• Journal of Chest Surgery
• /
• v.32 no.7
• /
• pp.603-612
• /
• 1999

Background : It has been documented that brief repetitive periods of ischemia and reperfusion (ischemic preconditioning, IP) enhances the recovery of post-ischemic contractile function and reduces infarct size after a longer period of ischemia. Many mechanisms have been proposed to explain this process. Recent studies have suggested that transient increase in the intracellular calcium may have triggered the activation of protein kinase C(PKC); however, there are still many controversies. Accordingly, the author performed the present study to test the hypothesis that preconditioning with high concentration of calcium before sustained subsequent ischemia(calcium preconditioning) mimics IP by PKC activation. Material and Method : The isolated hearts from the New Zealand White rabbits(1.5∼2.0 kg body weight) Method: The isolated hearts from the New Zealand White rabbits(1.5∼2.0 kg body weight) were perfused with Tyrode solution by Langendorff technique. After stabilization of baseline hemodynamics, the hearts were subjected to 45-minute global ischemia followed by a 120-minute reperfusion with IP(IP group, n=13) or without IP(ischemic control, n=10). IP was induced by single episode of 5-minute global ischemia and 10-minute reperfusion. In the Ca2+ preconditioned group, perfusate containing 10(n=10) or 20 mM(n=11) CaCl2 was perfused for 10 minutes after 5-minute ischemia followed by a 45-minute global ischemia and a 120-minute reperfusion. Baseline PKC was measured after 50-minute perfusion without any treatment(n=5). Left ventricular function including developed pressure(LVDP), dP/dt, heart rate, left ventricular end-diastolic pressure(LVEDP) and coronary flow(CF) was measured. Myo car ial cytosolic and membrane PKC activities were measured by 32P-${\gamma}$-ATP incorporation into PKC-specific pepetide. The infarct size was determined using the TTC (tetrazolium salt) staining and planimetry. Data were analyzed using one-way analysis of variance(ANOVA) variance(ANOVA) and Tukey's post-hoc test. Result: IP increased the functional recovery including LVDP, dP/dt and CF(p<0.05) and lowered the ascending range of LVEDP(p<0.05); it also reduced the infarct size from 38% to 20%(p<0.05). In both of the Ca2+ preconditioned group, functional recovery was not significantly different in comparison with the ischemic control, however, the infarct size was reduced to 19∼23%(p<0.05). In comparison with the baseline(7.31 0.31 nmol/g tissue), the activities of the cytosolic PKC tended to decrease in both the IP and Ca2+ preconditioned groups, particularly in the 10 mM Ca2+ preconditioned group(4.19 0.39 nmol/g tissue, p<0.01); the activity of membrane PKC was significantly increased in both IP and 10 mM Ca2+ preconditioned group (p<0.05; 1.84 0.21, 4.00 0.14, and 4.02 0.70 nmol/g tissue in the baseline, IP, and 10 mM Ca2+ preconditioned group, respectively). However, the activity of both PKC fractions were not significantly different between the baseline and the ischemic control. Conclusion: These results indicate that in isolated Langendorff-perfused rabbit heart model, calcium preconditioning with high concentration of calcium does not improve post-ischemic functional recovery. However, it does have an effect of limiting(reducing) the infart size by ischemic preconditioning, and this cardioprotective effect, at least in part, may have resulted from the activation of PKC by calcium which acts as a messenger(or trigger) to activate membrane PKC.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.171-193
• /
• 2018

LOD(Linked Open Data) cloud is a practical implementation of semantic web. We suggested a new method that provides identity links conveniently in LOD cloud. It also allows changes in LOD to be reflected to searching results without any omissions. LOD provides detail descriptions of entities to public in RDF triple form. RDF triple is composed of subject, predicates, and objects and presents detail description for an entity. Links in LOD cloud, named identity links, are realized by asserting entities of different RDF triples to be identical. Currently, the identity link is provided with creating a link triple explicitly in which associates its subject and object with source and target entities. Link triples are appended to LOD. With identity links, a knowledge achieves from an LOD can be expanded with different knowledge from different LODs. The goal of LOD cloud is providing opportunity of knowledge expansion to users. Appending link triples to LOD, however, has serious difficulties in discovering identity links between entities one by one notwithstanding the enormous scale of LOD. Newly added entities cannot be reflected to searching results until identity links heading for them are serialized and published to LOD cloud. Instead of creating enormous identity links, we propose LOD to prepare its own link policy. The link policy specifies a set of target LODs to link and constraints necessary to discover identity links to entities on target LODs. On searching, it becomes possible to access newly added entities and reflect them to searching results without any omissions by referencing the link policies. Link policy specifies a set of predicate pairs for discovering identity between associated entities in source and target LODs. For the link policy specification, we have suggested a set of vocabularies that conform to RDFS and OWL. Identity between entities is evaluated in accordance with a similarity of the source and the target entities' objects which have been associated with the predicates' pair in the link policy. We implemented a system "Change Acceptable In-Depth Searching System(CAIDS)". With CAIDS, user's searching request starts from depth_0 LOD, i.e. surface searching. Referencing the link policies of LODs, CAIDS proceeds in-depth searching, next LODs of next depths. To supplement identity links derived from the link policies, CAIDS uses explicit link triples as well. Following the identity links, CAIDS's in-depth searching progresses. Content of an entity obtained from depth_0 LOD expands with the contents of entities of other LODs which have been discovered to be identical to depth_0 LOD entity. Expanding content of depth_0 LOD entity without user's cognition of such other LODs is the implementation of knowledge expansion. It is the goal of LOD cloud. The more identity links in LOD cloud, the wider content expansions in LOD cloud. We have suggested a new way to create identity links abundantly and supply them to LOD cloud. Experiments on CAIDS performed against DBpedia LODs of Korea, France, Italy, Spain, and Portugal. They present that CAIDS provides appropriate expansion ratio and inclusion ratio as long as degree of similarity between source and target objects is 0.8 ~ 0.9. Expansion ratio, for each depth, depicts the ratio of the entities discovered at the depth to the entities of depth_0 LOD. For each depth, inclusion ratio illustrates the ratio of the entities discovered only with explicit links to the entities discovered only with link policies. In cases of similarity degrees with under 0.8, expansion becomes excessive and thus contents become distorted. Similarity degree of 0.8 ~ 0.9 provides appropriate amount of RDF triples searched as well. Experiments have evaluated confidence degree of contents which have been expanded in accordance with in-depth searching. Confidence degree of content is directly coupled with identity ratio of an entity, which means the degree of identity to the entity of depth_0 LOD. Identity ratio of an entity is obtained by multiplying source LOD's confidence and source entity's identity ratio. By tracing the identity links in advance, LOD's confidence is evaluated in accordance with the amount of identity links incoming to the entities in the LOD. While evaluating the identity ratio, concept of identity agreement, which means that multiple identity links head to a common entity, has been considered. With the identity agreement concept, experimental results present that identity ratio decreases as depth deepens, but rebounds as the depth deepens more. For each entity, as the number of identity links increases, identity ratio rebounds early and reaches at 1 finally. We found out that more than 8 identity links for each entity would lead users to give their confidence to the contents expanded. Link policy based in-depth searching method, we proposed, is expected to contribute to abundant identity links provisions to LOD cloud.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.77-97
• /
• 2010

Market timing is an investment strategy which is used for obtaining excessive return from financial market. In general, detection of market timing means determining when to buy and sell to get excess return from trading. In many market timing systems, trading rules have been used as an engine to generate signals for trade. On the other hand, some researchers proposed the rough set analysis as a proper tool for market timing because it does not generate a signal for trade when the pattern of the market is uncertain by using the control function. The data for the rough set analysis should be discretized of numeric value because the rough set only accepts categorical data for analysis. Discretization searches for proper "cuts" for numeric data that determine intervals. All values that lie within each interval are transformed into same value. In general, there are four methods for data discretization in rough set analysis including equal frequency scaling, expert's knowledge-based discretization, minimum entropy scaling, and na$\ddot{i}$ve and Boolean reasoning-based discretization. Equal frequency scaling fixes a number of intervals and examines the histogram of each variable, then determines cuts so that approximately the same number of samples fall into each of the intervals. Expert's knowledge-based discretization determines cuts according to knowledge of domain experts through literature review or interview with experts. Minimum entropy scaling implements the algorithm based on recursively partitioning the value set of each variable so that a local measure of entropy is optimized. Na$\ddot{i}$ve and Booleanreasoning-based discretization searches categorical values by using Na$\ddot{i}$ve scaling the data, then finds the optimized dicretization thresholds through Boolean reasoning. Although the rough set analysis is promising for market timing, there is little research on the impact of the various data discretization methods on performance from trading using the rough set analysis. In this study, we compare stock market timing models using rough set analysis with various data discretization methods. The research data used in this study are the KOSPI 200 from May 1996 to October 1998. KOSPI 200 is the underlying index of the KOSPI 200 futures which is the first derivative instrument in the Korean stock market. The KOSPI 200 is a market value weighted index which consists of 200 stocks selected by criteria on liquidity and their status in corresponding industry including manufacturing, construction, communication, electricity and gas, distribution and services, and financing. The total number of samples is 660 trading days. In addition, this study uses popular technical indicators as independent variables. The experimental results show that the most profitable method for the training sample is the na$\ddot{i}$ve and Boolean reasoning but the expert's knowledge-based discretization is the most profitable method for the validation sample. In addition, the expert's knowledge-based discretization produced robust performance for both of training and validation sample. We also compared rough set analysis and decision tree. This study experimented C4.5 for the comparison purpose. The results show that rough set analysis with expert's knowledge-based discretization produced more profitable rules than C4.5.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.27-65
• /
• 2020

Many companies on information and communication technology make public their own developed AI technology, for example, Google's TensorFlow, Facebook's PyTorch, Microsoft's CNTK. By releasing deep learning open source software to the public, the relationship with the developer community and the artificial intelligence (AI) ecosystem can be strengthened, and users can perform experiment, implementation and improvement of it. Accordingly, the field of machine learning is growing rapidly, and developers are using and reproducing various learning algorithms in each field. Although various analysis of open source software has been made, there is a lack of studies to help develop or use deep learning open source software in the industry. This study thus attempts to derive a strategy for adopting the framework through case studies of a deep learning open source framework. Based on the technology-organization-environment (TOE) framework and literature review related to the adoption of open source software, we employed the case study framework that includes technological factors as perceived relative advantage, perceived compatibility, perceived complexity, and perceived trialability, organizational factors as management support and knowledge & expertise, and environmental factors as availability of technology skills and services, and platform long term viability. We conducted a case study analysis of three companies' adoption cases (two cases of success and one case of failure) and revealed that seven out of eight TOE factors and several factors regarding company, team and resource are significant for the adoption of deep learning open source framework. By organizing the case study analysis results, we provided five important success factors for adopting deep learning framework: the knowledge and expertise of developers in the team, hardware (GPU) environment, data enterprise cooperation system, deep learning framework platform, deep learning framework work tool service. In order for an organization to successfully adopt a deep learning open source framework, at the stage of using the framework, first, the hardware (GPU) environment for AI R&D group must support the knowledge and expertise of the developers in the team. Second, it is necessary to support the use of deep learning frameworks by research developers through collecting and managing data inside and outside the company with a data enterprise cooperation system. Third, deep learning research expertise must be supplemented through cooperation with researchers from academic institutions such as universities and research institutes. Satisfying three procedures in the stage of using the deep learning framework, companies will increase the number of deep learning research developers, the ability to use the deep learning framework, and the support of GPU resource. In the proliferation stage of the deep learning framework, fourth, a company makes the deep learning framework platform that improves the research efficiency and effectiveness of the developers, for example, the optimization of the hardware (GPU) environment automatically. Fifth, the deep learning framework tool service team complements the developers' expertise through sharing the information of the external deep learning open source framework community to the in-house community and activating developer retraining and seminars. To implement the identified five success factors, a step-by-step enterprise procedure for adoption of the deep learning framework was proposed: defining the project problem, confirming whether the deep learning methodology is the right method, confirming whether the deep learning framework is the right tool, using the deep learning framework by the enterprise, spreading the framework of the enterprise. The first three steps (i.e. defining the project problem, confirming whether the deep learning methodology is the right method, and confirming whether the deep learning framework is the right tool) are pre-considerations to adopt a deep learning open source framework. After the three pre-considerations steps are clear, next two steps (i.e. using the deep learning framework by the enterprise and spreading the framework of the enterprise) can be processed. In the fourth step, the knowledge and expertise of developers in the team are important in addition to hardware (GPU) environment and data enterprise cooperation system. In final step, five important factors are realized for a successful adoption of the deep learning open source framework. This study provides strategic implications for companies adopting or using deep learning framework according to the needs of each industry and business.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.233-243
• /
• 2008

Recognition for the importance and roles of public transportation is increasing because of traffic problems in many cities. In spite of this paradigm change, previous researches related with public transportation trip assignment have limits in some aspects. Especially, in case of multimodal public transportation networks, many characters should be considered such as transfers. operational time schedules, waiting time and travel cost. After metropolitan integrated transfer discount system was carried out, transfer trips are increasing among traffic modes and this takes the variation of users' route choices. Moreover, the advent of high-technology public transportation card called smart card, public transportation users' travel information can be recorded automatically and this gives many researchers new analytical methodology for multimodal public transportation networks. In this paper, it is suggested that the methodology for establishment of brand new multimodal public transportation networks based on computer programming methods using transportation card data. First, we propose the building method of integrated transportation networks based on bus and urban railroad stations in order to make full use of travel information from transportation card data. Second, it is offered how to connect the broken transfer links by computer-based programming techniques. This is very helpful to solve the transfer problems that existing transportation networks have. Lastly, we give the methodology for users' paths finding and network establishment among multi-modes in multimodal public transportation networks. By using proposed methodology in this research, it becomes easy to build multimodal public transportation networks with existing bus and urban railroad station coordinates. Also, without extra works including transfer links connection, it is possible to make large-scaled multimodal public transportation networks. In the end, this study can contribute to solve users' paths finding problem among multi-modes which is regarded as an unsolved issue in existing transportation networks.

• Progress in Medical Physics
• /
• v.25 no.2
• /
• pp.100-109
• /
• 2014

In stereotactic body radiotherapy (SBRT), the accurate location of treatment sites should be guaranteed from the respiratory motions of patients. Lots of studies on this topic have been conducted. In this letter, a new verification method simulating the real respiratory motion of heterogenous treatment regions was proposed to investigate the accuracy of lung SBRT for Volumetric Modulated Arc Therapy. Based on the CT images of lung cancer patients, lung phantoms were fabricated to equip in $QUASAR^{TM}$ respiratory moving phantom using 3D printer. The phantom was bisected in order to measure 2D dose distributions by the insertion of EBT3 film. To ensure the dose calculation accuracy in heterogeneous condition, The homogeneous plastic phantom were also utilized. Two dose algorithms; Analytical Anisotropic Algorithm (AAA) and AcurosXB (AXB) were applied in plan dose calculation processes. In order to evaluate the accuracy of treatments under respiratory motion, we analyzed the gamma index between the plan dose and film dose measured under various moving conditions; static and moving target with or without gating. The CT number of GTV region was 78 HU for real patient and 92 HU for the homemade lung phantom. The gamma pass rates with 3%/3 mm criteria between the plan dose calculated by AAA algorithm and the film doses measured in heterogeneous lung phantom under gated and no gated beam delivery with respiratory motion were 88% and 78%. In static case, 95% of gamma pass rate was presented. In the all cases of homogeneous phantom, the gamma pass rates were more than 99%. Applied AcurosXB algorithm, for heterogeneous phantom, more than 98% and for homogeneous phantom, more than 99% of gamma pass rates were achieved. Since the respiratory amplitude was relatively small and the breath pattern had the longer exhale phase than inhale, the gamma pass rates in 3%/3 mm criteria didn't make any significant difference for various motion conditions. In this study, the new phantom model of 4D dose distribution verification using patient-specific lung phantoms moving in real breathing patterns was successfully implemented. It was also evaluated that the model provides the capability to verify dose distributions delivered in the more realistic condition and also the accuracy of dose calculation.

• Journal of Chest Surgery
• /
• v.36 no.6
• /
• pp.404-410
• /
• 2003

Different treatment options are available according to the stage and duration of the empyema. Stage I empyema (exudate stage) is treated concurrently by the administration of appropriate antibiotics and chest tube drainage. Stage III empyema (organized stage) is considered for decortication through an open thoracotomy. However, the treatment of fibrinopurulent, stage II empyema remains controversial. Recently, debridement with the use of Video-Assisted Thoracoscopic Surgery (VATS) has been proposed for the treatment of stage II empyema. We analyzed and report our initial experience of 5 cases of stage II empyema, treated with the use of VATS. Material and Method: Between June 2001 and February 2002, 5 patients with fibrinopurulent empyema that did not respond to antibiotics, chest tube drainage or Percutaneous Catheter drainage (PCD), and instillation of fibrinolytic agent were treated by debridement and irrigation with the use of VATS. A CT scan was performed in all patients before the operation to confirm the diagnosis of loculated empyema and to detect additional lung parenchymal diseases. Result: All 5 patients underwent successful debridement and irrigation with the use of VATS and the chest tube was inserted properly. And no patients needed conversion to open thoracotomy. The ratio of sex was 4 : 1 (male : female), the mean age was 53 years old (range, 26~73 years), the mean operative time was 73.4 minutes (range, 52~95 minutes), the mean duration of postoperative chest tube placement was 12.4 days (range, 6~19 days), and the mean duration of postoperative hospital stay was 20.8 days (range, 10~36 days). In all patients, clinical symptoms such as pain and fever subsided and simple chest PA view revealed satisfactory lung expansion. No major postoperative complication was observed during the hospital course and no patient suffered from the recurrence of empyema in the follow-up period. Conclusion: We think that early operation with the use of VATS is safe and efficient for stage II empyema which did not respond to medical treatment(antibiotics and chest tube drainage), therefore, it can prevent stage II empyema from advancing to stage III, organized empyema.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.345-361
• /
• 2005

A transform-space index indexes objects represented as points in the transform space An advantage of a transform-space index is that optimization of join algorithms using these indexes becomes relatively simple. However, the disadvantage is that these algorithms cannot be applied to original-space indexes such as the R-tree. As a way of overcoming this disadvantages, the authors earlier proposed the transform-space view join algorithm that joins two original- space indexes in the transform space through the notion of the transform-space view. A transform-space view is a virtual transform-space index that allows us to perform join in the transform space using original-space indexes. In a transform-space view join algorithm, the order of accessing disk pages -for which various space filling curves could be used -makes a significant impact on the performance of joins. In this paper, we Propose a new space filling curve called the adaptive row major order (ARM order). The ARM order adaptively controls the order of accessing pages and significantly reduces the one-pass buffer size (the minimum buffer size required for guaranteeing one disk access per page) and the number of disk accesses for a given buffer size. Through analysis and experiments, we verify the excellence of the ARM order when used with the transform-space view join. The transform-space view join with the ARM order always outperforms existing ones in terms of both measures used: the one-pass buffer size and the number of disk accesses for a given buffer size. Compared to other conventional space filling curves used with the transform-space view join, it reduces the one-pass buffer size by up to 21.3 times and the number of disk accesses by up to $74.6\%$. In addition, compared to existing spatial join algorithms that use R-trees in the original space, it reduces the one-pass buffer size by up to 15.7 times and the number of disk accesses by up to $65.3\%$.