• Journal of Multimedia Information System
• /
• 제2권3호
• /
• pp.255-262
• /
• 2015

The modern manufacturing systems and technologies produce products that are more accurate day by day. This can be reached mainly by improvement the manufacturing process with at the same time restricting more and more the quality specifications and reducing the uncertainty in part. The main objective an industry becomes to lower the part's variability, since the less variability - the better is product. One of the part of this task is measuring the object's uncertainty. The main purpose of this study is to understand the application of bootstrap method for uncertainty evaluation. Bootstrap method is a collection of sample re-use techniques designed to estimate standard errors and confidence intervals. In the case study a surface of an automobile engine block - (Top view side) is measured by Coordinate Measuring Machine (CMM) and analyzed for uncertainty using Geometric Least Squares in complex with bootstrap method. The designed experiment is composed by three similar measurements (the same features in unique reference system), but with different points (5, 10, 20) concentration at each level. Then each cloud of points was independently analyzed by means of non-linear Least Squares, after estimated results have been reported. A MatLAB software tool used to generate new samples using bootstrap function. The results of the designed experiment are summarized and show that the bootstrap method provides the possibility to evaluate the uncertainty without repeating the Coordinate Measuring Machine (CMM) measurements many times, i.e. potentially can reduce the measuring time.

• Journal of Multimedia Information System
• /
• 제5권3호
• /
• pp.209-214
• /
• 2018

Today is the era of artificial intelligence. With the development of artificial intelligence, machines have begun to impersonate various human characteristics today. Chatbot is one instance of this interactive artificial intelligence. Chatbot is a computer program that enables to conduct natural conversations with people. As mentioned above, Chatbot conducted conversations in text, but Chatbot, in this study evolves to perform commands based on speech-recognition. In order for Chatbot to perfectly emulate a human dialogue, it is necessary to analyze the sentence correctly and extract appropriate response. To accomplish this, the sentence is classified into three types: objects, actions, and preferences. This study shows how objects is analyzed and processed, and also demonstrates the possibility of evolving from an elementary model to an advanced intelligent system. By this study, it will be evaluated that speech-recognition based Chatbot have improved order-processing time efficiency compared to text based Chatbot. Once this study is done, speech-recognition based Chatbot have the potential to automate customer service and reduce human effort.

• Journal of Multimedia Information System
• /
• 제5권3호
• /
• pp.195-200
• /
• 2018

Recently, as the sensor and big data analysis technology have been developed, there have been a lot of researches that analyze the purchase-related data such as the trajectory information and the stay time. Such purchase-related data is usefully used for the purchase pattern prediction and the purchase time prediction. Because it is difficult to find periodic patterns in large-scale human data, it is necessary to look at actual data sets, find various feature patterns, and then apply a machine learning algorithm appropriate to the pattern and purpose. Although existing papers have been used to analyze data using various machine learning methods, there is a lack of statistical analysis such as finding feature patterns before applying the machine learning algorithm. Therefore, we analyze the purchasing data of Songjeong Maeil Market, which is a data gathering place, and finds some characteristic patterns through statistical data analysis. Based on the results of 1, we derive meaningful conclusions by applying the machine learning algorithm and present future research directions. Through the data analysis, it was confirmed that the number of visits was different according to the regional characteristics around Songjeong Maeil Market, and the distribution of time spent by consumers could be grasped.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.265-270
• /
• 2019

The technology to locate an individual has enabled various services, its utilization has increased. There were constraints such as the use of separate expensive equipment or the installation of specific devices on a facility, with most of the location technology studies focusing on the accuracy of location verification. These constraints can result in accuracy within a few tens of centimeters, but they are not technology that can be applied to a user's location in real-time in daily life. Therefore, this paper aims to track the locations of smartphones only using the basic components of smartphones. Based on smartphone sensor data, localization accuracy that can be used for verification of the users' locations is aimed at. Accelerometers, Wifi radio maps, and GPS sensor information are utilized to implement it. In forging the radio map, signal maps were built at each vertex based on the graph data structure This approach reduces traditional map-building efforts at the offline phase. Accelerometer data were made to determine the user's moving status, and the collected sensor data were fused using particle filters. Experiments have shown that the average user's location error is about 3.7 meters, which makes it reasonable for providing location-based services in everyday life.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.271-282
• /
• 2019

There is a description that you cannot manage what you do not measure. The Korea Ministry of National Defense (MND) is conducting evaluations in various fields to obtain meaningful effects from IT investments, and views that the evaluation of the defense informatization sector is divided into defense informatization policy evaluation and defense informatization project evaluation. The defense informatization level evaluation can measure the informatization level of MND and the armed forces or organizations. Since the evaluation system being studied to measure the level of defense informatization is composed mainly of qualitative metrics, it is necessary to reconstruct it based on quantitative metrics that can guarantee objectivity. In addition, for managing the level of change by evaluation objects, the evaluation system should be designed with a focus on homeostasis of metrics so that it can be measured periodically. Moreover, metrics need to be promoted in terms of performance against targets. To this end, this study proposes to measure the level of defense informatization by dividing it into defense information network, computer systems, interoperability and standardization, information security, information environment, and information system use, and suggests their metrics.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.217-224
• /
• 2019

As the world's population grows, how to maintain the food supply is becoming a bigger problem. Now and in the future, big data will play a major role in decision making in the agriculture industry. The challenge is how to obtain valuable information to help us make future decisions. Big data helps us to see history clearer, to obtain hidden values, and make the right decisions for the government and farmers. To contribute to solving this challenge, we developed the Agriculture Big Data Analysis System. The system consists of agricultural big data collection, big data analysis, and big data visualization. First, we collected structured data like price, climate, yield, etc., and unstructured data, such as news, blogs, TV programs, etc. Using the data that we collected, we implement prediction algorithms like ARIMA, Decision Tree, LDA, and LSTM to show the results in data visualizations.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.239-244
• /
• 2019

With the development of Cyber-Physical Systems(CPS), several technologies such as automation control, automotive and intelligent house systems have been developed. To enable communication among various components of such systems, several wired and wireless communication protocols are used. The Controller Area Network(CAN) is one of such wired communication protocols that is popularly used for communication in automobiles and other machinery in the industry. In this paper, we designed and implemented a response time analysis system for CAN communication. The reliable data transfer among various electronic components in a significant time is crucial for the smooth operation of an electric vehicle. Therefore, this system is designed to conveniently analyze the response time of various electronic components of a CAN enabled system. The priority for transmission of the messages in the CAN bus is determined by the message identifier. As the number of nodes increases the transmission of low priority messages is delayed due to the existence of higher priority messages on the bus. We used Raspberry Pi3 and PiCAN2 board to simulate the data transfer for studying the comparative delay in low priority nodes.