Backward Path Research Articles

Knowledge diffusion paths of blockchain domain: the main path analysis

Blockchain technology, as a disruptive technology, has received widespread attention in the past few years from all over the world, leading to rapid growth in research outputs. This paper adopts a quantitative method, the main path analysis, to comprehensively and systematically investigate the development trajectories of blockchain. Four different main paths, the global main path, the forward local main path, the backward local main path and the key-route main path are conducted simultaneously. By analyzing these various paths, on the one hand, this paper finds that papers on paths focus on two aspects, cryptocurrencies and blockchain-based applications. On the other hand, this paper discovers several major research areas of blockchain, including internet of things (IoT), healthcare, energy industry, voting, insurance and supply chain management. At the same time, this paper further analyzes the research hotspots, as well as the development trajectories of blockchain in the areas of IoT, healthcare and supply chain management by using the key-route main path analysis. This paper is conductive for both the new and experienced researchers to identify some influential papers and grasp the knowledge diffusion paths in these domains.

Robot Path Planning Method Based on Level Set

For the problem of robot path planning under the action of external force field, the directionality of outward force can promote and hinder the movement of the robot. The continuous path planning method can break through the traditional robot path planning algorithm based on grid search. Limit, effectively utilize the external force field existing in the space, and improve the numerical implementation method to ensure the feasibility of the planned path in the strong external force field. Based on the Level Set method, the path planning problem is defined. The particle tracking of the robot is transformed into the numerical evolution of the curve. The optimal time path is obtained by solving the Hamilton-Jacques equation. The numerical calculation accuracy of the improved backward path tracking is guaranteed. The feasibility of planning the path. The simulation results show that the algorithm can effectively deal with a variety of complex external force fields and maintain the path in a strong external force field.

Reinforcement Learning-Based Collision Avoidance and Optimal Trajectory Planning in UAV Communication Networks

In this paper, we propose a reinforcement learning approach of collision avoidance and investigate optimal trajectory planning for unmanned aerial vehicle (UAV) communication networks. Specifically, each UAV takes charge of delivering objects in the forward path and collecting data from heterogeneous ground IoT devices in the backward path. We adopt reinforcement learning for assisting UAVs to learn collision avoidance without knowing the trajectories of other UAVs in advance. In addition, for each UAV, we use optimization theory to find out a shortest backward path that assures data collection from all associated IoT devices. To obtain an optimal visiting order for IoT devices, we formulate and solve a no-return traveling salesman problem. Given a visiting order, we formulate and solve a sequence of convex optimization problems to obtain line segments of an optimal backward path for heterogeneous ground IoT devices. We use analytical results and simulation results to justify the usage of the proposed approach. Simulation results show that the proposed approach is superior to a number of alternative approaches.

An operator derivation of the Feynman–Vernon theory, with applications to the generating function of bath energy changes and to an-harmonic baths

We present a derivation of the Feynman–Vernon approach to open quantum systems in the language of super-operators. We show that this gives a new and more direct derivation of the generating function of energy changes in a bath, or baths. As found previously, this generating function is given by a Feynman–Vernon-like influence functional, with only time shifts in the kernels coupling the forward and backward paths. We further show that the new approach extends to an-harmonic and possible non-equilibrium baths, provided that the interactions are bi-linear, and that the baths do not interact between themselves. Such baths are characterized by non-trivial cumulants. Every non-zero cumulant of certain environment correlation functions is thus a kernel in a higher-order term in the Feynman–Vernon action.

Frictional behavior of sandstone fractures under forward-backward pre-peak cyclic loading

The objective of this study is to determine the effect of cyclic loading under pre-peak condition on shearing behavior of fractures in Phra Wihan sandstone, primarily to improve an understanding of the stability conditions of slope embankments along roadways and railways in the north of Thailand where seismic activities have often occurred. The fractures were artificially made in the laboratory by tension inducing method and cyclically sheared under forward to fully backward loading paths with constant normal stresses between 1 and 4 MPa. Two cyclic loading conditions were used on separate sets of specimens: constant stress amplitude and constant displacement amplitude. Fifty shear cycles were applied. The results indicated that the pre-peak cyclic loading under both loading conditions slightly reduce shear strengths and stiffness of the sandstone fractures due to the degradation of the second order fracture asperities. Fracture roughness notably reduced particularly under large shear stress and displacement amplitudes due to the deposition and packing of rock power. The subsequent monotonic loading performed after cyclic loading showed further reduction of fracture roughness due to the degradations of the first order asperities.

From software architecture to analysis models and back: Model-driven refactoring aimed at availability improvement

With the ever-increasing evolution of software systems, their architecture is subject to frequent changes due to multiple reasons, such as new requirements. Appropriate architectural changes driven by non-functional requirements are particularly challenging to identify because they concern quantitative analyses that are usually carried out with specific languages and tools. A considerable number of approaches have been proposed in the last decades to derive non-functional analysis models from architectural ones. However, there is an evident lack of automation in the backward path that brings the analysis results back to the software architecture. In this paper, we propose a model-driven approach to support designers in improving the availability of their software systems through refactoring actions. The proposed framework makes use of bidirectional model transformations to map UML models onto Generalized Stochastic Petri Nets (GSPN) analysis models and vice versa. In particular, after availability analysis, our approach enables the application of model refactoring, possibly based on well-known fault tolerance patterns, aimed at improving the availability of the architectural model. We validated the effectiveness of our approach on an Environmental Control System. Our results show that the approach can generate: (i) an analyzable availability model from a software architecture description, and (ii) valid software architecture models back from availability models. Finally, our results highlight that the application of fault tolerance patterns significantly improves the availability in each considered scenario. The approach integrates bidirectional model transformation and fault tolerance techniques to support the availability-driven refactoring of architectural models. The results of our experiment showed the effectiveness of the approach in improving the software availability of the system.

Forward and backward motions path following controls of a truck-trailer with references on the head-truck and on the trailer

This paper presents new control designs and implementations of truck-trailer path following in forward and backward motions. The path following controls are designed in two modes, which are the controls with reference on the head-truck (RH-control) and with reference on the trailer (RT-control). Both modes aim to converge the distance and orientation errors of the head-truck as well as the trailer with respect to the desired path to zero. Using the designed controls, the asymptotic stabilities of the equilibrium points (i.e., error points equal to zeros) are analyzed using the Lyapunov method. The performances of RH-and RT-controls in controlling the truck-trailer are compared for forward and backward motions. The simulation results show that the RT-controls perform better than the RH-controls and the RT-controls can be applied for a curve-path following in both forward and backward directions. The experimental results of a prototype truck-trailer show the effectiveness of the proposed controls.

Optimized highway deep learning network for fast single image super-resolution reconstruction

With the success of the deep residual network for image recognition tasks, the residual connection or skip connection has been widely used in deep learning models for various vision tasks, including single image super-resolution (SISR). Most existing SISR approaches pay particular attention to residual learning, while few studies investigate highway connection for SISR. Although skip connection can help to alleviate the vanishing gradient problem and enable fast training of the deep network, it still provides the coarse level of approximation in both forward and backward propagation paths and thus challenging to recover high-frequency details. To address this issue, we propose a novel model for SISR by using highway connection (HNSR), which composes of a nonlinear gating mechanism to further regulate the information. By using the global residual learning and replacing all local residual learning with designed gate unit in highway connection, HNSR has the capability of efficiently learning different hierarchical features and recovering much more details in image reconstruction. The experimental results have validated that HNSR can provide not only improved quality but also less prone to a few common problems during training. Besides, the more robust and efficient model is suitable for implementation in real-time and mobile systems.

Volumetric error measurement and compensation of three-axis machine tools based on laser bidirectional sequential step diagonal measuring method

This paper proposes an approach to the measurement, modeling, and compensation of the volumetric errors for three-axis machine tools, using laser bidirectional sequential step diagonal measurement. Disparate measuring tracks are specially arranged for forward and backward paths, and the conforming error decoupling method is demonstrated. By decoupling, all the geometric errors which can result in volumetric errors are distinguished simultaneously, including translational and angular errors. In comparison with the traditional unidirectional measuring method, the proposed bidirectional method distinguishes more geometric errors (the angular errors) by measuring the same four body diagonals. Uncertainty analysis based on the Monte Carlo simulation was conducted, followed by experimental validation on a vertical machining center. The result of the experiment indicates that the diagonal systematic deviation of positioning is reduced by 90% after volumetric compensation.

Exposure to particulate matter and gaseous pollutants during cab commuting in Nur-Sultan city of Kazakhstan

Exposure to particulate matter, carbon dioxide, and carbon monoxide inside a car during commuting were determined during the period October–November 2017 in Nur-Sultan, Kazakhstan. We choose to follow five bus routes (#10, 18, 19, 37 and 53) that cover the majority of the city's area. CO (ppm), CO2 (ppm) and PM1, PM2.5, PM4, and PM10 mass concentration (μg/m3) were measured in this study. PM1 was found to be the largest fraction of all sizes of PM. The mean PM1 concentrations along the forward (backward) paths for each of the five bus routes were measured as 11 ± 14 (11 ± 7), 14 ± 8 (16 ± 6), 25 ± 11 (21 ± 14), 23 ± 8 (15 ± 6) and 76 ± 26 (99 ± 55) μg/m3, respectively. Average CO concentrations among five bus routes (#10, 18, 19, 37 and 53) along the forward (backward) paths were 0.67 ± 0.16 (0.78 ± 0.17), 0.7 ± 0.16 (0.53 ± 0.32), 1.04 ± 0.01 (2.3 ± 0.95), 2.67 ± 1.3 (2.03 ± 0.41), 3.54 ± 3.57 (2.17 ± 0.37) ppm. The mean PM1/PM2.5 and PM2.5/PM10 ratios were 0.96 and 0.91, respectively. Nur-Sultan could be an example for those cities that are under major developments and candidates to be green cities by showing the exposures to atmospheric pollutants across the city. Those cities that are developing themselves as tourist attractions should create maps of PM exposures along major urban routes, and route traffic to exclude tourist areas from being hotspots.

Ghost radiance suppression using backward ray path analysis for a Risley prism scanner of an active laser ranging system.

The LAser raDAR (LADAR) system designed in this study shows a ghost pattern around the object image when operated. The system contains 4 wedge prisms, each with different rotational directions and speeds. Therefore, an efficient and thorough analysis method was established. Ray path analysis was performed, and categorized, for every instantaneous case sampled using a backward ray tracing method. The rays' flux and directions were accumulated according to their path histories. This backward ray tracing was performed repeatedly with different neutral density (ND) filter orientations, until no measurable ghost radiance remained in the field of regard (FOR): a tilt angle of 5°. The ND filter was replaced with a mechanical vignette. Subsequently, the ghost flux was 21% of the total accumulated point cloud, coinciding with the actual measurement of 19%. The final image has significantly improved resolution and shows no ghost reflections where they were previously.

Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning

In multi-agent reinforcement learning, it is essential for agents to learn communication protocol to optimize collaboration policies and to solve unstable learning problems. Existing methods based on actor-critic networks solve the communication problem among agents. However, these methods have difficulty in improving sample efficiency and learning robust policies because it is not easy to understand the dynamics and nonstationary of the environment as the policies of other agents change. We propose a method for learning cooperative policies in multi-agent environments by considering the communications among agents. The proposed method consists of recurrent neural network-based actor-critic networks and deterministic policy gradients to centrally train decentralized policies. The actor networks cause the agents to communicate using forward and backward paths and to determine subsequent actions. The critic network helps to train the actor networks by sending gradient signals to the actors according to their contribution to the global reward. To address issues with partial observability and unstable learning, we propose using auxiliary prediction networks to approximate state transitions and the reward function. We used multi-agent environments to demonstrate the usefulness and superiority of the proposed method by comparing it with existing multi-agent reinforcement learning methods, in terms of both learning efficiency and goal achievements in the test phase. The results demonstrate that the proposed method outperformed other alternatives.

A smoothed raster scanning trajectory based on acceleration-continuous B-spline transition for high-speed Atomic Force Microscopy

The scanning speed of atomic force microscopes (AFMs) is typically limited by the frequency of the triangular trajectory used in generating the raster scan. This is because the higher harmonics of the triangular trajectory have a tendency to excite the mechanical resonances of the nanopositioners incorporated in the AFM; thereby, introducing significant positioning errors. To address this issue, this article proposes a novel scanning trajectory smoothing method to enable high-speed raster scanning. The proposed method utilizes the acceleration-continuous B-spline to replace the backward path of the triangular trajectory for the fast axis. As a result, the advantage of uniform sampling along the forward path is preserved. The trajectory generation process is described in detail. A hysteresis compensation method is employed to improve the tracking performance of the scanner. Experiments conducted on a commercial piezoelectric tube scanner are presented to demonstrate the performance improvement delivered by the proposed method when compared with the traditional raster scanning method. It is shown that the proposed method enables a five-fold improvement in achievable scanning rate, from 10 to 50 Hz.

Multi-agent reinforcement learning with approximate model learning for competitive games.

We propose a method for learning multi-agent policies to compete against multiple opponents. The method consists of recurrent neural network-based actor-critic networks and deterministic policy gradients that promote cooperation between agents by communication. The learning process does not require access to opponents’ parameters or observations because the agents are trained separately from the opponents. The actor networks enable the agents to communicate using forward and backward paths while the critic network helps to train the actors by delivering them gradient signals based on their contribution to the global reward. Moreover, to address nonstationarity due to the evolving of other agents, we propose approximate model learning using auxiliary prediction networks for modeling the state transitions, reward function, and opponent behavior. In the test phase, we use competitive multi-agent environments to demonstrate by comparison the usefulness and superiority of the proposed method in terms of learning efficiency and goal achievements. The comparison results show that the proposed method outperforms the alternatives.

Feedback-based Self-improving CNN Algorithm for Breast Cancer Lymph Node Metastasis Detection in Real Clinical Environment.

Digital pathology can be thought of as a model composed of 3 main elements; classification algorithm, Graphical User Interface (GUI) and the pathologists. Currently there is only a one way interaction from the classification algorithm to the pathologist. This paper, proposes an additional backward path which is a new feedback-based method, aimed to improve the performance of the classification algorithms by utilizing the feedback of the pathologists. The GUI developed for this purpose, is aimed to be simple and adaptive to different classification algorithms. The method showed significant improvement in the classification performance of the applied Convolutional Neural Network (CNN) algorithm. The 25% quantile of the probability score of the predictions increased from 0.48 to 0.89 and the median of the data increased from 0.95 to 0.99.

An Auto Loss Compensation System for Capacitive-Coupled Body Channel Communication.

This paper proposes an auto loss compensation (ALC) system to attenuate the time-variant path loss for capacitive-coupled body channel communication (CC-BCC). The system employs a time-division gradient indicator to continuously monitor the compensation conditions, and dynamically adjust the compensation inductor through a proportional integral (PI) controller. With the closed-loop topology, the proposed ALC system has two major advantages: first, the path loss induced by the backward coupling effect can be compensated without calibration; second, this system can dynamically attenuate the path loss, even when the channel characteristics vary with time. The simulation and experimental results show that the proposed ALC system can significantly attenuate the backward path loss, especially under wearable and motion scenarios.

Variational h-adaption method for the phase field approach to fracture

The phase field approach to fracture is efficient in simulating crack nucleation and propagation but requires a very fine mesh to resolve the regularization length scale. To alleviate such difficulty we have developed a variational h-adaption method for this approach based on Mosler and Ortiz (Int J Numer Methods Eng 72(5):505–523, 2007, Int J Numer Methods Eng 77(3):437–450, 2009), which consists of a mesh refinement scheme based on edge bisection and a mesh coarsening scheme via node deletion. The main advantages are that a single criterion can be used for the adaption process without any undetermined constant as in a residual-based method and that there is no need to weigh the importance of the two coupled fields, as would be needed for a recovery-based method. We showed examples to demonstrate the efficiency of the proposed method and compared the performance of two bisection operations: simple edge bisection and the modified backward longest edge propagation path scheme. In particular, these two methods lead to condition numbers of the coefficient matrices on the same order of magnitude.

Forward or Backward Simulation?: A Comparative Study

The aim of this study is to present algorithms for the backward simulation of standard processes that are commonly used in financial applications. We extend the works of Ribeiro and Webber and Avramidis and L’Ecuyer on gamma bridge and obtain the backward construction of a Gamma process. Moreover, we are able to write a novel acceptance-rejection algorithm to simulate Inverse Gaussian (IG) processes backward in time. Therefore, using the time-change approach, we can easily get the backward generation of the Compound Poisson with infinitely divisible jumps, the Variance–Gamma the Normal–Inverse–Gaussian processes and then the time-changed version of the OU process (SubOU) introduced by Li and Linetsky. We then compare the computational costs of the sequential and backward path generation of such processes and show the advantages of adopting the latter one, in particular in the context of pricing American options or energy facilities like gas storages.

A Universal Intensity Standardization Method Based on a Many-to-One Weak-Paired Cycle Generative Adversarial Network for Magnetic Resonance Images.

In magnetic resonance imaging (MRI), different imaging settings lead to various intensity distributions for a specific imaging object, which brings huge diversity to data-driven medical applications. To standardize the intensity distribution of magnetic resonance (MR) images from multiple centers and multiple machines using one model, a cycle generative adversarial network (CycleGAN)-based framework is proposed. It utilizes a unified forward generative adversarial network (GAN) path and multiple independent backward GAN paths to transform images in different groups into a single reference one. To preserve image details and prevent resolution loss, two jump connections are applied in the CycleGAN generators. A weak-pair strategy is designed to fully utilize the prior knowledge of the organ structure and promote the performance of the GANs. The experiments were conducted on a T2-FLAIR image database with 8192 slices from 489 patients. The database was obtained from four hospitals and five MRI scanners and was divided into nine groups with different imaging parameters. Compared with the representative algorithms, the peak signal-to-noise ratio, the histogram correlation, and the structural similarity were increased by 3.7%, 5.1%, and 0.1% on average, respectively; the gradient magnitude similarity deviation, the mean square error, and the average disparity were reduced by 19.0%, 15.7%, and 9.9% on average, respectively. Experiments also showed the robustness of the proposed model with a different training set configuration and effectiveness of the proposed framework over the original CycleGAN. Therefore, the MR images with different imaging settings could be efficiently standardized by the proposed method, which would benefit various data-driven applications.

CNN-Based Multiple Path Search for Action Tube Detection in Videos

This paper presents an effective two-stream convolutional neural network (CNN)-based approach to detect multiple spatial-temporal action tubes in videos. A novel video localization refinement (VLR) scheme is first addressed to iteratively rectify the potentially inaccurate bounding boxes by exploiting the temporal consistency between adjacent frames. Then, to provide more faithful detection scores, a new fusion strategy is considered, which combines not only the appearance and the flow information of the two-stream networks but also the motion saliency, the latter of which is included to address the small camera motion. In addition, an efficient multiple path search (MPS) algorithm is developed to simultaneously identify multiple paths in a single run. In the forward message passing of MPS, each node stores information of a prescribed number of connections based on the accumulated scores determined in the previous stages. A backward path tracing is invoked afterward to find all multiple paths at the same time by fully reusing the information generated in the forward pass without repeating the search process. Thus, the complexity incurred can be reduced. The simulation results show that, together with VLR and the new fusion scheme, the proposed MPS, in general, can provide superior performance compared with the state-of-the-art works on four public datasets.