• Journal of KIISE:Information Networking
• /
• v.33 no.3
• /
• pp.201-217
• /
• 2006

In this paper, we collected the physical traces from high speed Internet backbone traffic and analyze the various characteristics of the underlying packet traces. Particularly, our work is focused on analyzing the characteristics of an anomalous traffic. It is found that in our data, the anomalous traffic is caused by UDP session traffic and we determined that it was one of the Denial of Service attacks. In this work, we adopted the unsupervised machine learning algorithm to classify the network flows. We apply the k-means clustering algorithm to train the learner. Via the Cramer-Yon-Misses test, we confirmed that the proposed classification method which is able to detect anomalous traffic within 1 second can accurately predict the class of a flow and can be effectively used in determining the anomalous flows.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.440-445
• /
• 2017

Due to the advance of e-commerce systems, the number of people using online shopping and products has significantly increased. Therefore, the need for an accurate recommendation system is becoming increasingly more important. Recurrent neural network is a deep-learning algorithm that utilizes sequential information in training. In this paper, an evaluation is performed on the application of recurrent neural networks to recommendation systems. We evaluated three recurrent algorithms (RNN, LSTM and GRU) and three optimal algorithms(Adagrad, RMSProp and Adam) which are commonly used. In the experiments, we used the TensorFlow open source library produced by Google and e-commerce session data from RecSys Challenge 2015. The results using the optimal hyperparameters found in this study are compared with those of RecSys Challenge 2015 participants.

• The KIPS Transactions:PartD
• /
• v.13D no.1 s.104
• /
• pp.133-138
• /
• 2006

Electric commerce of surpassing the traditional one appeared before the public and has currently led the change in the management of enterprises. To establish and maintain good relations with customers, electric commerce has various channels for customers that understand what they want to and suggest it to them. The bulletin board and e-mail among em are inbound information that enterprises can directly listen to customers' opinions and are different from other channels in characters. Enterprises can effectively manage the bulletin board and e-mail by understanding customers' ideas as many as possible and provide them with optimum answers. It is one of the important factors to improve the reliability of the notice board and e-mail as well as the whole electric commerce. Therefore this thesis researches into methods to classify various kinds of documents automatically in electric commerce; they are possible to solve existing problems of the bulletin board and e-mail, to operate effectively and to manage systematically. Moreover, it researches what the most suitable algorithm is in the automatic classification of Q&A documents by experiment the classifying performance of Naive Bayesian, TFIDF, Neural Network, k-NN

• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.659-668
• /
• 2010

Collaborative filtering systems grasp behaviors for a new user and need new information for the user in order to recommend interesting items to the user. For the purpose of acquiring the information the collaborative filtering systems learn behaviors for users based on the previous data and can obtain new information from the results. In this paper, we propose an inductive inference method to obtain new information for users and rank items by using the new information in the proposed method. The proposed method clusters users into groups by learning users through NMF among inductive machine learning methods and selects the group features from the groups by using chi-square. Then, the method classifies a new user into a group by using the bayesian probability model as one of inductive inference methods based on the rating values for the new user and the features of groups. Finally, the method decides the ranks of items by applying the Rocchio algorithm to items with the missing values.

• Smart Structures and Systems
• /
• v.25 no.5
• /
• pp.605-617
• /
• 2020

The existence of damages in structures causes changes in the physical properties by reducing the modal parameters. In this paper, we develop a two-stages approach based on normalized Modal Strain Energy Damage Indicator (nMSEDI) for quick applications to predict the location of damage. A two-dimensional IsoGeometric Analysis (2D-IGA), Machine Learning Algorithm (MLA) and optimization techniques are combined to create a new tool. In the first stage, we introduce a modified damage identification technique based on frequencies using nMSEDI to locate the potential of damaged elements. In the second stage, after eliminating the healthy elements, the damage index values from nMSEDI are considered as input in the damage quantification algorithm. The hybrid of Teaching-Learning-Based Optimization (TLBO) with Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) are used along with nMSEDI. The objective of TLBO is to estimate the parameters of PSO-ANN to find a good training based on actual damage and estimated damage. The IGA model is updated using experimental results based on stiffness and mass matrix using the difference between calculated and measured frequencies as objective function. The feasibility and efficiency of nMSEDI-PSO-ANN after finding the best parameters by TLBO are demonstrated through the comparison with nMSEDI-IGA for different scenarios. The result of the analyses indicates that the proposed approach can be used to determine correctly the severity of damage in beam structures.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.4
• /
• pp.256-261
• /
• 2018

There are three types of noise generated inside the vehicle: BSR (Buzz, Squeak, Rattle). In this paper, we propose a classifier that automatically classifies automotive BSR noise by using features extracted from deep convolutional neural networks. In the preprocessing process, the features of above three noises are represented as noise-map using STFT (Short-time Fourier Transform) algorithm. In order to cope with the problem that the position of the actual noise is unknown in the part of the generated noise map, the noise map is divided using the sliding window method. In this paper, internal parameter of the deep convolutional neural networks is visualized using the t-SNE (t-Stochastic Neighbor Embedding) algorithm, and the misclassified data is analyzed in a qualitative way. In order to analyze the classified data, the similarity of the noise type was quantified by SSIM (Structural Similarity Index) value, and it was found that the retractor tremble sound is most similar to the normal travel sound. The classifier of the proposed method compared with other classifiers of machine learning method recorded the highest classification accuracy (99.15 %).

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.222-228
• /
• 2016

Uniform navigation of NPCs in computer games is an important factor that can decrease the interest of game players. This problem is particularly noticeable in pathfinding when using a waypoint graph because the NPCs navigate using only predefined locations. In this paper we propose a method that enables adaptive navigations of NPCs by observing player movements. The proposed method involves modification of waypoints dynamically by observing the player's point designation and use of the modified waypoints for NPC's pathfinding. Also, we propose an algorithm to find the NPC-specific path by learning the landform preferences of players. We simulate the implemented algorithm in an RPG game made with Unity 4.0 and confirm that NPC navigations had more variety and improved according to player navigations.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.1
• /
• pp.11-20
• /
• 2012

Stream data shows a sequence of values changing continuously over time. Due to the nature of stream data, its trend is continuously changing according to various time intervals. Therefore the prediction of stream data must be carried out simultaneously with respect to multiple intervals, i.e. Continuous Multiple Prediction(CMP). In this paper, we propose a Continuous Integrated Hierarchical Temporal Memory (CIHTM) network for CMP based on the Hierarchical Temporal Memory (HTM) model which is a neocortex leraning algorithm. To develop the CIHTM network, we created three kinds of new modules: Shift Vector Senor, Spatio-Temporal Classifier and Multiple Integrator. And also we developed learning and inferencing algorithm of CIHTM network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.374-380
• /
• 2022

This paper shows the results of a study that predicts changes in seawater conditions in sea farms using machine learning-based long short term memory (LSTM) algorithms. Hardware was implemented using dissolved oxygen, salinity, nitrogen ion concentration, and water temperature measurement sensors to collect seawater condition information from sea farms, and transferred to a cloud-based Firebase database using LoRa communication. Using the developed hardware, seawater condition information around fish farms in Tongyeong and Geoje was collected, and LSTM algorithms were applied to learning results using these actual datasets to obtain predictive results showing 87% accuracy. Flask and REST APIs were used to provide users with predictive results for each of the four parameters, including dissolved oxygen. These predictive results are expected to help fishermen reduce significant damage caused by fish group death by providing changes in sea conditions in advance.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.51-60
• /
• 2021

The market size of wearable devices is growing rapidly every year, and manufacturers around the world are introducing products that utilize their unique characteristics to keep up with the demand. Among them, smart watches are wearable devices with a very high share in sales, and they provide a variety of services to users by using information collected in real-time. The quality of service depends on the accuracy of the data collected by the smart watch, but data measurement may not be possible depending on the situation. This paper introduces a method to restore data that a smart watch could not collect. It deals with the similarity calculation method of trajectory information measured over time for data restoration and introduces a procedure for restoring missing sections according to the similarity. To prove the performance of the proposed methodology, a comparative experiment with a machine learning algorithm was conducted. Finally, the expected effects of this study and future research directions are discussed.