Forecasting the Market with Machine Learning Algorithms: An Application of NMC-BERT-LSTM-DQN-X Algorithm in Quantitative Trading

Although machine learning (ML) algorithms have been widely used in forecasting the trend of stock market indices, they failed to consider the following crucial aspects for market forecasting: (1) that investors’ emotions and attitudes toward future market trends have material impacts on market trend forecasting (2) the length of past market data should be dynamically adjusted according to the market status and (3) the transition of market statutes should be considered when forecasting market trends. In this study, we proposed an innovative ML method to forecast China's stock market trends by addressing the three issues above. Specifically, sentimental factors (see Appendix [1] for full trans) were first collected to measure investors’ emotions and attitudes. Then, a non-stationary Markov chain (NMC) model was used to capture dynamic transitions of market statutes. We choose the state-of-the-art (SOTA) method, namely, Bidirectional Encoder Representations from Transformers ( BERT ), to predict the state of the market at time t , and a long short-term memory ( LSTM ) model was used to estimate the varying length of past market data in market trend prediction, where the input of LSTM (the state of the market at time t ) was the output of BERT and probabilities for opening and closing of the gates in the LSTM model were based on outputs of the NMC model. Finally, the optimum parameters of the proposed algorithm were calculated using a reinforced learning-based deep Q-Network. Compared to existing forecasting methods, the proposed algorithm achieves better results with a forecasting accuracy of 61.77%, annualized return of 29.25%, and maximum losses of −8.29%. Furthermore, the proposed model achieved the lowest forecasting error: mean square error (0.095), root mean square error (0.0739), mean absolute error (0.104), and mean absolute percent error (15.1%). As a result, the proposed market forecasting model can help investors obtain more accurate market forecast information.

Audio steganography based on least significant bits algorithm with 4D grid multi-wing hyper-chaotic system

Although variety in hiding methods used to protect data and information transmitted via channels but still need more robustness and difficulty to improve protection level of the secret messages from hacking or attacking. Moreover, hiding several medias in one media to reduce the transmission time and band of channel is the important task and define as a gain channel. This calls to find other ways to be more complexity in detecting the secret message. Therefore, this paper proposes cryptography/steganography method to hide an audio/voice message (secret message) in two different cover medias: audio and video. This method is use least significant bits (LSB) algorithm combined with 4D grid multi-wing hyper-chaotic (GMWH) system. Shuffling of an audio using key generated by GMWH system and then hiding message using LSB algorithm will provide more difficulty of extracting the original audio by hackers or attackers. According to analyses of obtained results in the receiver using peak signal-to-noise ratio (PSNR)/mean square error (MSE) and sensitivity of encryption key, the proposed method has more security level and robustness. Finally, this work will provide extra security to the mixture base of crypto-steganographic methods.

Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms

Environment-friendly concrete is gaining popularity these days because it consumes less energy and causes less damage to the environment. Rapid increases in the population and demand for construction throughout the world lead to a significant deterioration or reduction in natural resources. Meanwhile, construction waste continues to grow at a high rate as older buildings are destroyed and demolished. As a result, the use of recycled materials may contribute to improving the quality of life and preventing environmental damage. Additionally, the application of recycled coarse aggregate (RCA) in concrete is essential for minimizing environmental issues. The compressive strength (CS) and splitting tensile strength (STS) of concrete containing RCA are predicted in this article using decision tree (DT) and AdaBoost machine learning (ML) techniques. A total of 344 data points with nine input variables (water, cement, fine aggregate, natural coarse aggregate, RCA, superplasticizers, water absorption of RCA and maximum size of RCA, density of RCA) were used to run the models. The data was validated using k-fold cross-validation and the coefficient correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error values (RMSE). However, the model’s performance was assessed using statistical checks. Additionally, sensitivity analysis was used to determine the impact of each variable on the forecasting of mechanical properties.

Research on Teaching Practice of Blended Higher Education Based on Deep Learning Route

This paper establishes a hybrid education teaching practice quality evaluation system in colleges and constructs a hybrid teaching quality evaluation model based on a deep belief network. Karl Pearson correlation coefficient and root mean square error (RMSE) indicators are used to measure the closeness and fluctuation between the effective online teaching quality evaluation results evaluated by this method and the actual teaching quality results. The experimental results show the following: (1) As the number of iterations increases, the fitting error of the DBN model decreases significantly. When the number of iterations reaches 20, the fitting error of the DBN model stabilizes and decreases to below 0.01. The experimental results show that the model used in this method has good learning and training performance, and the fitting error is low. (2) The evaluation correlation coefficients are all greater than 0.85, and the root mean square error of the evaluation is less than 0.45, indicating that the evaluation results of this method are similar to the actual evaluation level and have small errors, which can be effectively applied to online teaching quality evaluation in colleges and universities.

Master Frame Extraction of Fetal Cardiac Images Using B Mode Ultrasound Images

Fetal Echocardiography is used for monitoring the fetal heart and for detection of Congenital Heart Disease (CHD). It is well known that fetal cardiac four chamber view has been widely used for preliminary examination for the detection of CHD. The end diastole frame is generally used for the analysis of the fetal cardiac chambers which is manually picked by the clinician during examination/screening. This method is subjected to intra and inter observer errors and also time consuming. The proposed study aims to automate this process by determining the frame, referred to as the Master frame from the cine loop sequences that can be used for the analysis of the fetal heart chambers instead of the clinically chosen diastole frame. The proposed framework determines the correlation between the reference (first) frame with the successive frames to identify one cardiac cycle. Then the Master frame is formed by superimposing all the frames belonging to one cardiac cycle. The master frame is then compared with the clinically chosen diastole frame in terms of fidelity metrics such as Dice coefficient, Hausdorff distance, mean square error and structural similarity index. The average value of the fidelity metrics considering the dataset used for this study 0.73 for Dice, 13.94 for Hausdorff distance, 0.99 for Structural Similarity Index and 0.035 for mean square error confirms the suitability of the proposed master frame extraction thereby avoiding manual intervention by the clinician. .

Discussion on Criterion of Determination of the Kinetic Parameters of the Linear Heating Reactions

Generally, the linear correlation coefficient is one of the most significant criteria to appraise the kinetic parameters computed from different reaction models. Actually, the optimal kinetic triplet should meet the following two requirements: first, it can be used to reproduce the original kinetic process; second, it can be applied to predict the other kinetic process. The aim of this paper is to attempt to prove that the common criteria are insufficient for meeting the above two purposes simultaneously. In this paper, the explicit Euler method and Taylor expansion are presented to numerically predict the kinetic process of linear heating reactions. The mean square error is introduced to assess the prediction results. The kinetic processes of hematite reduced to iron at different heating rates (8, 10 and 18 K/min) are utilized for validation and evaluation. The predicted results of the reduction of Fe2O3 → Fe3O4 indicated that the inferior linear correlation coefficient did provide better kinetic predicted curves. In conclusion, to satisfy the above two requirements of reproduction and prediction, the correlation coefficient is an insufficient criterion. In order to overcome this drawback, two kinds of numerical prediction methods are introduced, and the mean square error of the prediction is suggested as a superior criterion for evaluation.

Optimized Multivariate Adaptive Regression Splines for Predicting Crude Oil Demand in Saudi Arabia

This paper presents optimized linear regression with multivariate adaptive regression splines (LR-MARS) for predicting crude oil demand in Saudi Arabia based on social spider optimization (SSO) algorithm. The SSO algorithm is applied to optimize LR-MARS performance by fine-tuning its hyperparameters. The proposed prediction model was trained and tested using historical oil data gathered from different sources. The results suggest that the demand for crude oil in Saudi Arabia will continue to increase during the forecast period (1980–2015). A number of predicting accuracy metrics including Mean Absolute Error (MAE), Median Absolute Error (MedAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and coefficient of determination ( R 2 ) were used to examine and verify the predicting performance for various models. Analysis of variance (ANOVA) was also applied to reveal the predicting result of the crude oil demand in Saudi Arabia and also to compare the actual test data and predict results between different predicting models. The experimental results show that optimized LR-MARS model performs better than other models in predicting the crude oil demand.

Hourly Forecasting of Solar Photovoltaic Power in Pakistan Using Recurrent Neural Networks

The solar photovoltaic (PV) power forecast is crucial for steady grid operation, scheduling, and grid electricity management. In this work, numerous time series forecast methodologies, including the statistical and artificial intelligence-based methods, are studied and compared fastidiously to forecast PV electricity. Moreover, the impact of different environmental conditions for all of the algorithms is investigated. Hourly solar PV power forecasting is done to confirm the effectiveness of various models. Data used in this paper is of one entire year and is acquired from a 100 MW solar power plant, namely, Quaid-e-Azam Solar Park, Bahawalpur, Pakistan. This paper suggests recurrent neural networks (RNNs) as the best-performing forecasting model for PV power output. Furthermore, the bidirectional long-short-term memory RNN framework delivered high accuracy results in all weather conditions, especially under cloudy weather conditions where root mean square error (RMSE) was found lowest 0.0025, R square stands at 0.99, and coefficient of variation of root mean square error (RMSE) Cv was observed 0.0095%.

Pengamanan Lontar Digital Dengan Tanda Tangan Digital Menggunakan Algoritma RSA

Lontar is a relic of cultural heritage whose basic source of manufacture is from rontal or tal leaves containing evidence of all records of aspects of ancient historical life which include historical values, religion, philosophy, medicine, literature and other sciences so that their sustainability needs to be maintained. Security of digital lontar will make it easier to preserve a lontar work so that it is not changed or falsified by irresponsible parties, where digital lontar in PDF format will be given a digital signature to maintain the authenticity of the document. Documents that are signed will be difficult for other parties to change, if the contents of a digital ejection are changed it will cause the digital signature to change. Based on the research conducted, from the results of testing the security of digital ejection with digital signatures using the RSA algorithm, the test results from RMSE (Root Mean Square Error) for description results with an average of 69.7794143. The larger or random the description results, the more complex the description results will be.

DEVELOPMENT OF RAINFALL FORECASTING MODEL USING MACHINE LEARNING WITH SINGULAR SPECTRUM ANALYSIS

Agriculture is the key point for survival for developing nations like India. For farming, rainfall is generally significant. Rainfall updates are help for evaluate water assets, farming, ecosystems and hydrology. Nowadays rainfall anticipation has become a foremost issue. Forecast of rainfall offers attention to individuals and knows in advance about rainfall to avoid potential risk to shield their crop yields from severe rainfall. This study intends to investigate the dependability of integrating a data pre-processing technique called singular-spectrum-analysis (SSA) with supervised learning models called least-squares support vector regression (LS-SVR), and Random-Forest (RF), for rainfall prediction. Integrating SSA with LS-SVR and RF, the combined framework is designed and contrasted with the customary approaches (LS-SVR and RF). The presented frameworks were trained and tested utilizing a monthly climate dataset which is separated into 80:20 ratios for training and testing respectively. Performance of the model was assessed using Root Mean Square Error (RMSE) and Nash–Sutcliffe Efficiency (NSE) and the proposed model produces the values as 71.6 %, 90.2 % respectively. Experimental outcomes illustrate that the proposed model can productively predict the rainfall. ABSTRAK:Pertanian adalah titik utama kelangsungan hidup negara-negara membangun seperti India. Untuk pertanian, curah hujan pada amnya ketara. Kemas kini hujan adalah bantuan untuk menilai aset air, pertanian, ekosistem dan hidrologi. Kini, jangkaan hujan telah menjadi isu utama. Ramalan hujan memberikan perhatian kepada individu dan mengetahui terlebih dahulu mengenai hujan untuk menghindari potensi risiko untuk melindungi hasil tanaman mereka dari hujan lebat. Kajian ini bertujuan untuk menyelidiki kebolehpercayaan mengintegrasikan teknik pra-pemprosesan data yang disebut analisis-spektrum tunggal (SSA) dengan model pembelajaran yang diawasi yang disebut regresi vektor sokongan paling rendah (LS-SVR), dan Random-Forest (RF), ramalan hujan. Menggabungkan SSA dengan LS-SVR dan RF, kerangka gabungan dirancang dan dibeza-bezakan dengan pendekatan biasa (LS-SVR dan RF). Kerangka kerja yang disajikan dilatih dan diuji dengan menggunakan set data iklim bulanan yang masing-masing dipisahkan menjadi nisbah 80:20 untuk latihan dan ujian. Prestasi model dinilai menggunakan Root Mean Square Error (RMSE) dan Nash – Sutcliffe Efficiency (NSE) dan model yang dicadangkan menghasilkan nilai masing-masing sebanyak 71.6%, 90.2%. Hasil eksperimen menggambarkan bahawa model yang dicadangkan dapat meramalkan hujan secara produktif.