http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Efficient Recognition Method using 2 Layer Hidden Markov Models for Human Driving Behavior
신은재,윤인호,Dinh Xuan Hao,김상연,정구철 한국지식정보기술학회 2014 한국지식정보기술학회 논문지 Vol.9 No.5
This paper proposes a stochastic model for human driving behavior using a double layer Hidden Markov Model (HMM) with continuous observations. In the proposed model, gas pedal’s position, steering wheel’s angle, velocity and angular velocity of the vehicle is used and recorded in every 100 msec for recognizing driving task. Data acquisition is done during a simulated driving task, after that data is segmented and clustered into 9 different cases. The lower-layer with one-dimensional continuous HMM is used for recognizing translational acceleration of a vehicle. The upper-layer with one dimensional continuous HMM is used for recognizing angular velocity of a vehicle. For recognizing a user’s behavior, we used sliding windows with size of 10 samples and length of sequence with size of 30 samples. We apply a Kalman filter to reduce noise. After the filtering, the data was processed by sorting into three groups for a pedal, a steering wheel, and speed. We used two main features, which are angular velocity and the translational acceleration, in order to present driving behavior. We constructed a driving simulator based on Logitech G27 Racing platform to evaluate the proposed method. Using the developed driving simulator, some experiments were conducted for comparing the accuracy rate of the proposed method with that of the conventional method. Futhermore, we compared the average learning time of the proposed method with that of the conventional method because Learning time becomes also an important factor for investigating the performance of stochastic models. The experimental results confirm the accuracy of the proposed approach by revealing recognition accuracy around 96%-97%. Furthermore, the proposed method decreases learning time around 40%.
Bach, Quang-Vu,Le, Van Tam,Yoon, Yong Soo,Bui, Xuan Thanh,Chung, Woojin,Chang, Soon Woong,Ngo, Huu Hao,Guo, Wenshan,Nguyen, Dinh Duc Elsevier 2018 Journal of Cleaner Production Vol.178 No.-
<P><B>Abstract</B></P> <P>A new hybrid pilot plant configuration based on a modularized rolled pipe system (RPS) combined with a submerged flat sheet membrane bioreactor (MBR) was investigated to enhance the sewage treatment and membrane performance. The system was operated under actual conditions for more than four months, that is, at a constant flow rate of 30 m³/d and with two internal recycling ratios. The results indicate that the hybrid system produces an excellent effluent quality and considerably mitigated membrane fouling. The average concentrations of SS, COD, TN, NH<SUB>4</SUB> <SUP>+</SUP>-N, NO<SUB>3</SUB> <SUP>−</SUP>-N, and PO<SUB>4</SUB> <SUP>3-</SUP>-P remained below 2.81, 8.29, 8.77, 0.15, 8.17, and 1.49 mg/L, respectively. It was estimated that the periodic chemical cleaning of the membrane could be extended to approximately six months. The MBR and RPS can virtually complete nitrification and denitrification, respectively. The highest average denitrification rate of the RPS is 116.95 mg NO<SUB>3</SUB>-N/(g MLVSS d), with a hydraulic retention time of 1.05 h. Therefore, the RPS–MBR hybrid system has potential to improve the sewage treatability. The emerging RPS technique can obtain high rates of denitrification coupled with a compact design, ease of installation, and small footprint.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A new hybrid sewage treatment system was explored. </LI> <LI> Excellent denitrification is achieved with the novel rolled pipe system. </LI> <LI> High rates of simultaneous nitrification and denitrification are obtained. </LI> <LI> The hybrid system performs well in removing organic and nitrogen compounds. </LI> <LI> The membrane fouling rate of the hybrid system is significantly low. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>