• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.970-976
• /
• 2007

In this study, Polynomial Network Pattern Classifier(PNC) based on Fuzzy Inference Mechanism is designed and its parameters such as learning rate, momentum coefficient and fuzzification coefficient are optimized by means of Particle Swarm Optimization. The proposed PNC employes a partition function created by Fuzzy C-means(FCM) clustering as an activation function in hidden layer and polynomials weights between hidden layer and output layer. Using polynomials weights can help to improve the characteristic of the linear classification of basic neural networks classifier. In the viewpoint of linguistic analysis, the proposed classifier is expressed as a collection of "If-then" fuzzy rules. Namely, architecture of networks is constructed by three functional modules that are condition part, conclusion part and inference part. The condition part relates to the partition function of input space using FCM clustering. In the conclusion part, a polynomial function caries out the presentation of a partitioned local space. Lastly, the output of networks is gotten by fuzzy inference in the inference part. The proposed PNC generates a nonlinear discernment function in the output space and has the better performance of pattern classification as a classifier, because of the characteristic of polynomial based fuzzy inference of PNC.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.456-462
• /
• 2008

The classification is that a new data is classified into one of given classes and is one of the most generally used data mining techniques. Memory-Based Reasoning (MBR) is a reasoning method for classification problem. MBR simply keeps many patterns which are represented by original vector form of features in memory without rules for reasoning, and uses a distance function to classify a test pattern. If training patterns grows in MBR, as well as size of memory great the calculation amount for reasoning much have. NGE, FPA, and RPA methods are well-known MBR algorithms, which are proven to show satisfactory performance, but those have serious problems for memory usage and lengthy computation. In this paper, we propose DPA (Dynamic Partition Averaging) algorithm. it chooses partition points by calculating GINI-Index in the entire pattern space, and partitions the entire pattern space dynamically. If classes that are included to a partition are unique, it generates a representative pattern from partition, unless partitions relevant partitions repeatedly by same method. The proposed method has been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory and FPA, and RPA.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2010

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

• Resources Recycling
• /
• v.26 no.2
• /
• pp.46-55
• /
• 2017

In this study, the design methodology of Radial Basis Function Neural Networks is developed with the aid of Laser Induced Breakdown Spectroscopy and also applied to the practical plastics sorting system. To identify black plastics such as ABS, PP, and PS, RBFNNs classifier as a kind of intelligent algorithms is designed. The dimensionality of the obtained input variables are reduced by using PCA and divided into several groups by using K-means clustering which is a kind of clustering techniques. The entire data is split into training data and test data according to the ratio of 4:1. The 5-fold cross validation method is used to evaluate the performance as well as reliability of the proposed classifier. In case of input variables and clusters equal to 5 respectively, the classification performance of the proposed classifier is obtained as 96.78%. Also, the proposed classifier showed superiority in the viewpoint of classification performance where compared to other classifiers.

• 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.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.25-39
• /
• 2018

The purpose of this study is to develop an efficient incident detection algorithm by applying machine learning, which is being widely used in the transport sector. As a first step, network of the target site was constructed with micro-simulation model. Secondly, data has been collected under various incident scenarios produced with combination of variables that are expected to affect the incident situation. And, detection results from both McMaster algorithm, a well known incident detection algorithm, and the Naive Bayes algorithm, developed in this study, were compared. As a result of comparison, Naive Bayes algorithm showed less negative effect and better detect rate (DR) than the McMaster algorithm. However, as DR increases, so did false alarm rate (FAR). Also, while McMaster algorithm detected in four cycles, Naive Bayes algorithm determine the situation with just one cycle, which increases DR but also seems to have increased FAR. Consequently it has been identified that the Naive Bayes algorithm has a great potential in traffic incident detection.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.195-211
• /
• 2023

For the commercialization For the commercialization of autonomous vehicles (AV), the operational design domain (ODD) of automated driving systems (ADS) is to be clearly defined. A common language and consistent format must be prepared so that AV-related stakeholders can understand ODD at the same level. Therefore, overseas countries are presenting a standardized ODD framework and developing scenarios that can evaluate ADS-specific functions based on ODD. However, ODD includes conditions reflecting the characteristics of each country, such as road environment, weather environment, and traffic environment. Thus, it is necessary to clearly understand the meaning of the items defined overseas and to harmonize them to reflect the specific domestic conditions. Therefore, in this study, domestic optimization of the ODD classification system was performed by analyzing the domestic driving environment based on international standards. The driving environment of currently operating self-driving car test districts (Sangam, Seoul, and Gwangju) was investigated using the developed domestic ODD items. Then, based on the results obtained, the ranges of the ODDs in each test district were determined and compared.

• Journal of the Korea Society for Simulation
• /
• v.31 no.1
• /
• pp.11-18
• /
• 2022

Recently, research to classify human activity using imagery has been actively conducted for the purpose of crime prevention and facility safety in public places and facilities. In order to improve the performance of human activity classification, most studies have applied deep learning based-transfer learning. However, despite the increase in the number of backbone network models that are the basis of deep learning as well as the diversification of architectures, research on finding a backbone network model suitable for the purpose of operation is insufficient due to the atmosphere of using a certain model. Thus, this study applies the transfer learning into recently developed deep learning backborn network models to build an intelligent system that classifies human activity using imagery. For this, 12 types of active and high-contact human activities based on sports, not basic human behaviors, were determined and 7,200 images were collected. After 20 epochs of transfer learning were equally applied to five backbone network models, we quantitatively analyzed them to find the best backbone network model for human activity classification in terms of learning process and resultant performance. As a result, XceptionNet model demonstrated 0.99 and 0.91 in training and validation accuracy, 0.96 and 0.91 in Top 2 accuracy and average precision, 1,566 sec in train process time and 260.4MB in model memory size. It was confirmed that the performance of XceptionNet was higher than that of other models.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.154-159
• /
• 2007

Wake distribution data of stem flow fields have been accumulated systematically by model tests. If the correlation between geometrical hull information and wake distribution is grasped through the accumulated data, this correlation can be helpful to designing similar ships. In this paper, Neuro-Fuzzy system that is emerging as a new knowledge over a wide range of fields nowadays is tried to estimate the wake distribution on the propeller plan. Neuro-Fuzzy system is well known as one of prospective and representative analysis method for prediction, classification, diagnosis of real complicated world problem, and it is widely applied even in the engineering fields. For this study three-dimensional stern hull forms and nominal wake values from a model test ate structured as processing elements of input and output layer, respectively. The proposed method is proved as an useful technique in ship design by comparing measured wake distribution with predicted wake distribution.