• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2191-2201
• /
• 2012

Traffic classification seeks to assign packet flows to an appropriate quality of service (QoS) class based on flow statistics without the need to examine packet payloads. Classification proceeds in two steps. Classification rules are first built by analyzing traffic traces, and then the classification rules are evaluated using test data. In this paper, we use self-organizing map and K-means clustering as unsupervised machine learning methods to identify the inherent classes in traffic traces. Three clusters were discovered, corresponding to transactional, bulk data transfer, and interactive applications. The K-nearest neighbor classifier was found to be highly accurate for the traffic data and significantly better compared to a minimum mean distance classifier.

• International Journal of Reliability and Applications
• /
• v.10 no.1
• /
• pp.1-15
• /
• 2009

Even though the impact of manufacturing quality to reliability is not considered much as well as that of design area, a major cause of an early failure of the product is known as manufacturing problem. This research applies two different types of neural network algorithms, the Back propagation (BP) algorithm and Learning Vector Quantization (LVQ) algorithm, to identify and classify the nonrandom variation pattern on the control chart based on knowledge-based diagnosis of dimensional variation. The performance and efficiency of both algorithms are evaluated to choose the better pattern recognition system for auto body assembly process. To analyze hundred percent of the data obtained by Optical Coordinate Measurement Machine (OCMM), this research considers an application in which individual observations rather than subsample means are used. A case study for analysis of OCMM data in underbody assembly process is presented to demonstrate the proposed knowledge-based pattern recognition system.

• Journal of Computing Science and Engineering
• /
• v.1 no.2
• /
• pp.162-176
• /
• 2007

Machine Learning (ML) has become very popular within Data Mining (KDD) and Artificial Intelligence (AI) research and their applications. In the ML and KDD contexts, two main approaches can be used for inducing a Bayesian Network (BN) from data, namely, Conditional Independence (CI) and the Heuristic Search (HS). When a BN is induced for classification purposes (Bayesian Classifier - BC), it is possible to impose some specific constraints aiming at increasing the computational efficiency. In this paper a new CI based approach to induce BCs from data is proposed and two algorithms are presented. Such approach is based on the Markov Blanket concept in order to impose some constraints and optimize the traditional PC learning algorithm. Experiments performed with the ALARM, as well as other six UCI and three artificial domains revealed that the proposed approach tends to execute fewer comparison tests than the traditional PC. The experiments also show that the proposed algorithms produce competitive classification rates when compared with both, PC and Naive Bayes.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.11
• /
• pp.76-82
• /
• 1998

In this study, the Ball screw and Servo motor Mechanism is considered as a High Speed Tool Feed System for the machining of a piston of a reciprocating engine. For the machining of a piston, that shapes oval, high speed servo mechanism is needed as a positioning of a cutting tool, and the stroke of tool is 0.1 mm ~ 1 mm. Ball screw and servo motor Mechanism is available very much because this mechanism is used widely in general machine. This Mechanism has been designed with the use of the decrease in mass and partial wear of the ball screw for high speed positioning of tool. Also the periodic learning control method with the inverse transfer function compensation has been applied to the positioning control for the high accuracy positioning of tool. These applications lead the achievement of the machining of a piston with an accuracy of 5${\mu}{\textrm}{m}$ at 2500 rpm in CNC turning.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.207-212
• /
• 2021

Clustering Unlabeled Spatial-datasets to convert them to Labeled Spatial-datasets is a challenging task specially for geographical information systems. In this research study we investigated the NYC Taxi Limousine Commission dataset and discover that all of the spatial-temporal trajectory are unlabeled Spatial-datasets, which is in this case it is not suitable for any data mining tasks, such as classification and regression. Therefore, it is necessary to convert unlabeled Spatial-datasets into labeled Spatial-datasets. In this research study we are going to use the Clustering Technique to do this task for all the Trajectory datasets. A key difficulty for applying machine learning classification algorithms for many applications is that they require a lot of labeled datasets. Labeling a Big-data in many cases is a costly process. In this paper, we show the effectiveness of utilizing a Clustering Technique for labeling spatial data that leads to a high-accuracy classifier.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.273-281
• /
• 2022

In this paper, we propose a robot sound recognition system that detects various sound events. The proposed system is designed to detect various sound events in real-time by using a microphone on a robot. To get real-time performance, we use a VGG11 model which includes several convolutional neural networks with real-time normalization scheme. The VGG11 model is trained on augmented DB through 24 kinds of various environments (12 reverberation times and 2 signal to noise ratios). Additionally, based on random forest algorithm, a decision logic is also designed to generate event signals for robot applications. This logic can be used for specific classes of acoustic events with better performance than just using outputs of network model. With some experimental results, the performance of proposed sound recognition system is shown on real-time device for robots.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.397-399
• /
• 2022

Digit recognition is one of the applications of deep learning, which appears in many fields. CNN network enables us to recognize handwritten digits. Also, It can process various types of data. As we stack more layers in CNN network, we expect more performance improvements. In this paper, we added a convolution layer. as a result, we achieved an accuracy improvement from 76.96% to 98.87%, which is a nearly 21.81% increase.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.69-74
• /
• 2023

This study introduces an innovative model for zero-shot voice conversion that utilizes the capabilities of HuBERT. Zero-shot voice conversion models can transform the speech of one speaker to mimic that of another, even when the model has not been exposed to the target speaker's voice during the training phase. Comprising five main components (HuBERT, feature encoder, flow, speaker encoder, and vocoder), the model offers remarkable performance across a range of scenarios. Notably, it excels in the challenging unseen-to-unseen voice-conversion tasks. The effectiveness of the model was assessed based on the mean opinion scores and similarity scores, reflecting high voice quality and similarity to the target speakers. This model demonstrates considerable promise for a range of real-world applications demanding high-quality voice conversion. This study sets a precedent in the exploration of HuBERT-based models for voice conversion, and presents new directions for future research in this domain. Despite its complexities, the robust performance of this model underscores the viability of HuBERT in advancing voice conversion technology, making it a significant contributor to the field.

• Communications for Statistical Applications and Methods
• /
• v.30 no.6
• /
• pp.551-560
• /
• 2023

Recently, there has been significant research into the recognition of human activities using three-dimensional sequential skeleton data captured by the Kinect depth sensor. Many of these studies employ deep learning models. This study introduces a novel feature selection method for this data and analyzes it using machine learning models. Due to the high-dimensional nature of the original Kinect data, effective feature extraction methods are required to address the classification challenge. In this research, we propose using the first four moments as predictors to represent the distribution of joint sequences and evaluate their effectiveness using two datasets: The exergame dataset, consisting of three activities, and the MSR daily activity dataset, composed of ten activities. The results show that the accuracy of our approach outperforms existing methods on average across different classifiers.