• Journal of Information Processing Systems
• /
• 제18권6호
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.652-662
• /
• 2023

Identifying highly discriminating genes is a critical step in tumor recognition tasks based on microarray gene expression profile data and machine learning. Gene selection based on tree models has been the subject of several studies. However, these methods are based on a single-tree model, often not robust to ultra-highdimensional microarray datasets, resulting in the loss of useful information and unsatisfactory classification accuracy. Motivated by the limitations of single-tree-based gene selection, in this study, ensemble gene selection methods based on multiple-tree models were studied to improve the classification performance of tumor identification. Specifically, we selected the three most representative tree models: ID3, random forest, and gradient boosting decision tree. Each tree model selects top-n genes from the microarray dataset based on its intrinsic mechanism. Subsequently, three ensemble gene selection methods were investigated, namely multipletree model intersection, multiple-tree module union, and multiple-tree module cross-union, were investigated. Experimental results on five benchmark public microarray gene expression datasets proved that the multiple tree module union is significantly superior to gene selection based on a single tree model and other competitive gene selection methods in classification accuracy.

• 정보처리학회논문지A
• /
• 제10A권2호
• /
• pp.173-180
• /
• 2003

본 논문에서는 WWW을 기반으로 한 게시판을 이용하여 교사와 학습자 사이에 질의 응답이 가능한 양방향 원격 대화식 학습 방법(RECT) 모듈을 개발하였다. RECT로 DCOM 음성 모듈을 이용하였는데 음성 자료의 사용은 교사에게 학습 자료 제작의 수월성을 주고, 학습자에게는 학습 환경을 준비하는데 수월성을 주기 위함이다. 게시판에서의 모든 학습 자료 및 질의 응답은 음성 모듈의 녹음 기능을 이용하여 음성 파일로 제공한다. 먼저 교사는 기본적인 설명을 게시판에 게시하고, 학생들은 교사의 설명을 들으면서 학습한다. 학생들이 교사의 설명으로 문제를 해결할 수 없을 때는 문제가 해결 될 때까지 교사에게 질문을 할 수 있고, 교사는 그에 대한 답변을 함으로써 양방향 원격 대화식 학습을 하고자 한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.795-798
• /
• 2005

In this paper, we analyses of additive crypto-module architecture for a sensor network. Recent research in sensor networks has raised security issues for small embedded devices. Security concerns are motivated by the development of a large number of sensor devices in the field. Limitations in processing power, battery life, communication bandwidth and memoryconstrain devices. A mismatch between wide arithmetic for security and embedded data buscombined with lack of certain operations. Then, we compared the architecture of crypto-module in this paper.

• 한국정보통신학회논문지
• /
• 제14권7호
• /
• pp.1603-1609
• /
• 2010

본 논문은 해군 호위함급에 장착/운용되는 LAS(Line Array Sensor, 예인선배열센서)로부터 A, B, C그룹 수중음향 신호의 시리얼 데이터를 입력 받아 약속된 Protocol로 Packing하여, 고속 데이터통신과 Optic-fiber채널 장거리 전송이 가능한 SFM(Serial FPDP Module)을 통해 신호처리단으로 실시간 전송하는 센서데이터 입출력처리보드의 설계/제작 및 시험에 관해 언급한다. VME(Versa Module Eurocard) 6U크기의 한정된 보드 공간을 고려하여 Freescale사의 PowerPC계열인 MPC8265 CPU와, 기존 외장 FIFO등의 외부디바이스를 줄이고 자체 시뮬레이션 데이터생성 등을 위해 Altera사의 CycloneIII 계열 FPGA등을 사용하여 설계하고, 실시간 데이터 전송을 보장하며 각종 Device Driver, Peripheral Controller등의 Library를 제공하는 RTOS인 VxWorks를 Porting하여 소프트웨어를 개발하였다.

• 전기학회논문지
• /
• 제66권9호
• /
• pp.1402-1408
• /
• 2017

Recently, services for personal biometric data analysis based on real-time monitoring systems has been increasing and many of them have focused on recognition of emotions. In this paper, we propose a classification model to classify anxiety emotion using biometric data actually collected from people. We propose to deploy the support vector machine to build a classification model. In order to improve the classification accuracy, we propose two data pre-processing procedures, which are normalization and data deletion. The proposed algorithms are actually implemented based on Real-time Traffic Flow Measurement structure, which consists of data collection module, data preprocessing module, and creating classification model module. Our experiment results show that the proposed classification model can infers anxiety emotions of people with the accuracy of 65.18%. Moreover, the proposed model with the proposed pre-processing techniques shows the improved accuracy, which is 78.77%. Therefore, we can conclude that the proposed classification model based on the pre-processing process can improve the classification accuracy with lower computation complexity.

• 한국정밀공학회지
• /
• 제29권5호
• /
• pp.506-509
• /
• 2012

Laser assisted machining is the processing method that preheating brittle materials by laser heat source and cutting the soften area. This processing applied to various industries because it can be cutting difficult-to-cut materials. However, the laser assisted machining appeared the limitations of processing for equipped with the spindle. So, it assumed separate model that spindle and laser assisted machining. In feed, the calculation of changing the angle of the laser module according to preheat point and the shape of the feed is important and it tried easy calculating changing angle of 1-axis Manipulator in separate model. In 3 types feed shape, angle of 1-axis Manipulator was calculated when fixed and moved in the outside of spindle. In this study, suggest 2 types of methods for laser module when fixed and moved.

• 한국농공학회논문집
• /
• 제57권2호
• /
• pp.15-26
• /
• 2015

The purpose of this paper is to develop a software tool, PGA-CC (Projection of hydrology via Grid-based Assessment for Climate Change) to evaluate the present hydrologic cycle and the future watershed hydrology by climate change. PGA-CC is composed of grid-based input data pre-processing module, hydrologic cycle calculation module, output analysis module, and output data post-processing module. The grid-based hydrological model was coded by Fortran and compiled using Compaq Fortran 6.6c, and the Graphic User Interface was developed by using Visual C#. Other most elements viz. Table and Graph, and GIS functions were implemented by MapWindow. The applicability of PGA-CC was tested by assessing the future hydrology of South Korea by HadCM3 SRES B1 and A2 climate change scenarios. For the whole country, the tool successfully assessed the future hydrological components including input data and evapotranspiration, soil moisture, surface runoff, lateral flow, base flow etc. From the spatial outputs, we could understand the hydrological changes both seasonally and regionally.

• Smart Structures and Systems
• /
• 제13권6호
• /
• pp.1041-1063
• /
• 2014

This work introduces a two-module robotic pipe inspection system with ultrasonic NDE device to evaluate the integrity of pipe structures. The proposed robotic platform has high mobility. The two module mobile robot platform overcomes pipe obstacle structures such as elbow, or T-branch joints by cooperative maneuvers. Also, it can climb up the straight pipeline at a fast speed due to the wheel driven mechanism. For inspection of pipe structure, SH-waves generated by EMAT are applied with additional signal processing methods. A wavelet transform is implemented to extract a meaningful and specific signal from the superposed SH-wave signals. Intensity ratio which is normalized the defect signals intensity by the maximum intensity of directly transmitted signals in the wavelet transforms spectrum is applied to evaluate defects quantitatively. It is experimentally verified that the robotic ultrasonic inspection system with EMAT is capable of non-destructive inspection and evaluation of defects in pipe structure successfully by applying signal processing method based on wavelet transform.

• 정보저장시스템학회논문집
• /
• 제7권2호
• /
• pp.70-74
• /
• 2011

The mobile camera module is a device to be inserted in the digital device for camera feature. The mobile camera module is being shaken by vibrations such as handshake during the exposure time. The clarity is compromised by these vibrations, thus the vibration is considered as an external disturbance. Moreover the use of mobile camera module has been being expanded for automotive vibration should be considered. These external disturbances can cause image blurring, thus optical image stabilization should be applied for image compensation. The compensator is fulfilled mechanically by movable lens group or image sensor that adjusts the optical path to the camera movement. Open loop control is useful for well-defined systems like compliant mechanism. Notch filter and lead compensator are designed and applied to improve the stability and bandwidth. The final level of image compensating is confirmed by image processing with MATLAB and CODE V to verify the better performance.