http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Smartphone user segmentation based on app usage sequence with neural networks
Lee, Younghoon,Park, Inbeom,Cho, Sungzoon,Choi, Jinhae Elsevier 2018 Telematics and Informatics Vol.35 No.2
<P><B>Abstract</B></P> <P>The term user segmentation refers to classifying users into groups depending on their specific needs, characteristics, or behaviors. It is a key element of product development and marketing in many industries, such as the smartphone industry, which employs user segmentation to gather information about usage logs, to produce new products for such specific groups of users. However, previous studies on smartphone user segmentation have been primarily based on demographics and reported usage, which are inherently subjective and prone to skew by the observers and participants. Hamka et al. (2014) was the first to conduct a study, in which smartphone user segmentation was performed using log data collected through smartphone measurements. However, they focused only on network usage and the number of apps used, and not on characteristics or preferences. In this study, we proposed novel ways of segmenting smartphone users based on app usage sequences collected from smartphone logs. We proposed a variant of seq2seq architecture combining the advantages of previous deep neural networks: neural embedding architecture and seq2seq architecture. Furthermore, we compared the user segmentation results of the proposed method with an answer set of segmentation results conducted by domain experts. These experiments demonstrated that the proposed method effectively determines similarities between usage sequences and outperforms existing user segmentation methods.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Smartphone user segmentation method utilizing app usage sequence is proposed. </LI> <LI> We applied a neural network, a variant of the seq2seq architecture, which is suitable for usage sequence. </LI> <LI> Segmentation result of our proposed method outperforms all other segmentation methods. </LI> <LI> Our method also calculate vector representation of each app effectively. </LI> </UL> </P>
박선영(Sunyoung Park),신희진(Heejin Shin),정상원,김상덕(Sangdeok Kim),양인범(Inbeom Yang),김현수(Hyunsoo Kim) 한국자동차공학회 2015 한국자동차공학회 부문종합 학술대회 Vol.2015 No.5
In this paper, PTC heater-cabin thermal management simulator was developed to evaluate PTC heater performance. The specification of the target PHEV was used to develop cabin model and both PTC heater and the cabin model were validated with the test results. In addition, the graphical user interface(GUI) was developed using PTC heater-cabin temperature management simulator. The effects of outside temperature change on cabin temperature, heater power demand and the power loss were investigated. The GUI can make user easily change the parameters of the heater and estimate the performance.
불규칙한 교란을 받는 동적 시스템의 제어에 관한 실험적 연구
이종복(JongBok Lee),조윤현(YunHyun Cho),양인범(InBeom Yang),박성만(SungMan Park),허훈(Hoon Heo) 대한기계학회 2007 대한기계학회 춘추학술대회 Vol.2007 No.5
Experimental study on the control of randomly disturbing system is conducted. External and internal disturbances are imposed to the system in combined manner. A vertical propeller system exposed horizontal weak turbulent air flow is chosen as an experimental model. The aim of the control system is to maintain the angular position of vertical propeller in parallel to air flow. Trajectory Tracking Stochastic Controller (TTSC) is designed to ensure system's stability while following system command. The Trajectory Tracking Stochastic Controller is composed of two controller, one is stochastic controller to suppress internal random noise and the other one is trajectory-tracking controller to follow the command having random noise. The proposed hybrid controller, TTSC, shows remarkable performance in pitch control of vertical propeller system in wind-tunnel test.
Talaromyces halophytorum sp. nov. Isolated from Roots of Limonium tetragonum in Korea
( Young-hyun You ),( Md. Aktaruzzaman ),( Inbeom Heo ),( Jong Myong Park ),( Ji Won Hong ),( Seung-beom Hong ) 한국균학회 2020 Mycobiology Vol.48 No.2
Talaromyces halophytorum sp. nov. was isolated from the roots of halophyte Limonium tetragonum collected from Seocheon-gun, Korea in November 2015. It showed a slow growth on yeast extract sucrose agar at 25 ℃, no growth at 4 ℃ or 37℃ and produced smooth-walled and globose to sub-globose conidia. T. halophytorum is phylogenetically distinct from the other reported Talaromyces species of section Trachyspermi based on multi-locus sequence typing results using partial fragments of b-tubulin, calmodulin, ITS, and RNA polymerase II genes.
충돌 예방 시스템의 HILS를 위한 레이더 센서 에뮬레이터 개발
김원욱(Wonwook Kim),김선희(Sunhee Kim),김태욱(Taewook Kim),박기홍(Kihong Park),허승진(Seongjin Heo),황윤형(Yunhyoung Hwng),양인범(Inbeom Yang) 한국자동차공학회 2010 한국자동차공학회 학술대회 및 전시회 Vol.2010 No.11
The pre-crash safety systems are being actively studied in the automotive industries. The performance evaluation of the system on the test road is very limited due to danger, and so the hardware-in-the-loop simulation (HILS) method is widely adopted instead. In this research, a radar sensor emulator has been developed for use in real-time application. In this paper, a radar sensor emulator has been developed for use in real-time application. They take the position information about obstacles in the virtual environment and send out electrical sensor signals via CAN communication. Radar sensor emulator collects data on the CAN bus and transfer data to ACC ECU. These emulators were made as stand-alone modules on their own microcontroller. Their performance was evaluated on the pre-crash safety HILS system that was built in this study.