arXiv subjects

Bo Yang

Publications and source records attributed to Bo Yang.

At least 433 records · Page 24Linked to original sources

arXiv2021

Universal rogue wave patterns associated with the Yablonskii-Vorob'ev polynomial hierarchy

We show that universal rogue wave patterns exist in integrable systems. These rogue patterns comprise fundamental rogue waves arranged in shapes such as triangle, pentagon and heptagon, with a possible lower-order rogue wave at the center. These patterns appear when one of the internal parameters in bilinear expressions of rogue waves gets large. Analytically, these patterns are determined by the root structures of the Yablonskii-Vorob'ev polynomial hierarchy through a linear transformation. Thus, the induced rogue patterns in the space-time plane are simply the root structures of Yablonskii-Vorob'ev polynomials under actions such as dilation, rotation, stretch, shear and translation. As examples, these universal rogue patterns are explicitly determined and graphically illustrated for the generalized derivative nonlinear Schrödinger equations, the Boussinesq equation, and the Manakov system. Similarities and differences between these rogue patterns and those reported earlier in the nonlinear Schrödinger equation are discussed.

nlin.SI↗

arXiv2021

RadarLoc: Learning to Relocalize in FMCW Radar

Relocalization is a fundamental task in the field of robotics and computer vision. There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images. However, learning-based methods have not yet been applied to the radar sensory data. In this work, we investigate how to exploit deep learning to predict global poses from Emerging Frequency-Modulated Continuous Wave (FMCW) radar scans. Specifically, we propose a novel end-to-end neural network with self-attention, termed RadarLoc, which is able to estimate 6-DoF global poses directly. We also propose to improve the localization performance by utilizing geometric constraints between radar scans. We validate our approach on the recently released challenging outdoor dataset Oxford Radar RobotCar. Comprehensive experiments demonstrate that the proposed method outperforms radar-based localization and deep camera relocalization methods by a significant margin.

cs.RO↗

arXiv2021

The Gaffnian and Haffnian: physical relevance of non-unitary CFT for incompressible fractional quantum Hall effect

We motivate a close look on the usefulness of the Gaffnian and Haffnian quasihole manifold (null spaces of the respective model Hamiltonians) for well-known gapped fractional quantum Hall (FQH) phases. The conformal invariance of these subspaces are derived explicitly from microscopic many-body states. The resultant CFT description leads to an intriguing emergent primary field with $h=2,c=0$, and we argue the quasihole manifolds are quantum mechanically well-defined and well-behaved. Focusing on the incompressible phases at $ν=1/3$ and $ν=2/5$, we show the low-lying excitations of the Laughlin phase are quantum fluids of Gaffnian and Haffnian quasiholes, and give a microscopic argument showing that the Haffnian model Hamiltonian is gapless against Laughlin quasielectrons. We discuss the thermal Hall conductance and shot noise measurements at $ν=2/5$, and argue that the experimental observations can be understood from the dynamics within the Gaffnian quasihole manifold. A number of detailed predictions on these experimental measurements are proposed, and we discuss their relationships to the conventional CFT arguments and the composite fermion descriptions.

cond-mat.str-el↗

arXiv2021

Intelligent Spectrum Learning for Wireless Networks with Reconfigurable Intelligent Surfaces

Reconfigurable intelligent surface (RIS) has become a promising technology for enhancing the reliability of wireless communications, which is capable of reflecting the desired signals through appropriate phase shifts. However, the intended signals that impinge upon an RIS are often mixed with interfering signals, which are usually dynamic and unknown. In particular, the received signal-to-interference-plus-noise ratio (SINR) may be degraded by the signals reflected from the RISs that originate from non-intended users. To tackle this issue, we introduce the concept of intelligent spectrum learning (ISL), which uses an appropriately trained convolutional neural network (CNN) at the RIS controller to help the RISs infer the interfering signals directly from the incident signals. By capitalizing on the ISL, a distributed control algorithm is proposed to maximize the received SINR by dynamically configuring the active/inactive binary status of the RIS elements. Simulation results validate the performance improvement offered by deep learning and demonstrate the superiority of the proposed ISL-aided approach.

eess.SP↗

arXiv2021

ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems

In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we focus on integrating the multilingual automatic speech recognition (ASR) into one model, in which an end-to-end paradigm is developed to convert speech waveform into text directly, without any feature engineering or lexicon. In order to make up for the deficiency of the handcrafted feature engineering caused by ATC challenges, a speech representation learning (SRL) network is proposed to capture robust and discriminative speech representations from the raw wave. The self-supervised training strategy is adopted to optimize the SRL network from unlabeled data, and further to predict the speech features, i.e., wave-to-feature. An end-to-end architecture is improved to complete the ASR task, in which a grapheme-based modeling unit is applied to address the multilingual ASR issue. Facing the problem of small transcribed samples in the ATC domain, an unsupervised approach with mask prediction is applied to pre-train the backbone network of the ASR model on unlabeled data by a feature-to-feature process. Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i.e., wave-to-text. Experimental results on the ATCSpeech corpus demonstrate that the proposed approach achieves a high performance with a very small labeled corpus and less resource consumption, only 4.20% label error rate on the 58-hour transcribed corpus. Compared to the baseline model, the proposed approach obtains over 100% relative performance improvement which can be further enhanced with the increasing of the size of the transcribed samples.

cs.CL↗

arXiv2021

D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis

Static analysis tools are widely used for vulnerability detection as they understand programs with complex behavior and millions of lines of code. Despite their popularity, static analysis tools are known to generate an excess of false positives. The recent ability of Machine Learning models to understand programming languages opens new possibilities when applied to static analysis. However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code. We propose D2A, a differential analysis based approach to label issues reported by static analysis tools. The D2A dataset is built by analyzing version pairs from multiple open source projects. From each project, we select bug fixing commits and we run static analysis on the versions before and after such commits. If some issues detected in a before-commit version disappear in the corresponding after-commit version, they are very likely to be real bugs that got fixed by the commit. We use D2A to generate a large labeled dataset to train models for vulnerability identification. We show that the dataset can be used to build a classifier to identify possible false alarms among the issues reported by static analysis, hence helping developers prioritize and investigate potential true positives first.

cs.SE↗

arXiv2021

Improving speech recognition models with small samples for air traffic control systems

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert- and domain-dependent task. In this work, a novel training approach based on pretraining and transfer learning is proposed to address this issue, and an improved end-to-end deep learning model is developed to address the specific challenges of ASR in the ATC domain. An unsupervised pretraining strategy is first proposed to learn speech representations from unlabeled samples for a certain dataset. Specifically, a masking strategy is applied to improve the diversity of the sample without losing their general patterns. Subsequently, transfer learning is applied to fine-tune a pretrained or other optimized baseline models to finally achieves the supervised ASR task. By virtue of the common terminology used in the ATC domain, the transfer learning task can be regarded as a sub-domain adaption task, in which the transferred model is optimized using a joint corpus consisting of baseline samples and new transcribed samples from the target dataset. This joint corpus construction strategy enriches the size and diversity of the training samples, which is important for addressing the issue of the small transcribed corpus. In addition, speed perturbation is applied to augment the new transcribed samples to further improve the quality of the speech corpus. Three real ATC datasets are used to validate the proposed ASR model and training strategies. The experimental results demonstrate that the ASR performance is significantly improved on all three datasets, with an absolute character error rate only one-third of that achieved through the supervised training. The applicability of the proposed strategies to other ASR approaches is also validated.

cs.SD↗

arXiv2021

HSR: Hyperbolic Social Recommender

With the prevalence of online social media, users' social connections have been widely studied and utilized to enhance the performance of recommender systems. In this paper, we explore the use of hyperbolic geometry for social recommendation. We present Hyperbolic Social Recommender (HSR), a novel social recommendation framework that utilizes hyperbolic geometry to boost the performance. With the help of hyperbolic spaces, HSR can learn high-quality user and item representations for better modeling user-item interaction and user-user social relations. Via a series of extensive experiments, we show that our proposed HSR outperforms its Euclidean counterpart and state-of-the-art social recommenders in click-through rate prediction and top-K recommendation, demonstrating the effectiveness of social recommendation in the hyperbolic space.

cs.IR↗

arXiv2021

Contrastive Unsupervised Learning for Speech Emotion Recognition

Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how unsupervised representation learning on unlabeled datasets can benefit SER. We show that the contrastive predictive coding (CPC) method can learn salient representations from unlabeled datasets, which improves emotion recognition performance. In our experiments, this method achieved state-of-the-art concordance correlation coefficient (CCC) performance for all emotion primitives (activation, valence, and dominance) on IEMOCAP. Additionally, on the MSP- Podcast dataset, our method obtained considerable performance improvements compared to baselines.

cs.SD↗

arXiv2021

Negative Thermal Hall Conductance in Two-Dimer Shastry-Sutherland Model with π-flux Dirac Triplon

We introduce an effective 2-dimer tight-binding model for the family of Shastry-Sutherland models with geometrically tunable triplon excitations. The Rashba pseudospin-orbit coupling induced by the tilted external magnetic field leads to elementary excitations having nontrivial topological properties with π-Berry flux. The interplay between the in-plane and out-of-plane magnetic field thus allows us to effectively engineer the band structure in this bosonic system. In particular, the in-plane magnetic field gives rise to Berry curvature hotspot near the bottom of the triplon band, and at the same time significantly increases the critical magnetic field for the topological triplon band. We calculate explicitly the experimental signature of the thermal Hall effect of triplons in SrCu2(BO3)2, and show a pronounced and tunabled transport signals within the accessible parameter range, particularly with a change of sign of the thermal Hall conductance. The tilted magnetic field is also useful in reducing the bandwidth of the lowest triplon band. We show it can thus be a flexible theoretical and experimental platform for the correlated bosonic topological system.

cond-mat.mes-hall↗

arXiv2021

Adversarial example generation with AdaBelief Optimizer and Crop Invariance

Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep neural networks to output inaccurate predictions. Adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications. However, under the challenging black-box setting, most existing adversarial attacks often achieve relatively low success rates on adversarially trained networks and advanced defense models. In this paper, we propose AdaBelief Iterative Fast Gradient Method (ABI-FGM) and Crop-Invariant attack Method (CIM) to improves the transferability of adversarial examples. ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks. Moreover, our method can also be naturally combined with other gradient-based attack methods to build a more robust attack to generate more transferable adversarial examples against the defense models. Extensive experiments on the ImageNet dataset demonstrate the method's effectiveness. Whether on adversarially trained networks or advanced defense models, our method has higher success rates than state-of-the-art gradient-based attack methods.

cs.CV↗

arXiv2021

General rogue waves in the three-wave resonant interaction systems

General rogue waves in (1+1)-dimensional three-wave resonant interaction systems are derived by the bilinear method. These solutions are divided into three families, which correspond to a simple root, two simple roots and a double root of a certain quartic equation arising from the dimension reduction respectively. It is shown that while the first family of solutions associated with a simple root exist for all signs of the nonlinear coefficients in the three-wave interaction equations, the other two families of solutions associated with two simple roots and a double root can only exist in the so-called soliton-exchange case, where the nonlinear coefficients have certain signs. Many of these rogue wave solutions, such as those associated with two simple roots, and higher-order solutions associated with a simple root, are new solutions which have not been reported before. Technically, our bilinear derivation of rogue waves for the double-root case is achieved by a generalization to the previous dimension reduction procedure in the bilinear method, and this generalized procedure allows us to treat roots of arbitrary multiplicities. Dynamics of the derived rogue waves is also examined, and new rogue-wave patterns are presented. Connection between these bilinear rogue waves and those derived earlier by Darboux transformation is also explained.

nlin.SI↗

arXiv2021

Random Transformation of Image Brightness for Adversarial Attack

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications. However, under the challenging black-box setting, the attack success rate, i.e., the transferability of adversarial examples, still needs to be improved. Based on image augmentation methods, we found that random transformation of image brightness can eliminate overfitting in the generation of adversarial examples and improve their transferability. To this end, we propose an adversarial example generation method based on this phenomenon, which can be integrated with Fast Gradient Sign Method (FGSM)-related methods to build a more robust gradient-based attack and generate adversarial examples with better transferability. Extensive experiments on the ImageNet dataset demonstrate the method's effectiveness. Whether on normally or adversarially trained networks, our method has a higher success rate for black-box attacks than other attack methods based on data augmentation. We hope that this method can help to evaluate and improve the robustness of models.

cs.CV↗

arXiv2021

Rogue wave patterns in the nonlinear Schrödinger equation

Rogue wave patterns in the nonlinear Schrödinger equation are analytically studied. It is shown that when an internal parameter in the rogue waves (which controls the shape of initial weak perturbations to the uniform background) is large, these waves would exhibit clear geometric structures, which are formed by Peregrine waves in shapes such as triangle, pentagon, heptagon and nonagon, with a possible lower-order rogue wave at its center. These rogue patterns are analytically determined by the root structures of the Yablonskii-Vorob'ev polynomial hierarchy, and their orientations are controlled by the phase of the large parameter. It is also shown that when multiple internal parameters in the rogue waves are large but satisfy certain constraints, similar rogue patterns would still hold. Comparison between true rogue patterns and our analytical predictions shows excellent agreement.

nlin.SI↗

arXiv2020

Analysis of Truck Driver Behavior to Design Different Lane Change Styles in Automated Driving

Lane change is a very demanding driving task and number of traffic accidents are induced by mistaken maneuvers. An automated lane change system has the potential to reduce driver workload and to improve driving safety. One challenge is how to improve driver acceptance on the automated system. From the viewpoint of human factors, an automated system with different styles would improve user acceptance as the drivers can adapt the style to different driving situations. This paper proposes a method to design different lane change styles in automated driving by analysis and modeling of truck driver behavior. A truck driving simulator experiment with 12 participants was conducted to identify the driver model parameters and three lane change styles were classified as the aggressive, medium, and conservative ones. The proposed automated lane change system was evaluated by another truck driving simulator experiment with the same 12 participants. Moreover, the effect of different driving styles on driver experience and acceptance was evaluated. The evaluation results demonstrate that the different lane change styles could be distinguished by the drivers; meanwhile, the three styles were overall evaluated as acceptable on safety issues and reliable by the human drivers. This study provides insight into designing the automated driving system with different driving styles and the findings can be applied to commercial automated trucks.

cs.RO↗

arXiv2020

Natural grasp intention recognition based on gaze fixation in human-robot interaction

Eye movement is closely related to limb actions, so it can be used to infer movement intentions. More importantly, in some cases, eye movement is the only way for paralyzed and impaired patients with severe movement disorders to communicate and interact with the environment. Despite this, eye-tracking technology still has very limited application scenarios as an intention recognition method. The goal of this paper is to achieve a natural fixation-based grasping intention recognition method, with which a user with hand movement disorders can intuitively express what tasks he/she wants to do by directly looking at the object of interest. Toward this goal, we design experiments to study the relationships of fixations in different tasks. We propose some quantitative features from these relationships and analyze them statistically. Then we design a natural method for grasping intention recognition. The experimental results prove that the accuracy of the proposed method for the grasping intention recognition exceeds 89\% on the training objects. When this method is extendedly applied to objects not included in the training set, the average accuracy exceeds 85\%. The grasping experiment in the actual environment verifies the effectiveness of the proposed method.

cs.RO↗

arXiv2020

Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and Solutions

In a level-5 autonomous driving system, the autonomous driving vehicles (AVs) are expected to sense the surroundings via analyzing a large amount of data captured by a variety of onboard sensors in near-real-time. As a result, enormous computing costs will be introduced to the AVs for processing the tasks with the deployed machine learning (ML) model, while the inference accuracy may not be guaranteed. In this context, the advent of edge intelligence (EI) and sixth-generation (6G) wireless networking are expected to pave the way to more reliable and safer autonomous driving by providing multi-access edge computing (MEC) together with ML to AVs in close proximity. To realize this goal, we propose a two-tier EI-empowered autonomous driving framework. In the autonomous-vehicles tier, the autonomous vehicles are deployed with the shallow layers by splitting the trained deep neural network model. In the edge-intelligence tier, an edge server is implemented with the remaining layers (also deep layers) and an appropriately trained multi-task learning (MTL) model. In particular, obtaining the optimal offloading strategy (including the binary offloading decision and the computational resources allocation) can be formulated as a mixed-integer nonlinear programming (MINLP) problem, which is solved via MTL in near-real-time with high accuracy. On another note, an edge-vehicle joint inference is proposed through neural network segmentation to achieve efficient online inference with data privacy-preserving and less communication delay. Experiments demonstrate the effectiveness of the proposed framework, and open research topics are finally listed.

cs.NI↗

arXiv2020

A Novel Graphic Bending Transformation on Benchmark

Classical benchmark problems utilize multiple transformation techniques to increase optimization difficulty, e.g., shift for anti centering effect and rotation for anti dimension sensitivity. Despite testing the transformation invariance, however, such operations do not really change the landscape's "shape", but rather than change the "view point". For instance, after rotated, ill conditional problems are turned around in terms of orientation but still keep proportional components, which, to some extent, does not create much obstacle in optimization. In this paper, inspired from image processing, we investigate a novel graphic conformal mapping transformation on benchmark problems to deform the function shape. The bending operation does not alter the function basic properties, e.g., a unimodal function can almost maintain its unimodality after bent, but can modify the shape of interested area in the search space. Experiments indicate the same optimizer spends more search budget and encounter more failures on the conformal bent functions than the rotated version. Several parameters of the proposed function are also analyzed to reveal performance sensitivity of the evolutionary algorithms.

cs.NE↗