Verification Platform Research Articles

A plan verification platform for online adaptive proton therapy using deep learning-based Monte–Carlo denoising

Background PurposeThis study focused on developing a fast Monte Carlo (MC) plan verification platform via a deep learning (DL)-based denoising approach. It can maintain the MC dose calculation accuracy while significantly reducing the computation time. We also investigated its potential applications for online adaptive proton therapy (APT). MethodsFirst, we modeled an MC platform for proton therapy using the beam data library (BDL) required for treatment planning systems and then tested it with measured data. To accelerate the dose calculation, a dl-based denoising model with deep ResNet-deconvolution networks was developed. It was trained on the MC dose distribution of tumor sites obtained from 52 patients. The input MC dose distribution was with 1 × 106 simulated protons and the reference was 1 × 108. Fivefold cross-validation was performed. ResultsComparing the MC model with measured data, the range agreement (point-to-point difference) was better than 0.85 mm, and the lateral dose profile difference was below 2.41 %. For the denoising approach, we found a significant improvement in the dose volume histogram (DVH) for predicted images compared with input images. The root mean squared error (RMSE) for predicted versus reference images was 3.94 times lower than that of the input versus reference images. Moreover, for the gamma passing rate (3 mm/3%), the predicted versus reference images have an average of 99 %, much higher than the 82 % of the input versus reference images. The MC model successfully denoised the test dose map (high noise) to approach the reference (low noise). The elapsed time can be reduced to < 60 s (simulation time [high noise] + predicted time), much lower than the simulation time of a low noise dose map (e.g., >100 min of simulation of 1 + E8 particles). ConclusionsWe propose an analogous end-to-end fast plan verification platform using the combination of MC and DL methods. The platform yields dose calculation accuracy similar to MC codes while significantly reducing the elapsed time and can be used for online APT as an alternative to online plan verification.

Intelligent Tracking Technology of Light Source Based on Feedforward Inverse Compensation Control

In the construction of a photovoltaic power station, the effect of ray tracing directly affects the efficiency of power generation. In order to effectively control the tracking photovoltaic bracket and present the actual situation of the tracking bracket truly, intuitively and conveniently, a roamable photovoltaic tracking bracket control system is designed in this study. The system provides assistant decision-making for operators, and can remotely control the tracking support in real-time. It can also work independently according to the set parameters to realize the functions of the sun position calculation, tracking angle calculation, and tracking command output, and can communicate with the monitoring terminal. During the experimental test, the computer resource occupation is low, the operation is stable and reliable, and the monitoring terminal can run with a relatively smooth frame number. According to the system architecture mentioned in this paper, the verification platform is built, and the effectiveness of the photovoltaic tracking bracket control system is confirmed. The control system of the photovoltaic tracking bracket designed in this paper can effectively solve the problem of solar tracking accuracy of the photovoltaic power station, and play an important role in improving the power generation efficiency of the photovoltaic power station. At the same time, it can provide a reference for the same industry in light source tracking technology.

A multi-agent reinforcement learning-based collaborative jamming system: Algorithm design and software-defined radio implementation

In multi-agent confrontation scenarios, a jammer is constrained by the single limited performance and inefficiency of practical application. To cope with these issues, this paper aims to investigate the multi-agent jamming problem in a multi-user scenario, where the coordination between the jammers is considered. Firstly, a multi-agent Markov decision process (MDP) framework is used to model and analyze the multi-agent jamming problem. Secondly, a collaborative multi-agent jamming algorithm (CMJA) based on reinforcement learning is proposed. Finally, an actual intelligent jamming system is designed and built based on software-defined radio (SDR) platform for simulation and platform verification. The simulation and platform verification results show that the proposed CMJA algorithm outperforms the independent Q-learning method and provides a better jamming effect.

The Design and Implementation of Geospatial Information Verification Middle Platform for Natural Resources Government Affairs

Geospatial Information Verification Mid-End Platform for Natural Resource Administration is designed in response to issues such as repeated development, low scalability, and inconsistent verification rules in existing approval and supervision application systems. We first discussed the architecture of the middle platform and micro-services and also examined the business requirements. Secondly, we presented the architecture of the spatial information verification platform. Finally, the application method in the construction land approval business is introduced. Practical applications proved that the spatial information verification platform is highly scalable and maintainable, with reusable business components and data services for a variety of government affairs application systems.

Design of Image Acquisition System Based on Visual Intelligent Sensor and Video Signal Processing

With the rapid development and iteration of CMOS image sensor and other related technologies, in addition to the more advanced technology, the corresponding sensor also integrates the image signal processing system, so it is a leap for the image acquisition system. Based on this, this paper will take the visual intelligent sensor produced and developed by a semiconductor company as the hardware to complete the hardware design of the image acquisition and transmission system. In addition to the core processor of the system, this paper will also use audio and video processing chips and image data processing chips for collaborative analysis, so as to ensure the processing capacity and processing quality of the image acquisition system at the hardware design level. Compared with the traditional system, at the corresponding system software level, in order to further improve the quality of video signal processing, this paper creatively proposes a switch weighted median filter denoising algorithm, which has a significant impact on the processing of random impulse noise in video and the overall image filtering. At the same time, the algorithm also protects the edge details of the video image, thus improving the authenticity of the image and video. Based on this, this paper has built a verification platform based on supporting hardware and corresponding algorithms. Through hardware debugging and system operation analysis, when the operating frequency of the visual intelligent sensor is 100 MHz, the set acquisition depth is 10 bits, and the corresponding system collects data at a rate of 251 fps per second. In terms of the corresponding performance, the iteration number of the algorithm proposed in this paper is about 40% more than that of the traditional algorithm in unit time. In terms of the corresponding algorithm performance, the algorithm proposed in this paper is about 30% higher than the traditional algorithm. In terms of the efficiency of the corresponding image and video acquisition system, the algorithm proposed in this paper is about 44% higher than the traditional algorithm. Based on this, the system proposed in this paper has obvious advantages over the traditional algorithm.

Entanglement-Enhanced Quantum Metrology in Colored Noise by Quantum Zeno Effect.

In open quantum systems, the precision of metrology inevitably suffers from the noise. In Markovian open quantum dynamics, the precision can not be improved by using entangled probes although the measurement time is effectively shortened. However, it was predicted over one decade ago that in a non-Markovian one, the error can be significantly reduced by the quantum Zeno effect (QZE) [Chin, Huelga, and Plenio, Phys. Rev. Lett. 109, 233601 (2012)PRLTAO0031-900710.1103/PhysRevLett.109.233601]. In this work, we apply a recently developed quantum simulation approach to experimentally verify that entangled probes can improve the precision of metrology by the QZE. Up to n=7 qubits, we demonstrate that the precision has been improved by a factor of n^{1/4}, which is consistent with the theoretical prediction. Our quantum simulation approach may provide an intriguing platform for experimental verification of various quantum metrology schemes.

WhyMP, a formally verified arbitrary-precision integer library

Arbitrary-precision integer libraries such as GMP are a critical building block of computer algebra systems. GMP provides state-of-the-art algorithms that are intricate enough to justify formal verification. In this paper, we present a C library that has been formally verified using the Why3 verification platform in about four person-years. This verification deals not only with safety, but with full functional correctness. It has been performed using a mixture of mechanically checked handwritten proofs and automated theorem proving. We have implemented and verified a nontrivial subset of GMP's algorithms, including their optimizations and intricacies. Our library provides the same interface as GMP and is almost as efficient for smaller inputs. We detail our verification methodology and the algorithms we have implemented, and include some benchmarks to compare our library with GMP.

Design and implementation of a dynamic system simulation framework for plasma control system verification platform

The plasma control system (PCS) is a key part in tokamak operations, which requires test and verification. Dynamic system simulation tools have been widely utilized to build a simulation environment to verify the design of plasma control systems as well as other parts of tokamak systems under various operation scenarios, save the time and cost of real discharges, improve the efficiency of deployment and reduce risks. To provide a simulation platform based on open-source software as part of the infrastructure of the PCS-VP (Verification Platform) of the China Fusion Engineering Test Reactor (CFETR), a framework named DSSim (Dynamic System Simulation) is proposed. It is an environment for dynamic system simulation based on Python, which enables users to build and simulate hierarchical block diagram models with interconnected systems that corresponds to different dynamic systems. Solutions for special tasks that helps improve the accuracy of simulation like flattening the model hierarchy, scheduling system execution order and solving continuous systems are implemented and will be automatically invoked in different phases of simulation. A GUI client with the DSSim framework built in is developed to allow for constructing and simulating block diagram models in a more user-friendly way. A model of the vacuum field system of the Experimental and Advanced Superconducting Tokamak (EAST) is built and simulated with DSSim and the result is compared with that of the same model in MATLAB/Simulink to test the framework's precision and usability.

Blockchain-Based Reliable Traceability System for Telecom Big Data Transactions

Telecom big data generated by telecom networks have a high economic value. Thus, telecom operators actively explore telecom big data transactions methods to minimize the possibility of leaking users’ privacy. The existing solutions do not allow the data sets to leave the database, instead only allow the buyers to send data mining algorithms to the telecom operator’s platform for training. However, this centralized platform has a high risk of tampering. In addition, the currently existing solutions cannot be used to accurately and quickly trace the information of telecom big data transactions. To address these limitations, we propose a blockchain-based reliable traceability system for telecom big data transactions using smart contracts and the InterPlanetary File System. Two types of smart contracts are developed to store transaction information for tracing. Access control strategies and a reapproval prevention strategy are designed for ensuring the safe operation of the system and avoiding the problem of favoritism and fraud. We use Ethereum as a verification platform to develop and evaluate this system. The implementation of functions, such as purchasing data sets, sending algorithms, obtaining results, and tracing transactions in the smart contract and the implementation of the proposed strategies are verified. The results demonstrate that the performance of the proposed system is better than the existing solutions, and the traceability response time is improved to the order of seconds, so as to realize the safe and efficient traceability of telecom big data transactions. In addition, Ethereum and Hyperledger Fabric v0.6 were discussed to provide insights for future development.

Finite-Time Distributed Attitude Synchronization for Multiple Spacecraft With Angular Velocity and Input Constraints

The attitude synchronization problem for multiple spacecraft with angular velocity and input constraints is investigated in this article, under the mild assumptions that the leader’s states can reach each follower through a path and the communications between followers are bidirectional. An adaptive finite-time distributed observer is designed to estimate the leader’s states for each follower spacecraft, which has the superiority in the fully distributed that the communication topology or some other global information is not required, and the finite-time convergence can be guaranteed. Furthermore, the novel auxiliary systems are first proposed to avoid the angular velocity and input constraints being violated, while the finite-time command filtered backstepping controller is designed to track the leader’s attitude motion. The remarkable features of the developed algorithm are the global finite-time attitude consensus of multiple spacecraft, with the constraints satisfied. Moreover, the efficiency of the proposed method is illustrated by numerical simulations and real-time platform verification.

Positioning of Quadruped Robot Based on Tightly Coupled LiDAR Vision Inertial Odometer

Quadruped robots, an important class of unmanned aerial vehicles, have broad potential for applications in education, service, industry, military, and other fields. Their independent positioning plays a key role for completing assigned tasks in a complex environment. However, positioning based on global navigation satellite systems (GNSS) may result in GNSS jamming and quadruped robots not operating properly in environments sheltered by buildings. In this paper, a tightly coupled LiDAR vision inertial odometer (LVIO) is proposed to address the positioning inaccuracy of quadruped robots, which have poor mileage information obtained though legs and feet structures only. With this optimization method, the point cloud data obtained by 3D LiDAR, the image feature information obtained by binocular vision, and the IMU inertial data are combined to improve the precise indoor and outdoor positioning of a quadruped robot. This method reduces the errors caused by the uniform motion model in laser odometer as well as the image blur caused by rapid movements of the robot, which can lead to error-matching in a dynamic scene; at the same time, it alleviates the impact of drift on inertial measurements. Finally, the quadruped robot in the laboratory is used to build a physical platform for verification. The experimental results show that the designed LVIO effectively realizes the positioning of four groups of robots with high precision and strong robustness, both indoors or outdoors, which verify the feasibility and effectiveness of the proposed method.

Numerical simulation and experimental verification of the front air intake system of heavy trucks based on fluid-solid coupling and discrete phase models

The research object in this study was the front air intake (FAI) system of heavy trucks. Dust with various particle sizes was used to emulate the actual working conditions of a heavy-truck forward gas flow system and improve on research that considered only the internal flow field. On this basis, various changes in the flow field caused by the feedback effect of the pipe wall on the flow field were considered. Two-way fluid–solid coupling and discrete phase models were constructed. The models included the FAI pressure field, velocity field, other flow field characteristics, and filtration efficiency. The pressure drop, dust particle velocity and deposition, and the output of its filtration efficiency were also determined. A numerical simulation was conducted for experimental verification, including the overall pressure drop of the front intake system of the heavy truck and the filtration efficiency for three different particle sizes. The filtration statuses of various sizes of dust particles were found, and the rationality of the FAI system structure was examined and evaluated. The established simulation model can provide a tool for studying the flow characteristics and working performance of an FAI design and provide a verification platform for design optimization.

Infrared and Visible Image Fusion with Deep Neural Network in Enhanced Flight Vision System

The Enhanced Flight Vision System (EFVS) plays a significant role in the Next-Generation low visibility aircraft landing technology, where the involvement of optical sensing systems increases the visual dimension for pilots. This paper focuses on deploying infrared and visible image fusion systems in civil flight, particularly generating integrated results to contend with registration deviation and adverse weather conditions. The existing enhancement methods push ahead with metrics-driven integration, while the dynamic distortion and the continuous visual scene are overlooked in the landing stage. Hence, the proposed visual enhancement scheme is divided into homography estimation and image fusion based on deep learning. A lightweight framework integrating hardware calibration and homography estimation is designed for image calibration before fusion and reduces the offset between image pairs. The transformer structure adopting the self-attention mechanism in distinguishing composite properties is incorporated into a concise autoencoder to construct the fusion strategy, and the improved weight allocation strategy enhances the feature combination. These things considered, a flight verification platform accessing the performances of different algorithms is built to capture image pairs in the landing stage. Experimental results confirm the equilibrium of the proposed scheme in perception-inspired and feature-based metrics compared to other approaches.

EnviroCoin: A Holistic, Blockchain Empowered, Consensus-Based Carbon Saving Unit Ecosystem

The capacity of the greenhouse gas recycling mechanism in nature has long reached its limit, resulting in a sharply increasing trend in the marginal cost of recycling one unit of human-produced carbon and other greenhouse gas emissions. Externalities associated with the marginal cost of greenhouse gas emissions affect health, climate, and the economy, which have urged global authorities and governments to request urgent actions to slow down the production of such pollutants. Nonetheless, without public awareness and a holistic mechanism to monetise the impact of pollutants, a universal strategy to reduce greenhouse gas emissions is condemned to failure. This paper presents an overview of emerging technologies that can come together to offer an innovative solution for monetising, incentivising and realising the reduction of greenhouse gas emissions. Through a brief review of the literature, an innovative ecosystem is proposed for the first time, accounting for a unified platform for carbon verification, validation and monetisation, which can be adopted as a business model to validate and monetise the amount of incentivising businesses and people for carbon saving on a decentralised blockchain platform.

Study on the time and duration of restart on the AC/DC interconnected system based on dynamic energy

Concerning the difficulty in determining the restart strategy for AC/DC interconnected systems, this paper proposes a method of calculating the optimal restart strategy for AC/DC interconnected systems based on dynamic energy. First, a dynamic energy function that characterises the stability of system is constructed. Then, the analytical expressions of the dynamic energy function are calculated separately for the deionisation stage, the restart stage, and the alpha retard stage of the entire restart process. On this basis, the variation rate of the system dynamic energy is defined as the energy accumulation rate, which quantifies the accumulation or consumption of dynamic energy during the restart process, and facilitates detailed analysis of the effects of the restart time and restart duration on the stability of system. Then, a method to calculate the optimal restart time is proposed with the goal of minimising the dynamic energy accumulated in the system. Finally, hardware-in-the-loop tests are carried out on the RT-LAB platform for simulation verification. The experimental results show that the dynamic energy function constructed in this paper can reflect the stability of system. Using the proposed optimal restart strategy can reduce the accumulation of dynamic energy and improve the stability of system.

The Application of AI Technology in GPU Scheduling Algorithm Optimization

With the rapid development of integrated circuit technology, GPU computing capabilities continue to improve. Due to the continuous improvement and improvement of GPU programming capabilities, functions, and performance, GPUs have been widely used in the field of high-tech general-purpose computers. This article is aimed at studying the optimization of GPU scheduling algorithm based on AI technology. Through a combination of theoretical analysis and simulation experiments, the concepts of artificial intelligence technology and GPU scheduling are explained, and the impact of GPU architecture and GPGPU load on the energy efficiency of GPGPU is explained. On the basis of comprehensive analysis of GPU cluster characteristics, a new GA-TP scheduling algorithm based on genetic algorithm was designed, and based on the energy efficiency of the cluster, a simulation verification platform was built for the accuracy of simulation. Experimental results show that the acceleration rate of the GA-TP algorithm is significantly lower than that of the HEFT algorithm, the average acceleration rate is reduced by nearly 25%, and the scheduling efficiency of the GA-TP algorithm is higher.

FastSim: A Fast Simulation Framework for High-Level Synthesis

High-level synthesis (HLS) is a well-established framework used to translate high-level algorithmic behaviors into hardware designs. Despite the enduring research efforts, a major prevailing bottleneck of HLS is the large gap between the design and verification processes. Presently, register transfer level (RTL) simulation is the primary platform used for HLS design verification. Although most of the state-of-the-art RTL simulators provide an abstracted user-friendly platform for verification, they are undesirably slow and sometimes incomprehensible to non-field-programmable gate array experts to debug. The alternative software simulators (C simulation) introduced by commercial HLS tools render faster simulation, but are not cycle accurate and are not capable to estimate design performance. In this article, we introduce an automatic cycle-accurate simulation tool, FastSim, that manipulates certain unique features of HLS design to extract a concise, well-indented, and debug-friendly C behavior from the synthesized RTL. Our simulation tool ensures RTL correctness, provides cycle accuracy, accurate performance estimation, and renders on an average around 300 times faster simulation compared to RTL simulators and comparable performance to that of software C simulators.

Verification Platform of SOC Estimation Algorithm for Lithium-Ion Batteries of Electric Vehicles

As one of the core technologies of electric vehicles (EVs), the state of charge (SOC) estimation algorithm of lithium-ion batteries is directly related to the performance of the battery management system (BMS). Before EVs are put into the market, the SOC estimation algorithm must be tested and verified to ensure the reliability of the BMS and the safe operation of EVs. Therefore, this paper establishes a lithium-ion batteries’ SOC estimation algorithm verification platform for the comprehensive performance evaluation and verification of the new SOC estimation algorithm. In addition, there are two schemes, including real-time SOC estimation verification and offline SOC estimation verification can be selected, which improve the reliability and efficiency of verification. Firstly, the design idea of the verification platform (the research and development purpose, functional requirements, and the overall design scheme) is introduced in detail. Secondly, the modular design idea is used to design the hardware structure of the verification platform, which mainly includes the BMS host module, BMS slave module, battery charger module, and electronic load module. Finally, the software system, including the communication architecture, the SOC reference standard and evaluation indexes of the algorithm, and the upper computer function and implementation is designed to realize the functions of the verification platform.

Modeling and analysis of a three-degree-of-freedom piezoelectric vibration energy harvester for broadening bandwidth

This study proposes a multi-frequency response piecewise-linear piezoelectric vibration energy harvester (MFRPLP-VEH) by combining the linear multi-frequency resonance and nonlinear vibration bandwidth broadening methods to improve the working frequency bandwidth and environmental robustness of the piezoelectric vibration energy harvester. A theoretical model is established based on the electromechanical coupling and the dynamic response of the MFRPLP-VEH. The energy harvesting performance and broadening width efficiency of the MFRPLP-VEH were obtained through an experimental verification platform, where the resonant frequencies of the three beam are 28.9, 33.6, and 38.6 Hz, respectively. Furthermore, the operating frequency range is widened by 90.9% at an external excitation acceleration of 10 m/s2. The energy generated by the MFRPLP-VEH is 194% of the energy generated by its linear counterpart under the same excitation conditions. The numerical and experimental results verify the accuracy of the theoretical model and the broadband working frequency range of the MFRPLP-VEH.

Development of an open-source regional data assimilation system in PEcAn v. 1.7.2: application to carbon cycle reanalysis across the contiguous US using SIPNET

Abstract. The ability to monitor, understand, and predict the dynamics of the terrestrial carbon cycle requires the capacity to robustly and coherently synthesize multiple streams of information that each provide partial information about different pools and fluxes. In this study, we introduce a new terrestrial carbon cycle data assimilation system, built on the PEcAn model–data eco-informatics system, and its application for the development of a proof-of-concept carbon “reanalysis” product that harmonizes carbon pools (leaf, wood, soil) and fluxes (GPP, Ra, Rh, NEE) across the contiguous United States from 1986–2019. We first calibrated this system against plant trait and flux tower net ecosystem exchange (NEE) using a novel emulated hierarchical Bayesian approach. Next, we extended the Tobit–Wishart ensemble filter (TWEnF) state data assimilation (SDA) framework, a generalization of the common ensemble Kalman filter which accounts for censored data and provides a fully Bayesian estimate of model process error, to a regional-scale system with a calibrated localization. Combined with additional workflows for propagating parameter, initial condition, and driver uncertainty, this represents the most complete and robust uncertainty accounting available for terrestrial carbon models. Our initial reanalysis was run on an irregular grid of ∼ 500 points selected using a stratified sampling method to efficiently capture environmental heterogeneity. Remotely sensed observations of aboveground biomass (Landsat LandTrendr) and leaf area index (LAI) (MODIS MOD15) were sequentially assimilated into the SIPNET model. Reanalysis soil carbon, which was indirectly constrained based on modeled covariances, showed general agreement with SoilGrids, an independent soil carbon data product. Reanalysis NEE, which was constrained based on posterior ensemble weights, also showed good agreement with eddy flux tower NEE and reduced root mean square error (RMSE) compared to the calibrated forecast. Ultimately, PEcAn's new open-source regional data assimilation framework provides a scalable workflow for harmonizing multiple data constraints and providing a uniform synthetic platform for carbon monitoring, reporting, and verification (MRV) as well as accelerating terrestrial carbon cycle research.