• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.4
• /
• pp.1294-1300
• /
• 2010

In an environment where all nodes move, the sensor node receives anchor node's position information within communication radius and modifies the received anchor node's position information by one's traveled distance and direction in saving in one's memory, where if there at least 3, one's position is determined by performing localization through trilateration. The proposed localization mechanisms have been simulated in the Matlab. In an environment where certain distance is maintained and nodes move towards the same direction, the probability for the sensor node to meet at least 3 anchor nodes with absolute coordinates within 1 hub range is remote. Even if the sensor node has estimated its position with at least 3 beacon information, the angle ${\theta}$ error of accelerator and digital compass will continuously apply by the passage of time in enlarging the error tolerance and its estimated position not being relied. Dead reckoning technology is used as a supplementary position tracking navigation technology in places where GPS doesn't operate, where one's position can be estimated by knowing the distance and direction the node has traveled with acceleration sensor and digital compass. The localization algorithm to be explained is a localization technique that uses Dead reckoning where all nodes are loaded with omnidirectional antenna, and assumes that one's traveling distance and direction can be known with accelerator and digital compass. The simulation results show that our scheme performed better than other mechanisms (e.g. MCL, DV-distance).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1005-1018
• /
• 2017

This paper proposes an App Visualization (AppV) based on IoT Self-diagnosis Micro Control Unit (ISMCU) for accident prevention. It collects a current status of a vehicle through a sensor, visualizes it on a smart phone and prevents vehicles from accident. The AppV consists of 5 components. First, a Sensor Layer (SL) judges noxious gas from a current vehicle and a driver's driving habit by collecting data from various sensors such as an Accelerator Position Sensor, an O2 sensor, an Oil Pressure Sensor, etc. and computing the concentration of the CO collected by a semiconductor gas sensor. Second, a Wireless Sensor Communication Layer (WSCL) supports Zigbee, Wi-Fi, and Bluetooth protocol so that it may transfer the sensor data collected in the SL to ISMCU and the data in the ISMCU to a Mobile. Third, an ISMCU integrates the transferred sensor information and transfers the integrated result to a Mobile. Fourth, a Mobile App Block Programming Tool (MABPT) is an independent App generation tool that changes to visual data just the vehicle information which drivers want from a smart phone. Fifth, an Embedded Module (EM) records the data collected through a Smart Phone real time in a Cloud Server. Therefore, because the AppV checks a vehicle' fault and bad driving habits that are not known from sensors and performs self-diagnosis through a mobile, it can reduce time and cost spending on accidents caused by a vehicle's fault and noxious gas emitted to the outside.

• Journal of Advanced Navigation Technology
• /
• v.13 no.2
• /
• pp.262-271
• /
• 2009

The purpose of this study was to propose the method to recognize gestures based on inertia sensor which recognizes the movements of the user using inertia sensor and lets the user enjoy the game by comparing the recognized movements with the pre-defined movements for the game contents production. Additionally, it was tried to provide users with various data entry methods by letting them wear small controllers using three-axis accelerator sensor. Users can proceed the game by moving according to the action list printed on the screen. They can proceed the experiential games according to the accuracy and timing of their movements. If they use multiple small wireless controllers together wearing them on the major parts of hands and feet and utilize the proposed methods, they will be more interested in the game and be absorbed in it.

• Journal of Sensor Science and Technology
• /
• v.32 no.4
• /
• pp.246-251
• /
• 2023

Internet of Things (IoT) systems process signals from various sensors using signal processing algorithms suitable for the signal characteristics. To analyze complex signals, these systems usually use signal processing algorithms in the frequency domain, such as fast Fourier transform (FFT), filtering, and short-time Fourier transform (STFT). In this study, we propose a multi-mode sensor signal processor (SSP) accelerator with an FFT-based hardware design. The FFT processor in the proposed SSP is designed with a radix-2 single-path delay feedback (R2SDF) pipeline architecture for high-speed operation. Moreover, based on this FFT processor, the proposed SSP can perform filtering and STFT operation. The proposed SSP is implemented on a field-programmable gate array (FPGA). By sharing the FFT processor for each algorithm, the required hardware resources are significantly reduced. The proposed SSP is implemented and verified on Xilinxh's Zynq Ultrascale+ MPSoC ZCU104 with 53,591 look-up tables (LUTs), 71,451 flip-flops (FFs), and 44 digital signal processors (DSPs). The FFT, filtering, and STFT algorithm implementations on the proposed SSP achieve 185x average acceleration.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.207-210
• /
• 2005

Ubiquitous computing is one of the key technology areas in the "Project on Development of Ubiquitous computing and network technology" promoted by the Ministry of Science and Technology as a frontier business of the $21^{st}$ century in Korea, which is based on the new concept merging physical space and computer-based cyber space. With recent advances in Micro Electro Mechanical System (MEMS) technology, low cost and low-power consumption wireless micro sensor nodes have been available. Using these smart sensor nodes, there are many activities to monitor real world, for example, habitat monitoring, earthquake monitoring and so on. In this paper, we introduce web-based real environment monitoring system incorporating wireless sensor nodes. It collects sensing data produced by some wireless sensor nodes and stores them into a database system to analyze. Our environment monitoring system is composed of a networked camera and environmental sensor nodes, which are called Mica2 and developed by University of California at Berkeley. We have modified and ported network protocols over TinyOS and developed a monitoring application program using the MTS310 and MTS420 sensors that are able to observe temperature, relative humidity, light and accelerator. The sensed data can be accessed user-friendly because our environment monitoring system supports web-based user interface. Moreover, in this system, we can setup threshold values so the system supports a function to inform some anomalous events to administrators. Especially, the system shows two useful pre-processed data as a kind of practical uses: a discomfort index and a septicity index. To make both index values, the system restores related data from the database system and calculates them according to each equation relatively. We can do enormous works using wireless sensor technologies, but just environment monitoring. In this paper, we show just one of the plentiful applications using sensor technologies.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2005.06a
• /
• pp.1155-1160
• /
• 2005

In order to evaluate the safety of navigation at sea and the safety of mooring ship on berthing, it is necessary that the wave and wind induced ship dynamic motion should be measured in real time domain for the validity of theoretical evaluation method such as sea-keeping performance and safety of mooring. In this paper, the basic design of sensors is discussed and some system configurations were shown. The developed system mainly consists of 4 kinds of sensors such as three dimensional accelerator, two dimensional tilt sensor, two displacement sensors and azimuth sensor. Using the this measuring system, it can be obtained the 6 degrees of freedom of ship dynamic motions at sea and on berthing such as rolling, pitching, yawing, sway, heave, surge under the external forces.

• Journal of Ocean Engineering and Technology
• /
• v.20 no.2 s.69
• /
• pp.59-65
• /
• 2006

Steel, as a reinforcing mechanism in concrete, provides the tensile strength that is lacking in concrete, alone, and the high alkaline environment (pH 12.5) in concrete offers satisfactory protection against most corrosion of the steel. However, the corrosion of reinforcing steel in concrete can occur by chloride attack or carbonation, and it can cause a loss of integrity a section and concrete failure through cracking and spalling. In this study, a transient electro magnetic method (TEM) of a nondestructive technique is adapted to study the measuring method of steel corrosion in mortar. The sensor was made of an enameled wire, with a diameter of 0.25mm and anacril. He sensor configuration used was a coincident loop type. The secondary electro motive force (2nd EMF) was measured with SIROTEMIII, which equipped the accelerator. The accelerator allowsthe transmitter to turn off approximately $10\sim15$ times faster than normal. The high-resolution time series, used for very shallow or a high resistivity investigation was selected. After steels were corroded by the salt spray, during 4, 8, 15 and 25 days, they were embedded in mortar. The content results acquired in this study are as follows. The variation of the secondary electro motive force (2nd EMF) was shown by the change of steel surface with different corrosion time steel. It was confirmed that measurement of steel corrosion in mortar by a transient electro-magnetic method (TEM) can be possible.

• Journal of the Korean Society of Radiology
• /
• v.8 no.7
• /
• pp.383-387
• /
• 2014

In this paper, for a new detection system development with the better accurate dose evaluation and beam distribution imaging using the small field irradiation of linear accelerator, the compound semiconductor based detection sensors were fabricated and the performance evaluation was investigated. The special particle-in-binder sedimentation was used for a large area film sensor fabrication. The detection properties for high energy x-rays were investigated from a dark current, an output current, a rising time, a falling time, and response delay measurement. The experimental results, the $TiO_2$ mixed $HgI_2$ sensor showed the best electrical characteristics than $PbI_2$, PbO, pure $HgI_2$. Linearity, repeatability, and accuracy tests from LINAC were tested, the $TiO_2$ mixed $HgI_2$ sensor showed the better performance than the commercially available dosimetry devices.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.777-782
• /
• 2020

In this paper, we propose CNN-based HMI system using Doppler radar and voice sensor, and present hardware design and implementation results. To overcome the limitation of single sensor monitoring, the proposed HMI system combines data from two sensors to improve performance. The proposed system exhibits improved performance by 3.5% and 12% compared to a single radar and voice sensor-based classifier in noisy environment. In addition, hardware to accelerate the complex computational unit of CNN is implemented and verified on the FPGA test system. As a result of performance evaluation, the proposed HMI acceleration platform can be processed with 95% reduction in computation time compared to a single software-based design.