Search

Recently, intelligent data processing and interpretation based on deep learning (DL) have received considerable attention. Training data are vital for DL-based approaches. In geosciences, researchers have been facing a significant obstacle, i.e., the absence of authoritative and representative open data for training and testing artificial neural networks (ANNs). Although open-source works in geosciences are increasing, the quantity is currently limited. With the aid of the Society of Exploration Geophysicists (SEG) 2020 Machine Learning (ML) Blind-Test Challenge Data, we open source a package for DL-based seismic facies classification (SFC). We regard SFC as translating the seismic data into the facies by training a flexible end-to-end encoding–decoding-style ANN “BridgeNet” revised from U-Net. Inspired by the residual network (ResNet), we further enhance the BridgeNet by inserting the identity shortcut connections, which can theoretically ease the notorious problem of vanishing/exploding gradients. The evaluated framework, however, is not restricted to SFC. We hope that it can provide some insights that help researchers to construct and train ANNs that yield reliable and robust results in their own tasks. We carry out benchmarking experiments to investigate some crucial factors impacting the ANN’s performance to elucidate how we obtained our current optimal results on the SEG 2020 ML Challenge Data. The accuracy and continuity of predicted facies along the training and testing sections indicate that the results are consistent with geologic sedimentation, verifying the generalization capability of the enhanced flexible end-to-end encoding–decoding-style BridgeNet. For SFC, we recommend a memory-saving sparse categorical cross-entropy (CC) loss function to improve the efficiency. The codes are available at https://doi.org/10.5281/zenodo.5787673. [ABSTRACT FROM AUTHOR]

Localization services play an important role in Internet of Connected Vehicles (IoCV) and vehicle predictive localization information can greatly improve traffic efficiency and reduce accidents. However, a huge amount of computing and communication overhead is required to obtain such information by traditional methods. In this work, we propose a Behavior-based Clustering Method (BCM) to analyze the behavioral correlation between vehicles and classify them into different clusters. Based on BCM results coupled with a deep learning model, we further propose a Clustering-learning-based Long-term Predictive Localization (CLPL) algorithm to predict vehicles’ future location distribution. In the proposed CLPL algorithm, all the traffic roads are divided into consecutive small segments in order to pinpoint vehicles’ precise current locations and to obtain long-term predictions. Extensive simulations, notably involving real dataset, have been carried out to evaluate BCM and CLPL in terms of several performance criteria including matching rates. The analysis of the results validated how the designed methods can predict vehicle location much more accurately than existing algorithms. [ABSTRACT FROM AUTHOR]

Physical and/or economic constraints cause acquired seismic data to be incomplete; however, complete data are required for many subsequent seismic processing procedures. Data reconstruction is a crucial and long-standing topic in the exploration seismology field. We extended our previous works on deep learning (DL)-based irregularly and regularly missing 2-D data reconstruction to 3-D data. A key motivation is that the 3-D convolutional neural network (CNN) can take full advantage of the 3-D nature of the data, and the additional dimension allows more information to contribute to the data reconstruction. DL also avoids many assumptions (e.g., linearity, sparsity, and low-rank) limiting conventional nonintelligent reconstruction methods. We built an artificial neural network (ANN) based on an end-to-end U-Net encoder–decoder-style 3-D CNN. The ANN was trained on large quantities of various synthetic and field 3-D seismic data using a mean-squared-error (MSE) loss function and an Adam optimizer. We demonstrated that the developed 3-D CNN reconstruction method appears to outperform the 2-D CNN for 3-D restoration. We benchmarked the ANN’s generalization capacity for recovery of irregularly and regularly sampled 3-D data on several typical seismic data sets, particularly those with high missing percentages or large gaps. An ANN trained with irregularly sampled data can be partly applied to regularly sampled cases. We investigated how a key parameter, i.e., the learning rate, can be experimentally determined. In the context of the presented examples, our methodology provided a substantial improvement over an open-source state-of-the-art rank-reduction-based approach in terms of data fidelity and efficiency. [ABSTRACT FROM AUTHOR]

Haptic feedback is crucial to immersive experience in virtual and augmented reality applications. The existing promising maglev haptic devices have advantages of no mechanical friction and low inertia. However, their performance is limited by the navigation approach, which mainly results from the challenge that it is difficult to obtain high precision, high frequency, and good stability with lightweight design at the same time. In this study, we reformulate visual-inertial navigation as a regression problem, and adopt deep learning to perform fusion navigation for maglev haptic interaction. A cascade-LSTM-based q-increment learning method is first proposed to progressively learn the increments of target variables. Two cascade LSTM networks are then constructed to estimate the increments of position and orientation, which are pipelined to accomplish visual-inertial fusion navigation. Additionally, we set up a maglev haptic platform as the system testbed. Experimental results show that our cascade-LSTMbased visual-inertial fusion navigation approach can reach 200 Hz while maintaining high-precision navigation (the mean absolute error of the position and orientation is less than 1 mm and 0.02°, respectively) for a maglev haptic interactive deformation application. [ABSTRACT FROM AUTHOR]

With the development of intelligent applications (e.g., self-driving, real-time emotion recognition), there are higher requirements for cloud intelligence. However, cloud intelligence depends on the multi-modal data collected by user equipments (UEs). Due to the limited capacity of network bandwidth, offloading all data generated from the UEs to the remote cloud is impractical. Thus, in this article, we consider the challenging issue of achieving a certain level of cloud intelligence while reducing network traffic. In order to solve this problem, we design a traffic control algorithm based on label-less learning on the edge cloud, which is dubbed LLTC. By use of the limited computing and storage resources at the edge cloud, LLTC evaluates the value of data that will be offloaded. Specifically, we first give a statement of the problem and the system architecture. Then we design the LLTC algorithm in detail. Finally, we set up the system testbed. Experimental results show that the proposed LLTC can guarantee the required cloud intelligence while minimizing the amount of data transmission. [ABSTRACT FROM AUTHOR]