臺灣博碩士論文加值系統

近年來行動支付系統越來越普及，我們享受到越來越多的便利，若能更精準的定位出消費著的所在位置，我們可以透過即時的推播廣告來提升商家的銷售業績，例如：當你走進餐廳時，手機自動彈出餐廳的優惠卷，走進服飾店時，系統自動推送您喜歡的衣服，在離開停車場時手機可以在您的允許下自動繳交停車費。
過往，WIFI定位系統是由RFID自動定位、三角定位，近年來由於機器學習的發展出現了各式各樣基於機器學習定位的模型。例如：DBSCAN、 Deep learning、KNN模型，在這篇論文中我們重建了WIFI信號的地理資訊，透過卷積神經網路來進行WIFI定位，並且利用特徵工程的技巧降低模型的訓練以及預測時間，最後在商店定位中取得了92.5%的準確度。
實驗中我們使用支付寶的實時支付所蒐集到的WIFI訊息以及使用者的消費記錄，透過特徵工程的方法模擬出WIFI的相對位置，最後使用卷積神經網路來進行訓練以及預測，在實驗中我們使用三種具代表性的機器學習模型來驗證卷積神經網路的效能: Lighgbm(multiple classifier), Lightgbm(binary Classifier), Keras Deep Neural network。實驗結果中，卷積神經網路與Lightgbm(binary classifier) 均獲得了90.8%以上的準確率，我們將他進行模型融合後可以獲得92.5%的準確度, 並在天池大數據競賽中取得第16名的成績。

The mobile payment has been growing very quickly in these year, our life has become more and more convenient. Once we can locate user’s position precisely, we can broadcast the advertisement to the user to increase sales performance. For example: when you walk into the restaurant, the system sent you the coupon of this restaurant immediately, when you walk into the apparel store, the system list all of the clothes you might like, when you are leaving parking lot, the system auto-debiting your parking fee.
In the past, WIFI localization system is based on RFID localization, triangle localization. Nowadays, with the growing of machine learning such as DBSCAN, Deep learning, KNN, we can localize user’s location more precisely.
In this paper, we use Alipay real-time payment dataset to do our experiment. We rebuild the geographic information from WIFI signal and train the model with convolution neural networks. Besides, we reduce the training/testing time on overhead by feature engineering. Then we evaluate the result with three most representative machine learning models: Lighgbm (multiple classifier), Lightgbm (binary Classifier), Keras (Deep Neural network). Finally, we evaluate the pros and cons for each machine learning model, and discuss the result.

口試委員審定書 i
誌謝 ii
中文摘要 iii
Abstract iv
Contents v
List of Figures vii
List of Tables viii
Chapter 1 Introduction 9
Chapter 2 Related work 11
Chapter 3 Background 13
3.1 Ali-Tianch 13
3.2 PAI 14
3.3 Dataworks 15
3.4 Alipay real-time data 16
Chapter 4 Datasets 19
4.1 Alipay Dataset 19
4.2 Harversine 20
4.3 Feature Extraction 21
4.3.1 WIFI Feature 21
4.3.2 GPS Features 23
4.3.3 Visual Features 24
4.3.4 Statistics Features 26
Chapter 5 Methodology 26
5.1 The Framework of WIFI localization 26
5.2 Machine Learning Techniques 27
5.2.1 LightGBM 27
5.2.2 Skit-learn 28
5.2.3 Keras 28
Chapter 6 Evaluation 29
6.1 Performance metrics 29
6.2 Classification 30
6.2.1 Multiple classification 30
6.2.2 Binary classification 31
6.2.3 Convolution neural network 35
6.2.4 Deep neural network 37
6.3 Model Analysis 38
6.3.1 Performance comparison 38
6.3.2 Ensemble 39
Chapter 7 Conclusion 40
Bibliography 41

[1]Nowicki, M., & Wietrzykowski, J. (2017, March). Low-effort place recognition with WiFi fingerprints using deep learning. In International Conference Automation (pp. 575-584). Springer, Cham.
[2]Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P. A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research, 11(Dec), 3371-3408.
[3]Wang, X., Wang, X., & Mao, S. (2017, May). CiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi. In Communications (ICC), 2017 IEEE International Conference on (pp. 1-6). IEEE.
[4]LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[5]Ge, X., & Qu, Z. (2016, August). Optimization WIFI indoor positioning KNN algorithm location-based fingerprint. In Software Engineering and Service Science (ICSESS), 2016 7th IEEE International Conference on (pp. 135-137). IEEE.
[6]Guo, G., Wang, H., Bell, D., Bi, Y., & Greer, K. (2003, November). KNN model-based approach in classification. In OTM Confederated International Conferences" On the Move to Meaningful Internet Systems" (pp. 986-996). Springer, Berlin, Heidelberg.
[7]Gholoobi, A., & Stavrou, S. (2015, June). RSS based localization using a new WKNN approach. In Computational Intelligence, Communication Systems and Networks (CICSyN), 2015 7th International Conference on (pp. 27-30). IEEE.
[8]Fan, H., & Chen, Z. (2016, June). WiFi based indoor localization with multiple kernel learning. In Communication Software and Networks (ICCSN), 2016 8th IEEE International Conference on(pp. 474-477). IEEE.
[9]Shen, G., Yin, X., Wang, X., & Shen, C. (2017, April). A novel WiFi-based indoor localization system. In Computer Supported Cooperative Work in Design (CSCWD), 2017 IEEE 21st International Conference on (pp. 313-318). IEEE.
[10]Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems (pp. 3146-3154).