• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.265-288
• /
• 2023

Process mining has generally analyzed the default logs of Information Systems such as SAP ERP, but as the use of automation software called RPA expands, the logs by RPA bots can be utilized. In this study, the actual status of RPA automation in the field was identified by applying RPA bots to the work of three domestic manufacturing companies (cosmetic field) and analyzing them after leaving logs. Using Uipath and Python, we implemented RPA bots and wrote logs. We used Disco, a software dedicated to process mining to analyze the bot logs. As a result of log analysis in two aspects of bot utilization and performance through process mining, improvement requirements were found. In particular, we found that there was a point of improvement in all cases in that the utilization of the bot and errors or exceptions were found in many cases of process. Our approach is very scientific and empirical in that it analyzes the automation status and performance of bots using data rather than existing qualitative methods such as surveys or interviews. Furthermore, our study will be a meaningful basic step for bot behavior optimization, and can be seen as the foundation for ultimately performing process management.

• Journal of Korean Association for Spatial Structures
• /
• v.20 no.2
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.191-205
• /
• 2005

This paper presents a novel product recommender system as a tool fur differentiated marketing service of online shopping malls. Ihe proposed model uses genetic algorithnt one of popular global optimization techniques, to construct a personalized product recommender systen The genetic algorinun may be useful to recommendation engine in product recommender system because it produces optimal or near-optimal recommendation rules using the customer profile and transaction data. In this study, we develop a prototype of WeLbased personalized product recommender system using the recommendation rules fi:om the genetic algorithnL In addition, this study evaluates usefulness of the proposed model through the test fur user satisfaction in real world.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.139-161
• /
• 2006

In this paper, we introduce a new combinatorial auction mechanism - N-Bilateral Optimized Combinatorial Auction (N-BOCA). N-BOCA is a flexible iterative combinatorial auction model that offers optimized trading for multi-suppliers and multi-purchasers in the supply chain. We design the N-BOCA system from the perspectives of architecture, protocol, and trading strategy. Under the given N-BOCA architecture and protocol, auctioneers and bidders have diverse decision strategies f3r winner determination. This needs flexible modeling environments. Hence, we propose an optimization modeling agent for bid and auctioneer selection. The agent has the capability to automatic model formulation for Integer Programming modeling. Finally, we show the viability of N-BOCA through prototype and experiments. The results say both higher allocation efficiency and effectiveness compared with 1-to-N general combinatorial auction mechanisms.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.389-398
• /
• 2007

Case-based reasoning (CBR) is one of the most popular prediction techniques for medical diagnosis because it is easy to apply, has no possibility of overfitting, and provides a good explanation for the output. However, it has a critical limitation - its prediction performance is generally lower than other artificial intelligence techniques like artificial neural networks (ANNs). In order to obtain accurate results from CBR, effective retrieval and matching of useful prior cases for the problem is essential, but it is still a controversial issue to design a good matching and retrieval mechanism for CBR systems. In this study, we propose a novel approach to enhance the prediction performance of CBR. Our suggestion is the simultaneous optimization of feature weights, instance selection, and the number of neighbors that combine using genetic algorithms (GAs). Our model improves the prediction performance in three ways - (1) measuring similarity between cases more accurately by considering relative importance of each feature, (2) eliminating redundant or erroneous reference cases, and (3) combining several similar cases represent significant patterns. To validate the usefulness of our model, this study applied it to a real-world case for evaluating cytological features derived directly from a digital scan of breast fine needle aspirate (FNA) slides. Experimental results showed that the prediction accuracy of conventional CBR may be improved significantly by using our model. We also found that our proposed model outperformed all the other optimized models for CBR using GA.

• Journal of Intelligence and Information Systems
• /
• v.6 no.2
• /
• pp.1-14
• /
• 2000

The berth and crane scheduling problem in a container terminal encompasses the whole process of assigning berth to each ship, determining the duration of berthing, assigning container cranes to each ship, and determining the specific start and end time of each crane service, for all the ships scheduled to be arriving at the terminal during a certain scheduling horizon. This problem is basically a constraint satisfaction problem in which cranes and berths should be assigned in such a way that all the spatial and temporal constraints are satisfied without any interference. However, it is also an optimization problem because the requested arrival and departure time should be met for as many of the scheduled ships as possible, while the operation cost of the terminal should be minimized. In this paper, we present an effective and efficient approach to solving this type of problem, which combines constrain satisfaction search and heuristic repair. We first employ a constraint satisfaction search to find a feasib1e solution. Then, the feasible solution is modified to a more optimal one by iteratively applying our heuristic repair operations within the framework of constraint satisfaction search. Experimental results with a real data from Pusan East Container Terminal showed that our approach can derive a schedule of satisfactory quality in a very short time.

• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.4
• /
• pp.41-55
• /
• 1995

In this paper, an optimal idenfication method using fuzzy-neural networks is proposed for modeling of nonlinear complex systems. The proposed fuzzy-neural modeling implements system structure and parameter identification using the intelligent schemes together wlth optimization theory, linguistic fuzzy implication rules, and neural networks(NNs) from input and output data of processes. Inference type for this fuzzy-neural modeling is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of fuzzy-neural networks(FNNs) are tuned automatically using improved modified complex method and modified learning algorithm. For the purpose of its application to nonlinear processes, data for route choice of traffic problems and those for activateti sluge process of sewage treatment system are used for the purpose of evaluating the performance of the proposed fuzzy-neural network modeling. The results show that the proposed method can produce the intelligence model with higher accuracy than other works achieved previously.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.1
• /
• pp.1-12
• /
• 2016

The current economic crisis is making new demands on manufacturing industry, in particular, in terms of the flexibility and efficiency of production processes. This requires production and administrative processes to be meshed with each other by means of IT systems to optimise the use and capacity utilisation of machines and lines but also to be able to respond rapidly to wrong developments in production and thus to minimise adverse impacts on the business. The future scenario of the "smart factory" represents the zenith of this development. The factory can be modified and expanded at will, combines all components from different manufacturers and enables them to take on context-related tasks autonomously. Integrated user interfaces will still be required at most for basic functionalities. The complex control operations will run wirelessly and ad hoc via mobile terminals such as PDAs or smartphones. The comnination of IoT, and Big Data optimisation is bringing about huge opportunities. these processes are not just limited to manufacturing, anywhere a supply chain environment exists can benefit from information provided by linked devices and access to big data to inform their decision support. Building a smart factory with smart assets at its core means reaching those desired new levels of productivity and efficiency. It means smart products that leverage advanced traceability, connectivity and intelligence. For businesses, it means being able to address the talent crunch through more autonomous. In a Smart Factory, machinery and equipment will have the ability to improve processes through self-optimization and autonomous decision-making.