房地產價格是一個區域甚至是國家的經濟命脈，由於房地產本身是人們最基本的生活條件，亦會影響到商品、勞力的價格。也因此若我們可以提前得知房地產的價格，那麼對於國家經濟發展將會有巨大貢獻。過往研究中，大多利用二種方式進行房地產售價預測，其中包含了1)統計上相關演算法，針對此類型之相關過往研究，由於房地產價格，因有較多變量會造成不規律的情況發生，對於統計相關演算法，大多僅能以統計分析的方式進行處理，並不能實作成預測系統，在此我們將不做介紹。2)Artificial Intelligence類演算法，此類型研究，除了考慮在商業、經濟、金融以及房地產等期刊中利用指數(如股價指數及CPI等)數值進行分析及預測外，亦或是建構地理回歸模型，及卷積類神經網路等方式進行預測，但這類型的相關研究，由於大多因為房地產價格考慮因素過多，所以此類型研究都僅挑選單一因素進行預測，明顯考量不全。對此從上述內容可以發現，過往研究整體考慮因素都過於單一，並不符合實際情況。因此，本論文提出「基於開放資料之空間時間屬性與深度學習進行房屋售價預測-以台中市西屯區為例」，進行房地產售價的預測，不同於以往相關研究，在房地產售價預測上，本論文除了考慮房地產本身時間性因素外，亦考慮房地產周圍空間因素。在本論文中我們提出了空間時間序列圖—本論文所提出新型的時間序列圖，透過結合房地產買賣之相關空間及時間資訊進行整合，使得我們可以同時考慮到影響房地產的時間因素及空間因素，使得房地產售價預測更加準確。此外我們發現，由於房地產售價本身資料範圍過大，因此造成資料正規化範圍的問題，對此本論文使用fuzzy grouping進行分群，透過分群降低彼此群間數值範圍過大的問題，其中模糊化的重點在於整體值屬於相對性，也因此可以有效幫助我們挑選出群集。基於上述內容本論文進行整合，並利用深度學習進行系統的建構，目標在於建構出房地產售價預測系統。最終，本論文實驗結果證實了我們方法的有效性。

Real estate prices have always been the lifeblood of an area's economy, or even a country’s economy. Real estate is the fundamental requirement of people’s lives and exerts impact on the prices of goods and labor. Thus, being able to forecast future trends in real estate prices would be of significant contribution to a country’s economic development. Past studies have mainly employed two methods to predict real estate prices: statistical correlation algorithms and artificial intelligence algorithms. However, these methods lack adequate consideration of the numerous factors influencing real estate prices and are thus impractical. We therefore proposed a method to predict real estate prices using deep learning and the spatial and temporal attributes of open data. Unlike methods used in the past, the proposed approach considers the temporal factors of the real estate itself in price prediction but also takes the spatial factors of the real estate surroundings into account. A case study was conducted in Xitun District of Taichung City, Taiwan. In this study, we constructed a novel space-time series graph that integrates the space and time information of real estate transactions so that we can consider the temporal and spatial factors that influence real estate prices at the same time, thereby increasing the accuracy of real estate price predictions. Furthermore, we discovered that the significantly large scope of real estate price data causes data normalization issues. We thus utilized fuzzy grouping to reduce the scope of data. The focus of fuzzification is that overall values are relative in nature, which enables us to choose different estate groups. Based on the above content, we constructed a system for real estate price prediction using deep learning. Experiment results demonstrated the validity of the proposed method.

[1] A. Alazab, M. Hobbs, J. Abawajy, M. Alazab, Using feature selection for intrusion detection system, in: Proceedings of International Symposium on Communications and Information Technologies (ISCIT), 2012, pp. 296–301.
[2] A.J. Bency, S. Rallapalli, R.K. Ganti, M. Srivatsa, B.S. Manjunath. Beyond spatial auto-regressive models: Predicting housing prices with satellite imagery, Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017, p 320-329, May 11, 2017.
[3] P. Bruneau, L. Boudet. “Bayesian variable selection in neural networks for short-term meteorological prediction”, Lecture Notes in Computer Science, v 7666 LNCS, n PART 4, pp. 289-296, 2012.
[4] Y.-C. Chen, D.-L. Yang, T.-Y. Chang, P.-Y. Huang, M.-C. Tsai. Finding Depth-k Skyline Friends in Distributed Social Networks by Using Neuro-fuzzy Networks. Proceedings of the The 3rd Multidisciplinary International Social Networks Conference on SocialInformatics 2016, 2016.
[5] Y. Chen, J. Wang, B. Zhu, M. Tang, H. Lu. Pixel-wise Deep Sequence Learning for Moving Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 2017.
[6] H.-J. Chu, C.-Y. Liu, C.-K. Wang. “Identifying the Relationships of Water Quality and Land Cover Changes in the Tseng-Wen Reservoir Watershed of Taiwan”, International Journal of Environmental Research and Public Health, v 10(2), pp. 478-489, 2013.
[7] H.-J. Chu, S. J. Kong, C.H. Chang. “Spatio-temporal water quality mapping from satellite images using geographically and temporally weighted regression”, International Journal of Applied Earth Observation and Geoinformation, v 65, pp. 1-11, 2018.
[8] H.-J. Chu, Y.-C. Chen.” Crowdsourcing photograph locations for debris flow hot spot mapping”, Natural Hazards, v 90(3), pp.1259-1276, 2018.
[9] M. Das, S. K. Ghosh. “semBnet: A semantic Bayesian network for multivariate prediction of meteorological time series data”, Pattern Recognition Letters, v 93, pp. 192-201, 2017.
[10] “Department of commerce, moea, commerce industrial service portal,” https://gcis.nat.gov.tw/
[11] M. Ester, H.-P. Kriegel, J. Sander, X. Xu(1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Simoudis E, Han J, Fayyad UM (eds) Proceedings of the second international conference on knowledge discovery and data mining (KDD-96), pp 226–231. AAAI Press.
[12] R. Fu, Z. Zhang, L. Li. Using LSTM and GRU neural network methods for traffic flow prediction. Proceedings of the 31st Youth Academic Annual Conference of Chinese Association of Automation, pp. 324-328, 2016.
[13] F.A. Gers, J. Schmidhuber, F. “Cummins. Learning to forget: continual prediction with LSTM”, IEEE Conference Publication, v 2, n 470, pp. 850-855, 1999.
[14] K. Gupta, R.-R. Janghel. ”Dimensionality Reduction-Based Breast Cancer Classification Using Machine Learning”, Computational Intelligence: Theories, Applications and Future Directions, v 1, pp. 133-146,2018.
[15] A. Hassan, A. Mahmood. Deep Learning approach for sentiment analysis of short texts. Proceedings of the 2017 3rd International Conference on Control, Automation and Robotics, pp. 705-710, 2017.
[16] K. He, X. Zhang, S. Ren, J. Sun. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, v 2016-December, pp. 770-778, 2016.
[17] S. Hochreiter, J. Schmidhuber. “Long short-term memory”, Neural Computation, v 9, n 8, pp. 1735, 1997.
[18] J. J. Hopfield. “Neural networks and physical systems with emergent collective computational abilities”, Neurocomputing: foundations of research, Pages 457-464, 1998.
[19] C.-W. Hsu, C.-C. Chang, C.-J Lin. A Practical Guide to Support Vector Classification; Technical report, Departmentof Computer Science, National Taiwan University: Taipei, Taiwan, 2003; pp. 1–16.
[20] A. Işin, C. Direkoǧlu, M. Şah. “Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods”, Procedia Computer Science, v 102, p 317-324, 2016.
[21] A. Khatami, Y. Tai, A. Khosravi, L. Wei, MM. Dalvand, M. Zou, S. Nahavandi. A Deep Learning-Based Model for Tactile Understanding on Haptic Data Percutaneous Needle Treatment. In Proceedings of the International Conference on Neural Information Processing, pages 317–325, 2017.
[22] A. Krizhevsky, I. Sutskever, G-.E. Hinton.”ImageNet Classification with Deep Convolutional Neural Networks”, Neural Information Processing Systems, v 2, pp. 1097-1105, 2012.
[23] Y. Lecun, L. Bottou, Y. Bengio, P. Haffner. “Gradient based learning applied to document recognition”, Proceedings of the IEEE, v 86, n 11, p 2278-2323, 1998.
[24] W.T. Lim, L. Wang, Y. Wang, Q. Chang. Housing price prediction using neural networks, 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2016.
[25] S. F. Liu, S. Y. Gu, and J. Peng, “Self-adaptive Processing and Forecasting Algorithm for Univariate Linear Time Series,” Chinese Journal of Electronics, vol. 26, no. 6, pp. 1147-1153, 2017.
[26] W. Luo, W. Liu, S. Gao. Remembering history with convolutional LSTM for anomaly detection. Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 439-444, 2017.
[27] U. M. Mohapatra, B. Majhi, S. C. Satapathy. “Financial time series prediction using distributed machine learning techniques”, Neural Computing and Applications, pp. 1-16. 2017.
[28] A. Mughees, A. Ali, L. Tao. Hyperspectral image classification via shape-adaptive deep learning. Proceedings of International Conference on Image Processing, v 2017- September, pp. 375-379, 2017.
[29] J. Peng. Study on dynamic relation between share price index and housing price: co-integration analysis and application in share price index prediction, Advances in Intelligent and Soft Computing, v 56, p 837-846, 2009.
[30] S. Poornachandra, C. Naveena. Pre-processing of MR Images for Efficient Quantitative Image Analysis Using Deep Learning Techniques. Proceedings of ICRAECT 2017, pp. 191-195, 2017.
[31] B. Quost, T. Denœux.” Clustering and classification of fuzzy data using the fuzzy EM algorithm”, Fuzzy Sets and Systems, v 286, pp 134-156, 2016.
[32] T. Rimavicius, A. Gelzinis. “A comparison of the deep learning methods for solving seafloor image classification task”, Communications in Computer and Information Science, v 756, p 442-453, 2017.
[33] G. Rybarczyk.” Toward a spatial understanding of active transportation potential among a university population”, International Journal of Sustainable Transportation, v 12, n 9, pp. 625-636, 2018.
[34] M. Schuster, K-.K. Paliwal. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, v 45, n 11, pp. 2673-2681, 1997.
[35] S. Selvin, R. Vinayakumar, E.A. Gopalakrishnan, V.K. Menon, K.P. Soman. Stock price prediction using LSTM, RNN and CNN-sliding window model. Proceedings of ICACCI 2017, pp. 1643-1647, 2017.
[36] X. Shi, Z. Chen, H. Wang, D.Y. Yeung, W.K. Wong, W.C. Woo. “Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting”, Neural Information Processing Systems, v 2015-January, pp. 802-810, 2015.
[37] K. Simonyan, A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR. abs/1409.1556 (2014). https://arxiv.org/abs/1409.1556.
[38] H. Sun, C. Guo, J. Xu, J. Zhu, C. Zhang. “A combined model for time series prediction in financial markets”, Lecture Notes in Computer Science, v 10988 LNCS, pp. 138-147, 2018.
[39] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich. Going Deeper with Convolutions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, v 07-12-June-2015, pp. 1-9, 2015
[40] Z. Tan, Y. F. Wang, Y. Zhang, and J. Zhou, “A Novel Time Series Approach for Predicting the Long-Term Popularity of Online Videos,” IEEE Trans. On Broadcasting, vol. 62, no. 2, pp. 436-445, 2016.
[41] M. Ugur Gudelek, S. Arda Boluk, A. Murat Ozbayoglu. A deep learning based stock trading model with 2-D CNN trend detection. Proceedings of SSCI 2017, pp. 1-8, 2018.
[42] X. Wang, Y. Zhang, W. Zhang, and X. Lin. Distance-aware influence maximization in geo-social network. Proc IEEE 32nd International Conference on Data Engineering(ICDE), 2016.
[43] X. Wang, R. Jiang, L. Li, Y. Lin, X. Zheng, F-.Y. Wang. “Capturing Car-Following Behaviors by Deep Learning”, IEEE Transactions on Intelligent Transportation Systems, v 19, n 3, pp. 910-920, 2018.
[44] H. Wang, P. Wang, Z. Song, W. Li. Large-scale multimodal gesture recognition using heterogeneous networks. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, v 2018-January, pp. 3129-3137, 2018.
[45] X.-X. Wang, L.-H. Xu. “Short-term Traffic Flow Prediction Based on Deep Learning”, Journal of Transportation Systems Engineering and Information Technology, v 18, n 1, pp. 81-88. 2018.
[46] Y. Wu, S. Yang, and X. Yan. Ontology-based subgraph querying. In ICDE, pp 697–708, 2013.
[47] Z. Xue, S. Antani, L.R. Long, D. Demner-Fushman, George R. Improving face image extraction by using deep learning technique. Progress in Biomedical Optics and Imaging, Proceedings of SPIE, v 9789, 2016.
[48] C. Yiorkas, T. DImopoulos. Implementing GIS in real estate price prediction and mass valuation: The case study of Nicosia District, Proceedings of SPIE - The International Society for Optical Engineering, v 10444, 2017, Fifth International Conference on Remote Sensing and Geoinformation of the Environment, RSCy 2017.
[49] Z. Zhan, M. Xu, and S. Xu, “Predicting Cyber Attack Rates with Extreme Values”, IEEE Trans. on Information Forensics and Security, vol. 10, no. 8, pp. 1666-1677,2015.
[50] L. Zhang, G. Zhu, P. Shen, J. Song, S.A. Shah, M. Bennamoun. Learning spatiotemporal features using 3DCNN and convolutional LSTM for gesture recognition. Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops, v 2018-January, pp. 3120-3128, January 19, 2018.
[51] “內政部:::不動產交易實價查詢服務網,” http://lvr.land.moi.gov.tw/
[52] “全國建築管理Open data,” http://dbuild.cpami.gov.tw/
[53] “住宅出售,三房二廳二衛二陽台,七期旁超美採光大三房免整理-台中房地產出售-591售屋網,” https://sale.591.com.tw/home/house/detail/2/5365371.html