近年來量子計算可為非常熱門的研究議題，以往傳統電腦面對NP-hard的問題通常需要非常大量的時間來運算，而量子計算所擁有的平行能力鄭是非常好的解決方法。本論文針對基於量子神經網路融合演算法的方式來預測股票價格，及基於量子退火QUBO二次無約束二最佳化進行零工式工作排程，預測方面在Adaptive MCT-z Quantum Neural Network Model (AQNNM) 中利用 MCT閘門和Pauli-Z閘門，並利用Apple Inc. (AAPL), Google Inc. (GOOGL) and Microsoft Inc. (MSFT)等6種股票來驗證神經網路架構的精準度，本論文將誤差降至最低0.019 (MAE)。而工作排程方面，利用量子穿隧效應，讓我們更容易找到全域最佳解，量子退火主要由D’ Wave的量子退火機最為著名，其量子退火機須將問題轉換為二次無約束二元最佳化 (QUBO)才能映射到退火機上，本論文利用FT06及LA資料集來檢測量子退火的排程效果，在大多數資料集下都可達成100%的排程效率，最低也有93.4%的排程效率，對於大多數的排程都能有效的提供最佳化的方案。

Quantum computing emerged as an advanced research issue for information technology in the last few decades since classical computer spends too much time to solve an NP-hard problem. Quantum computing has parallel ability that is the best approach to solve high dimensional and complex problems. This thesis uses an MCT-z quantum neural network and a quantum annealing to predict the stock trend and to do job scheduling separately. The quantum neural network model (QNNM) is adopted for market trend prediction and to increase the accuracy by using the MCT gate and Pauli-Z gate. The stock data from Apple Inc. (AAPL), Google Inc. (GOOGL) and Microsoft Inc. (MSFT) are used for training and testing. Experimental results show that the error is down to 0.019 (MAE). In the job shop-scheduling problem, a quantum annealing method based on D’ Wave that is the most famous annealing machine for quantum computing is proposed. Since the annealing machine is used, it needs to transfer the problem to quadratic unconstrained binary optimization. FT06 and LA datasets are used to test the performance. Experimental results show that it can achieve 100% schedule score for most datasets, that means, the system can reduce the makespan significantly.

Contents
Validation Letter i
摘 要 ii
Abstract iii
Contents iv
Chapter 1 Introduction 1
1.1、 Overview of this thesis 2
1.2、 Contributions 2
Chapter 2 Literature Review 3
2.1、 Financial Prediction 3
2.2、 Job Shop Scheduling Problem 9
Chapter 3 The Proposed Method 12
3.1、 Definition 12
3.2、 Finance Prediction Model 14
3.3、 Job Shop-Scheduling Model 24
Chapter 4 Experiments 32
4.1、 Financial Prediction 33
4.1.1、 Analysis 34
4.1.2、 Experimental Results 36
4.2、 Job Shop-scheduling Problem 37
Chapter 5 Conclusions 41
References 42

[1]. Arévalo, R., García, J., Guijarro, F. and Peris, A., “A dynamic trading rule based on filtered flag pattern recognition for stock market price forecasting,” Expert Systems with Applications, 81, pp.177-192, 2017.
[2]. Ariyo, A.A., Adewumi, A.O. and Ayo, C.K, March., “Stock price prediction using the ARIMA model,” In 2014 UKSim-AMSS 16th international conference on computer modelling and simulation (pp. 106-112). IEEE, 2014.
[3]. Esfahanipour, A. and Aghamiri, W., “Adapted neuro-fuzzy inference system on indirect approach TSK fuzzy rule base for stock market analysis,” Expert Systems with Applications, 37(7), pp.4742-4748, 2010.
[4]. Maqsood, H., Mehmood, I., Maqsood, M., Yasir, M., Afzal, S., Aadil, F., Selim, M.M. and Muhammad, K., “A local and global event sentiment based efficient stock exchange forecasting using deep learning,” International Journal of Information Management, 50, pp.432-451, 2020.
[5]. Patil, P., Wu, C.S.M., Potika, K. and Orang, M., January. “Stock market prediction using ensemble of graph theory, machine learning and deep learning models” In Proceedings of the 3rd international conference on software engineering and information management (pp. 85-92), 2020.
[6]. Cai, S., Feng, X., Deng, Z., Ming, Z. and Shan, Z., “Financial news quantization and stock market forecast research based on CNN and LSTM,” In Smart Computing and Communication: Third International Conference, SmartCom 2018, Tokyo, Japan, December 10–12, 2018, Proceedings 3 (pp. 366-375). Springer International Publishing, 2018.
[7]. Li, C., Song, D. and Tao, D., “July. Multi-task recurrent neural networks and higher-order Markov random fields for stock price movement prediction: Multi-task RNN and higer-order MRFs for stock price classification,” In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 1141-1151), 2019.
[8]. Xu, B., Zhang, D., Zhang, S., Li, H. and Lin, H., “Stock market trend prediction using recurrent convolutional neural networks,” In Natural Language Processing and Chinese Computing: 7th CCF International Conference, NLPCC 2018, Hohhot, China, August 26–30, 2018, Proceedings, Part II 7 (pp. 166-177). Springer International Publishing, 2018.
[9]. Chang, P. C.,” A novel model by evolving partially connected neural network for stock price trend forecasting,” Expert Systems with Applications, 39(1), pp.611-620, 2012.
[10]. Paquet, E. and Soleymani, F., “QuantumLeap: Hybrid quantum neural network for financial predictions,” Expert Systems with Applications, 195, p.116583, 2022.
[11]. Liu, G. and Ma, W., “A quantum artificial neural network for stock closing price prediction,” Information Sciences, 598, pp.75-85, 2022.
[12]. Mugel, S., Abad, M., Bermejo, M., Sánchez, J., Lizaso, E. and Orús, R., “Hybrid quantum investment optimization with minimal holding period,” Scientific Reports, 11(1), p.19587, 2021.
[13]. Sabuncuoglu, I. and Kizilisik, O.B., “Reactive scheduling in a dynamic and stochastic FMS environment,” International journal of production research, 41(17), pp.4211-4231, 2003.
[14]. Shah, M.J., Damian, R. and Silverman, J., “January. Knowledge based dynamic scheduling in a steel plant,” In Sixth Conference on Artificial Intelligence for Applications (pp. 108-109). IEEE Computer Society, 1990.
[15]. Adibi, M.A., Zandieh, M. and Amiri, M., “Multi-objective scheduling of dynamic job shop using variable neighborhood search,” Expert Systems with Applications, 37(1), pp.282-287, 2010.
[16]. Zhang, Z., Guan, Z.L., Zhang, J. and Xie, X., “A novel job-shop scheduling strategy based on particle swarm optimization and neural network,” International Journal of Simulation Modelling, 18(4), pp.699-707, 2019.
[17]. Wang, C. and Jiang, P., “Manifold learning-based rescheduling decision mechanism for recessive disturbances in RFID-driven job shops,” Journal of Intelligent Manufacturing, 29, pp.1485-1500, 2018.
[18]. Zandieh, M., Khatami, A.R. and Rahmati, S.H.A., “Flexible job shop scheduling under condition-based maintenance: improved version of imperialist competitive algorithm,” Applied soft computing, 58, pp.449-464, 2017.
[19]. Kurowski, K., Wȩglarz, J., Subocz, M., Różycki, R. and Waligóra, G., “Hybrid quantum annealing heuristic method for solving job shop scheduling problem,” In Computational Science–ICCS 2020: 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI 20 (pp. 502-515). Springer International Publishing, 2020.
[20]. Chalumuri, A., Kune, R. and Manoj, B.S., “Training an artificial neural network using qubits as artificial neurons: a quantum computing approach,” Procedia Computer Science, 171, pp.568-575, 2020.
[21]. Gupta, I., Saxena, D., Singh, A.K., and Lee, C.N., “A multiple controlled toffoli driven adaptive quantum neural network model for dynamic workload prediction in cloud environments," Submitted to IEEE TPAMI, 2023. (Under minor revision)
[22]. D’Wave chimera architecture: https://docs.dwavesys.com/docs/latest/c_gs_4.html
[23]. Kurowski, K., Wȩglarz, J., Subocz, M., Różycki, R. and Waligóra, G., “Hybrid quantum annealing heuristic method for solving job shop scheduling problem,” In Computational Science–ICCS 2020: 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part VI 20 (pp. 502-515). Springer International Publishing, 2020.
[24]. Wang, L., Hu, X., Wang, Y., Xu, S., Ma, S., Yang, K., Liu, Z. and Wang, W., “Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning,” Computer networks, 190, p.107969, 2021.