• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.468-472
• /
• 2005

This paper is to investigate the influence of the endface quality on the loss characteristics of a plastic optical fiber connector for in-car network service. Using the parameters of the surface roughness and applied load, insertion loss of connector is measured. Due to scattering and change of refractive index, an optimal condition for low-loss coupling exists. We present the optimal condition as surface roughness $R_{rms}$ = 8 nm and contact load up to 50 N.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.257-262
• /
• 1997

A compact measurement system is developed to measure in-process errors due to thermal deformation of a machine tool, this system is composed of a gauge, 5gap-sensors and a PC. The gauge is made of invar, which is a material that has a very low thermal expansion coefficient. A new neural network model is constructed to estimate thermally induced machine tool errors based on the measured data,the given data,that is a width of cut,a depth of cut, a feed rate, a spindel speed etc, and the calculated data. The detail of the model proposed is described in the paper together with the experimental methodologies using a proposed compact measurement system to examine the validity of the proposed approach.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.1
• /
• pp.15-31
• /
• 2005

Nowadays, the road safety is an important research field. One of the principal research topics in this field is the vehicle localization in the road network. This article presents an approach of multi sensor fusion able to locate a vehicle with a decimeter precision. The different informations used in this method come from the following sensors: a low cost GPS, a numeric camera, an odometer and a steer angle sensor. Taking into account a complete model of errors on GPS data (bias on position and nonwhite errors) as well as the data provided by an original approach coupling a vision algorithm with a precise numerical map allow us to get this precision.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.311-315
• /
• 2006

Precision location and positioning of Asset within a network is an attractive feature with various applications, especially in indoor environments. Such a demand is met by the standard task group, IEEE 802.15.4a. Several methods, that is, pulse, chirp and chaotic communications have been proposed so far to satisfy the requirements of the standard. Among them, ultra wideband direct chaotic communications has advantageous features such as low hardware complexity, low cost, lower power consumption and flexible frequency band plan. In this paper, the feasibility of the ranging system using non-coherent chaotic transceiver is investigated by designing and implementing the system and the performance is proved by conducting location experiments in real indoor environments.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.6 s.183
• /
• pp.44-51
• /
• 2006

This paper deals with the aspects of die design for the multistage fine tooth hub gear in the cold forging process. In order to manufacture the cold forged product for the precision hub gear used as the ARD 370 system of bicycle, it examines the influences of different designs on the metal flow through experiments and FE-simulation. To find the combination of design parameters which minimize the damage value, the low gear length, upper gear length and inner diameter as design parameters are considered. An orthogonal fraction factorial experiment is employed to study the influence of each parameter on the objective function or characteristics. The optimal punch shape of fine tooth hub gear is designed using the results of FE-simulation and the artificial neural network. To verify the optimal punch shape, the experiments of the cold forging of the hub gear are executed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.217-220
• /
• 2014

Wireless sensor network（WSN） consists by a large number of low-cost micro-sensor nodes, collaborate to achieve the perception of information collection, processing and transmission tasks in deployment area. It can be widely used in national defense, intelligent transportation, medical care, environmental monitoring, precision agriculture, and industrial automation and many other areas. One of the key technologies of sensor networks is the data maintenance management technology. In this paper we analyze the data management technology of wireless sensor network and pointed their problems.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• Journal of Navigation and Port Research
• /
• v.40 no.5
• /
• pp.265-270
• /
• 2016

Extreme tropospheric anomalies such as typhoons or regional torrential rain can degrade positioning accuracy of the GPS signal. It becomes one of the main error terms affecting high-precision positioning solutions in network RTK. This paper proposed a detection algorithm to be used during atmospheric anomalies in order to detect the tropospheric irregularities that can degrade the quality of correction data due to network errors caused by inhomogeneous atmospheric conditions between multi-reference stations. It uses an atmospheric grid that consists of four meteorological stations and estimates the troposphere zenith total delay difference at a low performance point in an atmospheric grid. AWS (automatic weather station) meteorological data can be applied to the proposed tropospheric anomaly detection algorithm when there are different atmospheric conditions between the stations. The concept of probability density distribution of the delta troposphere slant delay was proposed for the threshold determination.

• Journal of the Optical Society of Korea
• /
• v.9 no.1
• /
• pp.1-5
• /
• 2005

Using tightly focused femtosecond laser pulses, we produce an optical waveguide and optical devices in transparent materials. This technique has the potential to generate not only channel waveguides, but also three-dimensional optical devices. In this paper, an optical splitter and U-grooves, which are used for fiber alignment, are simultaneously fabricated in a fused silica glass using near-IR femtosecond laser pulses. The fiber aligned optical splitter has a low insertion loss, less than 4㏈, including an intrinsic splitting loss of 3㏈ and excess loss due to the passive alignment of a single-mode fiber. Finally, we demonstrate the utility of the femtosecond laser writing technique by fabricating gratings at the surface and inside the silica glass.