CNN-GRU-AM for Shared Bicycles Demand Forecasting

The demand forecast of shared bicycles directly determines the utilization rate of vehicles and projects operation benefits. Accurate prediction based on the existing operating data can reduce unnecessary delivery. Since the use of shared bicycles is susceptible to time dependence and external factors, most of the existing works only consider some of the attributes of shared bicycles, resulting in insufficient modeling and unsatisfactory prediction performance. In order to address the aforementioned limitations, this paper establishes a novelty prediction model based on convolutional recurrent neural network with the attention mechanism named as CNN-GRU-AM. There are four parts in the proposed CNN-GRU-AM model. First, a convolutional neural network (CNN) with two layers is used to extract local features from the multiple sources data. Second, the gated recurrent unit (GRU) is employed to capture the time-series relationships of the output data of CNN. Third, the attention mechanism (AM) is introduced to mining the potential relationships of the series features, in which different weights will be assigned to the corresponding features according to their importance. At last, a fully connected layer with three layers is added to learn features and output the prediction results. To evaluate the performance of the proposed method, we conducted massive experiments on two datasets including a real mobile bicycle data and a public shared bicycle data. The experimental results show that the prediction performance of the proposed model is better than other prediction models, indicating the significance of the social benefits.

Short-Term IoT Data Forecast of Urban Public Bicycle Based on the DBSCAN-TCN Model for Social Governance

Internet of Things will play a vital role in the public transport systems to achieve the concepts of smart cities, urban brains, etc., by mining continuously generated data from sensors deployed in public transportation. In this sense, smart cities applied artificial intelligence techniques to offload data for social governance. Bicycle sharing is the last mile of urban transport. The number of the bike in the sharing stations, to be rented in future periods, is predicted to get the vehicles ready for deployment. It is an important tool for the implementation of smart cities using artificial intelligence technologies. We propose a DBSCAN-TCN model for predicting the number of rentals at shared bicycle stations. The proposed model first clusters all shared bicycle stations using the DBSCAN clustering algorithm. Based on the results of the clustering, the data on the number of shared bicycle rentals are fed into a TCN neural network. The TCN neural network structure is optimized. The effects of convolution kernel size and Dropout rate on the model performance are discussed. Finally, the proposed DBSCAN-TCN model is compared with the LSTM model, Kalman filtering model, and autoregressive moving average model. Through experimental validation, the proposed DBSCAN-TCN model outperforms the traditional three models in terms of two metrics, root mean squared logarithmic error, and error rate, in terms of prediction performance.

Characterization of fungal communities on shared bicycles in Southwest China

Background The widespread use of shared bicycles has increased the demand and sanitary requirements for shared bicycles. Previous studies have identified potentially pathogenic bacteria on the surfaces of shared bicycles, but fungal communities have not been investigated. Methods We sampled shared-bicycle handles and saddles from five selected locations in a metropolis (Chengdu, China, n = 98) and used surrounding air deposition samples as controls (n = 12). Full-length ITS sequencing and multiple bioinformatic analyses were utilized to reveal fungal community structures and differences. Results Aspergillus was dominant on both the handles and saddles of shared bicycles, and Alternaria and Cladosporium were the most abundant families in the air samples. Significant differences in fungal community structures were found among the three groups. The handle samples contained higher abundances of Aureobasidium melanogenum and Filobasidium magnum than the saddle and air samples. The saddle samples had a higher abundance of Cladosporium tenuissimum than the other two sample types (P < 0·05). A higher abundance of fungal animal pathogens on shared-bicycle surfaces than in air by FUNGuild (P < 0·05). Moreover, the co-occurrence network of fungi on handles was more stable than that on saddles. Conclusion There were more potential pathogens, including Aspergillus pseudoglaucus, Aureobasidium melanogenum, Kazachstania pintolopesii, Filobasidium magnum, Candida tropicalis, and Malassezia globose were found on shared bicycles than in air, suggesting that hands should not contact mucous membrane after cycling, especially in susceptible individuals, and hygiene management of shared bicycles should be given more attention by relevant organizations worldwide.

Shared Bicycle Distribution Connected to Subway Line Considering Citizens’ Morning Peak Social Characteristics for Urban Low-Carbon Development

The transport sector has produced numerous carbon emissions in China, and it is important to promote low carbon commuting. As an emerging mode of urban low-carbon transportation in China, shared bicycles have been used by more and more citizens on a daily basis, with advantages of green and low-carbon emissions to environment, flexibility for short trips, and convenience for covering the distance between the normal low-carbon transportation and destinations. However, the imbalanced distribution of shared bicycles along subway lines, especially during the morning peak hours, has directly restricted their performance in urban traffic. In this paper, an integer linear program model (ILPM) is proposed to obtain an optimal low-carbon distribution plan of shared bicycles connecting with the subway line (SBCSL) during the morning peak hours. First, an objective function is built to improve the carbon emission reduction of SBCSL. Second, constraint functions are extracted considering the quantity of bicycles to be distributed to the subway line as well as the distribution limits of each subway station. At last, a case study is conducted on the distribution of shared bicycles in Beijing Subway Line 13 of China during the morning peak hours. The results show that the ILPM is of significance to provide optimal distribution scheme of shared bicycles in subway line with different station types including office-oriented, residential-oriented, and hybrid-oriented stations.