Deep learning and time series-to-image encoding for financial forecasting
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
In the last decade, market financial forecasting has attracted high interests amongst the researchers in pattern recognition. Usually, the data used for analysing the market, and then gamble on its future trend, are provided as time series; this aspect, along with the high fluctuation of this kind of data, cuts out the use of very efficient classification tools, very popular in the state of the art, like the well known convolutional neural networks (CNNs) models such as Inception, ResNet, AlexNet, and so on. This forces the researchers to train new tools from scratch. Such operations could be very time consuming. This paper exploits an ensemble of CNNs, trained over Gramian angular fields (GAF) images, generated from time series related to the Standard & Poor's 500 index future; the aim is the prediction of the future trend of the U.S. market. A multi-resolution imaging approach is used to feed each CNN, enabling the analysis of different time intervals for a single observation. A simple trading system based on the ensemble forecaster is used to evaluate the quality of the proposed approach. Our method outperforms the buyand-hold (B&H) strategy in a time frame where the latter provides excellent returns. Both quantitative and qualitative results are provided.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“It consists of a simplified version of the VGG-16 network [31], composed by 5 convolutional layers and a fully-connected one.”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“In a successive step, we applied the RGB color map to the image, thus resulting in a three channel matrix (further details on this process can be found in [28] and [30]).”
MethodCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445 · cited 1×
“In [16], the authors have compared the capabilities of the support vector machines [17] in market prediction related issues against those obtained by using the radial basis function (RBF) networks and back propagation (BP).”
BackgroundUsing artificial neural network models in stock market index prediction
Guresen, E., Kayakutlu, G., & Daim, T. U. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.02.068 · Cited by 786 · cited 1×
“In [7], a similar approach has exploited eleven market indicators for building and training a recurrent neural network for monthly transition of the stock price index [8].”
BackgroundGao, S., Zhou, M., Wang, Y., Cheng, J., Yachi, H., & Wang, J. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2846646 · Cited by 698 · cited 1×
“In [7], a similar approach has exploited eleven market indicators for building and training a recurrent neural network for monthly transition of the stock price index [8].”
BackgroundStock market prediction system with modular neural networks
Kimoto, T., Asakawa, K., Yoda, M., & Takeoka, M. (1990) · 1990 IJCNN International Joint Conference on Neural Networks · doi:10.1109/ijcnn.1990.137535 · Cited by 650
Evaluating multiple classifiers for stock price direction prediction
Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.05.013 · Cited by 611 · cited 1×
“A comparison of different market price prediction approaches is shown in [21], where classification-based approaches usually provide better results, such as [22]–[24], rather than some regression-based competitors.”
BackgroundPredicting stock market index using fusion of machine learning techniques
Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.10.031 · Cited by 608 · cited 1×
“Interesting results have also been obtained when fusing together the above described techniques: as an example, in [19] the authors have fused ANN with decision trees (DT).”
MethodLiterature review: Machine learning techniques applied to financial market prediction
Henrique, B. M., Sobreiro, V. A., & Kimura, H. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.01.012 · Cited by 558 · cited 1×
“In [16], the authors have compared the capabilities of the support vector machines [17] in market prediction related issues against those obtained by using the radial basis function (RBF) networks and back propagation (BP).”
Background
Cited by
A novel graph convolutional feature based convolutional neural network for stock trend prediction
Chen, W., Jiang, M., Zhang, W.-G., & Chen, Z. (2021) · Information Sciences · doi:10.1016/j.ins.2020.12.068 · Cited by 281
Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., & Bhat, S. K. (2023) · International Journal of Financial Studies · doi:10.3390/ijfs11030094 · Cited by 262
“We believe that researchers can explore the possible usage of state-of-the-art deep learning and machine learning algorithms in stock trend prediction and classification (Jiang 2021; Nikou et al. 2019).”
BackgroundMulti-DQN: An ensemble of Deep Q-learning agents for stock market forecasting
Carta, S., Ferreira, A., Podda, A. S., Reforgiato Recupero, D., & Sanna, A. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113820 · Cited by 226
Self-citationNILM applications: Literature review of learning approaches, recent developments and challenges
Angelis, G.-F., Timplalexis, C., Krinidis, S., Ioannidis, D., & Tzovaras, D. (2022) · Energy and Buildings · doi:10.1016/j.enbuild.2022.111951 · Cited by 219
Integrated deep learning method for workload and resource prediction in cloud systems
Bi, J., Li, S., Yuan, H., & Zhou, M. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.11.011 · Cited by 162
esDNN: Deep Neural Network Based Multivariate Workload Prediction in Cloud Computing Environments
Xu, M., Song, C., Wu, H., Gill, S. S., Ye, K., & Xu, C. (2022) · ACM Transactions on Internet Technology · doi:10.1145/3524114 · Cited by 142
A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning
Carta, S., Corriga, A., Ferreira, A., Podda, A. S., & Recupero, D. R. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01839-5 · Cited by 161
“[4], best results were reported using GDAF.”
MethodInfluentialSelf-citationData-driven stock forecasting models based on neural networks: A review
Bao, W., Cao, Y., Yang, Y., Che, H., Huang, J., & Wen, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102616 · Cited by 214
Large-scale water quality prediction with integrated deep neural network
Bi, J., Lin, Y., Dong, Q., Yuan, H., & Zhou, M. (2021) · Information Sciences · doi:10.1016/j.ins.2021.04.057 · Cited by 118
EVDHM-ARIMA-Based Time Series Forecasting Model and Its Application for COVID-19 Cases
Sharma, R. R., Kumar, M., Maheshwari, S., & Ray, K. P. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3041833 · Cited by 112
“utilized for the time-series forecasting in [5].”
Multi-dimensional prediction method based on Bi-LSTMC for ship roll
Wang, Y., Wang, H., Zhou, B., & Fu, H. (2021) · Ocean Engineering · doi:10.1016/j.oceaneng.2021.110106 · Cited by 111
Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution
Yu, Y., Lei, Z., Wang, Y., Zhang, T., Peng, C., & Gao, S. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1004284 · Cited by 84
Stock Price Forecast Based on CNN-BiLSTM-ECA Model
Chen, Y., Fang, R., Liang, T., Sha, Z., Li, S., Yi, Y., Zhou, W., & Song, H. (2021) · Scientific Programming · doi:10.1155/2021/2446543 · Cited by 112
“[63] first utilized Gramian angular field technique to obtain 2D images from the time series data.”
MethodMa, P., Li, G., Zhang, H., Wang, C., & Li, X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3347787 · Cited by 70
“Because GADF enhances the time-dependent characteristics of time series, it has been applied in the fields of economic forecasting and pattern recognition [27], [28].”
MethodDeep learning for financial forecasting: A review of recent trends
Giantsidi, S., & Tarantola, C. (2025) · International Review of Economics & Finance · doi:10.1016/j.iref.2025.104719 · Cited by 118
Podda, A. S., Balia, R., Barra, S., Carta, S., Fenu, G., & Piano, L. (2022) · Journal of Computational Science · doi:10.1016/j.jocs.2022.101816 · Cited by 69
Self-citationHatata, A. Y., Essa, M. A. A. E. A., & Sedhom, B. E. (2022) · IEEE Access · doi:10.1109/access.2022.3177544 · Cited by 65
“…coordinate, the angular perspective can be exploited by taking into consideration the trigonometric difference/sum between each point to define the temporal correlation over various periods and determine the Gramian Difference Angular Field (GADF) and Gramian Summation Angular Field (GASF) [42].”
BackgroundTagnamas, J., Ramadan, H., Yahyaouy, A., & Tairi, H. (2024) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-024-00155-w · Cited by 68
“However, diagnosis using BUS requires probes that depend heavily on the operator [5].”
BackgroundA Local Feature Engineering Strategy to Improve Network Anomaly Detection
Carta, S., Podda, A. S., Recupero, D. R., & Saia, R. (2020) · Future Internet · doi:10.3390/fi12100177 · Cited by 53
Self-citationPatel, N., Patel, S., & Mankad, S. H. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-02979-3 · Cited by 61
RetractedRamzan, F., Sartori, C., Consoli, S., & Recupero, D. R. (2024) · AI · doi:10.3390/ai5020035 · Cited by 87
“When analyzing data from newly listed companies or startups, the lack of reliable data can significantly increase uncertainty and investment risk associated with these ventures [7–10].”
Self-citationShip Roll Prediction Algorithm Based on Bi-LSTM-TPA Combined Model
Wang, Y., Wang, H., Zou, D., & Fu, H. (2021) · Journal of Marine Science and Engineering · doi:10.3390/jmse9040387 · Cited by 53
“applied convolution neural network to financial forecasting [28].”
MethodLong Short-Term Memory Neural Network for Financial Time Series
Fjellström, C. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020784 · Cited by 63
“The accuracies are shown to be just near 50%, which is consistent with findings in literature (see, for example, [3, 11, 22]).”
BackgroundMethodResultPopularity Prediction of Instagram Posts
Carta, S., Podda, A. S., Recupero, D. R., Saia, R., & Usai, G. (2020) · Information · doi:10.3390/info11090453 · Cited by 49
Self-citationDeep‐learning‐based seizure detection and prediction from electroencephalography signals
Ibrahim, F. E., Emara, H. M., El‐Shafai, W., Elwekeil, M., Rihan, M., El‐Dokany, I. M., Taha, T. E., El‐Fishawy, A. S., El‐Rabaie, E. M., Abdellatef, E., et al. (2022) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.3573 · Cited by 43
“S. Barra et al. 25 presented a framework in which GAF images are used to train an ensemble of CNNs.”
MethodEvaluating time series encoding techniques for Predictive Maintenance
Santo, A. D., Ferraro, A., Galli, A., Moscato, V., & Sperlí, G. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118435 · Cited by 48
Data Science for Economics and Finance: Methodologies and Applications
Consoli, S., Recupero, D. R., & Saisana, M. (2021) · Springer eBooks · doi:10.1007/978-3-030-66891-4 · Cited by 67
Self-citationSong, J., Lee, Y. C., & Lee, J. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-022-01981-6 · Cited by 47
“Barra et al. (2020) presented time series imagingbased on Gramian angular field (GAF) aids for improving financial market forecasting using CNNs. Yang et al. (2019) demonstrated a working example of diagnosing sensor signals that combines the image encoding ofmultivariate time series data and CNNs…”
BackgroundHuang, H., & Qian, C. (2023) · Ecological Indicators · doi:10.1016/j.ecolind.2023.111138 · Cited by 36
Mendoza, M., & Tsvetkov, P. V. (2022) · Progress in Nuclear Energy · doi:10.1016/j.pnucene.2022.104529 · Cited by 36
Salim, M., & Djunaidy, A. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.03.007 · Cited by 32
Isern, J., Barranco, F., Deniz, D., Lesonen, J., Jari Hannuksela, A., & Carrillo, R. R. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.11.004 · Cited by 39
“Analysis of gramian angular fields (GAF) images from the Standard & Poor’s 500 index [7]), point cloud analysis (e.”
Heimdall: an AI-based infrastructure for traffic monitoring and anomalies detection
Atzori, A., Barra, S., Carta, S., Fenu, G., & Podda, A. S. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9431052 · Cited by 33
“Deep Learning is now widely used in video and image analysis in a variety of research areas, ranging from medical diagnostics [19], [20], financial forecasting [21], [22] and cybersecurity [23], and over the years has also had a positive impact on road safety [24].”
BackgroundSelf-citationVolatility forecasting using deep neural network with time-series feature embedding
Chen, W.-J., Yao, J., & Shao, Y. (2022) · Economic Research-Ekonomska Istraživanja · doi:10.1080/1331677x.2022.2089192 · Cited by 36
“Financial markets are highly uncertain because of economic dynamics (Barra et al., 2020; Wang et al., 2021).”
BackgroundTraMiner: vision-based analysis of locomotion traces for cognitive assessment in smart-homes
Zolfaghari, S., Khodabandehloo, E., & Riboni, D. (2022) · Cognitive Computation · doi:10.1007/s12559-020-09816-3 · Cited by 29
A Transactional-Behavior-Based Hierarchical Gated Network for Credit Card Fraud Detection
Xie, Y., Zhou, M., Liu, G., Wei, L., Zhu, H., & Meo, P. D. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2025.125243 · Cited by 36
Khusheef, A. S., Shahbazi, M., & Hashemi, R. (2023) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-023-08340-4 · Cited by 33
Anomaly detection of industrial multi-sensor signals based on enhanced spatiotemporal features
Jiang, L., Xu, H., Liu, J., Shen, X., Lu, S., & Shi, Z. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07101-y · Cited by 26
“Currently, industrial signal analysis is popular in industrial defect detection, fault diagnosis, and signal forecasting [1, 2].”
BackgroundImproved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction
Wahyuddin, E. P., Caraka, R. E., Kurniawan, R., Caesarendra, W., Gio, P. U., & Pardamean, B. (2024) · Journal of Open Innovation Technology Market and Complexity · doi:10.1016/j.joitmc.2024.100458 · Cited by 40
Zhang, H., Zhang, F., Gong, B., Zhang, X., & Zhu, Y. (2023) · Journal of Organizational and End User Computing · doi:10.4018/joeuc.318474 · Cited by 26
“The experimental environment is configured with an i7 central processing unit (CPU), 64-bit Windows 7 operating system, 16 GB random access memory (RAM), and MATLAB 2016b for programming (Barra et al., 2020; Zhang, 2019; Tsai & Peng, 2017; Giri & Sarker,2017; Dar et al., 2017).”
Deep Learning for Laying Hen Activity Recognition Using Wearable Sensors
Shahbazi, M., Mohammadi, K., Derakhshani, S. M., & Koerkamp, P. W. G. G. (2023) · Agriculture · doi:10.3390/agriculture13030738 · Cited by 36
Classification of image encoded SSVEP-based EEG signals using Convolutional Neural Networks
de Paula, P. O., Costa, T. B. D. S., Attux, R., & Fantinato, D. G. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119096 · Cited by 32
A Mean-VaR Based Deep Reinforcement Learning Framework for Practical Algorithmic Trading
Jin, B. (2023) · IEEE Access · doi:10.1109/access.2023.3259108 · Cited by 31
“…and critic network structure is shown in Fig.3, In addition, Several authors have leveraged convolutional Neural Networks(CNN) to perform financial trading strategy [47], [48], treating the stock trading problem as a computer vision application by using time-series representative images as input.”
BackgroundRetracted: A Hybrid Multistage DNN-Based Collaborative IDPS for High-Risk Smart Factory Networks
Illy, P., Kaddoum, G., de Araujo-Filho, P. F., Kaur, K., & Garg, S. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3202801 · Cited by 26
“Therefore, deep learning models, which are built with a large number of neural layers and produce better results than shallow learning models in fields like computer vision, speech recognition, and finance [11], [12], [13], [14], have inspired many studies in the field of intrusion detection.”
BackgroundRetractedForecasting with Deep Learning: S&P 500 index
Kamalov, F., Smail, L., & Gurrib, I. (2020) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid51228.2020.00102 · Cited by 23
“Many other researchers used ML models such as NNs and support vector regression machines (SVR) along with feature selection algorithms to select the input variables, while providing empirical evidence that feature selection algorithms improved their model’s performance [8, 2, 10] .”
MethodAdvanced AI and big data techniques in E-finance: a comprehensive survey
Najem, R., Bahnasse, A., Amr, M. F., & Talea, M. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00365-y · Cited by 62
“Silvio Barra et al. [50] also utilize modern technology in their work by employing CNNs to encode time series into images.”
Madhulatha, T. S., & Ghori, M. A. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-12516-3 · Cited by 22
“Barra et al. 81 utilized Gramian angular fields (GAF) images for financial forecasting, and deep learning models outperformed buy-and-hold strategies.”
Sun, C.-H., Wang, Z.-L., Zhang, S.-Y., Zhou, T., Li, J., & Tan, J.-R. (2022) · Structural And Multidisciplinary Optimization · doi:10.1007/s00158-022-03372-0 · Cited by 18
“The features of the images are more dependent on deep learning based on Convolutional Neural Network (CNN).”
BackgroundInfluentialChong, K. L., Huang, Y. F., Koo, C. H., Sherif, M. M., Ahmed, A. N., & El‐Shafie, A. (2022) · Applied Water Science · doi:10.1007/s13201-022-01790-5 · Cited by 25
“Financial forecasting (Barra et al. 2020), traffic time series (Huang et al.”
BackgroundZaher, M., Ghoneim, A. S., Abdelhamid, L., & Atia, A. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109399 · Cited by 22
ViT-Based Multi-Scale Classification Using Digital Signal Processing and Image Transformation
Kim, G.-I., & Chung, K. (2024) · IEEE Access · doi:10.1109/access.2024.3389808 · Cited by 27
“…process described in Section III-C and the process of generating images from the five features. return composite_image end preocedure By transforming time-series data into images, it is possible to effectively express the multidimensional features and temporal and spatial patterns of the data [29].”
BackgroundHuang, X., Wu, C. W., Du, X., Wang, H., & Ye, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123146 · Cited by 24
Oh, S., & Kim, D.-K. (2022) · Applied Sciences · doi:10.3390/app12031286 · Cited by 22
Seeing is believing: Forecasting crude oil price trend from the perspective of images
Ren, X., Jiang, W., Ji, Q., & Zhai, P. (2024) · Journal of Forecasting · doi:10.1002/for.3149 · Cited by 23
Ma, Y. X., & Yeung, K. L. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.124196 · Cited by 22
Exploring Deep Learning to Determine the Optimal Environment for Stock Prediction Analysis
Sharma, R., Mehta, K., & Sharma, O. (2021) · International Conference on Computational Performance Evaluation (ComPE) · doi:10.1109/compe53109.2021.9752138 · Cited by 18
Mining frequent pyramid patterns from time series transaction data with custom constraints
Wang, W., Jing, T., Lv, F. C., Xin, G., Ma, Y., & Wang, B. (2020) · Computers & Security · doi:10.1016/j.cose.2020.102088 · Cited by 18
Bumin, M., & Özçalıcı, M. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119301 · Cited by 21
Imaging feature-based clustering of financial time series
Wu, J., Zhang, Z., Rui, T., Zhou, Y., Hu, Z., & Liu, K. (2023) · PLoS ONE · doi:10.1371/journal.pone.0288836 · Cited by 17
Data Science Technologies in Economics and Finance: A Gentle Walk-In
Barbaglia, L., Consoli, S., Manzan, S., Recupero, D. R., Saisana, M., & Pezzoli, L. T. (2021) · Springer eBooks · doi:10.1007/978-3-030-66891-4_1 · Cited by 26
Self-citationAutomated diagnosis of EEG abnormalities with different classification techniques
Abdellatef, E., Emara, H. M., Shoaib, M. R., Ibrahim, F. E., Elwekeil, M., El‐Shafai, W., Taha, T. E., El‐Fishawy, A. S., El‐Rabaie, E. M., El‐Dokany, I. M., et al. (2023) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-023-02843-w · Cited by 15
Alamdari, M. K., Esfahanipour, A., & Dastkhan, H. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.111213 · Cited by 18
Financial trading decisions based on deep fuzzy self-organizing map
Pei, D., Luo, C., & Liu, X. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109972 · Cited by 17
“Barra et al [12] used the GAF imaging method in a trading system to encode financial time series data as images, a set of CNNs with the same structure but initialized with different kernel functions organized for image classification, and finally adopted a voting-based policy.”
MethodChen, Y., Liu, J., Gao, Y., He, W., Li, H., Zhang, G., & Wei, H. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1123578 · Cited by 15
“The factors that affect the volatility of the stock market are very complex, showing highly nonlinear and dynamic characteristics (Barra et al., 2020), which increases the difficulty and risk of investment.”
BackgroundLiu, Z., Wang, C., Yang, X., Zhang, N., Liu, F., & Zhang, B. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3266227 · Cited by 14
“An innovative approach by encoding time series to GAF images is proposed in [30].”
MethodSTRATEGIC MANAGEMENT: A COMPREHENSIVE REVIEW PAPER
Alharbi, I. B. (2024) · International Journal of Professional Business Review · doi:10.26668/businessreview/2024.v9i3.4373 · Cited by 57
A hybrid soft computing approach to analyze and forecast financial risks
Abhishek, M., Gadipuuri, R., Surjeet, Sabrol, H., Dalal, V., Ratnaparkhi, A. K., & Krishnamaneni, R. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-02586-x · Cited by 14
Kim, D.-K., Shyn, S. K., Kim, D.-H., Jang, S., & Kim, K. (2021) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9659950 · Cited by 20
FootApp: An AI-powered system for football match annotation
Barra, S., Carta, S., Giuliani, A., Pisu, A., Podda, A. S., & Riboni, D. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13359-0 · Cited by 13
“In the era of Big Data, data annotation activities are very popular, mainly for two reasons: the first is that they can provide a semantic structure to the data, like videos [10], images [15], time-series [5], and audio file [29].”
BackgroundSelf-citationPraveen, M., Dekka, S., Sai, D. M., Chennamsetty, D. P., & Chinta, D. P. (2025) · Computational Economics · doi:10.1007/s10614-025-10899-z · Cited by 22
Group Penalized Multinomial Logit Models and Stock Return Direction Prediction
Hu, X., & Yang, J. (2024) · IEEE Transactions on Information Theory · doi:10.1109/tit.2024.3376751 · Cited by 12
“…series analysis [1], [9], [12], fundamental analysis [33], technical analysis [10], [17], [32], [37], machine learning [7], [24] and deep learning[ [4], CNN(convolutional neural network); [28], [38], DNN(deep neural network); [49], RNN(recurrent neural network)] have been proposed to predict the…”
BackgroundŚwiderska-Chadaj, Ż., Gallego, J., Lucía, G.-L., & Bueno, G. (2020) · Applied Sciences · doi:10.3390/app10217761 · Cited by 12
Pan, Y. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/7536492 · Cited by 12
RetractedDa, F., & Chen, C. L. P. (2025) · Scientific Reports · doi:10.1038/s41598-025-21613-2 · Cited by 18
Gök, G., Salor, Ö., & Taplamacıoğlu, M. C. (2023) · IET Generation Transmission & Distribution · doi:10.1049/gtd2.12734 · Cited by 11
Huang, Y., Fan, F., Huang, C., Yang, H., & Gu, M. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3447242 · Cited by 14
“Common information fusion methods include single-dimensional stacking (SDS) [35], [39], pixel-by-pixel addition (PPA) [25], and pixel-by-pixel multiplication (PPM) [20].”
MethodShort-Term Infectious Diarrhea Prediction Using Weather and Search Data in Xiamen, China
Wang, Z., Huang, Y., He, B., Luo, T., Wang, Y., Fu, Y., & Huang, C. (2020) · Scientific Programming · doi:10.1155/2020/8814222 · Cited by 11
Dynamic Industry-Specific Lexicon Generation for Stock Market Forecast
Carta, S., Consoli, S., Piras, L., Podda, A. S., & Recupero, D. R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64583-0_16 · Cited by 10
Self-citationSoft measurement of oil–water two-phase flow using a multi-task sequence-based CapsNet
OuYang, L., Jin, N., Bai, L., & Ren, W. (2022) · ISA Transactions · doi:10.1016/j.isatra.2022.12.007 · Cited by 11
Pattern Control of Neural Networks with Two-Dimensional Diffusion and Mixed Delays
Luan, Y., Xiao, M., Yang, X., Du, X., Ding, J., & Cao, J. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11491-6 · Cited by 10
Chansri, C., & Srinonchat, J. (2024) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2024.3404101 · Cited by 16
Prediction of mine water quality by the Seq2Seq model based on attention mechanism
Wang, X., & Li, Y. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e37916 · Cited by 10
“The work of Barra et al. (2020) [7] was a typical example, in which they successfully applied CNN models to predict future market trends by converting time series data into Gramian Angular Field images.”
MethodGross, J., Buettner, R., & Baumgartl, H. (2022) · IEEE Access · doi:10.1109/access.2022.3148711 · Cited by 10
“Furthermore, we address the theoretical challenge of overcoming long-term dependencies in sequential time-series without information loss [24], [30], [43].”
BackgroundMethodResultInfluentialAn incremental type-2 fuzzy classifier for stock trend prediction
Shahparast, H., Hamzeloo, S., & Safari, E. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118787 · Cited by 10
Human Activity Recognition by the Image Type Encoding Method of 3-Axial Sensor Data
Kim, C., & Lee, W. (2023) · Applied Sciences · doi:10.3390/app13084961 · Cited by 9
Zhang, R., Bai, X., Pan, L., Dong, Z., & Song, R. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02686-8 · Cited by 10
“7 Sequence diagrams and GAF images of the four evaluation types Table 2 Experimental results on GADF and GASF Method Identification accuracy under GADF dataset Identification accuracy under GASF dataset Non-transfer learning(”
MethodInfluentialMTMI-DCNN: A PSR-Based Method for Time Series Sensor Data Classification
Liu, R., Wang, F., Tian, F., Qian, J., Chen, X., Cui, S., & Lin, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3149948 · Cited by 10
Liu, J., Xu, Z., Yang, Y., Zhou, K., & Kumar, M. (2024) · Journal of Organizational and End User Computing · doi:10.4018/joeuc.345925 · Cited by 14
Uncertainty-Aware Self-Attention Model for Time Series Prediction with Missing Values
Li, J., Wang, C., Su, W., Ye, D., & Wang, Z. (2025) · Fractal and Fractional · doi:10.3390/fractalfract9030181 · Cited by 10
“Time series predictive tasks such as classification, forecasting, and event detection are fundamental for extracting valuable information from sequential data across various fields, including environmental monitoring [1–3], financial forecasting [4,5], and healthcare [6–9].”
An Image Based Approach of Energy Signal Disaggregation Using Artificial Intelligence
Senarathna, M., Herath, M., Thilakanayake, T., Liyanage, M. H., & Angammana, C. J. (2021) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis53135.2021.9660638 · Cited by 9
Jahromi, Z. T., Hasheminejad, S. M. H., & Shojaedini, S. V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16278-w · Cited by 10
“Convolutional neural networks have applications in image and video recognition [12], recommender systems [13], image classification [46], image segmentation [49], image analysis [19], natural language processing [14], brain-computer interfaces [20], and financial time series [5].”
Hu, X., & Yang, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123476 · Cited by 8
Statistical Data Mining Methods in Predicting Happiness and Habits
Sulaiman, S. K., Jghef, Y. S., Abdullah, A. I., & Ahmed, S. R. (2024) · ITM Web of Conferences · doi:10.1051/itmconf/20246401019 · Cited by 8
Intrusion detection and prevention systems in industrial IoT network
Sharma, S., Kumar, A., Rathore, N., & Sharma, S. (2024) · Sadhana · doi:10.1007/s12046-024-02567-z · Cited by 8
Cui, S., Yang, G., Guan, J., He, Y., Zhou, X., Bi, M., Shen, H., & Xu, Y. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3551613 · Cited by 7
Transforming petrophysical well-logs to images: leveraging deep learning for lithology recognition
Mohammadi, K., Mousavi, S. H. R., Hosseini‐Nasab, S. M., & Shahbazi, M. (2025) · Earth Science Informatics · doi:10.1007/s12145-025-01953-3 · Cited by 8
Image-based Candlestick Pattern Classification with Machine Learning
Xu, C. (2021) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1145/3468891.3468896 · Cited by 9
“Another way of transformation is to extract different technical indicators at different time points and combine them into 2-dimesnional matrix representation [9].”
BackgroundYadav, K., Jain, A., Alharbi, Y. O., Alferaidi, A., Alkwai, L. M., Ahmed, N. M. O. S., & Hamad, S. A. S. (2022) · IET Communications · doi:10.1049/cmu2.12336 · Cited by 8
Zhang, F.-P. (2023) · Soft Computing · doi:10.1007/s00500-023-07915-5 · Cited by 11
“Silvio et al. (2020) generate Gramian angular field images from time series and exploit an ensemble of CNNs to predict the future price movement of stocks.”
BackgroundMulti-task meta label correction for time series prediction
Yang, L., Gao, T., Wei, W., Dai, M., Fang, C., & Duan, J. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110319 · Cited by 10
“Barra et al. [4] apply Gramian Angular Field for financial data to train an ensemble of CNNs. Chen et al. [5] compare the effectiveness of several visualization methods for converting financial time series to images, such as Candlestick Chart, Gramian Angular Field, Moving Average Mapping, and…”
Method
Metadata
- Authors
- Barra, S., Carta, S. M., Corriga, A., Podda, A. S., & Recupero, D. R.
- Affiliations
- University of Cagliari (IT)
- ORCID
- Venue
- IEEE/CAA Journal of Automatica Sinica
- Published
- 2020-05
- Volume
- 7
- Issue
- 3
- Pages
- 683-692
- ISSN
- 2329-9266 (ISSN-L)
- 2329-9274
- OpenAlex
- W3023384820
- Cited by
- 267
- References
- 30
- Citations by year
- 2026: 27 · 2025: 65 · 2024: 58 · 2023: 36 · 2022: 42 · 2021: 23 · 2020: 16
- FWCI
- 18.61
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- Locations
- IEEE/CAA Journal of Automatica Sinica (publishedVersion)
- UNICA IRIS Institutional Research Information System (University of Cagliari) (submittedVersion, other-oa)
- UNICA IRIS Institutional Research Information System (University of Cagliari) (submittedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Complex Systems and Time Series Analysis
- Keywords
- financial forecasting, Gramian Angular Field, ensemble convolutional neural networks, stock trend prediction, S&P 500, multi-resolution imaging, trading systems, buy-and-hold strategy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.