Open Access

ARTICLE

Yanming Wang^{1, 2, 3}, Kebin Jia^{1, 2, 3}, Pengyu Liu^{1, 2, 3, *}
Journal on Artificial Intelligence, Vol.2, No.3, pp. 113-124, 2020, DOI:10.32604/jai.2020.010137
Abstract In recent years, the problem of “Impolite Pedestrian” in front of the zebra crossing has aroused widespread concern from all walks of life. The traffic sector’s governance measures have become more serious. The traditional way of governance is onsite law enforcement, which requires a lot of manpower and material resources and is low efficiency. An enhanced YOLOv3-tiny model is proposed for pedestrians and vehicle detection in traffic monitoring. By modifying the backbone network structure of YOLOv3- tiny model, introducing deep detachable convolution operation, and designing the basic residual block unit of the network, the feature extraction ability of the backbone… More >

View

2717

Download

2013

Like

2

Cited by

3

Open Access

ARTICLE

Guanghui Yu¹, Honghui Fan¹, Hongyan Zhou¹, Tao Wu¹, Hongjin Zhu^{1, *}
Journal on Artificial Intelligence, Vol.2, No.3, pp. 125-135, 2020, DOI:10.32604/jai.2020.010501
Abstract When we use traditional computer vision Inspection technology to locate the vehicles, we find that the results were unsatisfactory, because of the existence of diversified scenes and uncertainty. So, we present a new method based on improved SSD model. We adopt ResNet101 to enhance the feature extraction ability of algorithm model instead of the VGG16 used by the classic model. Meanwhile, the new method optimizes the loss function, such as the loss function of predicted offset, and makes the loss function drop more smoothly near zero points. In addition, the new method improves cross entropy loss function of category prediction,… More >

View

2701

Download

1716

Like

2

Cited by

4

Open Access

ARTICLE

Yizhi Liu^{1, 2}, Xuesong Wang^{1, 2}, Jianxun Liu^{1, 2, *}, Zhuhua Liao^{1, 2}, Yijiang Zhao^{1, 2}, Jianjun Wang^{1, 2}
Journal on Artificial Intelligence, Vol.2, No.3, pp. 137-148, 2020, DOI:10.32604/jai.2020.010620
Abstract Cruising route recommendation based on trajectory mining can improve taxidrivers' income and reduce energy consumption. However, existing methods mostly recommend pick-up points for taxis only. Moreover, their performance is not good enough since there lacks a good evaluation model for the pick-up points. Therefore, we propose an entropy-based model for recommendation of taxis' cruising route. Firstly, we select more positional attributes from historical pick-up points in order to obtain accurate spatial-temporal features. Secondly, the information entropy of spatial-temporal features is integrated in the evaluation model. Then it is applied for getting the next pick-up points and further recommending a series… More >

View

2650

Download

1514

Open Access

ARTICLE

Ning Chen¹, Hui Li², Xinxin Fan^{3, 4}, Weiliang Kong¹, Yonghong Xie^{3, 4, *}
Journal on Artificial Intelligence, Vol.2, No.3, pp. 149-155, 2020, DOI:10.32604/jai.2020.09888
Abstract In recent years, there are some problems in science and technology management, such as untimely task supervision and independent information system, which makes it difficult to achieve accurate, quantitative and standardized management. The storage of scientific research test data is scattered, and there are many deficiencies in the management, promotion and use of existing intellectual property. In this paper, on the basis of the knowledge economy, intelligence economy under the conditions of knowledge management concept and cutting-edge technology, technology management and service management related data, information, knowledge, method of blend together. Based on science and technology management, knowledge management as… More >

View

2459

Download

1542