• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.46-63
• /
• 2024

One of the biggest dangers in the globe is water contamination. Water is a necessity for human survival. In most cities, the digging of borewells is restricted. In some cities, the borewell is allowed for only drinking water. Hence, the scarcity of drinking water is a vital issue for industries and villas. Most of the water sources in and around the cities are also polluted, and it will cause significant health issues. Real-time quality observation is necessary to guarantee a secure supply of drinking water. We offer a model of a low-cost system of monitoring real-time water quality using IoT to address this issue. The potential for supporting the real world has expanded with the introduction of IoT and other sensors. Multiple sensors make up the suggested system, which is utilized to identify the physical and chemical features of the water. Various sensors can measure the parameters such as temperature, pH, and turbidity. The core controller can process the values measured by sensors. An Arduino model is implemented in the core controller. The sensor data is forwarded to the cloud database using a WI-FI setup. The observed data will be transferred and stored in a cloud-based database for further processing. It wasn't easy to analyze the water quality every time. Hence, an Optimized Neural Network-based automation system identifies water quality from remote locations. The performance of the feed-forward neural network classifier is further enhanced with a hybrid GA- PSO algorithm. The optimized neural network outperforms water quality prediction applications and yields 91% accuracy. The accuracy of the developed model is increased by 20% because of optimizing network parameters compared to the traditional feed-forward neural network. Significant improvement in precision and recall is also evidenced in the proposed work.

• 전기학회논문지
• /
• 제67권11호
• /
• pp.1423-1433
• /
• 2018

Recently, a permanent magnet synchronous motor of middle and small-capacity has high torque, high precision control and acceleration / deceleration characteristics. But existing control has several problems that include unpredictable disturbances and parameter changes in the high accuracy and rigidity control industry or nonlinear dynamic characteristics not considered in the driving part. In addition, in the drive method for the control of low-vibration and high-precision, the process of connecting the permanent magnet synchronous motor and the load may cause the response characteristic of the system to become very unstable, to cause vibration, and to overload the system. In order to solve these problems, various studies such as adaptive control, optimal control, robust control and artificial neural network have been actively conducted. In this paper, an incremental encoder of the permanent magnet synchronous motor is used to detect the position of the rotor. And the position of the detected rotor is used for low vibration and high precision position control. As the controller, we propose augmented state feedback control with a speed observer and first order deadbeat disturbance observer. The augmented state feedback controller performs control that the position of the rotor reaches the reference position quickly and precisely. The addition of the speed observer to this augmented state feedback controller compensates for the drop in speed response characteristics by using the previously calculated speed value for the control. The first order deadbeat disturbance observer performs control to reduce the vibration of the motor by compensating for the vibrating component or disturbance that the mechanism has. Since the deadbeat disturbance observer has a characteristic of being vulnerable to noise, it is supplemented by moving average filter method to reduce the influence of the noise. Thus, the new controller with the first order deadbeat disturbance observer can perform more robustness and precise the position control for the influence of large inertial load and natural frequency. The simulation stability and efficiency has been obtained through C language and Matlab Simulink. In addition, the experiment of actual 2.5[kW] permanent magnet synchronous motor was verified.

• 한국ITS학회 논문지
• /
• 제20권3호
• /
• pp.74-85
• /
• 2021

전파를 수신하여 측위를 수행하는 GNSS 수신기는 본질적으로 재밍에 취약하다. 재밍 발생 검출, 재밍 신호 종류 판별, 재밍원 위치추정 기능을 갖는 GNSS 재밍 모니터링 시스템은 안전한 자율주행 환경구축에 도움을 준다. 이를 위하여 다수의 저가 GNSS 수신기들의 배치로 구성된 GNSS 모니터링 네트워크 구축이 필요하며, 앞서 언급한 3가지 기능 구현을 위하여 네트워크 내 독립된 저가 GNSS 수신기 간 정밀 시각 동기가 요구된다. 본 논문은 신호영역 TDOA 기술 직접 사용방식의 수신기 간 시각 동기화 기법을 제안한다. 계산 효율성을 위하여 상대적으로 낮은 샘플링 주파수에도 시각 동기 정밀도를 유지하고자 블록 보간법을 추가로 활용한다. 수치적 시뮬레이션을 통하여 제안한 GNSS 수신기 간 시각 동기화 기법의 가용성을 입증한다.

• Journal of Ubiquitous Convergence Technology
• /
• 제2권2호
• /
• pp.67-77
• /
• 2008

Representation of various types of information in an interactive virtual reality environment on mobile devices had been an attractive and valuable research in this new era. Our main focus is presenting spatial indoor location sensing information in 3D perception in mind to replace the traditional 2D floor map using handheld PDA. Designation of 3D virtual reality by Virtual Reality Modeling Language (VRML) demonstrates its powerful ability in providing lots of useful positioning information for PDA user in real-time situation. Furthermore, by interpolating portal culling algorithm would reduce the 3D graphics rendering time on low power processing PDA significantly. By fully utilizing the CC2420 chipbased sensor nodes, wireless sensor network was established to locate user position based on Received Signal Strength Indication (RSSI) signals. Implementation of RSSI-based indoor tracking method is low-cost solution. However, due to signal diffraction, shadowing and multipath fading, high accuracy of sensing information is unable to obtain even though with sophisticated indoor estimation methods. Therefore, low complexity and flexible accuracy refinement algorithm was proposed to obtain high precision indoor sensing information. User indoor position is updated synchronously in virtual reality to real physical world. Moreover, assignment of magnetic compass could provide dynamic orientation information of user current viewpoint in real-time.

• 한국정밀공학회지
• /
• 제29권10호
• /
• pp.1128-1136
• /
• 2012

In this paper, the states and parameters in a dynamic system are estimated by applying an Unscented Kalman Filter (UKF). The UKF is widely used in various fields such as sensor fusion, trajectory estimation, and learning of Neural Network weights. These estimations are necessary and important in determining the stability of a mobile system, monitoring, and predictions. However, conventional approaches are difficult to estimate based on the experimental data, due to properties of non-linearity and measurement noises. Therefore, in this paper, UKF is applied in estimating the states and parameters needed. An experimental dynamic system has been set up for obtaining data and the experimental data is collected for parameter estimation. The measurement noises are primarily reduced by applying the Low Pass Filter (LPF). Given the simulation results, the estimated error rate is 39 percent more efficient than the results obtained using the Least Square Method (LSM). Secondly, the estimated parameters have an average convergence period of four seconds.

• International Journal of Contents
• /
• 제18권2호
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.

• 한국정보통신학회논문지
• /
• 제18권11호
• /
• pp.2640-2644
• /
• 2014

최근의 기술발전과 함께 무선 센서 네트워크 (Wireless Sensor Network, WSN)는 수많은 작고 저렴한 센서 노드로 구성된 센서네트워크이다. 무선 센서 네트워크는 공동으로 배치된 지역 내에서 정보감지, 수집, 처리 및 전송임무를 수행한다. 또한, 지능형교통, 의료구조, 환경감시, 정밀농업 및 공업 자동화 등 다양한 방면에 응용할 수 있다. 그래서 센서 네트워크 환경에서 데이터 유지관리 기술은 센서 네트워크의 핵심 기술 중 하나이다. 본 논문은 현재 무선 센서 네트워크 데이터 관리를 위한 기술을 분석하고 이들의 문제점에 대해 살펴보았다. 향후 본 연구를 통해 센서 네트워크의 체계적인 개발 접근을 시도해볼 수 있을 것이다.

• 한국산학기술학회논문지
• /
• 제21권12호
• /
• pp.320-330
• /
• 2020

화재는 높은 비정형성으로 인해 딥러닝 모델을 이용한 영상인식 분야에서도 좋은 성능을 내기가 어려운 대상 중 하나이다. 특히 지하공동구 내 화재는 딥러닝 모델의 학습을 위한 화재 데이터 확보가 어렵고 열약한 영상 조건 및 화재로 오인할 수 있는 객체가 많아 화재 검출이 어렵고 성능이 낮다. 이러한 이유로 본 연구는 딥러닝 기반의 지하공동구 내 화재 탐지 모델을 제안하고, 제안된 모델의 성능을 평가하였다. 기존 합성곱 인공신경망에 GoogleNet의 Inception block과 ResNet의 skip connection을 조합하여 어두운 환경에서 발생되는 화재 탐지를 위한 모델 구조를 제안하였으며, 제안된 모델을 효과적으로 학습시키기 위한 방법도 함께 제시하였다. 제안된 방법의 효과를 평가하기 위해 학습 후 모델을 지하공동구 및 유사환경 조건의 화재 문제와 화재로 오인할 수 있는 객체를 포함한 이미지에 적용해 결과를 분석하였다. 또한 기존 딥러닝 기반 화재 탐지 모델의 정밀도, 검출률 지표와 비교함으로써 모델의 화재 탐지 성능을 정량적으로 평가하였다. 제안된 모델의 결과는 어두운 환경에서 발생되는 화재 문제에 대해 높은 정밀도와 검출률을 나타내었으며, 유사 화재 객체에 대해 낮은 오탐 및 미탐 성능을 가지고 있음을 보여주었다.

• 한국측량학회지
• /
• 제40권3호
• /
• pp.207-215
• /
• 2022

저가형 UAV기반 사진측량의 정밀도와 정확도를 평가하기 위한 실험을 수행하였다. 높은 정확도의 지상기준점과 검사점의 3차원 좌표를 추정하고자 GNSS정지관측과 기선해석, 망조정을 수행하였고, 신뢰수준 95%에 대하여 정확도가 1cm 이내인 좌표를 확보하였다. 실험 대상지에 대한 항공 사진은 DJI Phantom 4와 이에 탑재된 FC330 카메라로 7회 반복 촬영하였고, 이를 두 가지 소프트웨어로 처리하였다. 10개 검사점에 대한 소프트웨어 자동 추출좌표와 GNSS 추정해를 비교하여 표준편차 및 RMSE를 분석하였다. 두 소프트웨어 처리 결과, 95% 신뢰수준에 대해 표준편차는 남북, 동서, 높이 방향 각각 약 1cm, 2cm, 4cm 이내, RMSE는 수평과 높이 각각 9cm, 8cm 이내였으며, 표준편차가 RMSE에 비해 현저히 작았다. 두 소프트웨어 처리 결과의 통계적 차이를 확인하고자 F-ratio 검정을 수행하였다. 정밀도에 대해서는 모든 좌표 성분에 대해 한쪽꼬리 검정의 귀무가설이 기각되었고, RMSE에 대해서는 수평에 대한 것만 기각되었다. 이에 따라, 동일한 사진 자료를 처리하더라도 소프트웨어에 따라 그 결과에 통계적 차이가 있을 수 있음에 유의할 필요가 있다.