Binary Tree Network Research Articles

A deep material network approach for predicting the thermomechanical response of composites

Recent progress combining micromechanics and machine learning holds promise for accurately and rapidly predicting the mechanical behavior of complex composite materials. This study extends the Deep Material Network (DMN), a binary-tree network trained on linear direct-numerical-simulation data, to predict the thermo-elasto-viscoplastic behavior of composites. This extension incorporates the thermal expansion properties homogenization into the network’s building blocks and expands the online formulation to consider thermal boundary conditions. By comparing various implementations of these building blocks, we demonstrate the network’s extrapolation to thermomechanical problems. We then show how this extended DMN can be applied to uncertainty quantification and inverse design problems.

Early detection of colorectal cancer based on circular DNA and common clinical detection indicators.

BACKGROUNDColorectal cancer (CRC) is the third most common cancer worldwide, and it is the second leading cause of death from cancer in the world, accounting for approximately 9% of all cancer deaths. Early detection of CRC is urgently needed in clinical practice.AIMTo build a multi-parameter diagnostic model for early detection of CRC. METHODSTotal 59 colorectal polyps (CRP) groups, and 101 CRC patients (38 early-stage CRC and 63 advanced CRC) for model establishment. In addition, 30 CRP groups, and 62 CRC patients (30 early-stage CRC and 32 advanced CRC) were separately included to validate the model. 51 commonly used clinical detection indicators and the 4 extrachromosomal circular DNA markers NDUFB7, CAMK1D, PIK3CD and PSEN2 that we screened earlier. Four multi-parameter joint analysis methods: binary logistic regression analysis, discriminant analysis, classification tree and neural network to establish a multi-parameter joint diagnosis model. RESULTSNeural network included carcinoembryonic antigen (CEA), ischemia-modified albumin (IMA), sialic acid (SA), PIK3CD and lipoprotein a (LPa) was chosen as the optimal multi-parameter combined auxiliary diagnosis model to distinguish CRP and CRC group, when it differentiated 59 CRP and 101 CRC, its overall accuracy was 90.8%, its area under the curve (AUC) was 0.959 (0.934, 0.985), and the sensitivity and specificity were 91.5% and 82.2%, respectively. After validation, when distinguishing based on 30 CRP and 62 CRC patients, the AUC was 0.965 (0.930-1.000), and its sensitivity and specificity were 66.1% and 70.0%. When distinguishing based on 30 CRP and 32 early-stage CRC patients, the AUC was 0.960 (0.916-1.000), with a sensitivity and specificity of 87.5% and 90.0%, distinguishing based on 30 CRP and 30 advanced CRC patients, the AUC was 0.970 (0.936-1.000), with a sensitivity and specificity of 96.7% and 86.7%.CONCLUSIONWe built a multi-parameter neural network diagnostic model included CEA, IMA, SA, PIK3CD and LPa for early detection of CRC, compared to the conventional CEA, it showed significant improvement.

Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration

3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks.In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover’s Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.

Evolution of distributed detection performance over balanced binary relay tree networks with bit errors

Target detection based on wireless sensor networks can be considered as a distributed binary hypothesis testing problem. In this paper, the evolution of detection error probability with the increase in the network scale is studied for the balanced binary relay tree network with channel noise. Firstly, the iterative expressions of false-alarm probability and missed-detection probability depending on the number of tree network layers are given. Then, the iterative process of two types of error probabilities in the network space is described as a discrete nonlinear switched dynamic system, and the dynamic properties of two types of error probabilities are analyzed in a plane rectangular coordinate system. A globally attractive invariant set of the state of the dynamic system, which is not related to the channel noise, is derived. The switching mode of the system and the total error probability in the invariant set are further analyzed, and a necessary and sufficient convergence condition of the total error probability is provided. Based on this condition, the following detection properties of the network are revealed: (1) as long as the channel bit error probability is not zero, the total error probability does not tend to zero as the network size grows to infinity; (2) when the channel bit error probability is greater than \(\frac{2-\sqrt{3}}{2}\), the total error probability will continue to increase with the increase in the network size.

Side Tributary Distribution of Quasi-Uniform Iterative Binary Tree Networks for River Networks

Self-similarity and plane-filling are intrinsic structure properties of natural river networks. Statistical data indicates that most natural river networks are Tokunaga trees. Researchers have explored to use iterative binary tree networks (IBTNs) to simulate natural river networks. However, the characteristics of natural rivers such as Tokunaga self-similarity and plane-filling cannot be easily guaranteed by the configuration of the IBTN. In this paper, the generator series and a quasi-uniform iteration rule are specified for the generation of nonstochastic quasi-uniform iterative binary tree networks (QU-IBTNs). First, we demonstrate that QU-IBTNs definitely satisfy self-similarity. Second, we show that the constraint for a QU-IBTN to be a Tokunaga tree is that the exterior links must be replaced in the generator series with a neighboring generator that is larger than the interior links during the iterative process. Moreover, two natural river networks are examined to reveal the inherent consistency with QU-IBTN at low Horton-Strahler orders.

Learning Mesh Representations via Binary Space Partitioning Tree Networks.

Polygonal meshes are ubiquitous, but have only played a relatively minor role in the deep learning revolution. State-of-the-art neural generative models for 3D shapes learn implicit functions and generate meshes via expensive iso-surfacing. We overcome these challenges by employing a classical spatial data structure from computer graphics, Binary Space Partitioning (BSP), to facilitate 3D learning. The core operation of BSP involves recursive subdivision of 3D space to obtain convex sets. By exploiting this property, we devise BSP-Net, a network that learns to represent a 3D shape via convex decomposition without supervision. The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built over a set of planes, where the planes and convexes are both defined by learned network weights. BSP-Net directly outputs polygonal meshes from the inferred convexes. The generated meshes are watertight, compact (i.e., low-poly), and well suited to represent sharp geometry. We show that the reconstruction quality by BSP-Net is competitive with those from state-of-the-art methods while using much fewer primitives.We also explore variations to BSP-Net including using a more generic decoder for reconstruction, more general primitives than planes, as well as training a generative model with variational auto-encoders.

Structure‐aware 3D reconstruction for cable‐stayed bridges: A learning‐based method

AbstractA powerful deep learning‐based three‐dimensional (3D) reconstruction method for reconstructing structure‐aware semantic 3D models of cable‐stayed bridges is proposed herein. Typically, conventional bridge semantic 3D model reconstruction methods are not robust when low‐quality point clouds are used. Furthermore, they are suited particularly for their respective fields and less generalized for cable‐stayed bridges. Hence, a structure‐aware learning‐based cable‐stayed bridge 3D reconstruction framework is proposed. The encoder part of the network uses both multiview images and a photogrammetric point cloud as input, whereas the decoder part uses a recursive binary tree network to model a high‐level structural relation graph and low‐level 3D geometric shapes. Two actual cable‐stayed bridges are employed as examples to evaluate the proposed method. Test results demonstrate that the proposed method successfully reconstructs the bridge model with structural components and their relations. Quantitative results indicate that the predicted models achieved an average F1 score of 99.01%, a Chamfer distance of 0.0259, and a mesh‐to‐cloud distance of 1.78 m. The achieved result is similar to that obtained using the manual reconstruction approach in terms of component‐wise accuracy, and it is considerably better than that obtained using the manual approach in terms of spatial accuracy. In addition, the proposed recursive binary tree network is robust to noise and partial scans. The potential applications of the obtained 3D bridge models are discussed.

Strategic Social Team Crowdsourcing: Forming a Team of Truthful Workers for Crowdsourcing in Social Networks

With the increasing complexity of tasks that are crowdsourced, requesters need to form teams of professional workers that can satisfy complex task skill requirements. Team crowdsourcing in social networks (SNs) provides a promising solution for complex task crowdsourcing, where the requester hires a team of professional workers that are also socially connected can work together collaboratively. Previous social team formation approaches have mainly focused on the algorithmic aspect for social welfare maximization; however, within the traditional objective of maximizing social welfare alone, selfish workers can manipulate the crowdsourcing market by behaving untruthfully. This dishonest behavior discourages other workers from participating and is unprofitable for the requester. To address this strategic social team crowdsourcing problem, truthful mechanisms are developed to guarantee that a worker's utility is optimized when he behaves honestly. This problem is proved to NP-hard, and two efficient mechanisms are proposed to optimize social welfare while reducing time complexity for different scale applications. For small-scale applications where the task requires a small number of skills, a binary tree network is first extracted from the social network, and a dynamic programming-based optimal team is formed in the binary tree. For large-scale applications where the task requires a large number of skills, a team is formed greedily based on the workers' social structure, skill, and working cost. For both mechanisms, the threshold payment rule, which pays each worker his marginal value for task completion, is proposed to elicit truthfulness. Finally, the experimental results of a real-world dataset show that compared to the benchmark exponential VCG truthful mechanism, the proposed small-scale-oriented mechanism can reduce computation time while producing nearly the same social welfare results. Furthermore, compared to other state-of-the-art polynomial heuristics, the proposed large-scale-oriented mechanism can achieve truthfulness while generating better social welfare outcomes.

Improving quantum state transfer efficiency and entanglement distribution in binary tree spin network through incomplete collapsing measurements

In this work, quantum state transfer (QST) over binary-tree spin networks is studied by using advantages of partially collapsing measurements. To this aim, we perform initially a weak measurement (WM) on central qubit of the binary-tree network, which encoding the state of concern and after time evolution of the whole system, a quantum measurement reversal (QMR) on the destined qubit is performed. By taking the optimal value of the QMR, it is shown that the QST can be improved considerably by controlling the WM strength and by choosing it close enough to 1, near-perfect QST can be achieved. We also show that how entanglement distribution quality over the binary-tree spin network can be obviously improved by using this approach.

XMAS-Based QoS Analysis Methodology

On-chip communication system design starting from a high-level model can facilitate formal verification of system properties, such as safety and deadlock freedom. Yet, analyzing its quality-of-service (QoS) property, in our context, per-flow delay bound, is an open challenge. Based on executable micro-architectural specification (xMAS) which is a formal framework modeling communication fabrics, we first present how to model a classic input-queuing virtual channel router using the xMAS primitives and then a QoS analysis methodology using network calculus (NC). Thanks to the precise semantics of the xMAS primitives, the router can be modeled in different variants, which cannot be otherwise captured by normal ad hoc box diagrams. The analysis methodology consists of three steps: 1) given network and flow knowledge, we first create a well-defined precise xMAS model for a specific application on a concrete on-chip network; 2) the specific xMAS model is then mapped to an NC graph (NCG) following a set of mapping rules; and 3) finally, existing QoS analysis techniques can be applied to analyze the NCG to obtain end-to-end delay bound per flow. We also show how to apply the technique to a typical all-to-one communication pattern on a binary-tree network and conduct an SoC case study, exemplifying the step-by-step analysis procedure and discussing the tightness of the results.

Dense Convolutional Binary-Tree Networks for Lung Nodule Classification

This paper investigates the problem of benign or malignant diagnosis of pulmonary nodule with original thoracic computed tomography images, and presents a novel end-to-end deep learning architecture named dense convolutional binary-tree network (DenseBTNet). Besides introducing center-crop operation into the DenseNet, the DenseBTNet splits isolated transition layers of the DenseNet and merges them with dense blocks, then adjusts feature-maps transition mode to compact the model. The DenseBTNet has several compelling advantages: 1) the DenseBTNet not only preserves densely connected mechanism of the DenseNet to extract features of lung nodules in different level, but also further reinforces this mechanism to a level of dense blocks and enriches multi-scale features and 2) The DenseBTNet owns high parameter-efficiency and is lightweight in the scale of parameters as well. Experimental results show that the DenseBTNet largely boosts the performance of the DenseNet and achieves higher accuracies on the task of lung nodule classification in comparison with state-of-the-art approaches.

Switching topology approach for UAV formation based on binary-tree network

Formation control is one of the most active topics within the realm of coordination fields for unmanned aerial vehicles (UAVs). The formation pattern is an essential aspect which mainly influences the status of formation flight. This paper focuses on the switching topology approach for a few specific quadrotor UAV formations. A novel switching method based on the binary-tree network (BTN) is developed to realize the transformations between the V-shape and the complete binary tree shape (CBT-shape) topologies. The typical feature of the BTN is the chain structure. Based on the cascaded form of the BTN, a low level feedback controller is designed for the guidance and coordination of UAV swarms. Simulation results demonstrate that the BTN based approach is more superior in the computational cost and real-time performances than several traditional methods.

A Self-Routing on-Chip Network

This paper introduces a new nonblocking self-routing network, called a multi-root binary tree, which may be used to interconnect the cores in multicore chips. The multi-root binary tree network differs from other binary tree-based networks in that the cores are placed at the roots rather than the leaves or the interior nodes of the trees. The self-routing property of a multi-root binary tree is built on the concept of replication and clustering. A new replication and clustering method, called the triangular shift pairing is given to connect the cores together over dedicated paths. It is shown that connecting cores in clusters requires at least n=2 columns of pairings for an n-core network in a grid layout model and triangular shift wiring method matches this lower bound. The replication and clustering concept leads to a simple self-routing scheme that pairs cores by decoding both unicast and multicast connection requests using lg n-bit cluster address bits. In particular, it is established that cores can identify the cluster with which they pair with other cores using simple modulo addition of their own ids and addresses of the targeted cores in 2lg n single bit-decoding steps. It is also shown that, if connection requests are uniformly distributed among the cores then blocking due to target conflicts can be avoided if cores serve connection requests at a small multiple of the frequencies with which they receive them.

Current Steering Digital Analog Converter with Partial Binary Tree Network (PBTN)

DACs are essential devices in many digital systems which require high performance data converters. Thus, shrinking of supply voltage, budget constraints of test times, and rising bandwidth requirement causing DAC architectures to highly relying on matched components to perform data conversions. However, matched components are nearly impossible to fabricate; there are always mismatch errors which causes the difference between the designed and actual component value. Dynamic Element Matching (DEM) is one of the techniques that are commonly used to reduce component mismatch error. This technique is a randomization technique to select one of the appropriate codes for each of the digital input value before entering DAC block. Thus, in this research, a new DEM algorithm is proposed on Current-Steering DAC with Partial Binary Tree Network (PBTN) algorithm that utilizes a lower complexity circuit to produce output signals with less glitches. Simulation results for 6-bit 1-MSB PBTN DAC produces 0.3184LSB of DNL, 0.0062LSB of INL, and a power consumption of 14.13 mW, while using only 126 transmission gates.

Reaction-diffusion-advection equation in binary tree networks and optimal size ratio.

A simple reaction-diffusion-advection equation is proposed in a dichotomous tree network to discuss an optimal network. An optimal size ratio r is evaluated by the principle of maximization of total reaction rate. In the case of reaction-limited conditions, the optimal ratio can be larger than (1/2)(1/3) for a fixed value of branching number n, which is consistent with observations in mammalian lungs. We find furthermore that there is an optimal branching number nc when the Péclet number is large. Under the doubly optimal conditions with respect to the size ratio and branching number, the optimal value of r is close to (1/2)(1/3).

Exact Formulas for the Average Internode Distance in Mesh and Binary Tree Networks

The average internode distancein an interconnection network (or its average distance for short) is an indicator of expected message latency in that network under light and moderate network traffic. Unfortunately, it is not always easy to find an exact value for the average internode distance, particularly for networks that are not node-symmetric, because the computation must be repeated for many classes of nodes. In this short paper, we derive exact formulas for the average internode distance in mesh and complete binary tree networks.

New Divisible Load Distribution Methods using Pipelined Communication Techniques on Tree and Pyramid Networks

A divisible load can be arbitrarily divided into independent small load fractions which are assigned to processors in a parallel or distributed computing system for simultaneous processing. The theory and techniques of divisible load distribution have a wide range of aerospace applications, including satellite signal and image processing, radar and infrared tracking, target identification and searching, and data reporting and aggregation and processing in wireless sensor networks. We make new progress on divisible load distribution on tree and pyramid networks. We revisit the classic method for divisible load distribution on partitionable static interconnection networks (including complete tree and pyramid networks) and derive a closed-form expression of the parallel time and speedup. We propose two new methods which employ pipelined communication techniques to distribute divisible loads on tree and pyramid networks. We derive closed-form expressions of the parallel time and speedup for both methods and show that the asymptotic speedup of both methods is bβ+1 for a complete b-ary tree network and 4β+1 for a pyramid network, where β is the ratio of the time for computing a unit load to the time for communicating a unit load. The technique of pipelined communications leads to improved performance of divisible load distribution on tree and pyramid networks. Compared with the classic method, the asymptotic speedup of our new methods is 100% faster on a complete binary tree network and 33% faster on a pyramid network for large β.

Power-Law Behavior in Geometric Characteristics of Full Binary Trees

Natural river networks exhibit regular scaling laws in their topological organization. Here, we investigate whether these scaling laws are unique characteristics of river networks or can be applicable to general binary tree networks. We generate numerous binary trees, ranging from purely ordered trees to completely random trees. For each generated binary tree, we analyze whether the tree exhibits any scaling property found in river networks, i.e., the power-laws in the size distribution, the length distribution, the distance-load relationship, and the power spectrum of width function. We found that partially random trees generated on the basis of two distinct types of deterministic trees, i.e., deterministic critical and supercritical trees, show contrasting characteristics. Partially random trees generated on the basis of deterministic critical trees exhibit all power-law characteristics investigated in this study with their fitted exponents close to the values observed in natural river networks over a wide range of random-degree. On the other hand, partially random trees generated on the basis of deterministic supercritical trees rarely follow scaling laws of river networks.

New design of an RSFQ parallel multiply–accumulate unit

The multiply–accumulate unit (MAC) is a central component of a successiveinterference canceller, an advanced receiver for W-CDMA base stations.A 4 × 4 two’s complement fixed point RSFQ MAC with rounding to 5 bits has been simulated usingVHDL, and maximum performance is equal to 24 GMACS (giga-multiply–accumulates persecond). The clock distribution network has been re-designed from a linear ripple toa binary tree network in order to eliminate the data dependence of the clockpropagation speed and reduce the number of Josephson junctions in clock lines. The4 × 4 bit MAC has been designed for the HYPRES4.5 kA cm−2 process and its components have been experimentally tested at low frequency: the 5-bitcombiner, using an exhaustive test pattern, had margins on DC bias voltage of ± 18%, and the4 × 4 parallel multiplierhad margins equal to ± 2%.

THE MESH WITH BINARY TREE NETWORKS: AN ENHANCED MESH WITH LOW BUS-LOADING

The literature abounds with enhanced mesh models and numerous results for them. These models employ buses connecting a large (usually a polynomial) number of processors resulting in high bus loading and a very low bus data rate. In this paper we propose an enhanced mesh model called the mesh with binary-tree (multiple bus) network (MBTN) with low bus loading. We measure the cost of the model in terms of its loading, degree (connections per processor), number of buses and layout area. We also devise an algorithm to perform prefix computations on the MBTN. The MBTN's parameters can be selected to provide a wide range of tradeoffs between its cost and performance. Most importantly, for every major existing enhanced mesh model, there is a choice of parameters that makes the MBTN superior to the existing model. Key to the MBTN is a novel implementation of a binary-tree algorithm on a multiple bus network (MBN). We propose two constant loading MBNs that can run binary tree algorithms optimally. We also show that any network (such as the MBTN) that is capable of running binary tree algorithms efficiently can also solve linear recurrences efficiently. These results may be of independent interest.