• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• The Korean Society of Law and Medicine
• /
• v.19 no.2
• /
• pp.41-72
• /
• 2018

In the division of labor (or teamwork) in medicine, the responsibility of medical and nursing staff should be separated or distributed to justify negligent criminal offenses. The present work refers to the standards by which the due diligence and responsibility of the individual persons are to be determined and delimited. In this context, it has been proven that objective theory as a measure of due diligence is appropriate. From a moral point of view, when assessing due diligence, it makes sense to impose greater individual or higher performance demands on the perpetrator, but law and order require that due diligence should result from socially relevant human behavior. To give objective measure of negligence and to provide the highest level of personal responsibility, so that man can not be burdened too much responsibility and it is accordingly with an equality theorem. Afterwards some points are presented, which should be considered in a concrete fact in the determination of the medical negligence. Medical action has specific characteristics such as professionalism, discretionary and exclusive, unbalance of information. These characteristics distinguish medical actions from general negligence. The general level of knowledge, the urgency, working condition and working environment of the medical facility, duration of the professional practice, assessment of the medical activity are crucial in this context. As a standard of delineation of due diligence, I have used the permitted risk and the principle of trust. In the horizontal division of labor, the principle of trust applies. The principle of trust applies in principle in cases of division of labor interaction, when doctors in the same hospital exercise their own specific occupational field or everyone works in another hospital. However, this is not true for every case. In the vertical division of labor, the principle of trust does not apply and the senior physician can not trust the assistant doctors. In this case, the principle of trust is converted into a duty of supervision for assistant doctors by the senior physician. This supervision requirement could be used as a random check.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.3
• /
• pp.259-267
• /
• 2004

Purpose: NEMA NU2-2001 was proposed as a new standard for performance evaluation of whole body PET scanners. in this study, system performance of Siemens CTI ECAT EXACT 47 PET scanner including spatial resolution, sensitivity, scatter fraction, and count rate performance in 2D and 3D mode was evaluated using this new standard method. Methods: ECAT EXACT 47 is a BGO crystal based PET scanner and covers an axial field of view (FOV) of 16.2 cm. Retractable septa allow 2D and 3D data acquisition. All the PET data were acquired according to the NEMA NU2-2001 protocols (coincidence window: 12 ns, energy window: $250{\sim}650$ keV). For the spatial resolution measurement, F-18 point source was placed at the center of the axial FOV((a) x=0, and y=1, (b)x=0, and y=10, (c)x=70, and y=0cm) and a position one fourth of the axial FOV from the center ((a) x=0, and y=1, (b)x=0, and y=10, (c)x=10, and y=0cm). In this case, x and y are transaxial horizontal and vertical, and z is the scanner's axial direction. Images were reconstructed using FBP with ramp filter without any post processing. To measure the system sensitivity, NEMA sensitivity phantom filled with F-18 solution and surrounded by $1{\sim}5$ aluminum sleeves were scanned at the center of transaxial FOV and 10 cm offset from the center. Attenuation free values of sensitivity wire estimated by extrapolating data to the zero wall thickness. NEMA scatter phantom with length of 70 cm was filled with F-18 or C-11solution (2D: 2,900 MBq, 3D: 407 MBq), and coincidence count rates wire measured for 7 half-lives to obtain noise equivalent count rate (MECR) and scatter fraction. We confirmed that dead time loss of the last flame were below 1%. Scatter fraction was estimated by averaging the true to background (staffer+random) ratios of last 3 frames in which the fractions of random rate art negligibly small. Results: Axial and transverse resolutions at 1cm offset from the center were 0.62 and 0.66 cm (FBP in 2D and 3D), and 0.67 and 0.69 cm (FBP in 2D and 3D). Axial, transverse radial, and transverse tangential resolutions at 10cm offset from the center were 0.72 and 0.68 cm (FBP in 2D and 3D), 0.63 and 0.66 cm (FBP in 2D and 3D), and 0.72 and 0.66 cm (FBP in 2D and 3D). Sensitivity values were 708.6 (2D), 2931.3 (3D) counts/sec/MBq at the center and 728.7 (2D, 3398.2 (3D) counts/sec/MBq at 10 cm offset from the center. Scatter fractions were 0.19 (2D) and 0.49 (3D). Peak true count rate and NECR were 64.0 kcps at 40.1 kBq/mL and 49.6 kcps at 40.1 kBq/mL in 2D and 53.7 kcps at 4.76 kBq/mL and 26.4 kcps at 4.47 kBq/mL in 3D. Conclusion: Information about the performance of CTI ECAT EXACT 47 PET scanner reported in this study will be useful for the quantitative analysis of data and determination of optimal image acquisition protocols using this widely used scanner for clinical and research purposes.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.4
• /
• pp.318-324
• /
• 2004

Purpose: Philips GEMINI is a newly introduced whole-body GSO PET/CT scanner. In this study, performance of the scanner including spatial resolution, sensitivity, scatter fraction, noise equivalent count ratio (NECR) was measured utilizing NEMA NU2-2001 standard protocol and compared with performance of LSO, BGO crystal scanner. Methods: GEMINI is composed of the Philips ALLEGRO PET and MX8000 D multi-slice CT scanners. The PET scanner has 28 detector segments which have an array of 29 by 22 GSO crystals ($4{\times}6{\times}20$ mm), covering axial FOV of 18 cm. PET data to measure spatial resolution, sensitivity, scatter fraction, and NECR were acquired in 3D mode according to the NEMA NU2 protocols (coincidence window: 8 ns, energy window: $409[\sim}664$ keV). For the measurement of spatial resolution, images were reconstructed with FBP using ramp filter and an iterative reconstruction algorithm, 3D RAMLA. Data for sensitivity measurement were acquired using NEMA sensitivity phantom filled with F-18 solution and surrounded by $1{\sim}5$ aluminum sleeves after we confirmed that dead time loss did not exceed 1%. To measure NECR and scatter fraction, 1110 MBq of F-18 solution was injected into a NEMA scatter phantom with a length of 70 cm and dynamic scan with 20-min frame duration was acquired for 7 half-lives. Oblique sinograms were collapsed into transaxial slices using single slice rebinning method, and true to background (scatter+random) ratio for each slice and frame was estimated. Scatter fraction was determined by averaging the true to background ratio of last 3 frames in which the dead time loss was below 1%. Results: Transverse and axial resolutions at 1cm radius were (1) 5.3 and 6.5 mm (FBP), (2) 5.1 and 5.9 mm (3D RAMLA). Transverse radial, transverse tangential, and axial resolution at 10 cm were (1) 5.7, 5.7, and 7.0 mm (FBP), (2) 5.4, 5.4, and 6.4 mm (3D RAMLA). Attenuation free values of sensitivity were 3,620 counts/sec/MBq at the center of transaxial FOV and 4,324 counts/sec/MBq at 10 cm offset from the center. Scatter fraction was 40.6%, and peak true count rate and NECR were 88.9 kcps @ 12.9 kBq/mL and 34.3 kcps @ 8.84 kBq/mL. These characteristics are better than that of ECAT EXACT PET scanner with BGO crystal. Conclusion: The results of this field test demonstrate high resolution, sensitivity and count rate performance of the 3D PET/CT scanner with GSO crystal. The data provided here will be useful for the comparative study with other 3D PET/CT scanners using BGO or LSO crystals.

• The Journal of Korean Society for Radiation Therapy
• /
• v.29 no.2
• /
• pp.53-64
• /
• 2017

Purpose: To evaluate the usefulness of the $HexaPOD^{TM}$ evo RT system(6DoF couch) and the tendency of dose difference according to size of rotational direction error for volumetric rotational modulated radiotherapy(V-MAT) in patients with long target lengths. Therefore, it is suggested to recommend the need for rotational error correction. Materials and Methods: Ten patients with Esophagus cancer or Breast cancer including SCL treated with HexaPOD 6DoF(Six-Degree of Freedom) couch were included in this study. 6DoF couch was used to measure the difference in dose according to the rotation error in the directions of Rx(pitch), Ry(roll), and Rz(yaw). Each rotation error was applied. Positioning variation on x, y and z axis was verified and random variations were made by 6DoF couch with positioning variation. Modified DQA is conducted and point dose and gamma value are analyzed and compared. In addition, after applying the rotation error every $1^{\circ}$ to treatment plans of each target with a diameter of 3 cm, 5, 10, 15, and 20 cm respectively, gamma passing rate is being monitored by its aspect of change according to types and sizes of the target length and rotation error. Results: Mean error of the point dose and Gamma passing rate when the position variation was applied were $2.50{\pm}1.11%$ and $84.1{\pm}7.39%$ in the Rx direction, $2.36{\pm}1.16%$, and $81.0{\pm}8.49%$ in the Ry, $2.35{\pm}1.10%$ and $84.4{\pm}6.99%$ in the Rz direction, respectively. As a result of analysis on gamma passing rate according to types and sizes of the target length and rotation error, the gamma passing rate tended to decrease with increasing rotation error in the Rx and Rz directions except Ry direction. In particular, the lowest gamma passing rate (74.2 %) was in the case of $2.5^{\circ}$ rotation error in Rz direction of the target of 10 cm. Conclusion: The correction of the rotational error is needed for volumetric modulated radiotherapy of the treatment area with a long target length, and the use of 6DoF couch will improve the reproducibility of the patient position and the quality of the treatment.

• Journal of Global Scholars of Marketing Science
• /
• v.17 no.3
• /
• pp.1-19
• /
• 2007

1. Purpose Rural tourism is made by individuals with different characteristics, needs and wants. It is important to have information on the characteristics and preferences of the consumers of the different types of existing rural accommodation. The stud aims to identify the determinants of consumer preference by type of accommodations. 2. Methodology 2.1 Sample Data were collected from 1000 people by telephone survey with three-stage stratified random sampling in seven metropolitan areas in Korea. Respondents were chosen by sampling internal on telephone book published in 2006. We surveyed from four to ten-thirty 0'clock afternoon so as to systematic sampling considering respondents' life cycle. 2.2 Two-step cluster Analysis Our study is accomplished through the use of a two-step cluster method to classify the accommodation in a reduced number of groups, so that each group constitutes a type. This method had been suggested as appropriate in clustering large data sets with mixed attributes. The method is based on a distance measure that enables data with both continuous and categorical attributes to be clustered. This is derived from a probabilistic model in which the distance between two clusters in equivalent to the decrease in log-likelihood function as a result of merging. 2.3 Multinomial Logit Analysis The estimation of a Multionmial Logit model determines the characteristics of tourist who is most likely to opt for each type of accommodation. The Multinomial Logit model constitutes an appropriate framework to explore and explain choice process where the choice set consists of more than two alternatives. Due to its ease and quick estimation of parameters, the Multinomial Logit model has been used for many empirical studies of choice in tourism. 3. Findings The auto-clustering algorithm indicated that a five-cluster solution was the best model, because it minimized the BIC value and the change in them between adjacent numbers of clusters. The accommodation establishments can be classified into five types: Traditional House, Typical Farmhouse, Farmstay house for group Tour, Log Cabin for Family, and Log Cabin for Individuals. Group 1 (Traditional House) includes mainly the large accommodation establishments, i.e. those with ondoll style room providing meals and one shower room on family tourist, of original construction style house. Group 2 (Typical Farmhouse) encompasses accommodation establishments of Ondoll rooms and each bathroom providing meals. It includes, in other words, the tourist accommodations Known as "rural houses." Group 3 (Farmstay House for Group) has accommodation establishments of Ondoll rooms not providing meals and self cooking facilities, large room size over five persons. Group 4 (Log Cabin for Family) includes mainly the popular accommodation establishments, i.e. those with Ondoll style room with on shower room on family tourist, of western styled log house. While the accommodations in this group are not defined as regards type of construction, the group does include all the original Korean style construction, Finally, group 5 (Log Cabin for Individuals)includes those accommodations that are bedroom western styled wooden house with each bathroom. First Multinomial Logit model is estimated including all the explicative variables considered and taking accommodation group 2 as base alternative. The results show that the variables and the estimated values of the parameters for the model giving the probability of each of the five different types of accommodation available in rural tourism village in Korea, according to the socio-economic and trip related characteristics of the individuals. An initial observation of the analysis reveals that none of variables income, the number of journey, distance, and residential style of house is explicative in the choice of rural accommodation. The age and accompany variables are significant for accommodation establishment of group 1. The education and rural residential experience variables are significant for accommodation establishment of groups 4 and 5. The expenditure and marital status variables are significant for accommodation establishment of group 4. The gender and occupation variable are significant for accommodation establishment of group 3. The loyalty variable is significant for accommodation establishment of groups 3 and 4. The study indicates that significant differences exist among the individuals who choose each type of accommodation at a destination. From this investigation is evident that several profiles of tourists can be attracted by a rural destination according to the types of existing accommodations at this destination. Besides, the tourist profiles may be used as the basis for investment policy and promotion for each type of accommodation, making use in each case of the variables that indicate a greater likelihood of influencing the tourist choice of accommodation.

• Korean Journal of Occupational Health Nursing
• /
• v.6 no.2
• /
• pp.110-127
• /
• 1997

The aim of this study is to present the basic datum for the promotion of effectiveness and improvement of nursery tasks, by grasping the situation of operating room nurses tasks and the degree of their fatigue. For these researches, 70 nurses out of the operating rooms of 3 university-affiliated hospitals-two in Seoul and one in Pusan, were chosen at random by a non-probability sampling method. These researches were done from April 14 to April 26 in 1997 by questionairing method. The questionaire was composed of 30 items, which asks the examinees of their physical, mental, and neurosensory symptoms, with 10 items respectively. The reliability of the research instrument was turned out very high with Cronbach's ${\alpha}=.9376$. The datum were electronically processed using Statistics Program for Social Sciences(SPSS). The analysis of datum in this study has a general character, in which the demosociological character and the special ex-officio character was calculated by frequency and percentage. The situation of tasks in operating rooms was calculated by frequency and percentage. The fatigue of operating room nurses was calculated by average and standard deviation. To compare the fatigue with regard to the character of operating room nurse's tasks, t-test and F-test(ANOVA) were used after the character of variations, and the variations at the level of P<.05 which might have some meaning was verified after the fact with Duncan's Multiple Range(DMR). The results of this research are as follows : 1) The nurses working in operating rooms show their fatigue in three fields-in Group I physical symptoms 3.28, in Group III neurosensory symptoms 2.85, and in Group II mental symptoms 2.73, which shows I Dominant type (general type). 2) They complain, in Group I they are "feeling the heavy legs," 3.28 and in Group II they "occasionally forget soon what to do," 3.09. and in Group III, they "feel lumbago," 3.47, which is the highest rate of the three. The highest rate results from the character of their tasks, in which they have to move rapidly the heavy appliances and do their jobs standing many hours, especially wearing heavy radiation protector. 3) As to transportation, subway using group feel the greatest fatigue, 3.18(F=4.315, P=.008). 4) As to department, nurses in the orthopedic's surgery part feel the greatest fatigue, 3.26(F=2.040, P=.050). 5) As to the change of physical symptoms, the group answering that they found physical abnormality after working in operating rooms show the greatest fatigue, 3.12(t=-3.13, P=.003). 6) At to the general circumstances, the group answering that they receive insufficient consideration on their physical abnormality in their department, show the greatest fatigue, 3.10(F=3.200, P=0.47). 7) As to the relation with superior officers, the group answering that their superior officer has an impetuous temperament, show great fatigue, 3.11(F=4.855, P=.011). 8) As to the time of feeling fatigue, the fatigue reaches the highest point 1~2 hours after operations, 3.04(F=2.703, P=.046). 9) When they feel fatigue after scrub nurse duties, they feel the greatest fatigue 2 hours after the duties, 3.09( F=2.841, P=.038). 10) As to the operation instruments, when they use complex instruments borrowing from the outside in addition to the basic instruments, their fatigue becomes the greatest, 3.09(F=7.831, P=.000). 11) As to the kind of operation, when they participate in orthopedic's surgery operations, they feel the greatest fatigue, 3.18(F=4.362, P=.000). With the above results, it is proved that the degree of operating room nurses' fatigue is considerably high. So it may be concluded that the measure for lessening the fatigue should be find immediately, not on the level of personal matters but on the level of hospital nursing administration.

• Journal of Korean Society of Forest Science
• /
• v.98 no.3
• /
• pp.215-224
• /
• 2009

A review was given of the role of traditional morphometrics in plant morphological studies using 54 published studies in three major journals and others in Korea, such as Journal of Korean Forestry Society, Korean Journal of Plant Taxonomy, Korean Journal of Breeding, Korean Journal of Apiculture, Journal of Life Science, and Korean Journal of Plant Resources from 1997 to 2008. The two most commonly used techniques of data analysis, cluster analysis (CA) and principal components analysis (PCA) with other statistical tests were discussed. The common problem of PCA is the underlying assumptions of methods, like random sampling and multivariate normal distribution of data. The procedure was intended mainly for continuous data and was not efficient for data which were not well summarized by variances or covariances. Likewise CA was most appropriate for categorical rather than continuous data. Also, the CA produced clusters whether or not natural groupings existed, and the results depended on both the similarity measure chosen and the algorithm used for clustering. An additional problems of the PCA and the CA arised with both qualitative and quantitative data with a limited number of variables and/or too few numbers of samples. Some of these problems may be avoided if a certain number of variables (more than 20 at least) and sufficient samples (40-50 at least) are considered for morphometric analyses, but we do not think that the methods are all mighty tools for data analysts. Instead, we do believe that reasonable applications combined with focus on objectives and limitations of each procedure would be a step forward.

• Biomedical Science Letters
• /
• v.2 no.1
• /
• pp.71-90
• /
• 1996

There is considerable current interest in the effect of regular vigorous exercise and in particular endurance-running as a possible measure in improving myocardial function. Some data indicate that the aging heart may actually suffer from vigorous endurance exercise. On the contrary appropriate exercise in aged animals improves myocardial function and aerobic energy metabolism. So far there is relatively little data to indicate that endurance exercise is in fact beneficial in improving myocardial function or damaging to heart of aged animals. The present investigation aimed to study the possible effect of a long range treadmill training program on the heart in aging rats. Male rats aged 3, 10, and 20 months were divided at random into a control (sedentary) and an exercise group. The training group was exercised for 5 days a week on an automated treadmill for 20minutes at 18m/min over a period of 5 months. The exercise regimen of our experiments did not cause any significant changes in the tissues and ultrastructural as com-pared with sedentary age-matched control. Tissues and ultrastructures of myocardial cells in trained group aged 8 months are intact and well organized as well as sedentary control group. Age associated tissue and ultrastructural changes of trained group aged 15 months included : an increase in transformed mitochondria, vacuoles, lysosomes, lipid droplets and early lipofuscin. But the trained heart did not show significant difference in tissue and ultrastructural properties from those of sedentary controls. Endurance-trained group aged 25 months showed significant qualitative tissue and ultrastructural difference as compared with age-matched controls. In addition to those found in 25 months control group, focal necrosis, myofibril fraying, hypercontraction band, seperation of intercalated discs, degenerating nucleus and infiltration of collagenous fiber into myocyte were noted in trained 25 months group. The stereological examination of the mi-crographs disclosed no significant difference in the myoflbril, mitochondrion, sarcotubule and in-terstitium volume density and surface density of mitochondrial cristae and numerical density of mitochondria between trained and control group aged 8 and 15 months. In the trained 25 months group, significant increase in volume density of interstitium, lipofucsin granule were shown as compared to untrained age-matched control. On the other hand, significant decrease in mitochondrion volume density was shown. The myofibril volume density did not differ between trained and control group although trained group showed slight increase. From the data obtained a reduced mitochondria/myofibrils ratio was found in trained rat heart aged 25 months and there was no difference between trained and control rat aged 15 months. But a slight but not significant increase was found in the trained group aged 8 months as compared with same age control group. Such increase in the ratio in young animals is considered to be of great importance to cardiac pumping and adaptability. Whereas such adaptations don't seem to occur in aged heart muscle. This study proposed that repeated endurance exercise do not cause any significant qualitative and quantitative ultrastructural change of heart muscle in young(3months) and adult (10months) suggesting that the heart is able to adapt to the exercise. On the contrary, the repeated endurance exercise stress may actually induce degenerative changes in the aged heart muscle(20months).