• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.10
• /
• pp.1999-2007
• /
• 2017

In this paper, we implement a multi-band network selection (MNS) system based on Linux operating system which determines the optimal communication link for given network conditions among the available LTE, very high frequency (VHF), and high frequency (HF). The implemented software consists of a network interface, an MNS server, and a user GUI. We perform indoor test to verify the function of the implemented MNS system using two sets of MNS system. To this end, two types of VHF communication links that follow ITU-R M.1842-1 Annex 1 and Annex 4 are emulated in software. In addition, the HF transmission (reception) port of one MNS is directly connected to the HF reception (transmission) port of another MNS. We demonstrate through indoor tests that the implemented MNS system can support seamless maritime communication service in spite of artificial disconnection or re-connection of LTE, VHFs, and HF. The implemented MNS system is applicable to various maritime communication services including e-navigation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1865-1869
• /
• 2004

A new model for the propagation prediction for mobile communication network inside building is presented in this paper. The model is based on the determination of the dominant paths between the transmitter and the receiver. The field strength is predicted with adaptive neuro - fuzzy inference systems (ANFIS), trained with measurements. The advantage of the ANFIS with hybrid least squares and gradient descent algorithms is fast convergence compared with original neural network. The K-means algorithm for selection of training patterns is also used. Comparison of our predicted results to measurements indicate that improvements in accuracy over conventional empirical model are achieved.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.12
• /
• pp.1204-1208
• /
• 2014

As required performance of UAV (Unmanned Aerial Vehicle) becomes more complex and complicated, required positioning accuracy is becoming more and more higher. GPS is a reliable world wide positioning providing system. Therefore, UAV generally acquires position information from GPS. But when GPS is not available such as too weak signal or too less GPS satellites environments, UAV needs alternative positioning system such as network positioning system. RSSI (Received Signal Strength Indicator) based positioning, which is one method of network positioning technologies, determines its position using RSSI measurements containing distance information from AP (Access Point)s. In that method, a selected AP's configuration has strong and tight relationship with its positioning errors. In this paper, for, we additionally account AP's configuration information by adopting DOP (Dilution of Precision) into AP selection procedures and provide more accurate RSSI based positioning results.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.363-364
• /
• 2008

Localization algorithms are required for indoor sensor network applications. In this paper, we introduce an efficient algorithm for low complexity and high accuracy, termed multi-internal division localization(MID), which emphasizes simple refinement and low system-load for low-cost and low-rate wireless sensors. We inspect MID algorithm through MATLAB simulation.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.1
• /
• pp.1-8
• /
• 2002

It has been integrated into several navigation systems. This paper shows that system recognizes difficult indoor roads without any specific marks such as painted guide line or tape. In this method the robot navigates with visual sensors, which uses visual information to navigate itself along the read. The Neural Network System was used to learn driving pattern and decide where to move. In this paper, I will present a vision-based process for AMR(Autonomous Mobile Robot) that is able to navigate on the indoor read with simple computation. We used a single USB-type web camera to construct smaller and cheaper navigation system instead of expensive CCD camera.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.3
• /
• pp.136-142
• /
• 2008

Mobile robots can offer services like intelligent monitoring in an indoor environment using network connection with remote users. In this paper, we designed and developed a networked security robot system with various sensors, such as flame detector, gas detector, sound monitoring module, and temperature sensor, etc. The robot can be accessed through a web service and the user can check the status of the environment. Using ADAMS software, we defined the motor specification for a worst-case condition of climbing over a obstacle. We applied the robot system in monitoring office condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.3
• /
• pp.508-522
• /
• 2011

Femtocell is an economical solution to provide high speed indoor communication instead of the conventional macro-cellular networks. Especially, OFDMA femtocell is considered in the next generation cellular network such as 3GPP LTE and mobile WiMAX system. Although the femtocell has great advantages to accommodate indoor users, interference management problem is a critical issue to operate femtocell network. Existing OFDMA resource management algorithms only consider optimizing system-centric metric, and cannot manage the co-channel interference. Moreover, it is hard to cooperate with other femtocells to control the interference, since the self-configurable characteristics of femtocell. This paper proposes a novel interference-aware resource allocation algorithm for OFDMA femtocell networks. The proposed algorithm allocates resources according to a new objective function which reflects the effect of interference, and the heuristic algorithm is also introduced to reduce the complexity of the original problem. The Monte-Carlo simulation is performed to evaluate the performance of the proposed algorithm compared to the existing solutions.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.9
• /
• pp.868-875
• /
• 2006

The localization is one of the most important issues for mobile robot. This paper describes a novel localization system for the development of a location sensing network. The system comprises wirelessly controlled infrared landmarks and an image sensor which detects the pixel positions of infrared sources. The proposed localization system can operate irrespective of the illumination condition in the indoor environment. We describe the operating principles of the developed localization system and report the performance for mobile robot localization and navigation. The advantage of the developed system lies in its robustness and low cost to obtain location information as well as simplicity of deployment to build a robot location sensing network. Experimental results show that the developed system outperforms the state-of-the-art localization methods.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.12
• /
• pp.830-836
• /
• 2012

In this study, the effects of heating control methods on heating control performance and energy consumption in the floor radiant heating control system of residential apartments were research by computer simulation. A general regression neural network(GRNN) control method for reducing indoor temperature overshoot and saving energy in floor radiant heating system is suggested. The GRNN control method shows good responses in comparison with the conventional and outdoor reset control methods for improving indoor thermal environment and reducing energy consumption.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.188-195
• /
• 2024

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.