• Smart Media Journal
• /
• v.9 no.2
• /
• pp.51-62
• /
• 2020

Starting with the "Smart Grid National Road Map" in 2010, the Smart Grid 2030 was introduced through the basic plan and implementation plan of the intelligent power grid with the goal of building the world's first national smart grid. In this paper, we intend to build a power domain ontology based on the power business platform based on the upper and lower conceptual models of the "Smart Grid Interoperability Standard Framework and Roadmap", the standard of implementation plan. Ontology is suitable for expressing and utilizing the smart grid conceptual model because it considers hierarchical structure as knowledge defines the properties of entities and relationships between entities, but there is no research related to them. Therefore, in this paper, the upper ontology was defined as a major category for smart grid-related fields, and the lower ontology was defined as detailed systems and functions for the upper ontology to construct the ontology. In addition, scenarios in various situations that could occur in the power system were constructed and significant inference results were derived through inference engines and queries.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.1-16
• /
• 2007

According to the expansion of the Internet use and the utilization of e-business, there are an increasing number of studies of intelligent-based systems for the preparation of ubiquitous environment. In addition, expert systems have been developed from Stand Alone types to web-based Client-Server types, which are now used in various Internet environments. In this paper, we investigated the environment of development for web-based expert systems, we classified and analyzed them according to type, and suggested general typical models of web-based expert systems and their architectures. We classified the web-based expert systems with two perspectives. First, we classified them into the Server Oriented model and Client Oriented model based on the Load Balancing aspect between client and server. Second, based on the degree of knowledge and inference-sharing, we classified them into the No Sharing model, Server Sharing model, Client Sharing model and Client-Server Sharing model. By combining them we derived eight types of web-based expert systems. We also analyzed the location problems of Knowledge Bases, Fact Bases, and Inference Engines on the Internet, and analyzed the pros & cons, the technologies, the considerations, and the service types for each model. With the framework proposed from this study, we can develop more efficient expert systems in future environments.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.19
• /
• pp.8371-8376
• /
• 2014

Background: The use of statistical methods has become an imperative tool in breast cancer survival data analysis. The purpose of this study was to develop the best statistical probability model using the Bayesian method to predict future survival times for the black non-Hispanic female breast cancer patients diagnosed during 1973-2009 in the U.S. Materials and Methods: We used a stratified random sample of black non-Hispanic female breast cancer patient data from the Surveillance Epidemiology and End Results (SEER) database. Survival analysis was performed using Kaplan-Meier and Cox proportional regression methods. Four advanced types of statistical models, Exponentiated Exponential (EE), Beta Generalized Exponential (BGE), Exponentiated Weibull (EW), and Beta Inverse Weibull (BIW) were utilized for data analysis. The statistical model building criteria, Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) were used to measure the goodness of fit tests. Furthermore, we used the Bayesian approach to obtain the predictive survival inferences from the best-fit data based on the exponentiated Weibull model. Results: We identified the highest number of black non-Hispanic female breast cancer patients in Michigan and the lowest in Hawaii. The mean (SD), of age at diagnosis (years) was 58.3 (14.43). The mean (SD), of survival time (months) for black non-Hispanic females was 66.8 (30.20). Non-Hispanic blacks had a significantly increased risk of death compared to Black Hispanics (Hazard ratio: 1.96, 95%CI: 1.51-2.54). Compared to other statistical probability models, we found that the exponentiated Weibull model better fits for the survival times. By making use of the Bayesian method predictive inferences for future survival times were obtained. Conclusions: These findings will be of great significance in determining appropriate treatment plans and health-care cost allocation. Furthermore, the same approach should contribute to build future predictive models for any health related diseases.

• Journal of Korea Water Resources Association
• /
• v.38 no.7 s.156
• /
• pp.565-574
• /
• 2005

It is used water quality data that was measured at Pyeongchanggang real time monitoring stations in Namhan river. These characteristics were analyzed with the water qualify of rainy and nonrainy periods. TOC (Total Organic Carbon) data of rainy periods has correlation with discharge and shows high values of mean, maximum, and standard deviation. DO (Dissolved Oxygen) value of rainy periods is lower than those of nonrainy periods. Input data of the water quality forecasting models that they were constructed by neural network and neuro-fuzzy was chosen as the reasonable data, and water qualify forecasting models were applied. LMNN, MDNN, and ANFIS models have achieved the highest overall accuracy of TOC data. LMNN (Levenberg-Marquardt Neural Network) and MDNN (MoDular Neural Network) model which are applied for DO forecasting shows better results than ANFIS (Adaptive Neuro-Fuzzy Inference System). MDNN model shows the lowest estimation error when using daily time, which is qualitative data trained with quantitative data. The observation of discharge and water quality are effective at same point as well as same time for real time management. But there are some of real time water quality monitoring stations far from the T/M water stage. Pyeongchanggang station is one of them. So discharge on Pyeongchanggang station was calculated by developed runoff neural network model, and the water quality forecasting model is linked to the runoff forecasting model. That linked model shows the improvement of waterquality forecasting.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.20 no.1
• /
• pp.57-64
• /
• 2007

One of the cause of insulation failure in power cable is well known by electrical treeing discharge. This is occurred for imposed continuous stress at cable. And this event is related to safety, reliability and maintenance. In this paper, throughout analysis of partial discharge(PD) distribution when occurring the electrical tree, is studied for the purpose of knowing of electrical treeing discharge characteristics according to defects. Own characteristic of tree will be differently processed in each defect and this reason is the first purpose of this paper. To acquire PD data, three defective tree models were made. And their own data is shown by the phase-resolved partial discharge method (PRPD). As a result of PRPD, tree discharge sources have their own characteristics. And if other defects (void, metal particle) exist internal power cable then their characteristics are shown very different. This result Is related to the time of breakdown and this is importance of cable diagnosis. And classification method of PD sources was studied in this paper. It needs select the most useful method to apply PD data classification one of the proposed method. To meet the requirement, we select methods of different type. That is, neural network(NN-BP), adaptive neuro-fuzzy inference system and PCA-LDA were applied to result. As a result of, ANFIS shows the highest rate which value is 98 %. Generally, PCA-LDA and ANFIS are better than BP. Finally, we performed classification of tree progress using ANFIS and that result is 92 %.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.735-744
• /
• 2009

In this paper, we introduce a fast approach for Bayesian detection of change points in long-memory processes. Since a heavy computation is needed to evaluate the likelihood function of long-memory processes, a method for simplifying the computational process is required to efficiently implement a Bayesian inference. Instead of estimating the parameter, we consider selecting a element from the set of possible parameters obtained by categorizing the parameter space. This approach simplifies the detection algorithm and reduces the computational time to detect change points. Since the parameter space is (0, 0.5), there is no big difference between the result of parameter estimation and selection under a proper fractionation of the parameter space. The analysis of Nile river data showed the validation of the proposed method.