• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.4
• /
• pp.260-267
• /
• 2015

In the past, we implemented a web-based smart education platform, but this is not efficient in a smart or mobile education environment. Therefore, in this paper, we propose an Android-based e-board smart platform for a smart or mobile education system. Here, we use Anoto digital pen- and dot pattern-based technologies. This Android-based smart education platform is efficient for a smart education environment. Further, we implement the hardware and software parts of the technologies, an Anoto-based trajectory recognition algorithm, and a probabilistic neural network for handwritten digit and hand gesture recognition.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.27-29
• /
• 2004

This paper presents a sensor model design based on Monte Carlo Localization method. First, we define the measurement error of each sample using a map matching method by 2-D laser scanners and a pre-constructed grid-map of the environment. Second, samples are assigned probabilities due to matching errors from the gaussian probability density function considered of the sample's convergence. Simulation using real environment data shows good localization results by the designed sensor model.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.10
• /
• pp.1826-1835
• /
• 2007

In this paper, we present a new approach for automatic detection and tracking for multiple targets. We combine a highest probability data association(HPDA) algorithm for target detection with a particle filter for multiple target tracking. The proposed approach evaluates the probabilities of one-to-one assignments of measurement-to-track and the measurement with the highest probability is selected to be target- originated, and the measurement is used for probabilistic weight update of particle filtering. The performance of the proposed algorithm for target tracking in clutter is compared with the existing clustering algorithm and the sequential monte carlo method for probability hypothesis density(SMC PHD) algorithm for multi-target detection and tracking. Computer simulation studies demonstrate that the HPDA algorithm is robust in performing automatic detection and tracking for multiple targets even though the environment is hostile in terms of high clutter density and low target detection probability.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.179-184
• /
• 2019

This paper introduces a study for procedurally generating the behavior of objects in a virtual environment at runtime. This study was initiated to enable the behavioral model of objects in virtual reality applications to evolve in response to user behavior at runtime. Our approach is to describe the behavior of an object as a behavior tree, and to make a node of the behavior tree change to another type if a certain condition is satisfied. We defined four types of node changes: "parameterized", "probabilistic", "alternate", and "variant". We experimented with a virtual environment that includes a variety of simple procedural elements to explore the possibilities of our approach. As a result of the implementation, if an optimization algorithm that can select and apply the optimized procedural elements in response to the user's behavior is complemented, it is confirmed that more intelligent objects and agents can be implemented in virtual reality applications.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.181-183
• /
• 2006

This paper proposes an intelligent decision framework for update of the environment model using GSPN(generalized stochastic petri nets). The GSPN has several advantages over direct use of the Markov Process. The modeling, analysis, and performance evaluation are conducted on the mathematical basis. By adopting the probabilistic approach, our decision framework helps the robot to decide the time to update the map. The robot navigates autonomously for a long time in dynamic environments. Experimental results show that the proposed scheme is useful for service robots which work semi-permanently and improves dependability of navigation in dynamic environments.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.4
• /
• pp.411-421
• /
• 1992

In the conventional track while scan (TWS) system, there are two major functions to be performed : detection and tracking. These two functions are normally designed and optimised independently. So TWS algorithm ignores the available decision features that can help in resolving the plot-to-track association ambiguity. Therefore conventional TWS system cna't track the targets in a densed multi-target environment. This paper presents a new TWS algorithm for multi-target track to solve the existing TWS system problem in clutter environment. The algorithm proposed in this paper is derived by modifying the part of joint probabilistic data association (JPDA) algotithm to get the one to one correspondence instead of multiple correspondence and combined with maneuvering detection logic so that it could also track the low maneuvering targets. Simulations to confirm the performance are done in crossing, parallel and maneuvering target. The proposed algorithm was successfully tracking targets above target situations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.706-709
• /
• 2008

With the increasing popularity of P2P file sharing and advancement of mobile technologies, mobile P2P has revealed its attraction. Anonymity has become an increasing requirement in mobile networks. To reduce receiving garbage files, file validation and filtering are other requirements in the mobile P2P environment. If there are effective file filtering and validation mechanism, nodes' battery duration will be saved. In this paper, we do an analysis of security and anonymity in P2P file sharing and exchange system in mobile ad hoc environment, and propose a new efficient anonymous protocol, which can provide anonymity by broadcasting with a probabilistic algorithm and hiding real hop count information, the file validation by the file's special hash value and file filtering mechanism through the collaboration of middle nodes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.244-251
• /
• 2007

Intention reading technique is essential to provide personalized services toward more convenient and human-friendly services in complex ubiquitous environment such as a smart home. If a system has knowledge about an user's intention of his/her behavioral pattern, the system can provide mote qualified and satisfactory services automatically in advance to the user's explicit command. In this sense, learning capability is considered as a key function for the intention reading technique in view of knowledge discovery. In this paper, ore introduce a personalized media control method for a possible application iii a smart home. Note that data pattern such as human behavior contains lots of inconsistent data due to limitation of feature extraction and insufficiently available features, where separable data groups are intermingled with inseparable data groups. To deal with such a data pattern, we introduce an effective engineering approach with the combination of fuzzy logic and probabilistic reasoning. The proposed learning system, which is based on IFCS (Iterative Fuzzy Clustering with Supervision) algorithm, extract probabilistic fuzzy rules effectively from the given numerical training data pattern. Furthermore, an extended architectural design methodology of the learning system incorporating with the IFCS algorithm are introduced. Finally, experimental results of the media contents recommendation system are given to show the effectiveness of the proposed system.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.134-141
• /
• 2003

A major research issue associated with service robots is the creation of an environment recognition system for mobile robot navigation that is robust and efficient on various environment situations. In recent years, intelligent autonomous mobile robots have received much attention as the types of service robots for serving people and industrial robots for replacing human. To help people, robots must be able to sense and recognize three dimensional space where they live or work. In this paper, we propose a three dimensional environmental modeling method based on an edge enhancement technique using a planar fitting method and a neural network technique called "Growing Neural Gas Network." Input data pre-processing provides probabilistic density to the input data of the neural network, and the neural network generates a graphical structure that reflects the topology of the input space. Using these methods, robot's surroundings are autonomously clustered into isolated objects and modeled as polygon patches with the user-selected resolution. Through a series of simulations and experiments, the proposed method is tested to recognize the environments surrounding the robot. From the experimental results, the usefulness and robustness of the proposed method are investigated and discussed in detail.in detail.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.10a
• /
• pp.649-654
• /
• 2005

Shallow slope failures in residual soil during periods of prolonged infiltration are common over the world. One of the key factors that dominate slope stability is hydrological response associated with infiltration. Hence, the soil-water profile during rainfall infiltration into unsaturated soil must me examined to evaluate slope stability. However, the hydraulic response of unsaturated soil is complicated by inherent uncertainties of the soil hydraulic properties. This study presents a methodology for assessing the effects of parameter uncertainty of hydraulic properties on the response of a analytical infiltration model using first-order reliability method. The unsaturated soil properties are considered as uncertain variables with means, standard deviations, and marginal probability distributions. Sensitivities of the probabilistic outcome to the basic uncertainties in the input random variables are provided through importance factors.