• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.64-88
• /
• 2024

Security and reliability are the utmost importance facts in intelligent networked vehicles. Stochastic Petri Net and Z (SPZN) as an excellent formal verification tool for modeling concurrent systems, can effectively handles concurrent operations within a system, establishes relationships among components, and conducts verification and reasoning to ensure the system's safety and reliability in practical applications. However, the application of a system with numerous nodes to Petri Net often leads to the issue of state explosion. To tackle these challenges, a refinement and abstraction method based on SPZN is proposed in this paper. This approach can not only refine and abstract the Stochastic Petri Net but also establish a corresponding relationship with the Z language. In determining the implementation rate of transitions in Stochastic Petri Net, we employ the interval average and weighted average method, which significantly reduces the time and space complexity compared to alternative techniques and is suitable for expert systems at various levels. This reduction facilitates subsequent comprehensive system analysis and module analysis. Furthermore, by analyzing the properties of Markov Chain isomorphism in the case study, recommendations for minimizing system risks in the application of intelligent parking within the intelligent networked vehicle system can be put forward.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.1
• /
• pp.89-98
• /
• 2022

As deep learning technology was applied to various fields, research on adversarial attack techniques, a security problem of deep learning models, was actively studied. adversarial attacks have been mainly studied in the field of images. Recently, they have even developed a complete decision-based attack technique that can attack with just the classification results of the model. However, in the case of the audio field, research is relatively slow. In this paper, we applied several decision-based attack techniques to the audio field and improved state-of-the-art attack techniques. State-of-the-art decision-attack techniques have the disadvantage of requiring many queries for gradient approximation. In this paper, we improve query efficiency by proposing a method of reducing the vector search space required for gradient approximation. Experimental results showed that the attack success rate was increased by 50%, and the difference between original audio and adversarial examples was reduced by 75%, proving that our method could generate adversarial examples with smaller noise.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.39-57
• /
• 2012

Recently, due to the introduction of high-tech equipment in interactive exhibits, many people's attention has been concentrated on Interactive exhibits that can double the exhibition effect through the interaction with the audience. In addition, it is also possible to measure a variety of audience reaction in the interactive exhibition. Among various audience reactions, this research uses the change of the facial features that can be collected in an interactive exhibition space. This research develops an artificial neural network-based prediction model to predict the response of the audience by measuring the change of the facial features when the audience is given stimulation from the non-excited state. To present the emotion state of the audience, this research uses a Valence-Arousal model. So, this research suggests an overall framework composed of the following six steps. The first step is a step of collecting data for modeling. The data was collected from people participated in the 2012 Seoul DMC Culture Open, and the collected data was used for the experiments. The second step extracts 64 facial features from the collected data and compensates the facial feature values. The third step generates independent and dependent variables of an artificial neural network model. The fourth step extracts the independent variable that affects the dependent variable using the statistical technique. The fifth step builds an artificial neural network model and performs a learning process using train set and test set. Finally the last sixth step is to validate the prediction performance of artificial neural network model using the validation data set. The proposed model is compared with statistical predictive model to see whether it had better performance or not. As a result, although the data set in this experiment had much noise, the proposed model showed better results when the model was compared with multiple regression analysis model. If the prediction model of audience reaction was used in the real exhibition, it will be able to provide countermeasures and services appropriate to the audience's reaction viewing the exhibits. Specifically, if the arousal of audience about Exhibits is low, Action to increase arousal of the audience will be taken. For instance, we recommend the audience another preferred contents or using a light or sound to focus on these exhibits. In other words, when planning future exhibitions, planning the exhibition to satisfy various audience preferences would be possible. And it is expected to foster a personalized environment to concentrate on the exhibits. But, the proposed model in this research still shows the low prediction accuracy. The cause is in some parts as follows : First, the data covers diverse visitors of real exhibitions, so it was difficult to control the optimized experimental environment. So, the collected data has much noise, and it would results a lower accuracy. In further research, the data collection will be conducted in a more optimized experimental environment. The further research to increase the accuracy of the predictions of the model will be conducted. Second, using changes of facial expression only is thought to be not enough to extract audience emotions. If facial expression is combined with other responses, such as the sound, audience behavior, it would result a better result.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.2
• /
• pp.146-156
• /
• 2012

In-flight icing remains as one of the most persistent hazards for aircraft operations. The effect of icing on aircraft performance and safety has to be evaluated during the development and airworthiness certification process. The scaling method is a procedure to determine the scaled test conditions in icing wind tunnels in order to produce the same result as when the reference model is exposed to the desired cloud conditions. In this study, a scaling program is developed to provide an easy-to-use tool to the aero-icing community. The Olsen and Ruff 4th methods are employed for this purpose and the velocity is calculated by matching the dimensionless Weber number. To validate the program, the results are compared with the NASA scaling results. The scaling examples based on FAR (Federal Aviation Regulation) Part 25 Appendix C are also presented. Finally, a validation study using a state-of-the-art icing simulation code FENSAP-ICE is presented.

• Journal of Power Electronics
• /
• v.12 no.1
• /
• pp.145-156
• /
• 2012

These days, the application of electronic power transformers (EPTs) is expanding in place of ordinary power transformers. These transformers can transmit power via three or four wire converters. Their dynamic performance is extremely important, due to their complex structure. In this paper, a new method is proposed for improving the dynamic performance of distribution electronic power transformers (DEPT) by using sliding mode control (SMC). Hence, to express the dynamic characteristics of a system, different factors such as the voltage unbalance, voltage sag, voltage harmonics and voltage flicker in the system primary side are considered. The four controlling aims of the improvement in dynamic performance include: 1) maintaining the input currents so that they are in sinusoidal form and in phase with the input voltages so they have a unity power factor, 2) keeping the dc-link voltage within the reference amount, 3) keeping the output voltages at a fixed amount and 4) keeping the output voltages in sinusoidal and symmetrical forms. Simulation results indicate the potential and capability of the proposed method in improving DEPT behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3884-3910
• /
• 2016

Intrusion Detection System (IDS) in general considers a big amount of data that are highly redundant and irrelevant. This trait causes slow instruction, assessment procedures, high resource consumption and poor detection rate. Due to their expensive computational requirements during both training and detection, IDSs are mostly ineffective for real-time anomaly detection. This paper proposes a dimensionality reduction technique that is able to enhance the performance of IDSs up to constant time O(1) based on the Principle Component Analysis (PCA). Furthermore, the present study offers a feature selection approach for identifying major components in real time. The PCA algorithm transforms high-dimensional feature vectors into a low-dimensional feature space, which is used to determine the optimum volume of factors. The proposed approach was assessed using HTTP packet payload of ISCX 2012 IDS and DARPA 1999 dataset. The experimental outcome demonstrated that our proposed anomaly detection achieved promising results with 97% detection rate with 1.2% false positive rate for ISCX 2012 dataset and 100% detection rate with 0.06% false positive rate for DARPA 1999 dataset. Our proposed anomaly detection also achieved comparable performance in terms of computational complexity when compared to three state-of-the-art anomaly detection systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.2 s.308
• /
• pp.1-10
• /
• 2006

This paper is concerned with $H_2$ control design for active vibration control of a plate vibration system. We construct a plate vibration system with a plate, PZT ceramics actuators and sensors. The plate titration system is MIMO system and its transfer matrix is obtained by system identification experiments. We design a $H_2$ controller using the state space model obtained from system identification. Effectiveness and performance of the designed controller are verified by both simulation and experiment results.

• Structural Engineering and Mechanics
• /
• v.46 no.1
• /
• pp.19-37
• /
• 2013

The optimum design of base isolation system considering model parameter uncertainty is usually performed by using the unconditional response of structure obtained by the total probability theory, as the performance index. Though, the probabilistic approach is powerful, it cannot be applied when the maximum possible ranges of variations are known and can be only modelled as uncertain but bounded type. In such cases, the interval analysis method is a viable alternative. The present study focuses on the bounded optimization of base isolation system to mitigate the seismic vibration effect of structures characterized by bounded type system parameters. With this intention in view, the conditional stochastic response quantities are obtained in random vibration framework using the state space formulation. Subsequently, with the aid of matrix perturbation theory using first order Taylor series expansion of dynamic response function and its interval extension, the vibration control problem is transformed to appropriate deterministic optimization problems correspond to a lower bound and upper bound optimum solutions. A lead rubber bearing isolating a multi-storeyed building frame is considered for numerical study to elucidate the proposed bounded optimization procedure and the optimum performance of the isolation system.