Earticle

Vehicular positioning with GPS/IMU has been studied a lot to increase positioning accuracy. The positioning algorithms mainly use DR (Dead Reckoning) which uses EKF (Extended Kalman Filter). It is basic and very important core technology in positioning section. However, EKF has a major drawback in that it is impossible to make very accurate system and measurement models for a real environment. In this work, we propose an algorithm to estimate vehicle’s position as distribution form, and to control the system and measurement noise covariance to compensate for this major disadvantage. The proposed method to control noise covariance is independently processed, using fading factor and sensor error while considering the driving condition.

A distributed congestion control must be adaptable to varying target communication ranges as cellular V2X (C-V2X) is evolving to support flexible coverage suitable for various service scenarios. This study proposes range-adaptive distributed power control (Ra-DPC) based on deep reinforcement learning (DRL) with the Monte Carlo policy gradient algorithm. A key finding is that the agents learn Ra-DPC more effectively when the cumulative interference power of the subchannels is adopted as the state of the DRL model, rather than the channel busy ratio. The proposed Ra-DPC algorithm performs better in energy efficiency and packet delivery ratio than the existing technologies.

치관 국제적으로 전방차량을 따라 순항하거나 전방 장애물을 인식해 경고를 주는 등 교통 및 도로 상황에 대응하여 운전자에게 안전운전을 지원하는 기능을 갖춘 첨단안전차량(Advanced Safety Vehicle: ASV)이 개발되어 시판되고 있다. 국제표준기구(ISO) ITS기술위원회(TC2O4)의 도로/차량 경고 및 제어시스템(Vehicle/Roadway Warning and Control System) 분야(WGl4)에서는 ASV의 각종 기능과 관련한 국제표준을 제정하기 위한 작업이 활발히 진행되고 있다. 또한 각 국가들은 ASV 핵심기능들을 대상으로 그 나라의 도로 및 교통 환경 하에서 실차 주행시험을 통해 기능의 안전도 및 적합성을 평가하는 연구개발을 진행하고 있다 우리나라에서도 건설교통부 ITS 연구개발사업을 통해 ASV 핵심 기능의 하나인 감응식순항제어(Adaptive Cruise Control: ACC)에 대한 국내의 주행 적합성을 평가하기 위한 종합 시험평가 프로그램이 개발 제시되었다. 본 논문에서는 진행중인 국제표준을 근거로 국내의 도로/교통조건에 따른 차량주행 시나리오를 통해 개발된 ACC 종합시험평가 프로그램을 소개하고 이에 따라 실시된 시험결과를 분석한다 이를 통해 결과적으로 ACC의 곽내 주행을 위한 안전기준의 필요성을 제시한다.

Advanced safety vehicle (ASV) equipped with intelligent drivers advisory functions for controlling vehicle to follow the lead vehicle and/or warning drivers on forward traffic impediments according to the roadway and traffic circumstances has been recently developed and on the market internationally. Standardization processes for ASV system functions have been issued in IS0/TC204 Working Group 14 (Vehicle/Roadway Warning and Control System) since 1995. Research projects developing test and evaluation technologies for ASV in establishing safety standards and/or conformity related to the national roadway and traffic circumstances are under study internationally. In Korea, an integrated test and evaluation Program was developed for the assessment of adaptive cruise control (ACC) system under the ITS research and development projects funded by the Ministry of Construction and Transportation (MOCT). This paper demonstrates the integrated test and evaluation Programs for ACC system based on the draft international standard with related to the domestic roadway and traffic conditions. Field tests fulfilled under the scenarios based on the integrated test & evaluation programs for ACC system are discussed along with a review of earlier research work regarding international standards and the safety regulations.

본 논문에서는 시각장애인을 위한 적응적 전력 제어 장애물 회피 시스템을 제안한다. 그 시스템은 경로상에 놓인 장애물들을 회피할 수 있도록 다수의 초음파 센서를 이용한다. 우리는 보행자의 진행 방향을 몇 가지 패턴으로 나누고, 그 패턴들을 분석해서 진행 방향을 결정한다. 그때 내장된 가속도 센서를 이용하여 보행자의 움직임을 추정하고 은닉 마르코프 모델을 이용하여 가속도 정보를 처리한다. 우리의 시스템은 동작하는 초음파 센서의 개수를 가변적으로 조절하여 적응적 소비 전력 조절이 가능할 뿐만 아니라, 시각장애인이 안전하게 보행하도록 도와준다.

We propose adaptive power control of an obstacle avoidance system for visually impaired person. It utilizes multiple ultrasonic sensors to detect obstacles lying in the path. We evaluate complex structure in front of the user with predefined patterns and determine avoidance direction by analysing those patterns. It evaluates motion context using built-in accelerometer sensor and estimates acceleration information utilizing hidden Markov model. Our system safely guides visually impaired person as well as adaptively controls power consumption adjusting the number of active ultrasonic sensors.

This study presents model-free reinforcement learn ing methods for economic and ecological adaptive cruise control (Eco-ACC) of connected and autonomous electric vehicles. For model-free optimal control of Eco-ACC, we applied two reinforcement learning methods, Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG), in which deep neural networks of actors and critics were trained using IPG CarMaker simulations. For performance demonstrations, the HWFET, US06, and WLTP Class 3b driving cycles were used to simulate the front vehicle, and the energy consumptions of the host vehicle and front vehicle were compared. In high-fidelity IPG CarMaker simulations, the proposed reinforcement learning- based Eco-ACC methods demonstrated approximately 3–5% and 10–14% efficiency improvements in highway and city-highway driving scenarios, respectively, when compared with the front vehicle. A video of the CarMaker simulation is available at https://youtu.be/DIXzJxMVig8.

The adaptive power control of Code Division Multiple Access (CDMA) systems for communications between User Equipments (UEs) with a link-budget based Signal-to-Interference Ratio (SIR) estimate which has distance information is applied to three inner loop power control algorithms. The speed estimation performances of these algorithms with their consecutive Transmit-Power-Control (TPC) ratios are compared to each other, and it is concluded that the speed can be estimated using the TPC ratio information of Consecutive TPC Ratio Step-size Closed Loop Power Control (CS-CLPC) and Fixed Step-size Power Control (FSPC).

This paper introduces a system that uses Functional Electrical Stimulation (FES) for finger flexion control aimed rehabilitation for stroke patients. To address the variability in electrode between patients, Reinforcement Learning is applied together with a switching network that allows automatic electrode selection. This results in an adaptable system that does not require rigorous searching of the patient’s optimal stimulation points. Data that supports the differences in the stimulation location for individuals as well as the ability of the system to converge automatically to a stimulation point is presented.

This paper presents a model predictive control (MPC) based on a neural network (NN) model for air/fuel ration (AFR) control of automotive engines. The novelty of the paper is that the severe nonlinearity of the engine dynamics are modelled by a NN to a high precision, and adaptation of the NN model can cope with system uncertainty and time varying effects. A single dimensional optimization algorithm is used in the paper to speed up the optimization so that it can be implemented to the engine fast dynamics. Simulations on a widely used mean value engine model (MVEM) demonstrate effectiveness of the developed method.

IoT 서비스는 경량 디바이스 발전으로 그 범위가 계속 확대되고 있으며, 이에 따라 네트워크의 혼잡성은 크게 증가하고 있다. IoT 네트워크 환경에서 CoAP를 위한 기존 혼잡 제어 메커니즘은 동적 네트워크 조건에 대한 적응력이 부족하다. 본 연구에서는 IoT 서비스 환경의 네트워크 환경의 네트워크 혼잡 문제를 해결하기 위해 적응 형 신경망 기반 혼잡 제어(ANN-CoCC) 알고리즘을 제안한다. 정적 매개변수나 휴리스틱 규칙에 의존하는 기존의 혼잡 제어 방식과 달리 ANN-CoCC는 머신러닝 모델을 적용하여 실시간 네트워크 상태에 따라 재전송 시간 초과 (RTO), RTT 분산, 혼잡 윈도우와 같은 주요 전송 매개변수를 동적으로 최적화한다. 다양한 패킷 손실률과 노드 밀도에서 실험 평가를 수행한 결과, 본 연구에서 제안하는 알고리즘은 CoCoA+, BDP-CoAP, pCoCoA과 같은 기존 방식과 비교했을 때 처리량을 30% 이상 향상시키며, 지연 시간 감소, 패킷 손실을 최소화하는 것으로 확인되 었다.

The scope of IoT services continues to expand with the development of lightweight devices, and network congestion is increasing significantly. In this study, we propose an adaptive neural network-based congestion control (ANN-CoCC) algorithm to solve the network congestion problem in the network environment of IoT service environments. Unlike existing congestion control methods that rely on static parameters or heuristic rules, ANN-CoCC applies a machine learning model to dynamically optimize key transmission parameters such as retransmission timeout (RTO), RTT distribution, and congestion window according to real-time network conditions. The experimental evaluation results under various packet loss rates and node densities show that the proposed algorithm improves throughput by more than 30%, reduces delay, and minimizes packet loss compared to existing methods such as CoCoA+, BDP-CoAP, and pCoCoA.

본 연구는 정서인식 명확성과 대인관계 능력의 관계에서 자기연민과 적응적 정서조절방략의 매개효과를 살펴보고자 하였다. 또한 정서를 명확하게 인식하고 적응적인 정서조절방략을 선택하는 심리적 기제로써 자기연민을 탐색하고자 하였다. 이를 위해 성인 358명을 대상으로 설문조사를 실시하였다. 연구의 결과는 다음과 같다. 첫째, 정서인식 명확성, 자기연민, 적응적 정서조절방략, 대인관계 능력 간 상관관계가 유의미한 정적 상관을 확인하였다. 둘째, 정서인식 명확성과 대인관계 능력의 관계에서 자기연민과 적응적 정서조절방략의 이중매개효과가 나타났다. 그러나 자기연민과 적응적 정서조절방략이 매개하는 효과는 유의미하지 않았다. 이와 같은 연구결과를 바탕으로 본 연구의 의의와 제한점을 논의하였다.

This study tried to examine the mediating effect of self-compassion and adaptive emotion regulation strategies on the relationship between emotional recognition clarity and inter-personal ability. For this purpose, a survey was conducted on 358 early adults aged 20-40 in Gyeonggi-do. The research results are as follows. First, a significant positive correlation was confirmed between clarity of emotion recognition, self-compassion, adaptive emotion regulation strategy, and interpersonal ability. Second, there was a partial double mediating effect of self-compassion and adaptive emotion regulation strategy in the relationship between emotional recognition clarity and interpersonal ability. In other words, emotional recognition clarity directly increases interpersonal ability, indirectly increases self-compassion, and increases interpersonal ability by allowing adaptive emotion regulation strategies to be used. Based on these research results, the significance and limitations of this study were discussed.

본 연구는 청소년을 대상으로 하여 청소년의 게임이용시간과 자기통제의 시간에 따른 변화와 적응적 게임활용이 지니는 종단적 매개효과를 검증하기 위하여 잠재성장모형을 활용하였다. 적응적 게임활용의 종단매개효과 검증을 위하여 한국콘텐츠진흥원에서 주최한 2019 게임이용자패널연구 학술대회 참여를 통해 제공받은 청소년 863명의 게임이용자패널조사 4개년 응답자료를 활용하였다. 본 연구모형을 분석하기 위하여 SPSS 21.0과 Mplus 6.12를 활용하여, 각 변인의 시점별 정규성 확인 후 상관분석, 종단적 매개분석을 순차적으로 실시하였다. 연구결과를 요약하면 다음과 같다. 첫째, 잠재성장모형 분석 결과 게임이용시간과 적응적 게임활용, 자기통제는 모두 시간에 따라 선형적으로 성장하였다. 둘째, 측정된 변인들의 초기치와 변화율 간 관계를 분석한 결과 게임이용시간이 자기통제에 미치는 직접적인 영향은 유의하지 않았으나 적응적 게임활용을 통해 자기통제에 정적으로 유의한 영향을 미치는 것으로 나타났다. 지속적인 적응적 게임활용은 자기통제수준을 높이는 것으로 확인되었다. 셋째, Sobel 검증 결과, 적응적 게임활용의 초기치와 변화율 모두 완전 매개효과를 갖는 것으로 나타나 종단매개효과가 유의함을 확인하였다. 본 연구는 청소년의 자기통제 수준이 게임이용시간과 적응적 게임활용의 변화양상에 따라 변화를 보이는 종단적 과정을 통해 적응적 게임활용의 중요성을 확인하였다.

This study used a latent growth curve models(LGCM) to examine longitudinal changes in youth’s game usage, self-control and the longitudinal mediation effect of adaptive game use in the relationship between game usage and self-control. A four-year longitudinal data of 863 adolescents from the Game User Panel Survey, provided through participation in the 2019 Game User Panel Research Conference hosted by the Korea Creative Contents Agency, was used to verify the longitudinal mediation effect of adaptive game use. SPSS 21 was used for correlation analysis, and Mplus 6.12 was used to verify the longitudinal mediation effect. The results are as follows. First, game usage, self-control and adaptive game yielded linear temporal growth. Second, latent growth curve models showed that the direct effect of game usage on self-control was insignificant, but game usage had a significant indirect effect on self-control through adaptive game use. Continuous adaptive gaming increased self-control. Third, sobel test results showed that both the initial value and change rate of adaptive game use had a full-mediation effect, confirming the longitudinal mediation effect. This study verified the longitudinal change of self-control affected by change in game usage and adaptive game use.

본 연구는 학령후기 아동이 지각한 부모의 수용적 양육태도가 분노조절에 영향을 미치는 과정에서 정서인식 명확성과 적응적 인지정서조절 전략이 매개효과를 보이는지를 검증하고자 하였다. 초등학교 5, 6학년생 414명으로부터 자료를 수집하였으며, 구조방정식 모형을 이용하여 수집된 자료를 분석하였고, 연구 결과는 다음과 같다. 첫째, 학령후기 아동이 지각한 부모의 양육태도가 수용적일수록 정서인식 명확성이 높고, 적응적 인지정서조절 전략을 더 많이 사용하며, 분노조절을 잘했다. 그리고 정서인식 명확성이 적응적 인지정서조절 전략에 미치는 영향 및 정서인식 명확성과 적응적 인지정서조절 전략이 각각 분노조절에 미치는 영향도 유의하였다. 둘째, 학령후기 아동이 지각한 부모의 수용적 양육태도는 분노조절에 직접 영향도 미치지만, 정서인식 명확성과 적응적 인지정서조절 전략을 각각 부분매개로 하여 영향을 미쳤다. 셋째, 학령후기 아동이 지각한 부모의 수용적 양육태도는 정서인식 명확성과 적응적 인지정서조절 전략의 이중매개로도 분노조절에 영향을 미쳤다. 끝으로 본 연구의 의의와 제한점 및 앞으로의 연구방향이 논의되었다.

The present study aimed to confirm the mediating effect of emotional clarity and adaptive cognitive emotion regulation on the association between late school-aged children's perceived parental rearing attitudes and anger control. The data were collected from 414 elementary school students, and were analyzed through structural equation modeling. The main research findings were as follows: First, when higher scores on children's perceived parental rearing attitudes were associated with higher scores on emotional clarity, increased adaptive cognitive emotion regulation scores and higher levels of anger control were found. And emotional clarity had direct effect on adaptive cognitive emotion regulation. In addition, emotional clarity and adaptive cognitive emotion regulation had direct effect on anger control. Second, emotional clarity were found to significantly mediate the association between perceived parental rearing attitudes and anger control. And adaptive cognitive emotion regulation significantly mediated the relationship between perceived parental rearing attitudes and anger control. Third, perceived parental rearing attitudes had an effect on anger control through the sequential double mediation of emotional clarity and adaptive cognitive emotion regulation. Discussion of the significance and limitation of the present study and directions for future research were also presented.

최근 위성 통신 시스템은 링크 가용도와 대역폭 효율을 증대시키기 위해 ACM(Adaptive Coding and Modulation) 기술을 사용하고 있지만, PEP(Performance Enhancing Proxy)에서 동작하는 TCP는 ACM 동작에 따라 변경된 물리계층 전송능력을 감지하지 못하고 작아진 BDP (Bandwidth Delay Product) 네트워크에 혼잡을 발생 시킨다. 본 논문에서는 ACM과 PEP를 사용할 때 발생되는 문제점 을 극복하여 PEP의 성능을 향상시키는 기법을 제안한다. 이를 위해 ACM기능을 지원하는 물리/MAC(링크)계층 모듈과 전송계층 모듈인 TCP 간에 정보 전달 메시지를 적용하여 물리/MAC(링크)계층의 정보가 TCP에 전달되도록 하여 MODCOD (Modulation and Coding)에 따라 변경되는 물리계층 대역폭을 고려한 적응적인 TCP 혼잡제어를 수행하도록 하였다. 제안한 기법에 대해서 ns-2 를 이용한 모의시험 결과 물리계층과 전송계층간의 전송 속도를 적응적으로 정합시킴으로써 네트워크의 혼잡을 미리 방지하고 최적 화된 혼잡제어를 수행함으로써 PEP 성능을 향상 시킬 수 있음을 보였다.

Currently satellite communication systems usually use the ACM(Adaptive Coding and Modulation) to extend the link availability and to increase the bandwidth efficiency. However, when ACM system is used for satellite communications, we should carefully consider TCP congestion control to avoid network congestions. Because MODCODs in ACM are changed to make a packet more robust according to satellite wireless link conditions, bandwidth of satellite forward link is also changed. Whereas TCP has a severe problem to control the congestion window for the changed bandwidth, then packet overflow can be experienced at MAC or PHY interface buffers. This is a reason that TCP in transport layer does not recognize a change of bandwidth capability form MAC or PHY layer. To overcome this problem, we propose the adaptive congestion control scheme of TCP for supporting ACM in Satellite PEP (Performance Enhancing Proxy) systems. Simulation results by using ns-2 show that our proposed scheme can be efficiently adapted to the changed bandwidth and TCP congestion window size, and can be useful to improve TCP performance.

Overlay parameter control of the semiconductor photolithography process is researched in this paper. Overlay parameters denote the error in superposing the current pattern to the pattern previously created. The reduction of the overlay deviation is one of the key factors in improving the quality of the semiconductor products. The semiconductor process is affected by numerous environment and equipment factors. Through process condition prediction and control, the overlay inaccuracy can be reduced. Generally, three types of process condition change exist; uncontrollable white noise, slowly changing drift, and abrupt condition shift. To effectively control the aforementioned process changes, control scheme using adaptive deadband is proposed. The suggested approach and existing control method are cross evaluated through simulation.