• Journal of Korea Water Resources Association
• /
• v.57 no.5
• /
• pp.333-346
• /
• 2024

High-resolution medium-range streamflow prediction is crucial for sustainable water quality and aquatic ecosystem management. For reliable medium-range streamflow predictions, it is necessary to understand the characteristics of forcings and to effectively utilize weather forecast data with low spatio-temporal resolutions. In this study, we presented a comparative analysis of medium-range streamflow predictions using the distributed hydrological model, WRF-Hydro, and the numerical weather forecast Global Data Assimilation and Prediction System (GDAPS) in the Geumho River basin, Korea. Multiple forcings, ground observations (AWS&ASOS), numerical weather forecast (GDAPS), and Global Land Data Assimilation System (GLDAS), were ingested to investigate the performance of streamflow predictions with highresolution WRF-Hydro configuration. In terms of the mean areal accumulated rainfall, GDAPS was overestimated by 36% to 234%, and GLDAS reanalysis data were overestimated by 80% to 153% compared to AWS&ASOS. The performance of streamflow predictions using AWS&ASOS resulted in KGE and NSE values of 0.6 or higher at the Kangchang station. Meanwhile, GDAPS-based streamflow predictions showed high variability, with KGE values ranging from 0.871 to -0.131 depending on the rainfall events. Although the peak flow error of GDAPS was larger or similar to that of GLDAS, the peak flow timing error of GDAPS was smaller than that of GLDAS. The average timing errors of AWS&ASOS, GDAPS, and GLDAS were 3.7 hours, 8.4 hours, and 70.1 hours, respectively. Medium-range streamflow predictions using GDAPS and high-resolution WRF-Hydro may provide useful information for water resources management especially in terms of occurrence and timing of peak flow albeit high uncertainty in flood magnitude.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

• Journal of Ginseng Research
• /
• v.26 no.3
• /
• pp.111-131
• /
• 2002

Korean ginseng (Panax ginseng C.A. Meyer) received a great deal of attention from the Orient and West as a tonic agent, health food and/or alternative herbal therapeutic agent. However, controversy with respect to scientific evidence on pharmacological effects especially, evaluation of clinical efficacy and the methodological approach still remains to be solved. Author reviewed those articles published since 1980 when pharmacodynamic studies on ginseng have intensively started. Special concern was paid on metabolic disorders including diabetes mellitus, circulatory disorders, malignant tumor, sexual dysfunction, and physical and mental performance to give clear information to those who are interested in pharmacological study of ginseng and to promote its clinical use. With respect to chronic diseases such as diabetes mellitus, atherosclerosis, high blood pressure, malignant disorders, and sexual disorders, it seems that ginseng plays preventive and restorative role rather than therapeutics. Particularly, ginseng plays a significant role in ameliorating subjective symptoms and preventing quality of life from deteriorating by long term exposure of chemical therapeutic agents. Also it seems that the potency of ginseng is mild, therefore it could be more effective when used concomitantly with conventional therapy. Clinical studies on the tonic effect of ginseng on work performance demonstrated that physical and mental dysfunction induced by various stresses are improved by increasing adaptability of physical condition. However, the results obtained from clinical studies cannot be mentioned in the indication, which are variable upon the scientist who performed those studies. In this respect, standardized ginseng product and providing planning of the systematic clinical research in double-blind randomized controlled trials are needed to assess the real efficacy for proposing ginseng indication. Pharmacological mode of action of ginseng has not yet been fully elucidated. Pharmacodynamic and pharmacokinetic researches reveal that the role of ginseng not seem to be confined to a given single organ. It has been known that ginseng plays a beneficial role in such general organs as central nervous, endocrine, metabolic, immune systems, which means ginseng improves general physical and mental conditons. Such multivalent effect of ginseng can be attributed to the main active component of ginseng,ginsenosides or non-saponin compounds which are also recently suggested to be another active ingredients. As is generally the similar case with other herbal medicines, effects of ginseng cannot be attributed as a given single compound or group of components. Diversified ingredients play synergistic or antagonistic role each other and act in harmonized manner. A few cases of adverse effect in clinical uses are reported, however, it is not observed when standardized ginseng products are used and recommended dose was administered. Unfavorable interaction with other drugs has also been suggested, which the information on the products and administered dosage are not available. However, efficacy, safety, interaction or contraindication with other medicines has to be more intensively investigated in order to promote clinical application of ginseng. For example, daily recommended doses per day are not agreement as 1-2g in the West and 3-6 g in the Orient. Duration of administration also seems variable according to the purpose. Two to three months are generally recommended to feel the benefit but time- and dose-dependent effects of ginseng still need to be solved from now on. Furthermore, the effect of ginsenosides transformed by the intestinal microflora, and differential effect associated with ginsenosides content and its composition also should be clinically evaluated in the future. In conclusion, the more wide-spread use of ginseng as a herbal medicine or nutraceutical supplement warrants the more rigorous investigations to assess its effacy and safety. In addition, a careful quality control of ginseng preparations should be done to ensure an acceptable standardization of commercial products.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.281-290
• /
• 2020

With the spread of smartphones, services that want to use personalized data are increasing. In particular, healthcare-related services deal with a variety of data, and data visualization techniques are used to effectively show this. As data visualization techniques are used, interactions in visualization are also naturally emphasized. In the PC environment, since the interaction for data visualization is performed with a mouse, various filtering for data is provided. On the other hand, in the case of interaction in a mobile environment, the screen size is small and it is difficult to recognize whether or not the interaction is possible, so that only limited visualization provided by the app can be provided through a button touch method. In order to overcome the limitation of interaction in such a mobile environment, we intend to enable data visualization interactions through conversations with chatbots so that users can check individual data through various visualizations. To do this, it is necessary to convert the user's query into a query and retrieve the result data through the converted query in the database that is storing data periodically. There are many studies currently being done to convert natural language into queries, but research on converting user queries into queries based on visualization has not been done yet. Therefore, in this paper, we will focus on query generation in a situation where a data visualization technique has been determined in advance. Supported interactions are filtering on task x-axis values and comparison between two groups. The test scenario utilized data on the number of steps, and filtering for the x-axis period was shown as a bar graph, and a comparison between the two groups was shown as a line graph. In order to develop a natural language processing model that can receive requested information through visualization, about 15,800 training data were collected through a survey of 1,000 people. As a result of algorithm development and performance evaluation, about 89% accuracy in classification model and 99% accuracy in query generation model was obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.6
• /
• pp.1210-1230
• /
• 1997

In this paper, we suggest an architecture of DS/CDMA tranceiver composed of one pilot channel used as reference and multiple traffic channels. The pilot channel-an unmodulated PN code-is used as the reference signal for synchronization of PN code and data demondulation. The coherent demodulation architecture is also exploited for the reverse link as well as for the forward link. Here are the characteristics of the suggested DS/CDMA system. First, we suggest an interlaced quadrature spreading(IQS) method. In this method, the PN coe for I-phase 1st channel is used for Q-phase 2nd channels and the PN code for Q-phase 1st channel is used for I-phase 2nd channel, and so on-which is quite different from the eisting spreading schemes of DS/CDMA systems, such as IS-95 digital CDMA cellular or W-CDMA for PCS. By doing IQS spreading, we can drastically reduce the zero crossing rate of the RF signals. Second, we introduce an adaptive threshold setting for the synchronization of PN code, an initial acquistion method that uses a single PN code generator and reduces the acquistion time by a half compared the existing ones, and exploit the state machines to reduce the reacquistion time Third, various kinds of functions, such as automatic frequency control(AFC), automatic level control(ALC), bit-error-rate(BER) estimator, and spectral shaping for reducing the adjacent channel interference, are introduced to improve the system performance. Fourth, we designed and implemented the DS/CDMA MODEM to be used for variable transmission rate applications-from 16Kbps to 1.024Mbps. We developed and confirmed the DS/CDMA MODEM architecture through mathematical analysis and various kind of simulations. The ASIC design was done using VHDL coding and synthesis. To cope with several different kinds of applications, we developed transmitter and receiver ASICs separately. While a single transmitter or receiver ASC contains three channels (one for the pilot and the others for the traffic channels), by combining several transmitter ASICs, we can expand the number of channels up to 64. The ASICs are now under use for implementing a line-of-sight (LOS) radio equipment.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.113-129
• /
• 2015

Location branding is a very important income making activity, by giving special meanings to a specific location while producing identity and communal value which are based around the understanding of a place's location branding concept methodology. Many other areas, such as marketing, architecture, and city construction, exert an influence creating an impressive brand image. A place brand which shows great recognition to both native people of S. Korea and foreigners creates significant economic effects. There has been research on creating a strategically and detailed place brand image, and the representative research has been carried out by Anholt who surveyed two million people from 50 different countries. However, the investigation, including survey research, required a great deal of effort from the workforce and required significant expense. As a result, there is a need to make more affordable, objective and effective research methods. The purpose of this paper is to find a way to measure the intensity of the image of the brand objective and at a low cost through text mining purposes. The proposed method extracts the keyword and the factors constructing the location brand image from the related web documents. In this way, we can measure the brand image intensity of the specific location. The performance of the proposed methodology was verified through comparison with Anholt's 50 city image consistency index ranking around the world. Four methods are applied to the test. First, RNADOM method artificially ranks the cities included in the experiment. HUMAN method firstly makes a questionnaire and selects 9 volunteers who are well acquainted with brand management and at the same time cities to evaluate. Then they are requested to rank the cities and compared with the Anholt's evaluation results. TM method applies the proposed method to evaluate the cities with all evaluation criteria. TM-LEARN, which is the extended method of TM, selects significant evaluation items from the items in every criterion. Then the method evaluates the cities with all selected evaluation criteria. RMSE is used to as a metric to compare the evaluation results. Experimental results suggested by this paper's methodology are as follows: Firstly, compared to the evaluation method that targets ordinary people, this method appeared to be more accurate. Secondly, compared to the traditional survey method, the time and the cost are much less because in this research we used automated means. Thirdly, this proposed methodology is very timely because it can be evaluated from time to time. Fourthly, compared to Anholt's method which evaluated only for an already specified city, this proposed methodology is applicable to any location. Finally, this proposed methodology has a relatively high objectivity because our research was conducted based on open source data. As a result, our city image evaluation text mining approach has found validity in terms of accuracy, cost-effectiveness, timeliness, scalability, and reliability. The proposed method provides managers with clear guidelines regarding brand management in public and private sectors. As public sectors such as local officers, the proposed method could be used to formulate strategies and enhance the image of their places in an efficient manner. Rather than conducting heavy questionnaires, the local officers could monitor the current place image very shortly a priori, than may make decisions to go over the formal place image test only if the evaluation results from the proposed method are not ordinary no matter what the results indicate opportunity or threat to the place. Moreover, with co-using the morphological analysis, extracting meaningful facets of place brand from text, sentiment analysis and more with the proposed method, marketing strategy planners or civil engineering professionals may obtain deeper and more abundant insights for better place rand images. In the future, a prototype system will be implemented to show the feasibility of the idea proposed in this paper.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.