost all cases within a week after the infection, which lasted about 2 weeks. The roentgenological findings of the chest were essentially normal. A moderate degree of febril reaction appeared within 2 weeks with a duration of 3 or 4 days. 2. The gastrointestinal symptoms such as nausea, epigastric fullness, abdominal pain and loose bowel appeared in all cases immediately after the larvae intake. 3. The reduction of the red blood cell count was not remarkable, however, the hemoglobin content and especially the serum iron level showed the steady decreases until the end of the experiment. 4. The white blood cells and eosinophil cells, on the contrary, showed increases in parallel and reached peaks in 20 to 30 days after the infection. A small secondary rise was noted in 2 months. 5. The ova first appeared in the stool in 40. 1 days after the infection, ranging from 29 to 51 days, during which the occult blood reaction of the stool became also positive in almost cases. 6. The number of ova recovered per day was 164, 320 on the average, ranging from 89,500 to 253,800. The number of the worm evacuated by vermifuge was in rough correlation with the number of ova recovered. 7. The infectivity of ancylostoma duodenale was 14% on the average, ranging from 7.3 to 20.0%, which is relatively lower than those reported by other workers. 8. The mean fecal blood loss was 5.78ml. per day, with a range of from 2.6 to 11.7ml., and the mean blood loss per worm per day was 0.30ml., with a range of from 0.13 to 0.73ml., which is in rough coincidence with those reported by other authors. There appeared to exist, however, no correlation between the blood loss and the number of ova recovered. 9. The mean fecal iron loss was 2.02mg. per day, with a range of from 1.20 to 3.89mg., which is less than those appeared in the literature. 10. The mean plasma iron disappearance rate was 0.80hr., with a range of from 0.62 to 0.95hr., namely, a slight accerelation. 11. The hookworm anemia appeared to be iron deficiency in origin caused by continuous intestinal blood loss.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.6
• /
• pp.60-74
• /
• 2018

This study was to investigate the pedestrian's thermal environments in the North Sidewalk of E-W Street during summer heatwave. We carried out detailed measurements with four human-biometeorological stations on Dongjin Street, Jinju, Korea ($N35^{\circ}10.73{\sim}10.75^{\prime}$, $E128^{\circ}55.90{\sim}58.00^{\prime}$, elevation: 50m). Two of the stations stood under one row street tree and hedge(One-Tree), two row street tree and hedge (Two-Tree), one of the stations stood under shelter and awning(Shelter), while the other in the sun (Sunlit). The measurement spots were instrumented with microclimate monitoring stations to continuously measure microclimate, radiation from the six cardinal directions at the height of 1.1m so as to calculate the Universal Thermal Climate Index (UTCI) from 24th July to 21th August 2018. The radiant temperature of sidewalk's elements were measured by the reflective sphere and thermal camera at 29th July 2018. The analysis results of 9 day's 1 minute term human-biometeorological data absorbed by a man in standing position from 10am to 4pm, and 1 day's radiant temperature of sidewalk elements from 1:16pm to 1:35pm, showed the following. The shading of street tree and shelter were mitigated heat stress by the lowered UTCI at mid and late summer's daytime, One-Tree and Two-Tree lowered respectively 0.4~0.5 level, 0.5~0.8 level of the heat stress, Shelter lowered respectively 0.3~1.0 level of the heat stress compared with those in the Sunlit. But the thermal environments in the One-Tree, Two-Tree and Shelter during the heat wave supposed to user "very strong heat stress" while those in the Sunlit supposed to user "very strong heat stres" and "exterme heat stress". The main heat load temperature compared with body temperature ($37^{\circ}C$) were respectively $7.4^{\circ}C{\sim}21.4^{\circ}C$ (pavement), $14.7^{\circ}C{\sim}15.8^{\circ}C$ (road), $12.7^{\circ}C$ (shelter canopy), $7.0^{\circ}C$ (street funiture), $3.5^{\circ}C{\sim}6.4^{\circ}C$ (building facade). The main heat load percentage were respectively 34.9%~81.0% (pavement), 9.6%~25.2% (road), 24.8% (shelter canopy), 14.1%~15.4% (building facade), 5.7% (street facility). Reducing the radiant temperature of the pavement, road, building surfaces by shading is the most effective means to achieve outdoor thermal comfort for pedestrians in sidewalk. Therefore, increasing the projected canopy area and LAI of street tree through the minimal training and pruning, building dense roadside hedge are essential for pedestrians thermal comfort. In addition, thermal liner, high reflective materials, greening etc. should be introduced for reducing the surface temperature of shelter and awning canopy. Also, retro-reflective materials of building facade should be introduced for the control of reflective sun radiation. More aggressively pavement watering should be introduced for reducing the surface temperature of sidewalk's pavement.

• Tuberculosis and Respiratory Diseases
• /
• v.62 no.3
• /
• pp.184-191
• /
• 2007

Background: For the diagnosis of pleural tuberculosis, polymerase chain reaction (PCR) of pleural effusion specimens has shown very low sensitivity, which might be due to the small number of bacilli in the samples. The purpose of this investigation is to determine whether the sensitivity of PCR testing can be improved when increasing the amount of pleural effusion specimens. Methods: We prospectively analyzed pleural effusion specimens obtained from 53 patients for whom the exclusion of the possibility of tuberculous pleural effusion was necessary. We performed Mycobacterium tuberculosis PCR testing using the Cobas Amplicor MTB test (Roche Diagnostic Systems) with three different amounts (10ml, 25ml, and 50ml) of pleural effusion specimen in each patient. Pleural tuberculosis was defined as having one of the following: culture-positive pleural fluid sample, histopathologic finding consistent with tuberculosis on pleural biopsy, culture-positive sputum specimen, and/or positive response to anti-tuberculous medication without other possible causes of pleural effusion. Results: Of the 53 patients, 26 received the diagnosis of pleural tuberculosis. The sensitivities of AFB smearing, Mycobacterium tuberculosis culture of pleural effusion specimen, pleural biopsy, and measurement of ADA were 3.8%, 15.4%, 84.6%, and 88.5%, respectively. The results of PCR testing were positive for 3 (11.5%), 4 (15.4%), and 3 (11.5%) of the 26 patients when using 10ml, 25ml, and 50ml of pleural effusion specimens, respectively. These results did not show a statistically significant difference in the sensitivity of PCR testing when increasing the amount of pleural effusion samples (p>0.05, symmetry exact test). Conclusion: For specimens such as pleural effusion, in which the bacillary load is very low, the clinical utility of PCR testing seems highly limited with the kits designed for the diagnosis of pulmonary tuberculosis. An increased amount of pleural effusion sample does not improve the sensitivity of PCR testing.

• The Journal of Korean Academy of Prosthodontics
• /
• v.38 no.5
• /
• pp.583-594
• /
• 2000

Dislodgement of a crown or extension bridge and the loosening of a retainer of a bridge is a serious clinical problem in fixed restoration. Generally these problems are considered to be associated with deformation of the restoration. During biting, the restoration is subjected to complex forces and deforms considerably within the limit of its elasticity. Deformation of the restoration under the occlusal force induces excessive stress in the cement film, which then leads to the cement fracture. Such a fracture may eventually cause loss of the restoration. Because most of the past retention tests for full veneer crown were done without fatigue loading, they were not exactly simulating intraoral environment. And the purpose of this study was to evaluate the effect of cyclic cantilever loading on the retentive strength of full veneer crowns depending on different type of cements and taper of prepared abutment. Steel dies with $8^{\circ}\;or\;16^{\circ}$ convergence angle were fabricated through milling and crowns with the same method. These dies and crowns were divided into 8 groups. Group 1 : $16^{\circ}$ taper die, cementation with zinc phosphate cement, without loading Group 2 : $16^{\circ}$ taper die, cementation with zinc phosphate cement, with loading Group 3 : $8^{\circ}$ taper die, cementation with zinc phosphate cement, without loading Group 4 : $8^{\circ}$ taper die, cementation with zinc phosphate cement, with loading Group 5 : $16^{\circ}$ taper die, cementation with Panavia 21, without loading Group 6 : $16^{\circ}$ taper die, cementation with Panavia 21, with loading Group 7 : $8^{\circ}$ taper die, cementation with Panavia 21 without loading Group 8 : $8^{\circ}$ taper die, cementation with Panavia 21, with loading After checking the fit of die and crown, the luting surface of dies and inner surface of crowns were air-abraded for 10 seconds. The crowns were cemented to the dies, with cements mixed according to the manufacturer's recommendations. A static load of 5kg was then applied for 10 minutes with static loading device. Twenty-four hours later, group 1, 3, 5, 7 were only thermocycled, group 2, 4, 6, 8 were subjected to cyclic loading after thermocycling. Retentive tests were performed on the Instron machine. From the finding of this study, the following conclusions were obtained 1. Panavia 21 showed significantly higher retentive strength than zinc phosphate cement for all groups (p<0.05). 2. There was a significant difference in the retentive strength between $8^{\circ}\;and\;16^{\circ}$ taper for zinc phosphate cement(p<0.05), but no significant difference for Panavia 21 (p>0.05). 3. Cyclic loading significantly decreased the retentive strength for all groups(p<0.05). 4. For zinc phosphate cement, there was 35% reduction of the retentive strength after loading in the $16^{\circ}$ taper die, 25% in the $8^{\circ}$ taper die, and for Panavia 21, 21% in the $16^{\circ}$ taper die, 18% in the $8^{\circ}$ taper die.

• Korean Journal of Applied Biomechanics
• /
• v.12 no.2
• /
• pp.91-107
• /
• 2002

This research got the following conclusion as result that analyzed high clear action kinematically to 4 C girls' junior high school badminton players who are situated in Chungchong-bukdo. 1. Most of the subject didn't rotate their right shoulder and elbow joint at back swing and moved speedy to shuttle cock. And an cooperation action of joint decreases displaying only a good action on both subject`s specification joint part. 2. When the subject S1 and S2 swing slowly and largely the joint of shoulder and elbow and then the speed of right wrist and racket head is fast, the cooperation action of joint is better than other subject. 3. An angle change of right shoulder showed angle that all subjects are great being caused in softness of joint and angular velocity was exposed that load enough Impact force and increase the speed of racket head as angular velocity decreases rapidly in Impact except subject S3. 4. All subjects of right elbow angle change showed similar form and was exposed that subject S2 sees form of impact stage serious bends from back swing and do not use force effectively in angular velocity. 5. Angle of right wrist appeared that the speed of shuttle cock is decelerated because fast bends of wrist is not formed shortly after Impact because all subject do not accomplish big angle shortly after back swing. Angular velocity can assume that the subject S1 and S4 are using and move fast strong snap shot offering angular velocity value of Impact stage sound (-). 6. While size of Impact stage knee angle accomplishes angle that is big both subject, hip joint angles sees small angle and is playing swing that do on upper body and arm without using strong waist force that is composition action with knee and hip joint.

• Journal of Korean Society of Steel Construction
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2010

According to the capacity design concept which forms the basis of the current steel seismic codes, the braces in concentrically braced frames (CBFs) should dissipate seismic energy through cyclic tension yielding and cyclic compression buckling while the beams and the columns should remain elastic. Brace buckling in inverted V-braced frames induces unbalanced vertical forces which, in turn, impose the additional beam moments and column axial forces. However, due to difficulty in predicting the location of buckling stories, the most conservative approach implied in the design code is to estimate the column axial forces by adding all the unbalanced vertical forces in the upper stories. One alternative approach, less conservative and recommended by the current code, is to estimate the column axial forces based on the amplified seismic load expected at the mechanism-level response. Both are either too conservative or lacking technical foundation. In this paper, three combination rules for a rational estimation of the column axial forces were proposed. The idea central to the three methods is to detect the stories of high buckling potential based on pushover analysis and dynamic behavior. The unbalanced vertical forces in the stories detected as high buckling potential are summed in a linear manner while those in other stories are combined by following the SRSS(square root of sum of squares) rule. The accuracy and design advantage of the three methods were validated by comparing extensive inelastic dynamic analysis results. The mode-shape based method(MSBM), which is both simple and accurate, is recommended as the method of choice for practicing engineers among the three.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.