Search

This paper presents the development of a system for simulating and visualizing autonomous vehicle navigation using a single-beam LiDAR sensor integrated with an artificial neural network, implemented entirely in JavaScript. The single-beam LiDAR sensor in the simulation was configured to closely resemble real-world counterparts, such as the YDLIDAR TG30. The proposed neural network architecture, consisting of four output neurons, processes data from ten distinct angular measurements of the LiDAR sensor to predict necessary steering and speed adjustments for autonomous navigation. Furthermore, we introduce an enhanced collision detection algorithm that improves upon traditional methods by providing more precise identification of line segment intersections. Implementing the entire system in JavaScript demonstrates the viability of utilizing web technologies for complex machine learning tasks, representing a significant advancement in autonomous vehicle research. Experimental results validate the effectiveness of this approach across various scenarios, emphasizing its potential for broader applications in cost-sensitive autonomous systems. This work may also serve as a valuable resource for researchers new to machine learning, contributing to greater accessibility in the development of autonomous vehicles.

Fluid catalytic cracking (FCC) is an important process in petroleum processing. Effective monitoring of the status and quality of FCC is vital. Accurate description of the relationship between process and quality variables is the basis of quality-driven monitoring. Many process variables affect the quality of FCC; some of these effects are linear, and others are nonlinear. We propose a combination method from the perspective of linearity and nonlinearity to improve the monitoring performance of FCC quality. Partial least squares (PLS) is initially used to extract linear features, and its residual space is saved as the input of the deep feedforward neural network (DFNN). DFNN is then used to extract nonlinear features for the further decomposition of subspaces. The PLS-DFNN method accurately describes processes involving linearity and nonlinearity. We construct three monitoring statistics to characterize the types of faults. The proposed method proves its excellent effect on a numerical simulation data set. It effectively distinguishes the types of faults on the Tennessee Eastman process data set, and the fault detection rate is superior to other related methods. Finally, we apply this method to the actual FCC and verify the superiority of this combination. [ABSTRACT FROM AUTHOR]

Sensor-related indoor localization has attracted considerable attention in recent years. The accuracy of conventional fingerprint solutions based on a single sensor, such as a Wi-Fi sensor, is affected by multipath interferences from other electronic devices that are produced as a result of complex indoor environments. Light sensors and magnetic (i.e., geomagnetic) field sensors can be used to enhance the accuracy of a system since they are less vulnerable to disturbances. In this paper, we propose a deep feedforward (DFF)-neural-network-based method, termed DFF-WGL, which integrates the data from the embedded Wi-Fi sensor, geomagnetic field sensor, and light sensor (WGL) in a smart device to localize the device in an indoor environment. DFF-WGL does not require complex and expensive auxiliary equipment, except for basic fluorescent lamps and low-density Wi-Fi signal coverage, conditions that are easily satisfied in modern offices or educational buildings. The proposed system was implemented on a commercial off-the-shelf android device, and performance was evaluated through an experimental analysis conducted in two different indoor testbeds, one measuring 60.5 m2 and the other measuring 38 m2, with 242 and 60 reference points, respectively. The results indicate that the model prediction with an input consisting of the combination of light, a magnetic field sensor, and two Wi-Fi RSS signals achieved mean localization errors of 0.01 m and 0.04 m in the two testbeds, respectively, compared with any subset of combination of sensors, verifying the effectiveness of the proposed DFF-WGL method. [ABSTRACT FROM AUTHOR]

Copyright of Petroleum Geology & Oilfield Development in Daqing is the property of Editorial Department of Petroleum Geology & Oilfield Development in Daqing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Deuterium （D） and tritium （T） have been regarded as the first-generation fuels for achieving commercial fusion energy. However， the utilization of the radionuclide tritium introduces concerns related to radioactive safety. This study sought to investigate methods for estimating airborne tritium sources following a fusion reactor incident. An algorithm that combines an adaptive Kalman filter with a deep feedforward neural network was developed to determine the tritium release height and rate. By utilizing observed data both pre- and post-filtering as inputs， the neural network's predictions for the tritium release rate were analyzed. The findings indicate that filtering significantly lowers the prediction errors. Considering a 20% monitoring error， the average relative error for the estimated release height is approximately 3% and that for the release rate is approximately 4%.

The density regression fitting method is generally used to predict total organic carbon(TOC) content of shale reservoir with seismic data. Because it only considers the linear relationship of single factor, the prediction error is large. Aiming at the shortcomings of this method, a TOC content prediction method based on deep learning was proposed. Firstly, the elastic parameter curves with the highest correlation with the TOC content curve were selected from the logging data as the input data of the sample set, and the TOC content curve was used as the output data of the sample set. Based on the sample set, a deep feedforward neural network model for TOC content prediction was constructed. Then, the structure of the network model was adjusted and the parameters of the network were optimized by conjugate gradient method. Finally, the elastic parameter data volume obtained from prestack amplitude versus offset (AVO) inversion was input into the deep feedforward neural network model to predict the final TOC content volume. Through the application of actual logging and seismic data of shale reservoir in Sichuan Basin, the advantages of the new method over the conventional regression fitting method were compared, the practicability and feasibility of the proposed method were verified, which provides a new idea for TOC content prediction of shale reservoir. [ABSTRACT FROM AUTHOR]

Human body surface area (BSA) plays a crucial role in clinical medicine, but most of the existing BSA formulas only use two parameters: height and weight, and adopt the method of matching simple function to estimate the body surface area. Doctors also show that the existing clinical BSA formulas have a large calculation error. To solve these problems, a new BSA regression prediction model is proposed. The regression model consists of two parts: firstly, the factors of body surface area with high correlation are selected by correlation and significance analysis; secondly, a regression model is constructed by training the deep feed-forward neural network with 104 sets of human body data. 5-fold cross validation and independent test set and two verification methods are adopted in the experiments. Firstly, the accuracy of the deep feedforward neural network model and the traditional human surface area calculation formula are evaluated, and the results are compared and analyzed. Secondly, the accuracy of the deep feedforward neural network model and the three algorithm models are evaluated, and the results are compared and analyzed. Compared with the traditional methods, the determination coefficient of the deep feedforward neural network model is higher than that of the two traditional methods, and is six percentage points higher than the traditional method with better results, and the error of deep feedforward neural network model is nearly twice as low as that of the traditional method. Compared with the three algorithm models, the deep feedforward neural network improves the determination coefficient by two percentage points and reduce the error. The experimental results of consistency analysis also show that the 95% consistency limit of the deep feedforward neural network is the smallest and the consistency is the best. Through above experiments, it is proved that the proposed regression framework can better calculate body surface area and obtain more accurate prediction value. [ABSTRACT FROM AUTHOR]

In the vehicle industry, connectivity and autonomy are becoming increasingly important features. One of the most used protocols for in-vehicle communication is the Controller Area Network (CAN) bus which manages the communication between networked components. However, the CAN bus, despite its critical importance, lacks sufficient security features to protect its network as well as the overall car system. Thus, vehicle network security is becoming increasingly crucial. Methods of intrusion detection help to improve the security of the in-vehicle network. This work aims to provide a model that enables effective detection of attacks such as fuzzy, DoS, and impersonation using the Deep Feedforward Neural Network (DeepFNN) model as well as the Long Short- Term Memory model. Moreover, the LSTM model presents the most satisfying outcome in terms of precision and recall metrics. [ABSTRACT FROM AUTHOR]

Systolic time intervals (STIs), such as pre-ejection period (PEP), left ventricular ejection time (LVET) and PEP-to-LVET ratio, often measured by echocardiography, play vital roles in assessing cardiac contractility, cardiac efficiency, and sympathetic activity. However, to facilitate these measurements for wearables, multiple cardiac signals are needed, resulting in more required sensing devices. In this study, we developed a machine learning (ML) approach to estimate ventricular depolarization (VD) timings using only a single low-cost microelectromechanical system (MEMS)-based accelerometric sensor for measuring the STIs. A cardio-mechanical seismocardiogram (SCG) signal, manifested by rhythmic chest-vibrations, was acquired from the sensor. The SCG signal effectively captures the fiducial points required for measuring LVET. However, computing PEP involves VD timing instants, that are usually identified by the R-peaks of the electrocardiogram (ECG) signal. Consequently, measuring PEP requires more than one cardiac signal. To avoid the use of multiple sensing modalities, this study aims to compute R-peaks instants directly from the SCG signal. We devised a deep feedforward neural network (DFN) with SCG-based features to estimate VD events, which were referenced by R-peaks of concurrent electrocardiogram (ECG) signal. The estimated R-peaks along with the required SCG fiducial points can be used to measure the STIs. A set of self-recorded real-time SCG data collected in supine position was used to train and validate the model. The performance was validated using mean absolute error (MAE), root mean square error (RMSE), and standard deviation of error (SDE). Experimental results showed that the VD events detected using the proposed model has a MAE of 0.080, RMSE of 0.167, and SDE of 0.164. Also, the proposed DFN model was compared with classical ML models, such as random forest and eXtreme Gradient Boosting, where our DFN outperformed all. This demonstrates the standalone utilization of SCG as a cardiac tool for measuring left ventricular systolic functions, offering potential applications in assessing various ventricular anomalies. • A single cardiac signal acquired using a low-cost accelerometric sensor is utilized to represent both electric and mechanical phenomenon of the heart. • R-peaks associated with ventricular depolarization are localized on SCG signal using a neural network. • The performance of the proposed method is tested and validated with healthy subjects at supine position. • The performance validation is done with the R-peaks detected from reference ECG signals. • The performance of the network is also compared with conventional models, such as random forest and XGBoost. [ABSTRACT FROM AUTHOR]

The low-frequency component of seismic data is an inevitable part to obtain absolute P-impedance ( I p ) and V p / V s ratio of the subsurface, especially for the reservoir sweet spot. In this work, we train the deep feedforward neural network (DFNN) with band-pass seismic data and well log data to obtain favorable low-frequency components. Specifically, the Bayesian inference strategy is first applied to the pre-stack constrained sparse spike inversion process, obtaining an "initial" inverted band-pass parameters, which are subsequently used as input when applying the DFNN algorithm to predict low- and band-pass parameters. Moreover, the high linear correlation coefficient between the DFNN-based inversion results and the realistic well logging curves of the blind wells demonstrates that the DFNN-based inversion scheme exhibits strong robustness and good generalization ability. Ultimately, we apply the proposed DFNN-based inversion strategy to a tight sandstone reservoir located at the Sichuan basin field from onshore China. Both low- and band-pass I p and V p / V s inverted for the clastic formation of the Sichuan basin show a strong correlation with the corresponding I p and V p / V s logs. [ABSTRACT FROM AUTHOR]

This paper proposes a novel and efficient DNN-NSGAII approach which is an integration of the deep feedforward neural network (DNN) and the nondominated sorting genetic algorithm II (NSGAII) to solve multi-objective optimization (MOO) problems of laminated functionally graded carbon nanotube-reinforced composite (FG-CNTRC) quadrilateral plates. The core idea of the proposed approach is to use the DNN as an analyzer to evaluate the objective and constraint functions instead of using the time-consuming finite element analysis methods (FEAMs) during the optimization process, while the NSGAII is employed to find a set of Pareto-optimal solutions of the MOO problems. Accordingly, the proposed DNN-NSGAII remarkably saves the computational cost, but still provides a high accurate optimal solution. The precision, efficiency, and capability of the proposed method are demonstrated through two different MOO problems of the FG-CNTRC quadrilateral plates. Obtained results of the DNN-NSGAII are compared with those of other methods to investigate the reliability and efficiency of proposed method. Moreover, the effects of various boundary conditions and carbon nanotube (CNT) distributions on the Pareto-optimal solutions of MOO problems are also examined. [ABSTRACT FROM AUTHOR]

TeraHertz wireless communication has been regarded as an effective technology to satisfy the ever-increasing requirements of high-rate services, where the imperfections of TeraHertz devices, including in-phase/quadrature imbalance, phase noise and nonlinearity, regarded as hybrid distortions, have to be investigated. Due to the hybrid distortions, the explicit system model could not be mathematically derived, which limits the performance of the state-of-the-art demodulation methods. Here, a deep learning-assisted demodulation methodology is proposed to improve the bit error rate performance. Specifically, a multiple-output deep feedforward neural network is designed to fit the mapping between the received signal and likelihood information, where the number of outputs equals to the size of the modulation set, thus enabling the demodulation of the overlapped received signals corresponding to different constellation points. Besides, a training set generation method is proposed to generate the training examples without the prior knowledge of likelihood information. Simulation results validate that the proposed learning-assisted methodology could improve the demodulation performance of the TeraHertz wireless systems under severe hybrid distortions. [ABSTRACT FROM AUTHOR]

The development of industrial and urban places caused air pollution, which has resulted in a variety of effects on individuals and the atmosphere over the years. The measurement of the air quality index (AQI) depends on various environmental situations, such as emissions, dispersions, and chemical reactions. This paper developed the Internet of Things (IoT)-based Deep Learning (DL) technique for predicting air quality. Initially, the IoT simulation is performed, where the nodes receive input data. The routing technique is used to identify the best route toward the Base station (BS). The proposed Tangent Two-Stage Algorithm (TTSA) is used in the routing mechanism. For AQI prediction, the time series data is transmitted to the BS. The Z-score normalisation is employed to neglect the unessential data. Furthermore, feature indicator extraction is employed to extract the relevant feature indicators. The Deep Feedforward Neural Network (DFNN) is used to predict air quality. Furthermore, the proposed Fractional Tangent Two-Stage Optimisation (FTTSA) is employed for the training process of DFNN. Moreover, metrics such as energy, time, and distance are used to evaluate the routing process, and superior results such as 0.979J, 0.025s and 0.196 m are obtained. Furthermore, the AQI is predicted by metrics like root mean square error (RMSE), R-squared (R 2 ), mean square error (MSE), and mean absolute percentage error (MAPE), whereas the superior values such as 0.602, 0.598, 0.362, and 0.456 are attained.

TeraHertz (THz) wireless communication constitutes a promising technique of satisfying the ever-increasing appetite for high-rate services. However, the ultra-wide bandwidth of THz communications requires high-speed, high-resolution analog-to-digital converters, which are hard to implement due to their high complexity and power consumption. In this paper, a deep learning-assisted THz receiver is designed, which relies on single-bit quantization. Specifically, the imperfections of THz devices, including their in-phase/quadrature-phase imbalance, phase noise and nonlinearity are investigated. The deflection ratio of the maximum-likelihood detector used by our single-bit-quantization THz receiver is derived, which reveals the effect of phase offset on the demodulation performance, guiding the architecture design of our proposed receiver. To combat the performance loss caused by the above-mentioned distortions, a twin-phase training strategy and a neural network based demodulator are proposed, where the phase offset of the received signal is compensated before sampling. Our simulation results demonstrate that the proposed deep learning-assisted receiver is capable of achieving a satisfactory bit error rate performance, despite the grave distortions encountered. [ABSTRACT FROM AUTHOR]

This work investigates the proactive eavesdropping through a friendly full-duplex (FD) relay and a legitimate monitor over the wireless-powered suspicious communication network, where one suspect source performs energy harvesting (EH) from one dedicated power beacon and then communicates with one suspect destination. Under this setup, a relay-aided proactive eavesdropping scheme is designed to improve the surveillance performance of the system. The closed-form expressions are derived under linear and nonlinear EH models, including the decoding outage probability for the suspicious link, the eavesdropping outage probability for the eavesdropping link, and the average eavesdropping rate (AER). Based on these obtained expressions, an optimization problem to maximize the AER is formulated by jointly optimizing the power and location of the relay. The existence of the optimal solution is carefully analyzed. Moreover, the separate optimization issues of the power and location are first established, and then a bisection-based searching algorithm is presented for the joint optimization problem with the linear EH model. Furthermore, to reduce the complexity of joint optimization, a low-complexity learning-based iteration algorithm is further proposed by employing the well-fitting characteristic of the deep feedforward neural network. Numerical results verify the effectiveness of the proposed algorithm, and show that the optimized FD relay-aided proactive eavesdropping scheme outperforms the reference schemes. Finally, the application scenarios of the proposed proactive eavesdropping scheme are discussed.

Summary: This paper mainly analyzes the performance degradation of turbomachinery in gas turbines, classifies the main types of degradation: increased tip clearance, corrosion/wear, fouling, and multiple degradation, and predicts the degradation trend through deep neural networks. The deep feedforward neural network is used to build the regression model and two classification models. The regression model uses a back propagation algorithm optimized by Lenvenberg Marquardt to convert the efficiency and flow capacity calculated by the thermodynamic model into the values under full load and ISO conditions to ensure that the comparison is performed on the same performance benchmark. Compared with deep feedforward neural network and random forest regression, the optimized model has higher accuracy and no overfitting. The data after the overhaul is selected as the performance benchmark, and the efficiency and flow capacity of different degradation types are calculated according to the benchmark and classified by the classification model. By testing the simulated data, the classification accuracy of the compressor and the turbine exceeds 99.9% and 99.5% respectively. Long short‐term memory is used to predict the degradation trends and the degradation of the predictions is classified by the classification model. The degradation classification accuracy of the prediction reached 93.65% and 81.65% in compressor and turbine, which shows that the prediction model has high accuracy. [ABSTRACT FROM AUTHOR]

Generalization ability is known as an important performance index of artificial neural networks (ANNs). The generalization ability of an ANN usually refers to its ability to recognize untrained samples, but it lacks quantitative analysis. A method is designed by using frequency-domain signals to observe the generalization ability of deep feedforward neural networks (DFFNNs) which are popular ANN models. This method allows us to observe that the generalization ability of DFFNNs is limited to a small neighborhood around the trained samples. Then, the relationship between sample similarity and the DFFNN's generalization performance is further analyzed. The analysis results show that the correlation coefficient between samples has a certain positive correlation with the DFFNN's generalization performance. Based on this new understanding, an algorithm in which shadows of the trained samples are added into the training set is proposed to improve the generalization ability of DFFNNs. The proposed algorithm is tested with some simulated signals and some real-world data. The tests show that the proposed method can indeed improve the DFFNN's generalization ability by only changing the training sample set. [ABSTRACT FROM AUTHOR]

The neural network-based prediction method has shown great potential in the field of fatigue crack growth prediction due to its powerful nonlinear processing and generalization capabilities. However, traditional deep neural network-based methods often encounter problems such as overfitting, underfitting, and instability when predicting FCG rates on small datasets. To address these issues, this study proposes a SA-DNN prediction method for metal fatigue crack growth by introducing Delaunay data augmentation and simulated annealing algorithm into the basic DNN framework. The proposed SA-DNN model is then used to predict the fatigue crack growth process of AM60B magnesium alloy and 7055 Al alloy, and the intrinsic and extrinsic generalization abilities of the model are evaluated. In both the evaluation of intrinsic and extrinsic generalization abilities, the mean squared errors of the training, validation, and testing sets rapidly converge to the target error in various epochs. The lowest mean squared errors achieved are 1.07 e-5 and 1.241 e-5, respectively. Moreover, the results also indicate that the proposed model can accurately predict the fatigue crack growth process of metal materials with varying degrees of nonlinearity. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) reservoir geological modeling is an advanced reservoir characterization method, which runs through the exploration and the development process of oil and gas fields. Reservoir geological modeling is playing an increasingly significant role in determining the distribution, internal configuration, and quality of a reservoir as well. Conventional variogram-based methods such as statistical interpolation and reservoir geological modeling have difficulty characterizing complex reservoir geometries and heterogeneous reservoir properties. Taking advantage of deep feedforward neural networks (DFNNs) in nonlinear fitting, this paper compares the reservoir geological modeling results of different methods on the basis of an existing lithofacies model and seismic data from the X area of Karamay, Xinjiang, China. Adopted reservoir geological modeling methods include conventional sequential Gaussian simulation and DFNN-based reservoir geological modeling method. The constrained data in the experiment mainly include logging data, seismic attribute data, and lithofacies model. Then, based on the facies-controlled well-seismic combined reservoir geological modeling method, this paper explores the application of multioutput DFNN and transfer learning in reservoir geological modeling. The results show that the DFNN-based reservoir geological modeling results are closer to the actual model. In DFNN-based reservoir geological modeling, the facies control effect is obvious, and the simulation results have a higher coincidence rate in a test well experiment. The feasibility of applying multioutput DFNN and transfer learning in reservoir geological modeling provides solutions for further optimization methods, such as solving small-sample problems and improving the modeling efficiency.

• Fast inversion of nuclear accident source term is achieved based on deep feedforward neural network. • The hyperparameters of deep feedforward neural network suitable for the inversion of single-point and stable-release source are determined. • Sensitivity analysis and uncertainty analysis improve the reliability of the inversion source term and reduce the risk of failure to emergency response. Source term estimation based on environmental monitoring data is a key method for obtaining source information, which is required by the emergency response system. This study investigates the applicability of deep feedforward neural network (DFNN) for source inversion. Twenty thousand sets of simulated data containing I-131 release rate, meteorological information, and simulated radioactive concentration are generated based on radionuclide atmospheric dispersion codes RADC. These are used to train and test a DFNN. The influence of key network hyperparameters is studied. The results show that the average prediction error of DFNN is 2.24%, and that over 80% of prediction errors are less than 2.0%. The Bayesian MCMC algorithm is used to analyze the prediction uncertainty of DFNN when there are uncertainties in the input parameters. The confidence interval and risk curve are likely to provide more reliable source-term information for nuclear accident emergency response and decision-making. [ABSTRACT FROM AUTHOR]

Data-driven sensors are techniques capable of providing real-time information of unmeasured variables based on instrument measurements. They are valuable tools in several engineering fields, from car automation to chemical processes. However, they are subject to several sources of uncertainty, and in this way, they need to be able to deal with uncertainties. A way to deal with this problem is by using soft sensors and evaluating their uncertainties. On the other hand, the advent of deep learning (DL) has been providing a powerful tool for the field of data-driven modeling. The DL presents a potential to improve the soft sensor reliability. However, the uncertainty identification of the soft sensors model is a known issue in the literature. In this scenario, this work presents a strategy to identify the uncertainty of DL models prediction based on a novel Monte Carlo uncertainties training strategy. The proposed methodology is applied to identify a Soft Sensor to provide a real-time prediction of the productivity of a chemical process. The results demonstrate that the proposed methodology can yield a soft sensor based on DL that provides reliable predictions, with precision being proven by its corresponding coverage region. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) reservoir geological modeling is an advanced reservoir characterization method, which runs through the exploration and the development process of oil and gas fields. Reservoir geological modeling is playing an increasingly significant role in determining the distribution, internal configuration, and quality of a reservoir as well. Conventional variogram-based methods such as statistical interpolation and reservoir geological modeling have difficulty characterizing complex reservoir geometries and heterogeneous reservoir properties. Taking advantage of deep feedforward neural networks (DFNNs) in nonlinear fitting, this paper compares the reservoir geological modeling results of different methods on the basis of an existing lithofacies model and seismic data from the X area of Karamay, Xinjiang, China. Adopted reservoir geological modeling methods include conventional sequential Gaussian simulation and DFNN-based reservoir geological modeling method. The constrained data in the experiment mainly include logging data, seismic attribute data, and lithofacies model. Then, based on the facies-controlled well-seismic combined reservoir geological modeling method, this paper explores the application of multioutput DFNN and transfer learning in reservoir geological modeling. The results show that the DFNN-based reservoir geological modeling results are closer to the actual model. In DFNN-based reservoir geological modeling, the facies control effect is obvious, and the simulation results have a higher coincidence rate in a test well experiment. The feasibility of applying multioutput DFNN and transfer learning in reservoir geological modeling provides solutions for further optimization methods, such as solving small-sample problems and improving the modeling efficiency. [ABSTRACT FROM AUTHOR]

• Deep neural networks (cf. shallower architectures) better predict stock indices. • A rectifier linear (cf. tanh) activation function better predicts stock indices. • Relative predictive accuracy of deep neural networks peaks with increasing data. Many existing learning algorithms suffer from limited architectural depth and the locality of estimators, making it difficult to generalize from the test set and providing inefficient and biased estimators. Deep architectures have been shown to appropriately learn correlation structures in time series data. This paper compares the effectiveness of a deep feedforward Neural Network (DNN) and shallow architectures (e.g., Support Vector Machine (SVM) and one-layer NN) when predicting a broad cross-section of stock price indices in both developed and emerging markets. An extensive evaluation is undertaken, using daily, hourly, minute and tick level data related to thirty-four financial indices from 32 countries across six years. Our evaluation results show a considerable advantage from training deep (cf. shallow) architectures, using a rectifier linear (RELU) activation function, across all thirty-four markets when 'minute' data is used. However, the predictive performance of DNN was not significantly better than that of shallower architectures when using tick level data. This result suggests that when training a DNN algorithm, the predictive accuracy peaks, regardless of training size. We also examine which activation function works best for stock price index data. Our results demonstrate that the RELU activation function performs better than TANH across all markets and time horizons when using DNN to predict stock price indices. [ABSTRACT FROM AUTHOR]