• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.388-393
• /
• 2023

The analysis of engineering data using neural network based on supervised learning has been utilized in various engineering fields such as optimization of chemical engineering process, concentration prediction of particulate matter pollution, prediction of thermodynamic phase equilibria, and prediction of physical properties for transport phenomena system. The supervised learning requires training data, and the performance of the supervised learning is affected by the composition and the configurations of the given training data. Among the frequently observed engineering data, the data is given in log-scale such as length of DNA, concentration of analytes, etc. In this study, for widely distributed log-scaled training data of virtual 100×100 images, available loss functions were quantitatively evaluated in terms of (i) confusion matrix, (ii) maximum relative error and (iii) mean relative error. As a result, the loss functions of mean-absolute-percentage-error and mean-squared-logarithmic-error were the optimal functions for the log-scaled training data. Furthermore, we figured out that uniformly selected training data lead to the best prediction performance. The optimal loss functions and method for how to compose training data studied in this work would be applied to engineering problems such as evaluating DNA length, analyzing biomolecules, predicting concentration of colloidal suspension.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1153-1160
• /
• 2018

As the number of online game users increases and the market size grows, various kinds of cheating are occurring. Game bots are a typical illegal program that ensures playtime and facilitates account leveling and acquisition of various goods. In this study, we propose a method to detect game bots based on user action time interval (ATI). This technique observes the behavior of the bot in the game and selects the most frequent actions. We distinguish between normal users and game bots by applying Machine Learning to feature frequency, ATI average, and ATI standard deviation for each selected action. In order to verify the effectiveness of the proposed technique, we measured the performance using the actual log of the 'Aion' game and showed an accuracy of 97%. This method can be applied to various games because it can utilize all actions of users as well as character movements and social actions.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.47-53
• /
• 2017

In past few years, high-throughput sequencing, big-data generation, cloud computing, and computational biology are revolutionary. RNA sequencing is emerging as an attractive alternative to DNA microarrays. And the methods for constructing Gene Regulatory Network (GRN) from RNA-Seq are extremely lacking and urgently required. Because GRN has obtained substantial observation from genomics and bioinformatics, an elementary requirement of the GRN has been to maximize distinguishable genes. Despite of RNA sequencing techniques to generate a big amount of data, there are few computational methods to exploit the huge amount of the big data. Therefore, we have suggested a novel gene selection algorithm combining Support Vector Machines and Intensity-dependent normalization, which uses log differential expression ratio in RNAseq. It is an extended variation of support vector machine recursive feature elimination (SVM-RFE) algorithm. This algorithm accomplishes minimum relevancy with subsets of Big-Data, such as NCBI-GEO. The proposed algorithm was compared to the existing one which uses gene expression profiling DNA microarrays. It finds that the proposed algorithm have provided as convenient and quick method than previous because it uses all functions in R package and have more improvement with regard to the classification accuracy based on gene ontology and time consuming in terms of Big-Data. The comparison was performed based on the number of genes selected in RNAseq Big-Data.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.1-13
• /
• 2022

With the development of network technologies, the security to protect organizational resources from internal and external intrusions and threats becomes more important. Therefore in recent years, the anomaly detection algorithm that detects and prevents security threats with respect to various security log events has been actively studied. Security anomaly detection algorithms that have been developed based on rule-based or statistical learning in the past are gradually evolving into modeling based on machine learning and deep learning. In this study, we propose a deep-autoencoder model that transforms LSTM-autoencoder as an optimal algorithm to detect insider threats in advance using various machine learning analysis methodologies. This study has academic significance in that it improved the possibility of adaptive security through the development of an anomaly detection algorithm based on unsupervised learning, and reduced the false positive rate compared to the existing algorithm through supervised true positive labeling.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.1
• /
• pp.57-65
• /
• 2024

In a fire-resistant structure, uncertainties arise in factors such as ventilation, material elasticity modulus, yield strength, coefficient of thermal expansion, external forces, and fire location. The ventilation uncertainty affects thefactor contributes to uncertainties in fire temperature, subsequently impacting the structural temperature. These temperatures, combined with material properties, give rise to uncertain structural responses. Given the nonlinear behavior of structures under fire conditions, calculating fire fragility traditionally involves time-consuming Monte Carlo simulations. To address this, recent studies have explored leveraging machine learning algorithms to predict fire fragility, aiming to enhance efficiency while maintaining accuracy. This study focuses on predicting the fire fragility of a steel moment frame building, accounting for uncertainties in fire size, location, and structural material properties. The fragility curve, derived from nonlinear structural behavior under fire, follows a log-normal distribution. The results demonstrate that the proposed method accurately and efficiently predicts fire fragility, showcasing its effectiveness in streamlining the analysis process.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.207-213
• /
• 2024

In this paper, we study how to improve the performance of a machine learning-based automatic music transcription model by adding musical information to the input data. Where, the added musical information is information on the number of pitches that occur in each time frame, and which is obtained by counting the number of notes activated in the answer sheet. The obtained information on the number of pitches was used by concatenating it to the log mel-spectrogram, which is the input of the existing model. In this study, we use the automatic music transcription model included the four types of block predicting four types of musical information, we demonstrate that a simple method of adding pitch number information corresponding to the music information to be predicted by each block to the existing input was helpful in training the model. In order to evaluate the performance improvement proceed with an experiment using MIDI Aligned Piano Sounds (MAPS) data, as a result, when using all pitch number information, performance improvement was confirmed by 9.7 % in frame-based F1 score and 21.8 % in note-based F1 score including offset.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.67-70
• /
• 2003

인터넷의 정보 홍수 속에서 원하는 정보를 정확하게 제시간에 얻기란 쉬운 일이 아니며, 따라서 이러한 작업을 대신해주는 에이전트의 역할이 점점 커지고 있다. 대부분의 이벤트들이 실시간에 발생되고 처리되어야 하는 인터넷 환경에서는 분석가가 군집화의 방법과 결과 해석에 지속적으로 관여하기 어렵기 때문에 이러한 분석가의 업무를 대신하는 지능화된 에이전트가 필요하게 된다. 본 논문에서는 특히 자율학습 군집화에 대한 자동화된 시스템으로서 자동 군집화 에이전트를 제안하며 이 시스템은 군집화 수행 에이전트와 군집화 성능 평가 에이전트로 이루어져 있다. 두 개의 에이전트가 서로 정보를 교환하면서 자동적으로 최적의 군집화를 수행한다. 군집화 과정에서는 데이터를 분석하는 분석가가 군집화의 방법과 결과 해석에 실시간으로 관여하기 어렵기 때문에 이러한 작업을 담당하는 지능화된 에이전트가 자동화된 군집화를 담당하면 효과적인 군집화 전략이 될 수 있다. 또한 UCI Machine Repository의 IRIS 데이터와 Microsoft Web Log Data를 이용한 실험을 통해 제안 시스템의 성능 평가를 수행하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.118-120
• /
• 2017

모바일 이동통신망의 Core 노드들은 2G CDMA, 3G WCDMA, 4G LTE 교환기를 비롯하여 IMS 및 다양한 부가장비들로 이루어져 있다. 최근 5G로 진화하는 과정에는 NFV(Network Function Virtualization)가 그 중심에 서 있다. NFV 환경에서는 기존 통신 노드와 다르게 범용서버 및 범용 운영체제가 주축이 되어, 일반 IT 툴로도 통신망 내부 노드의 로그분석이 용이해 졌다. 또한 다양하고 복잡한 Core 네트워크에서 빅데이터로 발생하는 로그 또한 머신러닝으로 분석이 가능하며, 운용에 활용할 수 있다. 따라서 본 연구에서는 vDPI, vMMSGW OS 로그를 대상으로 분석하였으며, 잠재되어 있는 문제점들을 확인할 수 있었다. 또한 어플리케이션의 비정형화 된 로그에서도 비정상적인 패턴들을 발견하여 대용량 트래픽이 발생하며 SLA가 유난히 높은 통신환경에서도 비지도 머신러닝 분석이 유용함을 확인하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2188-2195
• /
• 2000

This paper deals with the problem of determining small-bands enclosing a given set of points on the sphere. The small-band is a spherical region, whose boundary is composed of two circles, and which does not contain any great circle. It is a kind of domains that is derived from formalizing the local accessibility problems for 3-axis NC machining into sperical containment problems so as to avoid the grouping. It also can be generated in 4- and 5-axis machine. When a set of points U and the size of a great-band are given, the methods for computing a feasible band and all feasible bands enclosing U in O(n) and O(n log n) time have been suggested, respectively. The methods can be applied into the cases of small bands since the solution region may contain holes. In this paper, we concentrate on the method for determining the smallest small-band enclosing U and suggest an O(n long n) time algorithm, where n is the number of points on the sphere.

• MALSORI
• /
• no.56
• /
• pp.173-183
• /
• 2005

We propose a speech emotion recognition method for affective human-robot interface. In the Proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes Pitch, jitter, duration, and rate of speech. Finally a pattern classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5 different directions. Experimental results show that the proposed method yields $48\%$ classification accuracy while human classifiers give $71\%$ accuracy.