RESUMO
Banking and stock markets consider gold to be an important component of their economic and financial status. There are various factors that influence the gold price trend and its fluctuations. Accurate and reliable prediction of the gold price is an essential part of financial and portfolio management. Moreover, it could provide insights about potential buy and sell points in order to prevent financial damages and reduce the risk of investment. In this paper, different architectures of deep neural network (DNN) have been proposed based on long short-term memory (LSTM) and convolutional-based neural networks (CNN) as a hybrid model, along with automatic parameter tuning to increase the accuracy, coefficient of determination, of the forecasting results. An illustrative dataset from the closing gold prices for 44 years, from 1978 to 2021, is provided to demonstrate the effectiveness and feasibility of this method. The grid search technique finds the optimal set of DNNs' parameters. Furthermore, to assess the efficiency of DNN models, three statistical indices of RMSE, RMAE, and coefficient of determination (R2), were calculated for the test set. Results indicate that the proposed hybrid model (CNN-Bi-LSTM) outperforms other models in total bias, capturing extreme values and obtaining promising results. In this model, CNN is used to extract features of input dataset. Furthermore, Bi-LSTM uses CNN's outputs to predict the daily closing gold price.
Assuntos
Sistemas Computacionais , Ouro , Investimentos em Saúde , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
In the dynamic landscape of financial markets, accurate forecasting of stock indices remains a pivotal yet challenging task, essential for investors and policymakers alike. This study is motivated by the need to enhance the precision of predicting the Shanghai Composite Index's opening price spread, a critical measure reflecting market volatility and investor sentiment. Traditional time series models like ARIMA have shown limitations in capturing the complex, nonlinear patterns inherent in stock price movements, prompting the exploration of advanced methodologies. The aim of this research is to bridge the gap in forecasting accuracy by developing a hybrid model that integrates the strengths of ARIMA with deep learning techniques, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. This novel approach leverages the ARIMA model's proficiency in linear trend analysis and the deep learning models' capability in modeling nonlinear dependencies, aiming to provide a comprehensive tool for market prediction. Utilizing a comprehensive dataset covering the period from December 20, 1990, to June 2, 2023, the study develops and assesses the efficacy of ARIMA, LSTM, GRU, ARIMA-LSTM, and ARIMA-GRU models in forecasting the Shanghai Composite Index's opening price spread. The evaluation of these models is based on key statistical metrics, including Mean Squared Error (MSE) and Mean Absolute Error (MAE), to gauge their predictive accuracy. The findings indicate that the hybrid models, ARIMA-LSTM and ARIMA-GRU, perform better in forecasting the opening price spread of the Shanghai Composite Index than their standalone counterparts. This outcome suggests that combining traditional statistical methods with advanced deep learning algorithms can enhance stock market prediction. The research contributes to the field by providing evidence of the potential benefits of integrating different modeling approaches for financial forecasting, offering insights that could inform investment strategies and financial decision-making.
Assuntos
Algoritmos , Benchmarking , China , Investimentos em Saúde , Memória de Longo Prazo , PrevisõesRESUMO
Stress has emerged as a major concern in modern society, significantly impacting human health and well-being. Statistical evidence underscores the extensive social influence of stress, especially in terms of work-related stress and associated healthcare costs. This paper addresses the critical need for accurate stress detection, emphasising its far-reaching effects on health and social dynamics. Focusing on remote stress monitoring, it proposes an efficient deep learning approach for stress detection from facial videos. In contrast to the research on wearable devices, this paper proposes novel Hybrid Deep Learning (DL) networks for stress detection based on remote photoplethysmography (rPPG), employing (Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), 1D Convolutional Neural Network (1D-CNN)) models with hyperparameter optimisation and augmentation techniques to enhance performance. The proposed approach yields a substantial improvement in accuracy and efficiency in stress detection, achieving up to 95.83% accuracy with the UBFC-Phys dataset while maintaining excellent computational efficiency. The experimental results demonstrate the effectiveness of the proposed Hybrid DL models for rPPG-based-stress detection.
Assuntos
Aprendizado Profundo , Humanos , Fotopletismografia , Face , Custos de Cuidados de Saúde , Memória de Longo PrazoRESUMO
This study introduces an augmented Long-Short Term Memory (LSTM) neural network architecture, integrating Symbolic Genetic Programming (SGP), with the objective of forecasting cross-sectional price returns across a comprehensive dataset comprising 4500 listed stocks in the Chinese market over the period from 2014 to 2022. Using the S&P Alpha Pool Dataset for China as basic input, this architecture incorporates data augmentation and feature extraction techniques. The result of this study demonstrates significant improvements in Rank Information coefficient (Rank IC) and IC information ratio (ICIR) by 1128% and 5360% respectively when it is applied to fundamental indicators. For technical indicators, the hybrid model achieves a 206% increase in Rank IC and an impressive surge of 2752% in ICIR. Furthermore, the proposed hybrid SGP-LSTM model outperforms major Chinese stock indexes, generating average annualized excess returns of 31.00%, 24.48%, and 16.38% compared to the CSI 300 index, CSI 500 index, and the average portfolio, respectively. These findings highlight the effectiveness of SGP-LSTM model in improving the accuracy of cross-sectional stock return predictions and provide valuable insights for fund managers, traders, and financial analysts.
Assuntos
Memória de Curto Prazo , Redes Neurais de Computação , Humanos , Estudos Transversais , Memória de Longo Prazo , PrevisõesRESUMO
Fatigue impairs cognitive and motor function, potentially leading to mishaps in high-pressure occupations such as aviation and emergency medical services. The current approach is primarily based on self-assessment, which is subjective and error-prone. An objective method is needed to detect severe and likely dangerous levels of fatigue quickly and accurately. Here, we present a quantitative evaluation tool that uses less than two minutes of facial video, captured using an iPad, to assess fatigue vs. alertness. The tool is fast, easy to use, and scalable since it uses cameras readily available on consumer-electronic devices. We compared the classification performance between a Long Short-Term Memory (LSTM) deep neural network and a Random Forest (RF) classifier applied to engineered features informed by domain knowledge. The preliminary results on an 11-subject dataset show that RF outperforms LSTM, with added interpretability on the features used. For the RF classifiers, the average areas under the receiver operating characteristic curve, based on the 11-fold and individualized 11-fold cross validations, are 0.72 ± 0.16 and 0.8 ± 0.12, respectively. Equal error rates are 0.34 and 0.26, respectively. This study presents a promising approach for rapid fatigue detection. Additional data will be collected to assess the generalizability across populations.
Assuntos
Memória de Longo Prazo , Redes Neurais de Computação , Curva ROC , EletrônicaRESUMO
Copper is an important mineral and fluctuations in copper prices can affect the stable functioning of some countries' economies. Policy makers, futures traders and individual investors are very concerned about copper prices. In a recent paper, we use an artificial intelligence model long short-term memory (LSTM) to predict copper prices. To improve the efficiency of long short-term memory (LSTM) model, we introduced a simulated annealing (SA) algorithm to find the best combination of hyperparameters. The feature engineering problem of the AI model is then solved by correlation analysis. Three economic indicators, West Texas Intermediate Oil Price, Gold Price and Silver Price, which are highly correlated with copper prices, were selected as inputs to be used in the training and forecasting model. Three different copper price time periods, namely 485, 363 and 242 days, were chosen for the model forecasts. The forecast errors are 0.00195, 0.0019 and 0.00097, respectively. Compared with the existing literature, the prediction results of this paper are more accurate and less error. The research in this paper provides a reliable reference for analyzing future copper price changes.
Assuntos
Inteligência Artificial , Cobre , Redes Neurais de Computação , Algoritmos , Memória de Longo Prazo , PrevisõesRESUMO
In the existing rolling bearing performance degradation assessment methods, the input signal is usually mixed with a large amount of noise and is easily disturbed by the transfer path. The time information is usually ignored when the model processes the input signal, which affects the effect of bearing performance degradation assessment. To solve the above problems, an end-to-end performance degradation assessment model of railway axle box bearing based on a deep residual shrinkage network and a deep long short-term memory network (DRSN-LSTM) is proposed. The proposed model uses DRSN to extract local abstract features from the signal and denoises the signal to obtain the denoised feature vector, then uses deep LSTM to extract the time-series information of the signal. The healthy time-series signal of the rolling bearing is input into the DRSN-LSTM reconstruction model for training. Time-domain, frequency-domain, and time-frequency-domain features are extracted from the signal both before and after reconstruction to form a multi-domain features vector. The mean square error of the two feature vectors is used as the degradation indicator to implement the performance degradation assessment. Artificially induced defects and rolling bearings life accelerated fatigue test data verify that the proposed model is more sensitive to early failures than mathematical models, shallow networks or other deep learning models. The result is similar to the development trend of bearing failures.
Assuntos
Fadiga , Nível de Saúde , Humanos , Fatores de Tempo , Memória de Longo PrazoRESUMO
With the continuous decline of water resources due to population growth and rapid economic development, precipitation prediction plays an important role in the rational allocation of global water resources. To address the non-linearity and non-stationarity of monthly precipitation, a combined prediction method based on complementary ensemble empirical mode decomposition (CEEMD) and a modified long short-term memory (LSTM) neural network was proposed. Firstly, the CEEMD method was used to decompose the monthly precipitation series into a set of relatively stationary sub-sequence components, which can better reflect the local characteristics of the sequence and further understand the nonlinear dynamic characteristics of the sequence. Then, improved LSTM neural networks were employed to predict each sub-sequence. The proposed improvement method optimized the hyper-parameters of LSTM neural networks using particle swarm optimization algorithm, which avoided the randomness of artificial parameter selection. Finally, the predicted results of each component were superimposed to obtain the final prediction result. The proposed method was validated by taking the monthly precipitation data from 1961 to 2020 in Changde City, Hunan Province as an example. The results of the case study show that, compared with other traditional prediction methods, the proposed method can better reflect the trend of precipitation changes and has higher prediction accuracy.
Assuntos
Algoritmos , Osteopatia , Desenvolvimento Econômico , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
Accurate product price forecasting is helpful for scientific decision-making and precise industrial planning. As a characteristic fruit that drives regional development, mango price prediction is of great significance to several economies. However, owing to the strong volatility of mango prices, forecasting is vulnerable to uncertainties and is very challenging. In this study, a deep-learning combination forecasting model based on a back-propagation (BP) long short-term memory (LSTM) neural network is proposed. Using daily mango price data from a large fruit wholesale trading center in China from January 2nd, 2014, to April 18th, 2022, mango price changes are learned and predicted to support the fruit industry. The results show that the root mean-square error, mean absolute percentage error, and the R2 determination coefficient of the BP-LSTM combination model are 0.0175, 0.14%, and 0.9998, respectively. The prediction results of the combined model are better than those of the separate BP and LSTM models. Furthermore, it best fits the actual price profile and has better generalizability.
Assuntos
Aprendizado Profundo , Mangifera , Redes Neurais de Computação , China , Memória de Longo Prazo , PrevisõesRESUMO
Crude Oil is one of the most important commodities in this world. We have studied the effects of Crude Oil inventories on crude oil prices over the last ten years (2011 to 2020). We tried to figure out how the Crude Oil price variance responds to inventory announcements. We then introduced several other financial instruments to study the relation of these instruments with Crude Oil variation. To undertake this task, we took the help of several mathematical tools including machine learning tools such as Long Short Term Memory(LSTM) methods, etc. The previous researches in this area primarily focussed on statistical methods such as GARCH (1,1) etc. (Bu (2014)). Various researches on the price of crude oil have been undertaken with the help of LSTM. But the variation of crude oil price has not yet been studied. In this research, we studied the variance of crude oil prices with the help of LSTM. This research will be beneficial for the options traders who would like to get benefit from the variance of the underlying instrument.
Assuntos
Aprendizado Profundo , Petróleo , Aprendizado de Máquina , Memória de Longo PrazoRESUMO
A significant correlation between financial news with stock market trends has been explored extensively. However, very little research has been conducted for stock prediction models that utilize news categories, weighted according to their relevance with the target stock. In this paper, we show that prediction accuracy can be enhanced by incorporating weighted news categories simultaneously into the prediction model. We suggest utilizing news categories associated with the structural hierarchy of the stock market: that is, news categories for the market, sector, and stock-related news. In this context, Long Short-Term Memory (LSTM) based Weighted and Categorized News Stock prediction model (WCN-LSTM) is proposed. The model incorporates news categories with their learned weights simultaneously. To enhance the effectiveness, sophisticated features are integrated into WCN-LSTM. These include, hybrid input, lexicon-based sentiment analysis, and deep learning to impose sequential learning. Experiments have been performed for the case of the Pakistan Stock Exchange (PSX) using different sentiment dictionaries and time steps. Accuracy and F1-score are used to evaluate the prediction model. We have analyzed the WCN-LSTM results thoroughly and identified that WCN-LSTM performs better than the baseline model. Moreover, the sentiment lexicon HIV4 along with time steps 3 and 7, optimized the prediction accuracy. We have conducted statistical analysis to quantitatively assess our findings. A qualitative comparison of WCN-LSTM with existing prediction models is also presented to highlight its superiority and novelty over its counterparts.
Assuntos
Aprendizagem , Memória de Longo Prazo , Paquistão , Projetos de Pesquisa , Análise de SentimentosRESUMO
In this study, we propose a predictive model TabLSTM that combines machine learning methods such as TabNet and Long Short-Term Memory Neural Network (LSTM) with a complete factor library for stock index trend prediction. Our motivation is based on the notion that there are numerous interrelated factors in the stock market, and the factors that affect each stock are different. Therefore, a complete factor library and an efficient feature selection technique are necessary to predict stock index. In this paper, we first build a factor database that includes macro, micro and technical indicators. Successively, we calculate the factor importance through TabNet and rank them. Based on a prespecified threshold, the optimal factors set will include only the highest-ranked factors. Finally, using the optimal factors set as input information, LSTM is employed to predict the future trend of 4 stock indices. Empirical validation of the model shows that the combination of TabNet for factors selection and LSTM outperforms existing methods. Moreover, constructing a factor database is necessary for stock index prediction. The application of our method does not only show the feasibility to predict stock indices across different financial markets, yet it also provides an complete factor database and a comprehensive architecture for stock index trend prediction, which may provide some references for stock forecasting and quantitative investments.
Assuntos
Memória de Curto Prazo , Redes Neurais de Computação , Investimentos em Saúde , Previsões , Memória de Longo PrazoRESUMO
This study aims to establish the model of the cryptocurrency price trend based on a financial theory using the Long Short-Term Memory (LSTM) networks model with multiple combinations between the window length and the predicting horizons. The Random Walk model is also applied with different parameter settings. The object of this study is the cryptocurrency and medical issues, primarily the Bitcoin and Ethereum and the COVID-19. Quantitative analysis is adopted as the method of this dissertation. The research tool is Python programming language, and the TensorFlow package is employed to model and analyze research topics. The results of this study show the limitations of the LSTM and Random Walk model for price prediction while demonstrating the different characteristics of both models with different parameter settings, providing a balance between the model's accuracy and the model's practicality.
Assuntos
COVID-19 , Aprendizado Profundo , Coleta de Dados , Humanos , Memória de Longo PrazoRESUMO
With the continuous improvement and development of the socialist market economic system, China's economic development has full momentum, but the domestic market is no longer sufficient to meet the needs of enterprise development. China has always focused on peaceful diplomacy, and the world market has a strong demand for Chinese products. This work aims to improve the accuracy of exchange rate forecasting. The risk factors that may be encountered in the investment process of multinational enterprises can be effectively avoided. Combining the advantages of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), the LSTM-CNN (Long Short-Term Memory-Convolutional Neural Network) model is proposed to predict the volatility trend of stocks. Firstly, the investment risk of multinational enterprises is analyzed, and, secondly, the principles of the used CNN and LSTM are expounded. Finally, the performance of the proposed model is verified by setting experiments. The experimental results demonstrate that when predicting the 10 selected stocks, the proposed LSTM-CNN model has the highest accuracy in predicting the volatility of stocks, with an average accuracy of 60.1%, while the average accuracy of the rest of the models is all below 60%. It can be found that the stock category does not have a great impact on the prediction accuracy of the model. The average prediction accuracy of the CNN model is 0.578, which is lower than that of the Convolutional Neural Network-Relevance model, and the prediction accuracy of the LSTM model is 0.592, which is better than that of the Long Short-Term Memory-Relevance model. The designed model can be used to predict the stock market to guide investors to make effective investments and reduce investment risks based on relevant cases. The research makes a certain contribution to improving the company's income and stabilizing the national economic development.
Assuntos
Aprendizado Profundo , Previsões , Investimentos em Saúde , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
With the rapid development of the Internet, malicious domain names pose more and more serious threats to many fields, such as network security and social security, and there have been many research results on malicious domain detection. This article proposes a malicious domain name detection model based on improved deep learning, which can combine the advantages of three different network models, convolutional neural network (CNN), temporal convolutional network (TCN), and long short-term memory network (LSTM) in malicious domain name detection, to obtain a better detection effect than that of the original single or two models. Experiments show that the effect of the improved deep learning model proposed in this article is better than that of the combined model of CNN and LSTM or the combined model of CNN and TCN, and the accuracy and regression rates reached 99.76% and 98.81%, respectively.
Assuntos
Aprendizado Profundo , Internet , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
In recent years, with the continuous increase of financial business, the risk of business is on the rise. Among them, major risk cases are frequent, the cases are increasingly complex, and the means of committing crimes are concealed. The main research contents of this paper include the preprocessing of internal and external financial data and the structure design of recurrent NNs. Its purpose is to design a financial risk control model based on a deep learning NNs, thereby reducing financial risk. The Borderline-SMOTE algorithm is used first to preprocess the sample data, and the oversampling method is used to eliminate the imbalance of the data, and then, the long short-term memory deep NNs algorithm is introduced to process the sample data with time series characteristics. The final experiment shows that LSTM has a better accuracy, reaching 0.9715, compared with traditional methods; the sample preprocessing method and risk control model proposed in this paper have better ability to identify fraudulent customers, and the model itself has faster iteration efficiency.
Assuntos
Aprendizado Profundo , Algoritmos , Memória de Longo Prazo , Redes Neurais de ComputaçãoRESUMO
We analyze the long-lasting effects of initial conditions on dynamical fluctuations in one-dimensional diffusive systems. We consider the mean-squared displacement of tracers in homogeneous systems with single-file diffusion, and current fluctuations for noninteracting diffusive particles. In each case we show analytically that the long-term memory of initial conditions is mediated by a single static quantity: a generalized compressibility that quantifies the density fluctuations of the initial state. We thereby identify a universality class of hyperuniform initial states whose dynamical variances coincide with the quenched cases studied previously, alongside a continuous family of other classes among which equilibrated (or annealed) initial conditions are but one member. We verify our predictions through extensive Monte Carlo simulations.
Assuntos
Memória de Longo Prazo , Difusão , Método de Monte CarloRESUMO
In a discussion paper published in the special issue of Cognitive Neuroscience, Sex Differences in the Brain, we investigated whether certain experimental parameters contributed to findings in functional magnetic resonance imaging studies of sex differences during long-term memory. Experimental parameters included: the number of participants, stimulus type(s), whether or not performance was matched, whether or not sex differences were reported, the type of between-subject statistical test used, and the contrast(s) employed. None of these parameters determined whether or not differences were observed, as all included studies reported sex differences. We also conducted a meta-analysis to determine if there were any brain regions consistently activated to a greater degree in either sex. The meta-analysis identified sex differences (male > female) in the lateral prefrontal cortex, visual processing regions, parahippocampal cortex, and the cerebellum. We received eight commentaries in response to that paper. Commentaries called for an expanded discussion on various topics including the influence of sex hormones, the role of gender (and other social factors), the pros and cons of equating behavioral performance between the sexes, and interpreting group differences in patterns of brain activity. There were some common statistical assumptions discussed in the commentaries regarding the 'file drawer' issue (i.e., the lack of reporting of null results) and effect size. The current paper provides further discussion of the various topics brought up in the commentaries and addresses some statistical misconceptions in the field. Overall, the commentaries echoed a resounding call to include sex as a factor in cognitive neuroscience studies.
Assuntos
Neurociência Cognitiva , Encéfalo/diagnóstico por imagem , Mapeamento Encefálico , Feminino , Humanos , Imageamento por Ressonância Magnética , Masculino , Memória de Longo PrazoRESUMO
BACKGROUND AND OBJECTIVE: Working memory is an essential cognitive skill for storing and processing limited amounts of information over short time periods. Researchers disagree about the extent to which socioeconomic position affects children's working memory, yet no study has systematically synthesised the literature regarding this topic. The current review therefore aimed to investigate the relationship between socioeconomic position and working memory in children, regarding both the magnitude and the variability of the association. METHODS: The review protocol was registered on PROSPERO and the PRISMA checklist was followed. Embase, Psycinfo and MEDLINE were comprehensively searched via Ovid from database inception until 3rd June 2021. Studies were screened by two reviewers at all stages. Studies were eligible if they included typically developing children aged 0-18 years old, with a quantitative association reported between any indicator of socioeconomic position and children's working memory task performance. Studies were synthesised using two data-synthesis methods: random effects meta-analyses and a Harvest plot. KEY FINDINGS: The systematic review included 64 eligible studies with 37,737 individual children (aged 2 months to 18 years). Meta-analyses of 36 of these studies indicated that socioeconomic disadvantage was associated with significantly lower scores working memory measures; a finding that held across different working memory tasks, including those that predominantly tap into storage (d = 0.45; 95% CI 0.27 to 0.62) as well as those that require processing of information (d = 0.52; 0.31 to 0.72). A Harvest plot of 28 studies ineligible for meta-analyses further confirmed these findings. Finally, meta-regression analyses revealed that the association between socioeconomic position and working memory was not moderated by task modality, risk of bias, socioeconomic indicator, mean age in years, or the type of effect size. CONCLUSION: This is the first systematic review to investigate the association between socioeconomic position and working memory in children. Socioeconomic disadvantage was associated with lower working memory ability in children, and that this association was similar across different working memory tasks. Given the strong association between working memory, learning, and academic attainment, there is a clear need to share these findings with practitioners working with children, and investigate ways to support children with difficulties in working memory.
Assuntos
Cognição/fisiologia , Transtornos da Memória/fisiopatologia , Memória de Longo Prazo/fisiologia , Memória de Curto Prazo/fisiologia , Fatores Socioeconômicos , Criança , Humanos , Transtornos da Memória/economiaRESUMO
From a macro perspective, futures index of agricultural products can reflect the trend of macroeconomy and can also have an early warning effect on the possible crisis and provide a reference for the government's economic forecast and macro control. Therefore, it is necessary to strengthen the research on early warning and prediction of agricultural futures price. For the prediction of futures price, there are two kinds of common models: one is the traditional classic time series model, and the other is the neural network model under the wave of artificial intelligence. This paper selects the 1976 closing data of agricultural futures index from January 10, 2012, to February 27, 2020, and uses the time series differential autoregressive integrated moving average model (ARIMA model) and long short-term memory model (LSTM model) to study this work, respectively, and compares the predicted effects of the two models in some metrics. Based on the predicted results of the two models, a simple trading strategy is established, and the trading effects of the two models are compared. The results show that the LSTM model has obvious advantage over ARIMA time series model in the price index prediction of agricultural futures market.