Data Bandwidth Research Articles

An Efficient On-Chip Data Storage and Exchange Engine for Spaceborne SAR System

Advancements in remote sensing technology and very-large-scale integrated circuit (VLSI) have significantly augmented the real-time processing capabilities of spaceborne synthetic aperture radar (SAR), thereby enhancing terrestrial observational capacities. However, the inefficiency of voluminous data storage and transfer inherent in conventional methods has emerged as a technical hindrance, curtailing real-time processing within SAR imaging systems. To address the constraints of a limited storage bandwidth and inefficient data transfer, this study introduces a three-dimensional cross-mapping approach premised on the equal subdivision of sub-matrices utilizing dual-channel DDR3. This method considerably augments storage access bandwidth and achieves equilibrium in two-dimensional data access. Concurrently, an on-chip data transfer approach predicated on a superscalar pipeline buffer is proposed, mitigating pipeline resource wastage, augmenting spatial parallelism, and enhancing data transfer efficiency. Building upon these concepts, a hardware architecture is designed for the efficient storage and transfer of SAR imaging system data, based on the superscalar pipeline. Ultimately, a data storage and transfer engine featuring register addressing access, configurable granularity, and state monitoring functionalities is realized. A comprehensive imaging processing experiment is conducted via a “CPU + FPGA” heterogeneous SAR imaging system. The empirical results reveal that the storage access bandwidth of the proposed superscalar pipeline-based SAR imaging system’s data efficient storage and transfer engine can attain up to 16.6 GB/s in the range direction and 20.0 GB/s in the azimuth direction. These findings underscore that the storage exchange engine boasts superior storage access bandwidth and heightened data storage transfer efficiency. This considerable enhancement in the processing performance of the entire “CPU + FPGA” heterogeneous SAR imaging system renders it suitable for application within spaceborne SAR real-time processing systems.

High-Level Synthesis Design of Scalable Ultrafast Ultrasound Beamformer With Single FPGA.

Ultrafast ultrasound imaging is essential for advanced ultrasound imaging techniques such as ultrasound localization microscopy (ULM) and functional ultrasound (fUS). Current ultrafast ultrasound imaging is challenged by the ultrahigh data bandwidth associated with the radio frequency (RF) signal, and by the latency of the computationally expensive beamforming process. As such, continuous ultrafast data acquisition and beamforming remain elusive with existing software beamformers based on CPUs or GPUs. To address these challenges, the proposed work introduces a novel method of implementing an ultrafast ultrasound beamformer specifically for ultrafast plane wave imaging (PWI) on a field programmable gate array (FPGA) by using high-level synthesis. A parallelized implementation of the beamformer on a single FPGA was proposed by 1) utilizing a delay compression technique to reduce the delay profile size, which enables both run-time pre-calculated delay profile loading from external memory and delay reuse, 2) vectorizing channel data fetching which is enabled by delay reuse, and 3) using fixed summing networks to reduce consumption of logic resources. Our proposed method presents two unique advantages over current FPGA beamformers: 1) high scalability that allows fast adaptation to different FPGA resources and beamforming speed demands by using Xilinx High-Level Synthesis as the development tool, and 2) allow a compact form factor design by using a single FPGA to complete the beamforming instead of multiple FPGAs. Current Xilinx FPGAs provide the capabilities of connecting up to 1024 ultrasound channels with a single FPGA and the newest JESD204B interface analog front end (AFE). This channel count is much more than the channel count needed by current linear arrays, which normally have 128 or 256 channels. With the proposed method, a sustainable average beamforming rate of 4.83 G samples/second in terms of input raw RF sample was achieved. The resulting image quality of the proposed beamformer was compared with the software beamformer on the Verasonics Vantage system for both phantom imaging and in vivo imaging of a mouse brain. Multiple imaging schemes including B-mode, power Doppler and ULM were assessed to verify that the image quality was not compromised for speed.

Artificial Leaky Integrate-and-Fire Sensory Neuron for In-Sensor Computing Neuromorphic Perception at the Edge.

Neuromorphic perception and computing show great promise in terms of energy efficiency and data bandwidth compared to von Neumann's computing architecture. In-sensor computing allows perception information processing at the edge, which is highly dependent on the functional fusion of receptors and neurons. Here, a leaky integrate-and-fire (LIF) artificial spiking sensory neuron (ASSN) based on a NbOx memristor and an a-IGZO thin-film transistor (TFT) is successfully developed. The ASSN is fabricated mainly through simple sputter deposition processes, showing the prospect of high process compatibility and potential for integration fabrication. The device shows excellent spike encoding ability to deliver the neuromorphic information through spike rate and time-to-first spike. Moreover, in the ASSN, the a-IGZO TFT not only provides the fundamental spike signal computing function of the artificial neuron but also has NO2 gas and ultraviolet (UV) light dual sensitivity to introduce the neuromorphic perception capability. As a result, the ASSN successfully exhibits an inhibitory property under NO2 stimulation while exhibiting an excitatory state under UV light stimulation. Futhermore, self-adaption and lateral regulation circuits between different ASSNs are proposed at the edge in mimicking biological neurons' rich interconnection and feedback mechanisms. The ASSNs successfully achieve self-regulation after a huge response during a burst stimulus. In addition, the neuron transmits a more obvious output when the target-sensitive events occur through the edge internal regulation. The self-adaption and lateral regulation demonstrated in ASSN move an important step forward to in-sensor computing, which provides the potential for a multiscene perception in complex environments.

Threefold layered optical wireless network: illumination, communication, and positioning.

Visible light communication (VLC) technology has traditionally emerged as a complementary solution to radio frequency, due to its huge available bandwidth and high data rates. Relying on visible spectrum, VLC allows both illumination and communication, thus representing a green technology with reduced energy impact. However, VLC can also be exploited for localization, and thanks to its huge bandwidth it can reach very high accuracy (i.e., <0.1 m). In this paper, we deal with a VLC network intended as a fully integrated indoor system providing at the same time both illumination, communication, and positioning tasks. Three different optimization problems are presented, aiming to seek for the minimum number of white LEDs that can achieve different constraints of illumination, data rate, and localization accuracy. Different types of LEDs are considered, according to which tasks they are intended to pursue. We consider traditional white LEDs aiming to provide illumination, communication, and positioning; otherwise, we distinguish between devices designed for localization-only and communication-only. Such distinction results in different optimization problems, and related solutions, as confirmed through extensive simulation results.

Eliminating Space Scanning: Fast mmWave Beam Alignment with UWB Radios

Due to their large bandwidth and impressive data speed, millimeter-wave (mmWave) radios are expected to play a key role in the 5G and beyond (e.g., 6G) communication networks. Yet, to release mmWave’s true power, the highly directional mmWave beams need to be aligned perfectly. Most existing beam alignment methods adopt an exhaustive or semi-exhaustive space scanning, which introduces up to seconds of delays. To eliminate the need for complex space scanning, this article presents an Ultra-wideband (UWB)-assisted mmWave communication framework, which leverages the co-located UWB antennas to estimate the best angles for mmWave beam alignment. One major challenge of applying this idea in the real world is the barrier of limited antenna numbers. Commercial-Off-The-Shelf (COTS) devices are usually equipped with only a small number of UWB antennas, which are not enough for the existing algorithms to provide an accurate angle estimation. To solve this challenge, we design a novel Multi-Frequency MUltiple SIgnal Classification (MF-MUSIC) algorithm, which extends the classic MUltiple SIgnal Classification (MUSIC) algorithm to the frequency domain and overcomes the antenna limitation barrier in the spatial domain. Extensive real-world experiments and numerical simulations illustrate the advantage of the proposed MF-MUSIC algorithm. MF-MUSIC uses only three antennas to achieve an accurate angle estimation, which is a mere 0.15° (or a relative difference of 3.6%) different from the state-of-the-art 16-antenna-based angle estimation method.

Ultrahigh Capacity MMWoF Link Using 2-λ VCSEL Front-Haul Transmitter Encoded With Broadband Generalized FDM Data Stream

By employing a dual-wavelength (2-λ) vertical cavity surface emitting laser (VCSEL) directly encoded by novel quadrature amplitude modulation generalized frequency division multiplexing (QAM-GFDM) modulation schemes with optimized data capacity, a 28-GHz millimeter-wave-over-fiber (MMWoF) link is created for fusing the long-reach single-mode-fiber wired network and the beyond fifth generation (B5G) mobile wireless network without using any localized synthesizer and mixer at the remote receiver end. Detuning the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> subcarrier to 2 optimizes the electrical-to-electrical 5-GHz 64-QAM-GFDM link with an error vector magnitude (EVM) of 3.04%, a signal-to-noise ratio (SNR) of 30.3 dB and a bit error ratio (BER) of 2.1×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-13</sup> . By using this condition to perform the long-reach 50-km optical transmission, the 5-GHz 64-QAM GFDM carried by the 2-λ VCSEL exhibits an SNR of 23.8 dB, an EVM of 6.47% and a BER of 2.2×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-4</sup> . By fixing the optimized <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> subcarriers, the maximal bandwidth and raw data rate of the 64-QAM-GFDM transmission can be achieved to 6.75 GHz and 40 Gbit/s, respectively. For the wireless transmission at the remote end, the photo-mixed MMW carrier at 28-GHz exhibits a peak power of -11.4 dBm and a carrier-to-noise ratio (CNR) of 45 dB. After performing the self-heterodyne down-conversion via power envelope detection, the receiving data amplitude is improved from 26.2 to 132 mV with adding a 3-dB attenuator for impedance matching. Under the 2-m wireless transmission via horn antenna pair, the maximal bandwidth and data rate of the received 4-QAM GFDM data respectively achieve 2 GHz and 4 Gbit/s.

Firing-rate-modulated spike detection and neural decoding co-design

Objective. Translational efforts on spike-signal-based implantable brain-machine interfaces (BMIs) are increasingly aiming to minimise bandwidth while maintaining decoding performance. Developing these BMIs requires advances in neuroscience and electronic technology, as well as using low-complexity spike detection algorithms and high-performance machine learning models. While some state-of-the-art BMI systems jointly design spike detection algorithms and machine learning models, it remains unclear how the detection performance affects decoding. Approach. We propose the co-design of the neural decoder with an ultra-low complexity spike detection algorithm. The detection algorithm is designed to attain a target firing rate, which the decoder uses to modulate the input features preserving statistical invariance in long term (over several months). Main results. We demonstrate a multiplication-free fixed-point spike detection algorithm with an average detection accuracy of 97% across different noise levels on a synthetic dataset and the lowest hardware complexity among studies we have seen. By co-designing the system to incorporate statistically invariant features, we observe significantly improved long-term stability, with decoding accuracy degrading by less than 10% after 80 days of operation. Our analysis also reveals a nonlinear relationship between spike detection and decoding performance. Increasing the detection sensitivity improves decoding accuracy and long-term stability, which means the activity of more neurons is beneficial despite the detection of more noise. Reducing the spike detection sensitivity still provides acceptable decoding accuracy whilst reducing the bandwidth by at least 30%. Significance. Our findings regarding the relationship between spike detection and decoding performance can provide guidance on setting the threshold for spike detection rather than relying on training or trial-and-error. The trade-off between data bandwidth and decoding performance can be effectively managed using appropriate spike detection settings. We demonstrate improved decoding performance by maintaining statistical invariance of input features. We believe this approach can motivate further research focused on improving decoding performance through the manipulation of data itself (based on a hypothesis) rather than using more complex decoding models.

A Model of Energy and Spectral Shape for the Internal Gravity Wave Field in the Deep Sea: The Parametric IDEMIX Model

Abstract The spectral description of the energy of oceanic internal gravity waves is generally represented by the Garrett–Munk (GM) model, a function with a power-law decrease of spectral energy in wavenumber–frequency space. Besides the slopes of these power laws, the spectrum is expressed as a function of energy and a bandwidth parameter that fixes the range of vertical modes excited in the respective state. Whereas concepts have been developed and agreed upon of what processes feed the wave spectrum and what dissipates energy, there is no explanation of what shapes the spectral distribution, i.e., how the power laws come about and what sets the bandwidth. The present study develops a parametric spectral model of energy and bandwidth from the basic underlying energy balance in terms of forcing, propagation, refraction, spectral transfer, and dissipation. The model is an extension of the IDEMIX (Internal Wave Dissipation, Energy and Mixing) models where bandwidth was taken as a constant parameter. The current version of the model is restricted to single-column mode and the slopes of the spectral power laws are fixed. A coupled system of predictive equations for energy and bandwidth (for up- and downward propagating waves) results. The equations imply that bandwidth relates to energy by a power law with an exponent given by the dynamical parameters. It agrees favorably with energy, bandwidth, and slope data from previously published fits of the GM model to Argo float observations. Numerical solutions of the coupled energy–bandwidth model in stand-alone modus are presented.

TCX: A RISC Style Tensor Computing Extension and a Programmable Tensor Processor

Neural network processors and accelerators are domain-specific architectures deployed to solve the high computational requirements of deep learning algorithms. This article proposes a new instruction set extension for tensor computing, TCX, using Reduced Instruction Set Computer (RISC) instructions enhanced with variable length tensor extensions. It features a multi-dimensional register file, dimension registers, and fully generic tensor instructions. It can be seamlessly integrated into existing RISC Instruction Set Architectures and provides software compatibility for scalable hardware implementations. We present a tensor accelerator implementation of the tensor extensions using an out-of-order RISC microarchitecture. The tensor accelerator is scalable in computation units from several hundred to tens of thousands. An optimized register renaming mechanism is described that allows for many physical tensor registers without requiring architectural support for large tensor register names. We describe new tensor load and store instructions that reduce bandwidth requirements using tensor dimension registers. Implementations may balance data bandwidth and computation utilization for different types of tensor computations such as element-wise, depthwise, and matrix-multiplication. We characterize the computation precision of tensor operations to balance area, generality, and accuracy loss for several well-known neural networks. The TCX processor runs at 1 GHz and sustains 8.2 Tera operations per second using a 4,096 multiply-accumulate compute unit. It consumes 12.8 mm 2 while dissipating 0.46W/TOPs in TSMC 28-nm technology.

Information and Communication Technology in Brazilian Public Schools: A Sustainable Legacy of the Pandemic?

The present study aimed to analyze the sustainability of the post-COVID-19 pandemic Information and Communication Technology (ICT) legacy. The survey was conducted using raw secondary data from three census studies, one carried out before the pandemic and two after the return to in-person classes. The descriptive survey focused on Brazilian public schools and used a comparative intersectional design. Descriptive statistics were used to analyze the raw data. The poorest conditions in terms of the availability of technological resources were found in municipal public school systems. The amount of equipment available, bandwidth, and Internet data transmission rate in most public schools were far below desirable, despite advances in 2021 compared to 2019. Although there have been important improvements in ICT in Brazilian public schools, there was no evidence of inherited ICT resources as a legacy of the Government’s COVID-19 policies related to education. The study highlights the need for government to implement enduring public policies that guarantee the use of sustainable ICT resources to improve education, irrespective of global or national health challenges.

Model-constrained and data-driven double-supervision acoustic impedance inversion

Seismic impedance inversion is an important technique for structure identification and reservoir prediction. Model-based and data-driven impedance inversion are the commonly used inversion methods. In practice, the geophysical inversion problem is essentially an ill-posedness problem, which means that there are many solutions corresponding to the same seismic data. Therefore, regularization schemes, which can provide stable and unique inversion results to some extent, have been introduced into the objective function as constrain terms. Among them, given a low-frequency initial impedance model is the most commonly used regularization method, which can provide a smooth and stable solution. However, this model-based inversion method relies heavily on the initial model and the inversion result is band limited to the effective frequency bandwidth of seismic data, which cannot effectively improve the seismic vertical resolution and is difficult to be applied to complex structural regions. Therefore, we propose a data-driven approach for high-resolution impedance inversion based on the bidirectional long short-term memory recurrent neural network, which regards seismic data as time-series rather than image-like patches. Compared with the model-based inversion method, the data-driven approach provides higher resolution inversion results, which demonstrates the effectiveness of the data-driven method for recovering the high-frequency components. However, judging from the inversion results for characterization the spatial distribution of thin-layer sands, the accuracy of high-frequency components is difficult to guarantee. Therefore, we add the model constraint to the objective function to overcome the shortages of relying only on the data-driven schemes. First, constructing the supervisor1 based on the bidirectional long short-term memory recurrent neural network, which provides the predicted impedance with higher resolution. Then, convolution constraint as supervisor2 is introduced into the objective function to guarantee the reliability and accuracy of the inversion results, which makes the synthetic seismic data obtained from the inversion result consistent with the input data. Finally, we test the proposed scheme based on the synthetic and field seismic data. Compared to model-based and purely data-driven impedance inversion methods, the proposed approach provides more accurate and reliable inversion results while with higher vertical resolution and better spatial continuity. The inversion results accurately characterize the spatial distribution relationship of thin sands. The model tests demonstrate that the model-constrained and data-driven impedance inversion scheme can effectively improve the thin-layer structure characterization based on the seismic data. Moreover, tests on the oil field data indicate the practicality and adaptability of the proposed method.

Dual‐sensor wavefield separation in a compressed domain using parabolic dictionary learning

AbstractIn the marine seismic industry, the size of the recorded and processed seismic data is continuously increasing and tends to become very large. Hence, applying compression algorithms specifically designed for seismic data at an early stage of the seismic processing sequence helps to save cost on storage and data transfer. Dictionary learning methods have been shown to provide state‐of‐the‐art results for seismic data compression. These methods capture similar events from the seismic data and store them in a dictionary of atoms that can be used to represent the data in a sparse manner. However, as with conventional compression algorithms, these methods still require the data to be decompressed before a processing or imaging step is carried out. Parabolic dictionary learning is a dictionary learning method where the learned atoms follow a parabolic travel time move out and are characterized by kinematic parameters such as the slope and the curvature. In this paper, we present a novel method where such kinematic parameters are used to allow the dual‐sensor (or two‐components) wavefield separation processing step directly in the dictionary learning compressed domain for 2D seismic data. Based on a synthetic seismic data set, we demonstrate that our method achieves similar results as an industry‐standard FK‐based method for wavefield separation, with the advantage of being robust to spatial aliasing without the need for data preconditioning such as interpolation and reaching a compression rate around 13. Using a field data set of marine seismic acquisition, we observe insignificant differences on a 2D stacked seismic section between the two methods, whereas reaching a compression ratio higher than 15 when our method is used. Such a method could allow full bandwidth data transfer from vessels to onshore processing centres, where the compressed data could be used to reconstruct not only the recorded data sets, but also the up‐ and down‐going parts of the wavefield.

FPGA Implementation of a Deep Learning Acceleration Core Architecture for Image Target Detection

Due to the flexibility and ease of deployment of Field Programmable Gate Arrays (FPGA), more and more studies have been conducted on developing and optimizing target detection algorithms based on Convolutional Neural Networks (CNN) models using FPGAs. Still, these studies focus on improving the performance of the core algorithm and optimizing hardware structure, with few studies focusing on the unified architecture design and corresponding optimization techniques for the algorithm model, resulting in inefficient overall model performance. The essential reason is that these studies do not address arithmetic power, speed, and resource consistency. In order to solve this problem, we propose a deep learning acceleration core architecture based on FPGAs, which is designed for target detection algorithms with CNN models, using multi-channel parallelization of CNN network models to improve the arithmetic power, using scheduling tasks and intensive computation pipelining to meet the algorithm’s data bandwidth requirements and unifying the speed and area of the orchestrated computation matrix to save hardware resources. The proposed framework achieves 14 Frames Per Second (FPS) inference performance of the TinyYolo model at 5 Giga Operations Per Second (GOPS) with 30% higher running clock frequency, 2–4 times higher arithmetic power, and 28% higher Digital Signal Processing (DSP) resource utilization efficiency using less than 25% of FPGA resource usage.

High-density optical interconnects based on self-imaging in coupled waveguide arrays

Rapidly increasing demand for higher data bandwidths has motivated exploration of new communication channels based on spatially multiplexed in-fibre and on-chip coupled light guides. However, the conventionally used periodically arranged coupled waveguides display complicated light propagation patterns, ranging from quasiperiodic to nearly chaotic. Taking a different approach, we spectrally engineer interwaveguide coupling to instigate self-imaging of the input light state at the array output and thus enable construction of novel high-fidelity interconnects. Simple implementation via modulation of the interwaveguide separations makes these interconnects realizable in all fabrication platforms. Their competitive advantages are negligible crosstalk-induced information loss, high density that exceeds the current standards by an order of magnitude, and compatibility with both classical and quantum information encoding schemes. Moreover, the wavelength-dependent self-imaging opens up new possibilities for wavelength and spatial division demultiplexing. The proposed analytical designs are supported by extensive numerical simulations of silicon-on-insulator, silicon nitride and silica glass waveguide arrays, and a statistical feasibility study.

ECG data compression using the formation of QRS-complex segment bank and integer DCT-based plateau region processing

Electrocardiogram (ECG) data is essential for evaluating cardiac health conditions. Long-term ECG signal monitoring needs a considerable amount of memory for storage, impacting data bandwidth allocation. The ECG data compression is challenging in preserving significant features, using low computational resources, and achieving a higher compression ratio at lower reconstruction error. This paper proposes an innovative QRS-complex and plateau (Non-QRS) region segregation for QRS-complex subsegment bank formation and integer cosine transform-based ECG data compression. An adaptive QRS-complex subsegment template bank is formed by: (i) QRS and Non-QRS region segmentation; (ii) QRS region identification; (iii) QRS region alignment; (iv) Dc equalization and sub-template formation of the QRS region. A discrete integer cosine transform, quantization, and grouping with a significance map are used on the non-QRS segment of the ECG. Both the QRS and non-QRS regions are coded by lossless arithmetic encoding. Experiments are enumerated on the MIT BIH arrhythmia database, which validates the potential of the proposed approach by achieving an average value equal to 31.51, 0.84, and 28.57 for compression ratio, percentage-root-mean-square-difference, and quality-score, respectively. The average distortion measure for the proposed ECG compressor is less than 2%, which is within the clinically acceptable limit. The proposed method is also compared to existing state-of-the-art ECG compression techniques. It performs better in terms of compression ratio and preservation of ECG features. Additionally, this method typically requires less computational resources and is easy to implement, which is an advantage over other ECG compression methods.

Recent Advances in Optical Injection Locking for Visible Light Communication Applications

The introduction of visible light communication (VLC) technology could increase the capacity of existing wireless communication systems towards 6G networks. In practice, VLC can make good use of lighting system infrastructures to transmit data using light fidelity (Li-Fi). The use of semiconductor light sources, including light-emitting diodes (LEDs) and laser diodes (LDs) are essential to VLC technology because these devices are energy-efficient and have long lifespans. To achieve high-speed VLC links, various technologies have been utilized, including injection locking. Optical injection locking (OIL) is an optical frequency and phase synchronization technique that has been implemented in semiconductor laser systems for performance enhancement. High-performance optoelectronic devices with narrow linewidth, wide tunable emission, large modulation bandwidth and high data transmission rates are desired for advanced VLC. Thus, the features of OIL could be promising for building high-performance VLC systems. In this paper, we present a comprehensive review of the implementation of the injection-locking technique in optical communication systems. The enhancement of characteristics through OIL is elucidated. The applications of OIL in VLC systems are discussed. The prospects of OIL for future VLC systems are evaluated.

Rock brittleness index inversion method with constraints of seismic and well logs via a CNN-GRU fusion network based on the spatiotemporal attention mechanism

Rock brittleness is an important parameter for evaluating the fracability of the unconventional oil and gas reservoirs such as tight sandstone and shale oil. Compared with the laboratory measurement, rock brittleness in 3D stratum using the joint inversion of seismic and well logs is more significant for oil exploration and development, but the resolution of the inversion results is low due to the narrowly effective bandwidth of seismic data. Deep neural network (DNN) can establish the complex nonlinear mapping relationship between input and output data to improve the resolution of inversion results, but it has the problem of unstable prediction results in the case of insufficient training samples in the geophysical field. Aiming at the problem, firstly, the ratio of Young ‘s modulus to Poisson ‘s ratio is defined as the rock brittleness index, and an AVO approximation equation with brittleness index is derived, thus establishing the convolution model between the rock brittleness index and seismic data. Secondly, an objective function containing the loss of logging data, seismic data and low-frequency components obtained by the inverse distance weighted interpolation of seismic and well logs is proposed to improve the spatial constraints of seismic and well logs. Then, the spatiotemporal attention mechanism is fused with the convolutional neural network (CNN) and gate recurrent unit (GRU) network to improve the sensitivity of the network proposed to important spatiotemporal characteristics. Finally, a DNN based on the double constraints of convolution model and data is established to solve the inversion stability in the case of small samples. The inversion results of the geological model with sand body superposition and pinchout and the tight sandstone reservoir in Junggar Basin verify that the generalization and prediction accuracy of the network proposed.

Deep Multimodal Habit Tracking System: A User-adaptive Approach for Low-power Embedded Systems

The pace of population ageing is increasing and is currently becoming one of the challenges our society faces. The introduction of Cyber-Physical Systems (CPS) has fostered the development of e-Health solutions that ease the associated economic and social burden. In this work, a CPS-based solution is presented to partially tackle the problem: a Deep Multimodal Habit Tracking system. The aim is to monitor daily life activities to alert in case of life-threatening situations improving their autonomy and supporting healthy lifestyles while living alone at home. Our approach combines video and heart rate cues to accurately identify indoor actions, running the processing locally in embedded edge nodes. Local processing provides inherent protection of data privacy since no image or vital signs are transmitted to the network, and reduces data bandwidth usage. Our solution achieves an accuracy of more than 80% in average, reaching up to a 95% for specific subjects after adapting the system. Adding heart-rate information improves F1-score by 2.4%. Additionally, the precision and recall for critical actions such as falls reaches up to 93.75%. Critical action detection is crucial due to their dramatic consequences, it helps to reduce false alarms, leading to building trust in the system and reducing economic cost. Also, the model is optimized and integrated in a Nvidia Jetson Nano embedded device, reaching real-time performance below 3.75 Watts. Finally, a dataset specifically designed for indoor action recognition using synchronized video and heart rate pulses has been collected.

Cooperative Body Channel Communications for Energy-Efficient Internet of Bodies

The Internet of Bodies (IoB) is a network formed by wearable, implantable, ingestible, and injectable smart devices to collect physiological, behavioral, and structural information from the human body. Thus, the IoB technology can revolutionize the quality of human life by using these context-rich data in myriad smart-health applications. Radio frequency (RF) transceivers have been typically preferred due to their availability and maturity. However, for most RF standards (e.g., Bluetooth low energy), the highly radiative omnidirectional RF propagation (even at the lowest settings) reaches tens of meters of coverage, thereby reducing energy efficiency, causing interference and co-existence issues, and raising privacy and security concerns. On the other hand, body channel communication (BCC) confines low-power and low-frequency (10 kHz–100 MHz) signals to the human body, leading to more secure and efficient communications. Since energy efficiency is one of the critical design parameters of IoB networks, this article focuses on energy-efficient orthogonal body channel access (OBA) and non-OBA (NOBA) schemes with and without cooperation. To this aim, three main BCC topologies are presented: 1) point-to-point channel; 2) medium access channel; and 3) broadcast channel. These topologies are then used as building blocks to create IoB networks relying on OBA and NOBA schemes for downlink (DL) and uplink (UL) traffic. For all schemes and traffic directions, optimal transmit power and phase time allocations are derived in closed-form, which is essential to reduce energy consumption by eliminating computational power. The closed-form expressions are further leveraged to obtain maximum network size as a function of data rate requirement, bandwidth, and hardware parameters.

AOEHO: A New Hybrid Data Replication Method in Fog Computing for IoT Application.

Recently, the concept of the internet of things and its services has emerged with cloud computing. Cloud computing is a modern technology for dealing with big data to perform specified operations. The cloud addresses the problem of selecting and placing iterations across nodes in fog computing. Previous studies focused on original swarm intelligent and mathematical models; thus, we proposed a novel hybrid method based on two modern metaheuristic algorithms. This paper combined the Aquila Optimizer (AO) algorithm with the elephant herding optimization (EHO) for solving dynamic data replication problems in the fog computing environment. In the proposed method, we present a set of objectives that determine data transmission paths, choose the least cost path, reduce network bottlenecks, bandwidth, balance, and speed data transfer rates between nodes in cloud computing. A hybrid method, AOEHO, addresses the optimal and least expensive path, determines the best replication via cloud computing, and determines optimal nodes to select and place data replication near users. Moreover, we developed a multi-objective optimization based on the proposed AOEHO to decrease the bandwidth and enhance load balancing and cloud throughput. The proposed method is evaluated based on data replication using seven criteria. These criteria are data replication access, distance, costs, availability, SBER, popularity, and the Floyd algorithm. The experimental results show the superiority of the proposed AOEHO strategy performance over other algorithms, such as bandwidth, distance, load balancing, data transmission, and least cost path.