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

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

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.21-44
• /
• 2018

In recent years, the rapid development of internet technology and the popularization of smart devices have resulted in massive amounts of text data. Those text data were produced and distributed through various media platforms such as World Wide Web, Internet news feeds, microblog, and social media. However, this enormous amount of easily obtained information is lack of organization. Therefore, this problem has raised the interest of many researchers in order to manage this huge amount of information. Further, this problem also required professionals that are capable of classifying relevant information and hence text classification is introduced. Text classification is a challenging task in modern data analysis, which it needs to assign a text document into one or more predefined categories or classes. In text classification field, there are different kinds of techniques available such as K-Nearest Neighbor, Naïve Bayes Algorithm, Support Vector Machine, Decision Tree, and Artificial Neural Network. However, while dealing with huge amount of text data, model performance and accuracy becomes a challenge. According to the type of words used in the corpus and type of features created for classification, the performance of a text classification model can be varied. Most of the attempts are been made based on proposing a new algorithm or modifying an existing algorithm. This kind of research can be said already reached their certain limitations for further improvements. In this study, aside from proposing a new algorithm or modifying the algorithm, we focus on searching a way to modify the use of data. It is widely known that classifier performance is influenced by the quality of training data upon which this classifier is built. The real world datasets in most of the time contain noise, or in other words noisy data, these can actually affect the decision made by the classifiers built from these data. In this study, we consider that the data from different domains, which is heterogeneous data might have the characteristics of noise which can be utilized in the classification process. In order to build the classifier, machine learning algorithm is performed based on the assumption that the characteristics of training data and target data are the same or very similar to each other. However, in the case of unstructured data such as text, the features are determined according to the vocabularies included in the document. If the viewpoints of the learning data and target data are different, the features may be appearing different between these two data. In this study, we attempt to improve the classification accuracy by strengthening the robustness of the document classifier through artificially injecting the noise into the process of constructing the document classifier. With data coming from various kind of sources, these data are likely formatted differently. These cause difficulties for traditional machine learning algorithms because they are not developed to recognize different type of data representation at one time and to put them together in same generalization. Therefore, in order to utilize heterogeneous data in the learning process of document classifier, we apply semi-supervised learning in our study. However, unlabeled data might have the possibility to degrade the performance of the document classifier. Therefore, we further proposed a method called Rule Selection-Based Ensemble Semi-Supervised Learning Algorithm (RSESLA) to select only the documents that contributing to the accuracy improvement of the classifier. RSESLA creates multiple views by manipulating the features using different types of classification models and different types of heterogeneous data. The most confident classification rules will be selected and applied for the final decision making. In this paper, three different types of real-world data sources were used, which are news, twitter and blogs.

• Journal of Korean Society of Environmental Engineers
• /
• v.22 no.7
• /
• pp.1331-1343
• /
• 2000

Through the integration of USLE and GIS, the methodology to estimate the soil loss was developed, and applicated to the Sacheon river in Gangrung. Using GIS, spatial analysis such as watershed boundary determination, flow routing. slope steepness calculation was done. Spatial information from the GIS application was given for each grid. With soil and land use map, information about soil classification and land use was given for each grid too. Based upon these data, thematic maps about the factors of USLE were made. We estimated the soil loss by overlaying the thematic maps. In this manner, we can assess the degree of soil loss for each grid using GIS. Annual average soil loss of Sacheon river watershed is 1.36 ton/ha/yr. Soil loss in forest, dry field, and paddy field is 0.15 ton/ha/yr, 27.04 ton/ha/yr, 0.78 ton/ha/yr respectively. The area of dry field, which is 4% of total area, is $2.4km^2$. But total soil loss of dry field is 6561 ton/yr, and it occupies 84.9 % of total soil loss eroded in Sacheon river watershed. Comparing with the 11.2 ton/ha/yr of an average soil loss tolerance for cropland, provision for the soil loss in dry field is necessary. Run-off and water quality of Sacheon river were measured two times in flood season: from July 24, 1998 to July 28 and from September 29 to October 1. As the run-off of the river increased, SS, TN, TP concentrations and pollutant loadings increased. SS, TN, TP loads of Sacheon river discharged during the 2 heavy rains were 21%, 39%, and 19% of the total pollutant loadings generated in the Sacheon river watershed for one year. We can see that much pollutants are discharged in short period of flood season.

• Proceedings of the KOSOMBE Conference
• /
• v.1992 no.05
• /
• pp.27-47
• /
• 1992

Engineers have developed new instruments that aid in diagnosis and therapy Ultrasonic imaging has provided a nondamaging method of imaging internal organs. A complex transducer emits ultrasonic waves at many angles and reconstructs a map of internal anatomy and also velocities of blood in vessels. Fast computed tomography permits reconstruction of the 3-dimensional anatomy and perfusion of the heart at 20-Hz rates. Positron emission tomography uses certain isotopes that produce positrons that react with electrons to simultaneously emit two gamma rays in opposite directions. It locates the region of origin by using a ring of discrete scintillation detectors, each in electronic coincidence with an opposing detector. In magnetic resonance imaging, the patient is placed in a very strong magnetic field. The precessing of the hydrogen atoms is perturbed by an interrogating field to yield two-dimensional images of soft tissue having exceptional clarity. As an alternative to radiology image processing, film archiving, and retrieval, picture archiving and communication systems (PACS) are being implemented. Images from computed radiography, magnetic resonance imaging (MRI), nuclear medicine, and ultrasound are digitized, transmitted, and stored in computers for retrieval at distributed work stations. In electrical impedance tomography, electrodes are placed around the thorax. 50-kHz current is injected between two electrodes and voltages are measured on all other electrodes. A computer processes the data to yield an image of the resistivity of a 2-dimensional slice of the thorax. During fetal monitoring, a corkscrew electrode is screwed into the fetal scalp to measure the fetal electrocardiogram. Correlations with uterine contractions yield information on the status of the fetus during delivery To measure cardiac output by thermodilution, cold saline is injected into the right atrium. A thermistor in the right pulmonary artery yields temperature measurements, from which we can calculate cardiac output. In impedance cardiography, we measure the changes in electrical impedance as the heart ejects blood into the arteries. Motion artifacts are large, so signal averaging is useful during monitoring. An intraarterial blood gas monitoring system permits monitoring in real time. Light is sent down optical fibers inserted into the radial artery, where it is absorbed by dyes, which reemit the light at a different wavelength. The emitted light travels up optical fibers where an external instrument determines O2, CO2, and pH. Therapeutic devices include the electrosurgical unit. A high-frequency electric arc is drawn between the knife and the tissue. The arc cuts and the heat coagulates, thus preventing blood loss. Hyperthermia has demonstrated antitumor effects in patients in whom all conventional modes of therapy have failed. Methods of raising tumor temperature include focused ultrasound, radio-frequency power through needles, or microwaves. When the heart stops pumping, we use the defibrillator to restore normal pumping. A brief, high-current pulse through the heart synchronizes all cardiac fibers to restore normal rhythm. When the cardiac rhythm is too slow, we implant the cardiac pacemaker. An electrode within the heart stimulates the cardiac muscle to contract at the normal rate. When the cardiac valves are narrowed or leak, we implant an artificial valve. Silicone rubber and Teflon are used for biocompatibility. Artificial hearts powered by pneumatic hoses have been implanted in humans. However, the quality of life gradually degrades, and death ensues. When kidney stones develop, lithotripsy is used. A spark creates a pressure wave, which is focused on the stone and fragments it. The pieces pass out normally. When kidneys fail, the blood is cleansed during hemodialysis. Urea passes through a porous membrane to a dialysate bath to lower its concentration in the blood. The blind are able to read by scanning the Optacon with their fingertips. A camera scans letters and converts them to an array of vibrating pins. The deaf are able to hear using a cochlear implant. A microphone detects sound and divides it into frequency bands. 22 electrodes within the cochlea stimulate the acoustic the acoustic nerve to provide sound patterns. For those who have lost muscle function in the limbs, researchers are implanting electrodes to stimulate the muscle. Sensors in the legs and arms feed back signals to a computer that coordinates the stimulators to provide limb motion. For those with high spinal cord injury, a puff and sip switch can control a computer and permit the disabled person operate the computer and communicate with the outside world.

• Journal of Navigation and Port Research
• /
• v.40 no.4
• /
• pp.197-205
• /
• 2016

Our country, which relies on maritime transport a majority of import and export trade volume and faced with unexpected accidents, it is difficult to operate the normal function of container terminal. It also caused by reliability issue raised is likely to be given a blow to the new volumes to attract and maintain existing volumes. Under this views, the container terminal is a situation that highlights the role of the harbor workers and cope with aggressive work to provide the best quality services to customers 365 days. On these grounds, the heavy work burden is passed on to the harbor workers and caused accidents every year. The study was analyzed the safety status of the container terminal under the real following the conditions as disaster status analysis, insufficient safety training circumstances and safety training from 2012 year to 2015 in the target current K.Y terminal. As a result of equipments safety training analysis, it shows that 2012 year happened 45 cases and 31 cases in 2013 year until not practicing the training over the Gantry Crane equipment. One hand 23 cases took place in 2014 while preparation training and the other intensive training period of 2015, 8 cases occurred. it shows that 2012 year happened 13 cases and 19 cases in 2013 year until not practicing the training over the Transfer Crane equipment. One hand 12 cases took place in 2014 while preparation training and the other intensive training period of 2015, 8 cases occurred. it shows that 2012 year happened 9 cases and 9 cases in 2013 year until not practicing the training over the Yard Tractor equipment. One hand 9 cases took place in 2014 while preparation training and the other intensive training period of 2015, 4 cases occurred. Because safety training of the container terminal was given to greatly impact on the mandatory safety training, self-educational enforcement and specified equipments safety training, hence the container terminal is to strengthen the safety education to prevent accidents in advance.

• Food Science and Preservation
• /
• v.16 no.2
• /
• pp.276-285
• /
• 2009

This study evaluated the microbiological quality and safety of food items(seafood, meat, eggs, and frozen food) supplied to elementary school food services, during delivery, and analyzed the distribution/delivery system. To this end, 10 food items supplied by 13 factories in Daegu and Gyeongbuk were chosen for study. Beef and pork were delivered directly to schools in freezer vans. Seafood, chicken, and frozen food were delivered to schools by refrigerated vans(${\leq}10^{\circ}C$) that made other delivery stops before arriving at schools. After food was delivered to schools, total bacterial counts and coliforms(respectively) were as follows: mackerel($2.0{\times}10^2-3.2{\times}10^5$, $<5-4.0{\times}10^3CFU/g$), common squid($2.5{\times}10^4-6.6{\times}10^5$, $1.6{\times}10^2-6.0{\times}10^3CFU/g$), shellfish($3.2{\times}10^5-1.7{\times}10^3$, $4.0{\times}10^3-3.0{\times}10\;CFU/g$), boiled fish paste($1.9{\times}10^4$, <5 CFU/g), beef($9.2{\times}10^2-6.4{\times}10^4$, $<5-2.0{\times}10\;CFU/g$), pork($2.6{\times}10^3-1.3{\times}10^6$, $<5-2.7{\times}10^2CFU/g$), chicken($1.0{\times}10^4$, $2.4{\times}10^2CFU/g$), egg($<5-2.3{\times}10^2$, <5 CFU/g), frozen mandu($3.2{\times}10^3-9.5{\times}10^4$, <5 CFU/g), and frozen noodles($<5-9.0{\times}10$, <5 CFU/g). Bacillus cereus($2.0{\times}10\;CFU/g$) and E. coli($1.0{\times}10\;CFU/g$) were detected on shellfish, and Staphylococcus aureuswas detected on pork($3.1{\times}10\;CFU/g$) and chicken($7.8{\times}10\;CFU/g$). Most food items were double-wrapped in vinyl and placed in corrugated cardboard boxes prior to delivery, and the boxes weremixed with other food items when they were put in the vans. There was no cross-contamination during distribution. However, total shellfish bacterial counts increased slightly. These results indicate that foods need to be completely pasteurized during processing. Frozen food items should not be mixed and should be delivered by freezer vans(${\leq}4^{\circ}C$). The number of stops made during distribution/delivery should be reduced.

• Journal of Korean Academy of Nursing
• /
• v.28 no.4
• /
• pp.958-969
• /
• 1998

In this study, we attempted to investigate the needs and problems of the terminal cancer patients and their family caregivers to provide them with nursing information to improve their quality of life and prepare for a peaceful death. Data was collected from August 1, 1995 to July 31, 1996 at the internal medicine unit of S hospital in Seoul area with the two groups of participants who were family members of terminal cancer patients seventy four of them were in-patients and 34 were out-patients who were discharged from the same hospital for home care. The research tool used in this study has been developed by selecting the questionnaires from various references, modifying them for our purpose and refining them based on the results of preliminary study. While general background information about the patients was obtained by reviewing their medical records, all other information was collected by interviewing the primary family caregivers of the patients using the questionnaire. The data collected were analyzed with the SPSS PC/sup +/ program. The results of this study are summarized as follows ; 1) Most frequently complained symptoms of the terminal cancer patients were in the order of pain(87%), weakness(86.1%), anorexia(83.3%) and fatigue (80.6%). 2) Main therapies for the terminal cancer patients were pain control (58.3%), hyperalimentation(47.2%) and antibiotics(21.3%). 3) Special medical devices that terminal cancer patients used most were oxygen device (11.1%), and feeding tube(5.6%). Other devices were used by less than 5% of the patients. 4) The mobility of 70.4% of the patients was worse than ECOG 3 level, they had to stay in bed more than 50% of a day. 5) Patients wanted their medical staffs to help relieve pain(45.4%), various physical symptoms(29.6%), and problems associated with their emotion(11.1%). 6) 16.7% of the family caregivers hoped for full recovery of the patients, refusing to admit the status of the patients. Also, 37% wished for the extension of the patient's life at least for 6 months. 7) Only 38.9% of the family members was preparing for the patient's funeral. 8) 45.4% of family caregivers prefer hospital as the place for the patient's death, 39.8% their own home, and 14.8% undetermined. 9) Caregivers of the patients were mostly close family members, i.e., spouse(62%), and sons and daughters or daughter-in-laws(21.3%). 10) 43.5% of the family caregivers were aware of hospice care. 46.8% of them learned about the hospice care from the mass media, 27.7% from health professionals, and the rest from books and other sources. 11) Caregivers were asked about the most difficult problems they encounter in home care, 41 of them pointed out the lack of health professionals they can contact, counsel and get help from in case of emergency, 17 identified the difficulty of finding appropriate transportation to hospital, and 13 stated the difficulty of admission in hospital as needed. 12) 93.6% of family caregivers demanded 24-hour hot line, 80% the visiting nurses and doctors, and 69.4% the volunteer's help. The above results indicate that terminal patients and their family caregivers demand help from qualified health professionals whenever necessary. Hospice care system led by well-trained medical and nursing staffs is one of the viable answers for such demands.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.11 no.4
• /
• pp.138-147
• /
• 2001

The stochiometric mixtures mixture of evaporating materials for the $ZnIn_{2}S_{4}$ single crystal thin film was prepared from horizontal furnace. To obtain the $ZnIn_{2}S_{4}$ single crystal thin film, $ZnIn_{2}S_{4}$ mixed crystal was deposited on throughly etched semi-insulting GaAs(100) in the Hot Wall Epitaxy(HWE) system. The sourceand substrate temperature were $610^{\circ}C$ and $450^{\circ}C$, respectively and the growth rate of the $ZnIn_{2}S_{4}$ single crystal thin film was about 0.5$\mu\textrm{m}$/hr. The crystalline structure of $ZnIn_{2}S_{4}$ single crystal thin film was investigated by photoluminescence and double crystal X-ray diffraction (DCXD) measurement. The carrier density and mobility of $ZnIn_{2}S_{4}$ single crystal thin film measured from Hal effect by van der Pauw method are $8.51{\times}10^{17}{\textrm}{cm}^{-3}$, 291$\textrm{cm}^2$/V.s at $293^{\circ}$K, respectively. From the photocurrent spectrum by illumination of perpendicular light on the c-axis of the $ZnIn_{2}S_{4}$ single crystal thin film, we have found that the values of spin orbit splitting $\Delta$So and the crystal filed splitting DCr were 0.0148eV and 0.1678 eV at $10^{\circ}$K, respectively. From the photoluminescence measurement of $ZnIn_{2}S_{4}$ single crystal thin film, we observed free excition($E_{X}$) typically observed only in high quality crystal and neutral donor bound exicton ($D^{\circ}$, X) having very strong peak intensity. The full width at half maximum and binding energy of neutral donor bound excition were 9meV and 26meV, respectively. The activation energy of impurity measured by Haynes rule was 130meV.