Yiwei Ma

Yiwei Ma

Auto-generated profile, based on publicly available information

Yiwei Ma

School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 April 2020 in Sensors
Verified
Journal Article
Open access
PDF file
MLMingjie Liu
Mingjie Liu
XWXianhao Wang
Xianhao Wang
AZAnjian Zhou
Anjian Zhou
XFXiuyuan Fu
Xiuyuan Fu
YMYiwei Ma
Yiwei Ma
CPChanghao Piao
Changhao Piao
Object detection, as a fundamental task in computer vision, has been developed enormously, but is still challenging work, especially for Unmanned Aerial Vehicle (UAV) perspective due to small scale of the target. In this study, the authors develop a special detection method for small objects in UAV perspective. Based on YOLOv3, the Resblock in darknet is first optimized by concatenating two ResNet units that have the same width and height. Then, the entire darknet structure is improved by increasing convolution operation at an early layer to enrich spatial information. Both these two optimizations can enlarge the receptive filed. Furthermore, UAV-viewed dataset is collected to UAV perspective or small object detection. An optimized training method is also proposed based on collected UAV-viewed dataset. The experimental results on public dataset and our collected UAV-viewed dataset show distinct performance improvement on small object detection with keeping the same level performance on normal dataset, which means our proposed method adapts to different kinds of conditions.

19 September 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YMYiwei Ma
Yiwei Ma
WMWeixing Ma
Weixing Ma
XLXingzhen Li
Xingzhen Li
YSYimeng Shen
Yimeng Shen
Ultrashort term photovoltaic (PV) power prediction is one of the important tasks for the intraday scheduling of PV power station integrated into the power grid system. To tackle the deficiency problem of conventional prediction methods, a novel two-stage long short-term memory network (LSTM) optimization method considering major meteorological factors is proposed for ultrashort term PV power prediction. In the first stage, an input data optimization method is developed to improve the accuracy and efficiency of LSTM, which combines major meteorological factors extraction based on factor analysis, similar pattern clustering using fuzzy c-means algorithm, and maximum similar pattern recognition based on grey correlation analysis and cosine similarity. In the second stage, a LSTM optimization method using an improved sparrow search algorithm is proposed to further improve prediction accuracy. Finally, comprehensive experiment results indicate that compared with other methods, the proposed method has higher accuracy and faster computational efficiency in ultrashort term PV power prediction.

1 July 2015 in Journal of Electrical Engineering & Technology
Verified
Journal Article
Closed access
YMYiwei Ma
Yiwei Ma
PYPing Yang
Ping Yang
HGHongxia Guo
Hongxia Guo
YWYuewu Wang
Yuewu Wang

5 July 2019 in E3S Web of Conferences
Verified
Conference Paper
Open access
PDF file
YMYiwei Ma
Yiwei Ma
YCYuyang Chen
Yuyang Chen
XCXin Chen
Xin Chen
FDFuchun Deng
Fuchun Deng
XSXiantong Song
Xiantong Song
In order to achieve a prospective economic effect of renewable energy generations and vehicle to grid (V2G), this paper proposes an optimal dispatch method of wind-PV-battery microgrid considering V2G under time-of-use (TOU) tariffs for those isolated communities in remote islands and mountainous areas. A cooperative dispatch strategy and an optimal dispatch model are both presented for the total operation cost minimization and higher utilization of renewable energy generation. Finally, the simulation results show that the proposed method is effective and feasible.

1 September 2019
Verified
Conference Paper
Open access
DLDingrui Li
Dingrui Li
YMYiwei Ma
Yiwei Ma
CZChengwen Zhang
Chengwen Zhang
HYHe Yin
He Yin
IRIshita Ray
Ishita Ray
LTLeon M. Tolbert
Leon M. Tolbert

1 December 2014
Verified
Conference Paper
Closed access
YMYiwei Ma
Yiwei Ma
PYPing Yang
Ping Yang
YWYuewu Wang
Yuewu Wang
Zhuoli ZhaoZhuoli Zhao
Zhuoli Zhao
QZQunru Zheng
Qunru Zheng
This paper proposes an optimal sizing and control strategy for islanded microgrid, consisting of renewable energy sources such as wind turbine generators (WT) and solar photovoltaic generators (PV), diesel generators (DE) and battery storage system (BS). The problem is formulated to minimize the annualized system cost (ASC) based on a control strategy with two modes. In mode 1, BS is the main power source and DE is backup power, but in mode 2, the master unit is DE and BS assists DE to improve reliability and economic operation benefit. Combination with the control strategy, particle swarm optimization (PSO) is used for a minimized optimization objective of the annualized system cost including initial cost, maintenance and operation (M&O) cost, replacement cost, fuel cost and pollutant emission cost. A case study of an islanded microgrid in Dong'ao Island is introduced to verify the proposed method.