• 한국추진공학회지
• /
• 제10권2호
• /
• pp.102-109
• /
• 2006

본 논문에서 항공기용 터보 축 엔진의 결함 진단 알고리즘을 개발하기 위해 Support Vector Machine(SVM)과 인공신경망(ANN)을 이용하였다. 신경망을 이용한 시스템은 비선형성이 과도한 데이터를 학습할 때 지역 최소점(Local Minima)에 빠져 분류 정확률이 낮아질 수 있다. 이러한 위험성을 보안하기 위해 SVM에 의한 ANN의 분할 학습 알고리즘(SLA)을 제안하였다. 이것은 SVM을 이용하여 결함 위치를 판별 한 후 신경망이 선택적으로 학습을 하는 방법으로 학습 데이터의 비선형성을 줄여 분류 정확률을 높이기 때문에 신경망을 단독으로 사용할 때보다 개선된 성능을 보여주었다.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.55-64
• /
• 2002

In this paper, we introduce SVM(support vector machine) developed to solve the problem of generalization of neural networks. We also introduce boosting algorithm which is a general method to improve accuracy of some given learning algorithm. We propose a new algorithm combining SVM and boosting to solve classification problem. Through the experiment with real and simulated data sets, we can obtain better performance of the proposed algorithm.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1324-1330
• /
• 2007

In this paper, we propose pattern recognition algorithm for activities of daily living by adopting extreme learning machine based on single layer feedforward networks(SLFNs) to the signal from bidirectional accelerometer. For activity classification, 20 persons are participated and we acquire 6, types of signals at standing, walking, running, sitting, lying, and falling. Then, we design input vector using reduced model for ELM input. In ELM classification results, we can find accuracy change by increasing the number of hidden neurons. As a result, we find the accuracy is increased by increasing the number of hidden neuron. ELM is able to classify more than 80 % accuracy for experimental data set when the number of hidden is more than 20.

• International journal of advanced smart convergence
• /
• 제6권3호
• /
• pp.17-21
• /
• 2017

In this paper, the service execution accuracy was compared by ontology based rule inference method and machine learning method, and the amount of data at the point when the service execution accuracy of the machine learning method becomes equal to the service execution accuracy of the rule inference was found. The rule inference, which measures service execution accuracy and service execution accuracy using accumulated data and pattern matching on service results. And then machine learning method measures service execution accuracy using cross validation data. After creating a confusion matrix and measuring the accuracy of each service execution, the inference algorithm can be selected from the results.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.239-245
• /
• 2020

Blockchain, machine learning, and big data are among the key components of the future IT track. These technologies are used in various fields; hence their increasing application. This paper discusses the technologies developed in various research fields, such as data representation, Blockchain application, 3D shape recognition and classification, query method, classification method, and search algorithm, to provide insights into the future paradigm. In this paper, we present a summary of 18 high-quality accepted articles following a rigorous review process in the fields of Blockchain, machine learning, and big data.

• 한국CDE학회논문집
• /
• 제2권2호
• /
• pp.111-121
• /
• 1997

This study intends to develop a fixture planning module as a part of the planning system for cutting. The fixture module uses machine learning method to reuse previous failure results so that the system can reduce the repeated failures. Machine learning is one of efforts to incorporate human reasoning ability into a computerized system. A human expert designs better than a novice does because he has a wide experience in a specific area. This study implements the machine learning algorithm to have a wide experience in the fixture planning area as a human expert does. When the fixture planner finds a setup failure for the suggested operations by a process planner, it makes the process planner store its attributes and other information for the failed setup. Then the process planner applies the learned knowledge when it meets a similar case so that the planner can reduce possibility of setup failure. Also the system can teach a novice user by showing a failed setup with a modified setup.

• International journal of advanced smart convergence
• /
• 제7권4호
• /
• pp.27-39
• /
• 2018

Since the global positioning system (GPS) has been included in mobile devices (e.g., for car navigation, in smartphones, and in smart watches), the impact of personal GPS log data on daily life has been unprecedented. For example, such log data have been used to solve public problems, such as mass transit traffic patterns, finding optimum travelers' routes, and determining prospective business zones. However, a real-time analysis technique for GPS log data has been unattainable due to theoretical limitations. We introduced a machine learning model in order to resolve the limitation. In this paper presents a new, three-stage real-time prediction model for a person's daily route activity. In the first stage, a machine learning-based clustering algorithm is adopted for place detection. The training data set was a personal GPS tracking history. In the second stage, prediction of a new person's transient mode is studied. In the third stage, to represent the person's activity on those daily routes, inference rules are applied.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권1호
• /
• pp.45-49
• /
• 2022

In this paper, we propose a method for estimating the error of the Ultra-Wideband (UWB) distance measurement using the channel impulse response (CIR) of the UWB signal based on machine learning. Due to the recent demand for indoor location-based services, wireless signal-based localization technologies are being studied, such as UWB, Wi-Fi, and Bluetooth. The constructive obstacles constituting the indoor environment make the distance measurement of UWB inaccurate, which lowers the indoor localization accuracy. Therefore, we apply machine learning to learn the characteristics of UWB signals and estimate the error of UWB distance measurements. In addition, the performance of the proposed algorithm is analyzed through experiments in an indoor environment composed of various walls.

• Computers and Concrete
• /
• 제32권6호
• /
• pp.607-613
• /
• 2023

The objective of this work is to determine the compressive strength of geopolymer concrete utilizing four distinct machine learning approaches. These techniques are known as gradient boosting machine (GBM), generalized linear model (GLM), extremely randomized trees (XRT), and deep learning (DL). Experimentation is performed to collect the data that is then utilized for training the models. Compressive strength is the response variable, whereas curing days, curing temperature, silica fume, and nanosilica concentration are the different input parameters that are taken into consideration. Several kinds of errors, including root mean square error (RMSE), coefficient of correlation (CC), variance account for (VAF), RMSE to observation's standard deviation ratio (RSR), and Nash-Sutcliffe effectiveness (NSE), were computed to determine the effectiveness of each algorithm. It was observed that, among all the models that were investigated, the GBM is the surrogate model that can predict the compressive strength of the geopolymer concrete with the highest degree of precision.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.91-100
• /
• 2023

As SDN devices and systems hit the market, security in SDN must be raised on the agenda. SDN has become an interesting area in both academics and industry. SDN promises many benefits which attract many IT managers and Leading IT companies which motivates them to switch to SDN. Over the last three decades, network attacks becoming more sophisticated and complex to detect. The goal is to study how traffic information can be extracted from an SDN controller and open virtual switches (OVS) using SDN mechanisms. The testbed environment is created using the RYU controller and Mininet. The extracted information is further used to detect these attacks efficiently using a machine learning approach. To use the Machine learning approach, a dataset is required. Currently, a public SDN based dataset is not available. In this paper, SDN based dataset is created which include legitimate and non-legitimate traffic. Classification is divided into two categories: binary and multiclass classification. Traffic has been classified with or without dimension reduction techniques like PCA and LDA. Our approach provides 98.58% of accuracy using a random forest algorithm.