| 1. |
- Jiang, Haiyang, et al.
(författare)
-
Machine-Learning-Based User Position Prediction and Behavior Analysis for Location Services
- 2021
-
Ingår i: Information. - : MDPI AG. - 2078-2489. ; 12:5
-
Tidskriftsartikel (refereegranskat)abstract
- Machine learning (ML)-based methods are increasingly used in different fields of business to improve the quality and efficiency of services. The increasing amount of data and the development of artificial intelligence algorithms have improved the services provided to customers in shopping malls. Most new services are based on customers' precise positioning in shopping malls, especially customer positioning within shops. We propose a novel method to accurately predict the specific shops in which customers are located in shopping malls. We use global positioning system (GPS) information provided by customers' mobile terminals and WiFi information that completely covers the shopping mall. According to the prediction results, we learn some of the behavior preferences of users. We use these predicted customer locations to provide customers with more accurate services. Our training dataset is built using feature extraction and screening from some real customers' transaction records in shopping malls. In order to prove the validity of the model, we also cross-check our algorithm with a variety of machine learning algorithms. Our method achieves the best speed-accuracy trade-off and can accurately locate the shops in which customers are located in shopping malls in real time. Compared to other algorithms, the proposed model is more accurate. User preference behaviors can be used in applications to efficiently provide more tailored services.
|
|
| 2. |
- Yao, Nannan, et al.
(författare)
-
Efficient Charge Transport Enables High Efficiency in Dilute Donor Organic Solar Cells
- 2021
-
Ingår i: The Journal of Physical Chemistry Letters. - : American Chemical Society. - 1948-7185. ; 12:20, s. 5039-5044
-
Tidskriftsartikel (refereegranskat)abstract
- The donor/acceptor weight ratio is crucial for photovoltaic performance of organic solar cells (OSCs). Here, we systematically investigate the photovoltaic behaviors of PM6:Y6 solar cells with different stoichiometries. It is found that the photovoltaic performance is tolerant to PM6 contents ranging from 10 to 60 wt %. Especially an impressive efficiency over 10% has been achieved in dilute donor solar cells with 10 wt % PM6 enabled by efficient charge generation, electron/ hole transport, slow charge recombination, and field-insensitive extraction. This raises the question about the origin of efficient hole transport in such dilute donor structure. By investigating hole mobilities of PM6 diluted in Y6 and insulators, we find that effective hole transport pathway is mainly through PM6 phase in PM6:Y6 blends despite with low PM6 content. The results indicate that a low fraction of polymer donors combines with near-infrared nonfullerene acceptors could achieve high photovoltaic performance, which might be a candidate for semitransparent windows.
|
|
