Vol. 49, No. 2,
Feb. 2022
Digital Library
Multimodal Haptic Rendering for Interactive VR Sports Applications
Minjae Mun, Seungjae Oh, Chaeyong Park, Seungmoon Choi
http://doi.org/10.5626/JOK.2022.49.2.97
This study explores how to deliver realistic haptic sensations for virtual collision events in virtual reality (VR). For this purpose, we implemented a multifaceted haptic device that produced both vibration and impact and designed a haptic rendering method combining the simulated interactions of a physics engine and the collision data of real objects. We also designed a virtual simulation of three sports activities, billiards, ping-pong, and tennis, in which a user could interact with virtual objects having different material properties. We performed a user study to evaluate the subjective quality of the haptic feedback from three rendering conditions, vibration, impact, and multimodal of combining both, and compared it to real haptic sensations. The results suggested that each rendering condition had different perceptual characteristics. Therefore, the addition of a haptic modality can broaden the dynamic range of virtual collisions.
Reinforcement Learning-based Pod Autoscaling Technique Using the Queueing Model
Yonghyeon Jang, Heonchang Yu, Eunyoung Lee
http://doi.org/10.5626/JOK.2022.49.2.106
Recently, studies on reinforcement learning-based autoscaling policies have been conducted in order to use optimal autoscaling policies that are adaptive to environmental changes and fit the purpose. However, there is a problem that much time and many resources are required in the process of training the reinforcement learning-based autoscaling policy and comparing the performance between each reinforcement learning-based autoscaling policy. In this study, we proposed a queueing model-based simulation technique, which enables performance comparison between autoscaling policies to be performed through simulation, and compared several reinforcement learning-based pod autoscaling techniques through simulation experiments.
New Flash Commands for Building Flash Storage Systems with Plausible Deniability
Geonhee Cho, Myungsuk Kim, Jihong Kim
http://doi.org/10.5626/JOK.2022.49.2.120
Traditional encryption cannot defend against coercive attackers who compel the user to hand over decryption keys as it cannot hide the existence of the ciphertext. To solve this problem, there have been studies on a deniable storage solution that applies plausible deniability, a characteristic that allows the user to deny the existence of sensitive data, to a storage device. The hidden volume mechanism is being used in various deniable storage solutions due to its relatively low-performance overhead compared to other mechanisms, and has recently evolved to defend against multiple-snapshot attacks. However, the existing hidden volume mechanism fundamentally requires a dummy random data pool to hide the ciphertext. Due to the existence of dummy random data stored in the storage device, the plausible deniability characteristic is exposed, which can reveal the intention to hide the data. This study proposes a flash chip-level access control command set that simultaneously supports data sanitization and plausible deniability, and using this, we propose a hidden volume-based deniable storage solution that supports plausible deniability characteristics without dummy random data.
Data Augmentation for Image based Parking Space Classification Deep Model
http://doi.org/10.5626/JOK.2022.49.2.126
A parking occupancy state determination system using an ultrasonic sensor or a camera is mainly used in indoor parking lots. However, in the case of an outdoor parking lot, there is a limit to the introduction of these systems due to the high installation cost and accuracy problems. In addition, the application of deep learning is restricted because it is difficult to obtain representative learning data due to diverse lighting conditions, camera positions, and features. In this paper, we analyzed the effect of augmentation techniques on the performance of a deep model for parking status classification in such a data shortage situation. To this end, the parking area images were classified by situations. Four augmentation techniques were applied to the training of ResNet, EfficientNet, and MobileNet. Based on performance evaluation, the accuracy was improved by up to 5.2%, 8.67%, and 15.44%p in the case of mixup, stopper, and rescaling methods, respectively. On the other hand, in the case of center crop, which was known to have performance improvement in other studies, the accuracy decreased by an average of 4.86%p.
Detecting Design Infringement Using Multi-Modal Visual Data and Auto Encoder based on Convolutional Neural Network
Jeonggeol Kim, Jiyou Seo, Chanjae Lee, Seongmin Jo, Seungmin Kim, Seokmin Yoon, Young Yoon
http://doi.org/10.5626/JOK.2022.49.2.137
Recently, it has become very difficult to distinguish between counterfeit products and authentic goods, and the volume of these forgeries is increasing at an alarming rate. Prompt detection of these counterfeit products is challenging since only humans can identify these forgeries through trained expertise. In this paper, given the photograph and design drawing, we use convolutional neural networks and auto-encoders to detect the possible infringement of design rights without dissembling or damaging the suspected items. We have developed an easy-to-expand system that supports the constant addition of new goods to be examined. We present the result of our system tested with a set of authentic and forged goods.
Safety Guards and Virtual Experience Injection Techniques for Safe Reinforcement Learning of Cyber-Physical Systems
http://doi.org/10.5626/JOK.2022.49.2.145
A Cyber-Physical System(CPS) that connects the real world and the cyber world is increasing in its application in diverse areas. Among the research on artificial intelligence, reinforcement learning, in particular, is achieving higher processing performance by learning the optimal policy with taking the reward. The convergence of reinforcement learning and CPS has been the focus of recent research. However, the randomness arising from the exploration by reinforcement learning can cause the problem of being able to transit safety-critical CPS to a dangerous state. This paper attempts to support the safe operation of CPS by proposing safety guards and virtual experience injection techniques for safe reinforcement learning of CPS. Although a safety guard prevents the CPS from transitioning to a dangerous state during learning, the guard has a disadvantage as it does not have a learning experience for the dangerous state. Virtual experience injection can minimize this disadvantage for a dangerous state into the learning process. The proposed safety guard and virtual experience injection techniques provide a primary safety device for transitioning to a safe state instead of a dangerous state while ensuring safe reinforcement learning of CPS. This approach has proven its effectiveness through an experimental study and simulations.
Estimation of Finger Motion using Transient EMG Signals
http://doi.org/10.5626/JOK.2022.49.2.157
In this paper, we propose a deep learning model for estimating finger movements based on EMG signals. We have also evaluated and analyzed the accuracy of the model. We have applied the U-Net structure, which is widely used in medical image analysis, to our model. In general, U-Net is mainly used for processing of two-dimensional images. However, in this paper, 8-channel one-dimensional time series EMG data is used as inputs, and information about finger movement is obtained as results. We have acquired the data set consisting of 8,000 motions, which is divided into the training and evaluation data sets. The accuracy of the prediction of our model is about 89.32%.
Training Data Augmentation Technique for Machine Comprehension by Question-Answer Pairs Generation Models based on a Pretrained Encoder-Decoder Model
http://doi.org/10.5626/JOK.2022.49.2.166
The goal of Machine Reading Comprehension (MRC) research is to find answers to questions in documents. MRC research requires large-scale, high-quality data. However, individual researchers or small research institutes have limitations in constructing them. To overcome the limitations, in this paper, we propose an MRC data augmentation technique using a pre-training language model. This MRC data augmentation technique consists of a Q&A pair generation model and a data validation model. The Q&A pair generation model consists of an answer extraction model and a question generation model. Both models are constructed by fine-tuning the BART model. The data validation model is added to increase the reliability of the augmented data. It is used to verify the generated augmented data. The validation model is used by fine-tuning the ELECTRA model as an MRC model. To see the performance improvement of the MRC model through the data augmentation technique, we applied the data augmentation technique to KorQuAD v1.0 data. As a result of the experiment, compared to the previous model, the Exact Match(EM) Score increased up to 7.2 and the F1 Score increased up to 5.7.
Design Threat Analysis and Risk Assessment of Battery Management System
Woongsub Park, Daehui Jeong, Hyuk Lee
http://doi.org/10.5626/JOK.2022.49.2.176
Climate change due to emission of greenhouse gases and air pollutants is currently the most important international environmental problem. As a result of advances in technology and efforts by automobile manufacturers to address these issues, automobiles are changing from internal combustion engines to electric motors. Electric vehicles have a high proportion of electronic components. Software technologies such as battery management systems, infotainment, and advanced driver assistance systems (ADAS) are integrated. An increase in the proportion of software increases the internal connectivity and complexity of the entire system, leading to expansion of the potential security attack surface. To secure cyber security for automobiles, it is recommended to comply with the ISO/SAE-21434 international standard and perform threat analysis and risk assessment activities. In this paper, high-level threat analysis and risk assessment for the battery management system were performed based on the HEAVENS security model. Threats that can occur in the battery management system were identified through the STRIDE technique. Possible damage and threat scenarios were then derived. Through systematic risk assessment, an impact rating and an attack potential rating for threats were assigned and a security rating was derived. Finally, by analyzing the security level of the threat, it is suggested to apply threat analysis and risk assessment activities to improve the design level security of the battery management system.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr