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

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

• Journal of Animal Environmental Science
• /
• v.14 no.2
• /
• pp.129-138
• /
• 2008

This study was carried out to investigate the operating characteristics, water balance and chemical properties of compost during the composting with pig slurry on-farm trial. The composting plant with sawdust pile filteration was done in a forced aeration inside a house and equipped with a turning machine moving on a rails. The composting pit was 4.6m wide, 53m long and the maximum height was 2m. A field scale aerobic composting facility was tested the composting efficiency of high moisture pig slurry. The sawdust materials remained 6 months. Pig slurry was added to compost pile every other day during 6 months run. The temperature in compost pile and compost house, and input and output of moisture were measured during composting process. The result are summarized as follows; 1. The temperature of compost was varied in range of at $22.4^{\circ}C{\sim}71.1^{\circ}C$. After turning, the composting temperature decreased to $50^{\circ}C{\sim}36^{\circ}C$ during $3{\sim}5$ hours, and then raised to $64.5^{\circ}C$ 2. The temperature of compost house was maintained $20^{\circ}C{\sim}30^{\circ}C$, and relative humidity was varied in range of $50{\sim}99%$. 3. BOD, CODcr and SS of leachate water was reduced 89.5%, 81.2%, 97.5%, respectively. 4. The content of heavy metal in the final compost was lower those of Korea standards. 5. The amount of effluent was 10.2%. Total evaporation during composting Period were 74.8%. The amount of slurry per $1m^3$ sawdust was $3.16m^3$ without treatment of effluent output.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.155-169
• /
• 2014

With the rapid advances in technologies, organizations are more likely to depend on information systems in their decision-making processes. Business Intelligence (BI) systems, in particular, have become a mainstay in dealing with complex problems in an organization, partly because a variety of advanced computational methods from statistics, machine learning, and artificial intelligence can be applied to solve business problems such as demand forecasting. In addition to the ability to analyze past and present trends, these predictive analytics capabilities provide huge value to an organization's ability to respond to change in markets, business risks, and customer trends. While the performance effects of BI system use in organization settings have been studied, it has been little discussed on the use of predictive analytics technologies embedded in BI systems for forecasting tasks. Thus, this study aims to find important factors that can help to take advantage of the benefits of advanced technologies of a BI system. More generally, a BI system can be viewed as an advisor, defined as the one that formulates judgments or recommends alternatives and communicates these to the person in the role of the judge, and the information generated by the BI system as advice that a decision maker (judge) can follow. Thus, we refer to the findings from the advice-giving and advice-taking literature, focusing on the role of explanations of the system in users' advice taking. It has been shown that advice discounting could occur when an advisor's reasoning or evidence justifying the advisor's decision is not available. However, the majority of current BI systems merely provide a number, which may influence decision makers in accepting the advice and inferring the quality of advice. We in this study explore the following key factors that can influence users' advice taking within the setting of a BI system: explanations on how the box-office grosses are predicted, types of advisor, i.e., system (data mining technique) or human-based business advice mechanisms such as prediction markets (aggregated human advice) and human advisors (individual human expert advice), users' evaluations of the provided advice, and individual differences in decision-makers. Each subject performs the following four tasks, by going through a series of display screens on the computer. First, given the information of the given movie such as director and genre, the subjects are asked to predict the opening weekend box office of the movie. Second, in light of the information generated by an advisor, the subjects are asked to adjust their original predictions, if they desire to do so. Third, they are asked to evaluate the value of the given information (e.g., perceived usefulness, trust, satisfaction). Lastly, a short survey is conducted to identify individual differences that may affect advice-taking. The results from the experiment show that subjects are more likely to follow system-generated advice than human advice when the advice is provided with an explanation. When the subjects as system users think the information provided by the system is useful, they are also more likely to take the advice. In addition, individual differences affect advice-taking. The subjects with more expertise on advisors or that tend to agree with others adjust their predictions, following the advice. On the other hand, the subjects with more knowledge on movies are less affected by the advice and their final decisions are close to their original predictions. The advances in predictive analytics of a BI system demonstrate a great potential to support increasingly complex business decisions. This study shows how the designs of a BI system can play a role in influencing users' acceptance of the system-generated advice, and the findings provide valuable insights on how to leverage the advanced predictive analytics of the BI system in an organization's forecasting practices.

• Asian Journal of Turfgrass Science
• /
• v.24 no.2
• /
• pp.211-217
• /
• 2010

This study was conducted to investigate a proper method of ball mark repair by comparing the creeping bentgrass recovery speed on golf course green treated by various methods of ball mark repair. Nine general repairing methods were tested and compared; control (no repair, A type), two common methods of USGA (B type) and GCSAA (C type), three methods with fork shaped hand set performing at Korean golf courses (Ansung Benest, D; Sky72, E; Lakeside, F type), and three methods using the repair machine with 6, 8, or 14 teeth (G, H, I type, respectively). Three creeping bentgrass cultivar of 'Penncross', 'T-1', and 'CY-2' were tested in this field experiment. This test was carried out from September to November in 2009 at the nursery on the Seoul Lakeside Golf course. The average speed of turfgrass recovery after various ball mark repairing methods have been ranked as in the order of E, D, C, B, F, I, H, G, and A. The methods of hand practise showed more effective results than repair method using machines. The ball mark recovery speeds of 'Penncross' were in the order of E, D, B, C, F, I, H, and A. In the case of 'T1' and 'CY-2', similar orders were showed as D, E, B, F, C, H, I, A, G and the order of D, E, C, F, B, H, G, I, A, respectively. The ball mark recovery speed among creeping bentgrass cultivar resulted in the order of 'CY-2', 'Penncross', and 'T-1'. The most proper method of ball mark repair was repair method using a hand set tool especially the method of the Sky72 Golf course (E type). At the first, remove a damaged grass area with fork and tap. And then gather the side grasses into the center area with pulling the grasses with fork. After that, make harden and flat on the turf surface by pounding and rolling with the round wooden stick. The final Nstep, water the repaired grass surface. This ball mark repairing practise showed a most rapid and proper recovery method on creeping bentgrass green.

• Restorative Dentistry and Endodontics
• /
• v.14 no.1
• /
• pp.41-56
• /
• 1989

The purpose of this study was to examine the effect of temperature dependence of the behavior on the physical properties of posterior composite resins. Three light cure posterior composite resins (Heliomolar, Litefil-P, and P-50) and one chemical cure posterior composite resin (Bisfil-II) were used as experimental materials. Composite resin was placed in a cylindrical brass mold (2.5 mm high and 6.5 mm inside diameter) that was rested on a glass plate. Another flat glass was placed on top of the mold, and the plate was tightly clamped together. After the mold had been filled with the light cure composite material, the top surface was cured for 30 seconds with a light source. Chemical cure resin specimens were made in the same manner as above. Three hundreds and twenty composite resin specimens were constructed from the four composite materials. One hundred and sixty specimens of them were placed in a heater at $50^{\circ}C$, $75^{\circ}C$, $100^{\circ}C$, $125^{\circ}C$, $150^{\circ}C$, $175^{\circ}C$ and $200^{\circ}C$ for 5 minutes or 10 minutes respectively before compressive strengths were measured. Another one hundred and sixty specimens were tested for the diametral tensile strengths in the same way as above. They were randomly divided into eight groups according to the mode of heating methods as follows and stored in distilled water at $37^{\circ}C$ for 24 hours. Group $37^{\circ}C$ - specimens were stored at $37^{\circ}C$ in distilled water for 24 hours. Group $50^{\circ}C$ - specimens were heated at $50^{\circ}C$ after curing. Group $75^{\circ}C$ - specimens were heated at $75^{\circ}C$ after curing. Group $100^{\circ}C$ - specimens were heated at $100^{\circ}C$ after curing. Group $125^{\circ}C$ - specimens were heated at $125^{\circ}C$ after curing. Group $150^{\circ}C$ - specimens were heated at $150^{\circ}C$ after curing. Group $175^{\circ}C$ - specimens were heated at $175^{\circ}C$ after curing. Group $200^{\circ}C$ - specimens were heated at $200^{\circ}C$ after curing. Twenty specimens of each of four composite resins were respectively made by insertion of materials into same mold for examining the dimensional changes between before and after heating. The final eighty specimens were stored in distilled water at $37^{\circ}C$ for 24 hours before testing the dimensional changes. Compressive and diametral tensile strengths were measured crosshead speed 1mm/minute and 500Kg in full scale with a mechanical testing machine (DLC 500 Type, Shimadzu Co., Japan). Dimensional changes were determined by measuring the diametral changes of eighty specimens with micrometer (Mitutoyo Co., Japan). Results were as follows: 1. Diametral tensile strengths of specimens in all groups were increased with time heated compared with control group except for that in group $50^{\circ}C$ and the maximum diametral tensile strength was appeared in the specimen of Litefil-P heated for 10 minutes at $100^{\circ}C$. In heliomolar and P-50, it could be seen in the specimen heated for 10 minutes at $150^{\circ}C$, but in Bisfil-II, it could be found in the specimen heated for 5 minutes at $150^{\circ}C$. 2. Compressive strengths of specimens in all groups was tended to be also increased with time heated but that in group $50^{\circ}C$ and the maximum compressive strengths were showed in the same specimens conditioned as the diametral tensile strengths of four composite materials tested. 3. In Heliomolar, Litefil-P, and Bisfil-II, it was decreased in diameters of resin specimens between before heating and increased in diameters of resin specimens after storing in distilled water, but it was not in P-50. 4. There is little difference in diametral tensile strengths, compressive strengths, and dimensional changes followed by heating the resin specimens for 5 minutes and 10 minutes, but there is no statistical significances.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.11 no.2
• /
• pp.110-116
• /
• 2003

This study was executed to evaluate the utilization and efficiency of the ceramic biocarrier as the promoter of decomposing on the organic matters for the composting using with pig manure by analyzing of the physico-chemical properties during composting. The treatments of this experiment were consisted of the control(C),microorganism(M), M with natural zeolite(M+Z), M with synthesized zeolite(M+SZ), and M with ceramic biocarrier(M+CZ). The process term of composting was conducted for 30days in the rapidly fermented machine(as pilot system). The results of the physico-chemical properties of the composts were as follows. The changes of temperature during composting was not relative with the microorganism and zeolite materials used in the composts. At all of the treatments were similar to changing of temp. from the initial stage to the final stage. But the added microorganism treatments were higher than control. And the entire pH value of treatments were appeared the same that above temperature result, also the M+CZ and M+SZ treatment among the treatment were higher. At the results of T-C, T-N and C/N ratio, in case of T-C value, the M+CZ treatment was highly more decreased than others. However at the T-N value, there were not the differences from the each treatment. And the C/N ratio was changed according to the changes of T-C and T-N value. Especially, at the M+CZ aud M+SZ treatments were remarkably reduced by about 21.4-23.3 value. In the result of G.I for evaluating of the compost humidity, the M+CZ and M+SZ treatments were close up approximately 110 value compared with the control(G.I value 100). Therefore, the examined ceramic biocarrier amended with compost-promoting-bacteria could be applied to the production of many high quality fertilizers. It is also expected that the results of this researches could be applied to the recycle of the organic wastes based on the experimental results of ceramic biocarrier and compost-promoting-bacteria application.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.26 no.2
• /
• pp.121-143
• /
• 2010

To investigate the effect of implant types and bone resorption on the fracture characteristics. 4 types of Osstem$^{(R)}$Implant were chosen and classified into external parallel, internal parallel, external taper, internal taper groups. Finite elements analysis was conducted with ANSYS Multi Physics software. Fatigue fracture test was performed by connecting the mold to the dynamic load fatigue testing machine with maximum load of 600N and minimum load of 60N. The entire fatigue test was performed with frequency of 14Hz and fractured specimens were observed with Hitachi S-3000 H scanning electron microscope. The results were as follows: 1. In the fatigue test of 2 mm exposed implants group, Tapered type and external connected type had higher fatigue life. 2. In the fatigue test of 4 mm exposed implants group, Parallel type and external connected types had higher fatigue life. 3. The fracture patterns of all 4 mm exposed implant system appeared transversely near the dead space of the fixture. With a exposing level of 2 mm, all internally connected implant systems were fractured transversely at the platform of fixture facing the abutment. but externally connected ones were fractured at the fillet of abutment body and hexa of fixture or near the dead space of the fixture. 4. Many fatigue striations were observed near the crack initiation and propagation sites. The cleavage with facet or dimple fractures appeared at the final fracture sites. 5. Effective stress of buccal site with compressive stress is higher than that of lingual site with tensile stress, and effective stress acting on the fixture is higher than that of the abutment screw. Also, maximum effective stress acting on the parallel type fixtures is higher. It is careful to use the internal type implant system in posterior area.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.15-24
• /
• 2007

The recognition of postal address images is indispensable for the automatic sorting of postal envelopes. The process of the address image recognition is composed of three steps-address image preprocessing, character recognition, address interpretation. The extracted character images from the preprocessing step are forwarded to the character recognition step, in which multiple candidate characters with reliability scores are obtained for each character image extracted. aracters with reliability scores are obtained for each character image extracted. Utilizing those character candidates with scores, we obtain the final valid address for the input envelope image through the address interpretation step. The envelope sorting rate depends on the performance of all three steps, among which character recognition step could be said to be very important. The good character recognizer would be the one which could produce valid candidates with very reliable scores to help the address interpretation step go easy. In this paper, we propose the method of generating character candidates with reliable recognition scores. We utilize the existing MLP(multilayered perceptrons) neural network of the address recognition system in the current automatic postal envelope sorters, as the classifier for the each image from the preprocessing step. The MLP is well known to be one of the best classifiers in terms of processing speed and recognition rate. The false alarm problem, however, might be occurred in recognition results, which made the address interpretation hard. To make address interpretation easy and improve the envelope sorting rate, we propose promising methods to reestimate the recognition score (confidence) of the existing MLP classifier: the generation method of the statistical recognition properties of the classifier and the method of the combination of the MLP and the subspace classifier which roles as a reestimator of the confidence. To confirm the superiority of the proposed method, we have used the character images of the real postal envelopes from the sorters in the post office. The experimental results show that the proposed method produces high reliability in terms of error and rejection for individual characters and non-characters.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.427-435
• /
• 2023

Changes in flowering time due to weather fluctuations impact plant growth and ecosystem dynamics. Accurate prediction of flowering timing is crucial for effective forest ecosystem management. This study uses a process-based model to predict flowering timing in 2023 for five major tree species in Korean forests. Models are developed based on nine years (2009-2017) of flowering data for Abeliophyllum distichum, Robinia pseudoacacia, Rhododendron schlippenbachii, Rhododendron yedoense f. poukhanense, and Sorbus commixta, distributed across 28 regions in the country, including mountains. Weather data from the Automatic Mountain Meteorology Observation System (AMOS) and the Korea Meteorological Administration (KMA) are utilized as inputs for the models. The Single Triangle Degree Days (STDD) and Growing Degree Days (GDD) models, known for their superior performance, are employed to predict flowering dates. Daily temperature readings at a 1 km spatial resolution are obtained by merging AMOS and KMA data. To improve prediction accuracy nationwide, random forest machine learning is used to generate region-specific correction coefficients. Applying these coefficients results in minimal prediction errors, particularly for Abeliophyllum distichum, Robinia pseudoacacia, and Rhododendron schlippenbachii, with root mean square errors (RMSEs) of 1.2, 0.6, and 1.2 days, respectively. Model performance is evaluated using ten random sampling tests per species, selecting the model with the highest R². The models with applied correction coefficients achieve R² values ranging from 0.07 to 0.7, except for Sorbus commixta, and exhibit a final explanatory power of 0.75-0.9. This study provides valuable insights into seasonal changes in plant phenology, aiding in identifying honey harvesting seasons affected by abnormal weather conditions, such as those of Robinia pseudoacacia. Detailed information on flowering timing for various plant species and regions enhances understanding of the climate-plant phenology relationship.

• Journal of Korean Neurosurgical Society
• /
• v.30 no.10
• /
• pp.1210-1219
• /
• 2001

Introduction : The purpose of this study was to analyze the safety, pullout strength and radiographic characteristics of unicortical and bicortical screws of cervical facet within cadaveric specimens and evaluate the influence of level of training on the positioning of these screws. Methods : Twenty-one cadavers, mean 78.9 years of age, underwent bilateral placement of 3.5mm AO lateral mass screw from C3-C6(n=168) using a slight variation of the Magerl technique. Intraoperative imaging was not used. The right side(unicortical) utilized only 14mm screws(effective length of 11mm) while on the left side to determine the length of the screw after the ventral cortex had been drilled. Three spine surgeons(attending, fellow, chief resident) with varying levels of spine training performed the procedure on seven cadavers each. All spines were harvested and lateral radiographs were taken. Individual cervical vertebrae were carefully dissected and then axial radiographs were taken. The screws were evaluated clinically and radiographically for their safety. Screws were graded clinically for their safety with respect to the spinal cord, facet joint, nerve root and vertebral artery. The grades consisted of the following categories : "satisfactory", "at risk" and "direct injury". Each screw was also graded according to its zone placement. Screw position was quantified by measuring a sagittal angle from the lateral radiograph and an axial angle from the axial radiograph. Pull-out force was determined for all screws using a material testing machine. Results : Dissection revealed that fifteen screws on the left side actually had only unicortical and not bicortical purchase as intended. The majority of screws(92.8%) were satisfactory in terms of safety. There were no injuries to the spinal cord. On the right side(unicortical), 98.9% of the screws were "satisfactory" and on the left side(bicortical) 68.1% were "satisfactory". There was a 5.8% incidence of direct arterial injury and a 17.4% incidence of direct nerve root injury with the bicortical screws. There were no "direct injuries" with the unicortical screws for the nerve root or vertebral artery. The unicortical screws had a 21.4% incidence of direct injury of the facet joint, while the bicortical screws had a 21.7% incidence. The majority of "direct injury" of bicortical screws were placed by the surgeon with the least experience. The performance of the resident surgeon was significantly different from the attending or fellow(p<0.05) in terms of safety of the nerve root and vertebral artery. The attending's performance was significantly better than the resident or fellow(p<0.05) in terms of safety of the facet joint. There was no relationship between the safety of a screw and its zone placement. The axial deviation angle measured $23.5{\pm}6.6$ degrees and $19.8{\pm}7.9$ degrees for the unicortical and bicortical screws, respectively. The resident surgeon had a significantly lower angle than the attending or fellow(p<0.05). The sagittal angle measured $66.3{\pm}7.0$ degrees and $62.3{\pm}7.9$ degrees for the unicortical and bicortical screws, respectively. The attending had a significantly lower sagittal angle than the fellow or resident(p<0.05). Thirty-three screws that entered the facet joint were tested for pull-out strength but excluded from the data because they were not lateral mass screws per-se and had deviated substantially from the intended final trajectory. The mean pull-out force for all screws was $542.9{\pm}296.6N$. There was no statistically significant difference between the pull-out force for unicortical($519.9{\pm}286.9N$) and bicortical($565.2{\pm}306N$) screws. There was no significant difference in pull-out strengths with respect to zone placement. Conclusion : It is our belief that the risk associated with bicortical purchase mandates formal spine training if it is to be done safely and accurately. Unicortical screws are safer regardless of level of training. It is apparent that 14mm lateral mass screws placed in a supero-lateral trajectory in the adult cervical spine provide an equivalent strength with a much lower risk of injury than the longer bicortical screws placed in a similar orientation.