arXiv subjects

Fei Chen

Publications and source records attributed to Fei Chen.

At least 127 records · Page 7Linked to original sources

arXiv2021

HACK3D: Crowdsourcing the Assessment of Cybersecurity in Digital Manufacturing

Digital manufacturing (DM) cyber-physical system is vulnerable to both cyber and physical attacks. HACK3D is a series of crowdsourcing red-team-blue-team events hosted by the NYU Center for Cybersecurity to assess the strength of the security methods embedded in designs using DM. This study summarizes the lessons learned from the past three offerings of HACK3D, including ingenious ways in which skilled engineers can launch surprising attacks on DM designs not anticipated before. A key outcome is a taxonomy-guided creation of DM security benchmarks for use by the DM community.

cs.CR↗

arXiv2021

Risk Variance Penalization

The key of the out-of-distribution (OOD) generalization is to generalize invariance from training domains to target domains. The variance risk extrapolation (V-REx) is a practical OOD method, which depends on a domain-level regularization but lacks theoretical verifications about its motivation and utility. This article provides theoretical insights into V-REx by studying a variance-based regularizer. We propose Risk Variance Penalization (RVP), which slightly changes the regularization of V-REx but addresses the theory concerns about V-REx. We provide theoretical explanations and a theory-inspired tuning scheme for the regularization parameter of RVP. Our results point out that RVP discovers a robust predictor. Finally, we experimentally show that the proposed regularizer can find an invariant predictor under certain conditions.

cs.LG↗

arXiv2021

Intuitive Tasks Planning Using Visuo-Tactile Perception for Human Robot Cooperation

Designing robotic tasks for co-manipulation necessitates to exploit not only proprioceptive but also exteroceptive information for improved safety and autonomy. Following such instinct, this research proposes to formulate intuitive robotic tasks following human viewpoint by incorporating visuo-tactile perception. The visual data using depth cameras surveils and determines the object dimensions and human intentions while the tactile sensing ensures to maintain the desired contact to avoid slippage. Experiment performed on robot platform with human assistance under industrial settings validates the performance and applicability of proposed intuitive task formulation.

eess.SY↗

arXiv2021

Eye-gaze Estimation with HEOG and Neck EMG using Deep Neural Networks

Hearing-impaired listeners usually have troubles attending target talker in multi-talker scenes, even with hearing aids (HAs). The problem can be solved with eye-gaze steering HAs, which requires listeners eye-gazing on the target. In a situation where head rotates, eye-gaze is subject to both behaviors of saccade and head rotation. However, existing methods of eye-gaze estimation did not work reliably, since the listener's strategy of eye-gaze varies and measurements of the two behaviors were not properly combined. Besides, existing methods were based on hand-craft features, which could overlook some important information. In this paper, a head-fixed and a head-free experiments were conducted. We used horizontal electrooculography (HEOG) and neck electromyography (NEMG), which separately measured saccade and head rotation to commonly estimate eye-gaze. Besides traditional classifier and hand-craft features, deep neural networks (DNN) were introduced to automatically extract features from intact waveforms. Evaluation results showed that when the input was HEOG with inertial measurement unit, the best performance of our proposed DNN classifiers achieved 93.3%; and when HEOG was with NEMG together, the accuracy reached 72.6%, higher than that with HEOG (about 71.0%) or NEMG (about 35.7%) alone. These results indicated the feasibility to estimate eye-gaze with HEOG and NEMG.

eess.SP↗

arXiv2021

The effect of speech and noise levels on the quality perceived by cochlear implant and normal hearing listeners

Electrical hearing by cochlear implants (CIs) may be fundamentally different from acoustic hearing by normal-hearing (NH) listeners, presumably showing unequal speech quality perception in various noise environments. Noise reduction (NR) algorithms used in CI reduce the noise in favor of signal-to-noise ratio (SNR), regardless of plausible accompanying distortions that may degrade the speech quality perception. To gain better understanding of CI speech quality perception, the present work aimed investigating speech quality perception in a diverse noise conditions, including factors of speech/noise levels, type of noise, and distortions caused by NR models. Fifteen NH and seven CI subjects participated in this study. Speech sentences were set to two different levels (65 and 75 dB SPL). Two types of noise (Cafeteria and Babble) at three levels (55, 65, and 75 dB SPL) were used. Sentences were processed using two NR algorithms to investigate the perceptual sensitivity of CI and NH listeners to the distortion. All sentences processed with the combinations of these sets were presented to CI and NH listeners, and they were asked to rate the sound quality of speech as they perceived. The effect of each factor on the perceived speech quality was investigated based on the group averaged quality rated by CI and NH listeners. Consistent with previous studies, CI listeners were not as sensitive as NH to the distortion made by NR algorithms. Statistical analysis showed that the speech level has significant effect on quality perception. At the same SNR, the quality of 65 dB speech was rated higher than that of 75 dB for CI users, but vice versa for NH listeners. Therefore, the present study showed that the perceived speech quality patterns were different between CI and NH listeners in terms of their sensitivity to distortion and speech level in complex listening environment.

eess.AS↗

arXiv2020

MetaAugment: Sample-Aware Data Augmentation Policy Learning

Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the other hand, learning different policies for different samples naively could greatly increase the computing cost. In this paper, we learn a sample-aware data augmentation policy efficiently by formulating it as a sample reweighting problem. Specifically, an augmentation policy network takes a transformation and the corresponding augmented image as inputs, and outputs a weight to adjust the augmented image loss computed by a task network. At training stage, the task network minimizes the weighted losses of augmented training images, while the policy network minimizes the loss of the task network on a validation set via meta-learning. We theoretically prove the convergence of the training procedure and further derive the exact convergence rate. Superior performance is achieved on widely-used benchmarks including CIFAR-10/100, Omniglot, and ImageNet.

cs.LG↗

arXiv2020

Reproducible Pruning System on Dynamic Natural Plants for Field Agricultural Robots

Pruning is the art of cutting unwanted and unhealthy plant branches and is one of the difficult tasks in the field robotics. It becomes even more complex when the plant branches are moving. Moreover, the reproducibility of robot pruning skills is another challenge to deal with due to the heterogeneous nature of vines in the vineyard. This research proposes a multi-modal framework to deal with the dynamic vines with the aim of sim2real skill transfer. The 3D models of vines are constructed in blender engine and rendered in simulated environment as a need for training the robot. The Natural Admittance Controller (NAC) is applied to deal with the dynamics of vines. It uses force feedback and compensates the friction effects while maintaining the passivity of system. The faster R-CNN is used to detect the spurs on the vines and then statistical pattern recognition algorithm using K-means clustering is applied to find the effective pruning points. The proposed framework is tested in simulated and real environments.

cs.RO↗

arXiv2020

Vision Based Adaptation to Kernelized Synergies for Human Inspired Robotic Manipulation

Humans in contrast to robots are excellent in performing fine manipulation tasks owing to their remarkable dexterity and sensorimotor organization. Enabling robots to acquire such capabilities, necessitates a framework that not only replicates the human behaviour but also integrates the multi-sensory information for autonomous object interaction. To address such limitations, this research proposes to augment the previously developed kernelized synergies framework with visual perception to automatically adapt to the unknown objects. The kernelized synergies, inspired from humans, retain the same reduced subspace for object grasping and manipulation. To detect object in the scene, a simplified perception pipeline is used that leverages the RANSAC algorithm with Euclidean clustering and SVM for object segmentation and recognition respectively. Further, the comparative analysis of kernelized synergies with other state of art approaches is made to confirm their flexibility and effectiveness on the robotic manipulation tasks. The experiments conducted on the robot hand confirm the robustness of modified kernelized synergies framework against the uncertainties related to the perception of environment.

cs.RO↗

arXiv2020

Dislocation-induced Y segregation at basal-prismatic interfaces in Mg

Solute segregation at twin boundaries in Mg has been widely investigated, yet this phenomenon has not been studied at the equally important basal-prismatic interfaces. To fill this critical gap, this work investigates the segregation behavior of Y at basal-prismatic interfaces with various structures using atomistic simulations. The calculated interfacial energies show that short coherent interfaces and long semi-coherent interfaces containing disconnections and dislocations are more energetically stable than disordered interfaces, which is supported by our experimental observations. The segregation energy of Y at these lowest energy basal-prismatic interfaces shows a clear correlation with the atomic hydrostatic stress, highlighting the importance of local compressive stresses for segregation. In addition, sites around dislocations at the semi-coherent basal-prismatic interfaces demonstrate lower segregation energy, indicating that local defects such as interfacial dislocations can further enhance the segregation. In its entirety, this study indicates that the segregation of solutes can be affected by a number of different aspects of the local structure at complex interfaces in Mg alloys.

cond-mat.mtrl-sci↗

arXiv2020

Evolution of nematic fluctuations in CaK(Fe$_{1-x}$Ni$_{x}$)$_{4}$As$_{4}$ with spin-vortex crystal magnetic order

The CaK(Fe$_{1-x}$Ni$_{x}$)$_{4}$As$_{4}$ superconductors resemble the archetypal 122-type iron-based materials but have a crystal structure with distinctly lower symmetry. This family hosts one of the few examples of the so-called spin-vortex crystal magnetic order, a non-collinear magnetic configuration that preserves tetragonal symmetry, in contrast to the orthorhombic collinear stripe-type magnetic configuration common to the 122-type systems. Thus, nematic order is completely absent from its phase diagram. To investigate the evolution of nematic fluctuations in such a case, we present elastoresistance and elastic modulus measurements in CaK(Fe$_{1-x}$Ni$_{x}$)$_{4}$As$_{4}$ ($x = 0-0.05$) combined with phenomenological modeling and density functional theory. We find clear experimental signatures of considerable nematic fluctuations, including softening of the Young's modulus $Y_{[110]}$ and a Curie-Weiss type divergence of the B2g elastoresistance coefficient in CaK(Fe$_{0.951}$Ni$_{0.049}$)$_4$As$_4$. Overall, nematic fluctuations within this series bear strong similarities to the hole-doped Ba$_{1-x}$K$_x$Fe$_2$As$_2$ series, including a substitution-induced sign change. Our theoretical analysis addresses the effect of the specific crystal symmetry of the 1144-type structure in determining its magnetic ground state and on the nematic fluctuations.

cond-mat.supr-con↗

arXiv2020

Leveraging Kernelized Synergies on Shared Subspace for Precision Grasp and Dexterous Manipulation

Manipulation in contrast to grasping is a trajectorial task that needs to use dexterous hands. Improving the dexterity of robot hands, increases the controller complexity and thus requires to use the concept of postural synergies. Inspired from postural synergies, this research proposes a new framework called kernelized synergies that focuses on the re-usability of the same subspace for precision grasping and dexterous manipulation. In this work, the computed subspace of postural synergies; parameterized by probabilistic movement primitives, is treated with kernel to preserve its grasping and manipulation characteristics and allows its reuse for new objects. The grasp stability of the proposed framework is assessed with a force closure quality index. For performance evaluation, the proposed framework is tested on two different simulated robot hand models using the Syngrasp toolbox and experimentally, four complex grasping and manipulation tasks are performed and reported. The results confirm the hand agnostic approach of the proposed framework and its generalization to distinct objects irrespective of their shape and size.

cs.RO↗

arXiv2020

Simultaneous Generation of Arbitrary Assembly of Polarization States with Geometrical-Scaling-Induced Phase Modulation

Manipulating the polarization of light on the microscale or nanoscale is essential for integrated photonics and quantum optical devices. Nowadays, the metasurface allows one to build on-chip devices that efficiently manipulate the polarization states. However, it remains challenging to generate different types of polarization states simultaneously, which is required to encode information for quantum computing and quantum cryptography applications. By introducing geometrical-scaling-induced (GSI) phase modulations, we demonstrate that an assembly of circularly polarized (CP) and linearly polarized (LP) states can be simultaneously generated by a single metasurface made of L-shaped resonators with different geometrical features. Upon illumination, each resonator diffracts the CP state with a certain GSI phase. The interaction of these diffractions leads to the desired output beams, where the polarization state and the propagation direction can be accurately tuned by selecting the geometrical shape, size, and spatial sequence of each resonator in the unit cell. As an example of potential applications, we show that an image can be encoded with different polarization profiles at different diffraction orders and decoded with a polarization analyzer. This approach resolves a challenging problem in integrated optics and is inspiring for on-chip quantum information processing.

physics.optics↗

arXiv2020

The Importance and the Limitations of Sim2Real for Robotic Manipulation in Precision Agriculture

In recent years Sim2Real approaches have brought great results to robotics. Techniques such as model-based learning or domain randomization can help overcome the gap between simulation and reality, but in some situations simulation accuracy is still needed. An example is agricultural robotics, which needs detailed simulations, both in terms of dynamics and visuals. However, simulation software is still not capable of such quality and accuracy. Current Sim2Real techniques are helpful in mitigating the problem, but for these specific tasks they are not enough.

cs.RO↗

arXiv2020

LAVAPilot: Lightweight UAV Trajectory Planner with Situational Awareness for Embedded Autonomy to Track and Locate Radio-tags

Tracking and locating radio-tagged wildlife is a labor-intensive and time-consuming task necessary in wildlife conservation. In this article, we focus on the problem of achieving embedded autonomy for a resource-limited aerial robot for the task capable of avoiding undesirable disturbances to wildlife. We employ a lightweight sensor system capable of simultaneous (noisy) measurements of radio signal strength information from multiple tags for estimating object locations. We formulate a new lightweight task-based trajectory planning method-LAVAPilot-with a greedy evaluation strategy and a void functional formulation to achieve situational awareness to maintain a safe distance from objects of interest. Conceptually, we embed our intuition of moving closer to reduce the uncertainty of measurements into LAVAPilot instead of employing a computationally intensive information gain based planning strategy. We employ LAVAPilot and the sensor to build a lightweight aerial robot platform with fully embedded autonomy for jointly tracking and planning to track and locate multiple VHF radio collar tags used by conservation biologists. Using extensive Monte Carlo simulation-based experiments, implementations on a single board compute module, and field experiments using an aerial robot platform with multiple VHF radio collar tags, we evaluate our joint planning and tracking algorithms. Further, we compare our method with other information-based planning methods with and without situational awareness to demonstrate the effectiveness of our robot executing LAVAPilot. Our experiments demonstrate that LAVAPilot significantly reduces (by 98.5%) the computational cost of planning to enable real-time planning decisions whilst achieving similar localization accuracy of objects compared to information gain based planning methods, albeit taking a slightly longer time to complete a mission.

cs.RO↗

arXiv2020

When Distributed Formation Control Is Feasible under Hard Constraints on Energy and Time?

This paper studies distributed optimal formation control with hard constraints on energy levels and termination time, in which the formation error is to be minimized jointly with the energy cost. The main contributions include a globally optimal distributed formation control law and a comprehensive analysis of the resulting closed-loop system under those hard constraints. It is revealed that the energy levels, the task termination time, the steady-state error tolerance, as well as the network topology impose inherent limitations in achieving the formation control mission. Most notably, the lower bounds on the achievable termination time and the required minimum energy levels are derived, which are given in terms of the initial formation error, the steady-state error tolerance, and the largest eigenvalue of the Laplacian matrix. These lower bounds can be employed to assert whether an energy and time constrained formation task is achievable and how to accomplish such a task. Furthermore, the monotonicity of those lower bounds in relation to the control parameters is revealed. A simulation example is finally given to illustrate the obtained results.

eess.SY↗

arXiv2020

Deep Job Understanding at LinkedIn

As the world's largest professional network, LinkedIn wants to create economic opportunity for everyone in the global workforce. One of its most critical missions is matching jobs with processionals. Improving job targeting accuracy and hire efficiency align with LinkedIn's Member First Motto. To achieve those goals, we need to understand unstructured job postings with noisy information. We applied deep transfer learning to create domain-specific job understanding models. After this, jobs are represented by professional entities, including titles, skills, companies, and assessment questions. To continuously improve LinkedIn's job understanding ability, we designed an expert feedback loop where we integrated job understanding models into LinkedIn's products to collect job posters' feedback. In this demonstration, we present LinkedIn's job posting flow and demonstrate how the integrated deep job understanding work improves job posters' satisfaction and provides significant metric lifts in LinkedIn's job recommendation system.

cs.IR↗

arXiv2020

MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection

Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user. We observe this ubiquitous phenomenon on both public and private datasets and address the model selection problem in pursuit of optimizing the quality of recommendation for each user. We propose a meta-learning framework to facilitate user-level adaptive model selection in recommender systems. In this framework, a collection of recommenders is trained with data from all users, on top of which a model selector is trained via meta-learning to select the best single model for each user with the user-specific historical data. We conduct extensive experiments on two public datasets and a real-world production dataset, demonstrating that our proposed framework achieves improvements over single model baselines and sample-level model selector in terms of AUC and LogLoss. In particular, the improvements may lead to huge profit gain when deployed in online recommender systems.

cs.IR↗

arXiv2020

Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction

Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this paper, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio-temporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a novel graph-based spatio-temporal convolutional layer to extract features from a graph representation of traffic flows. Then several such layers are stacked together to predict future flows over time. Meanwhile, the relations between traffic flows in the graph are often time variant as the traffic condition changes over time. To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream. Experiments on real datasets demonstrate that the proposed model achieves competitive performances compared with the other state-of-the-art methods.

cs.CV↗