• Journal of Korea Technology Innovation Society
• /
• v.21 no.1
• /
• pp.151-200
• /
• 2018

At the Davos Forum in 2016, the Fourth Industrial Revolution, a reference to cloud Schwab, is dramatically changing our lives, and at its height, self-driving cars are emerging as the talk of the day. But there are still many hurdles to overcome before the nation can successfully introduce and establish self-driving cars. In particular, it is necessary to change the paradigm of the legal system centered on human beings to one that includes artificial intelligence. The stable operation of the self-driving car era requires drastic changes to the people-centric legislation system. That is, it is necessary to collect information on the total number of drivers of self-driving cars (what is available), general vehicles on general roads, civil and criminal liability issues in the event of traffic accidents, and collection of insurance problems concerning autonomous driving vehicles. In this study, a separate bill was proposed to address the various legal issues arising from the operation of self-driving cars from a legislative perspective by considering the domestic laws related to road transport, the current state of legislation on foreign soil and legal issues related to self-driving cars.

• 한국정보교육학회:학술대회논문집
• /
• 2010.08a
• /
• pp.15-18
• /
• 2010

As robots are proved to be effective in enhancing students' creativity and problem-solving abilities and satisfying various needs in special education for the gifted, many students participate in private education and after-school robot classes. However, it is difficult for students in the lower social economy class to use robots for their learning because of the high expense of robots. On this point, as a part of u-Learnng project, this research attempts to provide students in the lower social economy class with the opportunities to use robots for one year. At the end of the year, we will compare the experimental group and the control group in order to examine learning effects of using robots. Until now we have found many cases that show positive effects of the use of robots in students' learning.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.503-512
• /
• 2011

Recently in HCI research, emotion recognition is one of the core processes to implement emotional intelligence. There are many studies using bio signals in order to recognize human emotions, but it has been done merely for the basic emotions and very few exists for the other emotions. The purpose of present study is to confirm the difference of autonomic nervous system (ANS) response in three emotions (boredom, pain, and surprise). There were totally 217 of participants (male 96, female 121), we presented audio-visual stimulus to induce boredom and surprise, and pressure by using the sphygmomanometer for pain. During presented emotional stimuli, we measured electrodermal activity (EDA), skin temperature (SKT), electrocardiac activity (ECG) and photoplethysmography (PPG), besides; we required them to classify their present emotion and its intensity according to the emotion assessment scale. As the results of emotional stimulus evaluation, emotional stimulus which we used was shown to mean 92.5% of relevance and 5.43 of efficiency; this inferred that each emotional stimulus caused its own emotion quite effectively. When we analyzed the results of the ANS response which had been measured, we ascertained the significant difference between the baseline and emotional state on skin conductance response, SKT, heart rate, low frequency and blood volume pulse amplitude. In addition, the ANS response caused by each emotion had significant differences among the emotions. These results can probably be able to use to extend the emotion theory and develop the algorithm in recognition of three kinds of emotions (boredom, surprise, and pain) by response measurement indicators and be used to make applications for differentiating various human emotions in computer system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.262-269
• /
• 2020

Recently, many attempts have been made to reduce the time required for payment in various shopping environments. In addition, for the Fourth Industrial Revolution era, artificial intelligence is advancing, and Internet of Things (IoT) devices are becoming more compact and cheaper. So, by integrating these two technologies, access to building an unmanned environment to save people time has become easier. In this paper, we propose a smart shopping cart system based on low-cost IoT equipment and deep-learning object-detection technology. The proposed smart cart system consists of a camera for real-time product detection, an ultrasonic sensor that acts as a trigger, a weight sensor to determine whether a product is put into or taken out of the shopping cart, an application for smartphones that provides a user interface for a virtual shopping cart, and a deep learning server where learned product data are stored. Communication between each module is through Transmission Control Protocol/Internet Protocol, a Hypertext Transmission Protocol network, a You Only Look Once darknet library, and an object detection system used by the server to recognize products. The user can check a list of items put into the smart cart via the smartphone app, and can automatically pay for them. The smart cart system proposed in this paper can be applied to unmanned stores with high cost-effectiveness.

• Journal of Bio-Environment Control
• /
• v.3 no.1
• /
• pp.42-51
• /
• 1994

Visual features of a mushromm(Lentinus Edodes L.) are critical in sorting and grading as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. Though actions involved in human grading look simple, it decision making underneath the simple action comes from the result of the complex neural processing of visual image. Recently, an artificial neural network has drawn a great attention because of its functional capability as a partial substitute of the human brain. Since most agricultural products are not uniquely defined in its physical properties and do not have a well defined job structure, the neuro -net based computer visual information processing is the promising approach toward the automation in the agricultural field. In this paper, first, the neuro - net based classification of simple geometric primitives were done and the generalization property of the network was tested for degraded primitives. And then the neuro-net based grading system was developed for a mushroom. A computer vision system was utilized for extracting and quantifying the qualitative visual features of sampled mushrooms. The extracted visual features of sampled mushrooms and their corresponding grades were used as input/output pairs for training the neural network. The grading performance of the trained network for the mushrooms graded previously by the expert were also presented.

• Journal of Service Research and Studies
• /
• v.7 no.3
• /
• pp.57-70
• /
• 2017

It is anticipated that the employment structure of the whole industry will change drastically as the Fourth Industrial Revolution era arrives. Particularly, there are numerous reseraches that the development of artifical intelligence will promote automation causing jobs in manufacturing industry to decrease; thus, the economy will be reorganized with service-centered jobs, which heavily depend on human ability. This study was conducted to verify the trend-forecasting model based on the theoretical analysis. We analyzed the change in employment structure over the past decades in each country and period to gain insights from the changes in the employment structure caused by the Fourth Industrial Revoltion. The results of this study are as follows: First, we investigaed whether the current economy is moving along the U-shaped model suggested by an existing researcher. As a result of the analysis, the data substantiated that the change of the employment structure is moving along the U-shaped model. It is also suggested that this U-shaped trend is expected to accelerate in the era of the Fourth Industrial Revolution. In the future, more accurate data analyses are needed to verify the model, and additional researches on the change in the employment structed is also needed.

• The KIPS Transactions:PartC
• /
• v.17C no.1
• /
• pp.27-36
• /
• 2010

In Web registration pages and online polling applications, CAPTCHA(Completely Automated Public Turing Test To Tell Computers and Human Apart) is used for distinguishing human users from automated programs. Text-based CAPTCHAs have been widely used in many popular Web sites in which distorted text is used. However, because the advanced optical character recognition techniques can recognize the distorted texts, the reliability becomes low. Image-based CAPTCHAs have been proposed to improve the reliability of the text-based CAPTCHAs. However, these systems also are known as having some drawbacks. First, some image-based CAPTCHA systems with small number of image files in their image dictionary is not so reliable since attacker can recognize images by repeated executions of machine learning programs. Second, users may feel uncomfortable since they have to try CAPTCHA tests repeatedly when they fail to input a correct keyword. Third, some image-base CAPTCHAs require high communication cost since they should send several image files for one CAPTCHA. To solve these problems of image-based CAPTCHA, this paper proposes a new CAPTCHA based on both image and text. In this system, an image and keywords are integrated into one CAPTCHA image to give user a hint for the answer keyword. The proposed CAPTCHA can help users to input easily the answer keyword with the hint in the fused image. Also, the proposed system can reduce the communication costs since it uses only a fused image file for one CAPTCHA. To improve the reliability of the image-text fusion CAPTCHA, we also propose a dynamic building method of large image dictionary from gathering huge amount of images from theinternet with filtering phase for preserving the correctness of CAPTCHA images. In this paper, we proved that the proposed image-text fusion CAPTCHA provides users more convenience and high reliability than the image-based CAPTCHA through experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.566-575
• /
• 2010

In recent, artificial immune system has become an important research direction in the anomaly detection of networks. The conventional artificial immune systems are usually based on the negative selection that is one of the computational models of self/nonself discrimination. A main problem with self and non-self discrimination is the determination of the frontier between self and non-self. It causes false positive and false negative which are wrong detections. Therefore, additional functions are needed in order to detect potential anomaly while identifying abnormal behavior from analogous symptoms. In this paper, we design novel network attack detection and response schemes based on artificial immune system, and evaluate the performance of the proposed schemes. We firstly generate detector set and design detection and response modules through adopting the interaction between dendritic cells and T-cells. With the sequence of buffer occupancy, a set of detectors is generated by negative selection. The detection module detects the network anomaly with a set of detectors and generates alarm signal to the response module. In order to reduce wrong detections, we also utilize the fuzzy number theory that infers the degree of threat. The degree of threat is calculated by monitoring the number of alarm signals and the intensity of alarm occurrence. The response module sends the control signal to attackers to limit the attack traffic.

• Informatization Policy
• /
• v.25 no.3
• /
• pp.3-28
• /
• 2018

The purpose of this study is to analyze the research trends and present future research directions in the field of Cyber Physical System (CPS), a key element in the 4th Industrial Revolution, Industry 4.0, and Smart Manufacturing that are currently promoted as important innovation agenda both at home and abroad. In this study, (1) the concepts of industry 4.0, smart manufacturing and CPS are summarized; (2) analysis criteria of these fields are established; and 3) analysis results are presented and future research direction is proposed. 74 overseas and 8 domestic literature on manufacturing CPS from 2013 to 2017 are identified through 'Google Scholar Search'. Major results of the analysis are summarized as follows: (1) research on a common methodology and framework for the manufacturing CPS needs to be done based on the analysis of the existing methodologies and frameworks of various perspectives; (2) in order to improve the maturity of the manufacturing CPS, it is necessary to study actual deployment and operations of CPS, including the existing systems; (3) it is necessary to study the diagnostic methodology that can evaluate manufacturing CPS and suggest improvement strategy; and (4) as for the detailed model and tool, it is necessary to reinforce research on SCM production planning and human-machine collaboration while considering the characteristics of CPS.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.169-176
• /
• 2020

Recently, deep neural networks (DNNs) have brought revolutions to many mobile and embedded devices by providing human-level machine intelligence for various applications. However, high inference accuracy of such DNNs comes at high computational costs, and, hence, there have been significant efforts to reduce computational overheads of DNNs either by compressing off-the-shelf models or by designing a new small footprint DNN architecture tailored to resource constrained devices. One notable recent paradigm in designing small footprint DNN models is sharing parameters in several layers. However, in previous approaches, the parameter-sharing techniques have been applied to large deep networks, such as ResNet, that are known to have high redundancy. In this paper, we propose a parameter-sharing method for already parameter-efficient small networks such as ShuffleNetV2. In our approach, small templates are combined with small layer-specific parameters to generate weights. Our experiment results on ImageNet and CIFAR100 datasets show that our approach can reduce the size of parameters by 15%-35% of ShuffleNetV2 while achieving smaller drops in accuracies compared to previous parameter-sharing and pruning approaches. We further show that the proposed approach is efficient in terms of latency and energy consumption on modern embedded devices.