Random forests decode index finger positions from EEG.
problem Decoding detailed body part positions from non-invasive EEG.
method Leave-one-subject-out cross-validation with random forest.
result Index finger positions can be distinguished with high accuracy.
Deep neural network predicts finger counting and numerosity estimation.
problem Developing a model for predicting finger counting and numerosity estimation.
method The model is trained in an unsupervised manner using RBMs or autoencoders, then supervised. Finger counting positions are also generated.
result The model shows similarities to human subitizing behavior and confirms the importance of unsupervised training.
FINGER computes von Neumann graph entropy efficiently for online graph sequence analysis.
problem Efficiently compute von Neumann graph entropy for online graph sequence analysis.
method Fast Incremental von Neumann Graph Entropy (FINGER) framework.
result FINGER reduces VNGE computation complexity from cubic to linear.
Study knot diagrams on a sphere without vertical lines, focusing on minimal crossings.
problem Understanding minimal crossings of knot diagrams on a punctured sphere.
method Mathematical model of string figures using knot diagrams on xyz-space with missing vertical lines, analyzing minimal crossings under Reidemeister moves. result Minimal number of crossings of knot diagrams on a punctured sphere.
Developed Taylor series for muscle-finger system analysis.
problem Understanding the complex relationship between muscle activity and finger movement.
method Used Dendrite Net to develop Taylor series and construct relation spectrum.
result Found muscle synergy and coupling in hand movement.
We report analytical results for the development of the viscous fingering instability in a cylindrical Hele-Shaw cell of radius a and thickness b. We derive a generalized version of Darcy's law in such cylindrical background, and find it recovers the usual Darcy's law for flow in flat, rectangular cells, with correctio…
Link Floer homology operations and basepoint moves are analyzed.
problem Understanding the effects of basepoint moves on link Floer homology.
method Proving quasi-stabilization and developing a basepoint moving calculus.
result A conjecture about finger moves on link Floer complex is proven.
Robot learns to grasp and adjust using vision and touch.
problem Robotic grasping relies solely on visual input, missing tactile feedback.
method End-to-end action-conditional model that learns from visuo-tactile data.
result Model predicts grasp adjustment outcomes and selects efficient actions.
RL learns dexterous object reorientation on a physical robot.
problem Learning complex in-hand manipulation tasks on physical robots.
method Reinforcement learning in a simulated environment, transfer learning.
result RL policies transfer from simulation to physical robot.
Positive definite operator-valued kernels generalize the well-known notion of reproducing kernels, and are naturally adapted to multi-output learning situations. This paper addresses the problem of learning a finite linear combination of infinite-dimensional operator-valued kernels which are suitable for extending func…
Method tracks finger movements to render shapes on display devices.
problem Designing touchless user interfaces for electronic devices.
method Leap Motion controller tracks finger movements, analyzes trajectories, and uses HMM for gesture recognition.
result Method achieves 92.87% accuracy in rendering shapes on display devices.
Touch sensing improves grasp prediction accuracy.
problem Predicting grasp outcomes from indirect measurements like vision is challenging.
method Investigated touch sensing's value in multimodal grasping using visuo-tactile deep neural networks.
result Tactile readings significantly improve grasp prediction accuracy.
DIGIT is a low-cost tactile sensor for in-hand manipulation.
problem Difficulty in sensing contact forces limits robotic manipulation.
method DIGIT miniaturizes and improves a vision-based tactile sensor.
result DIGIT enables better control of interactions with the environment.
Method estimates fingertip forces, torques, and curvatures from fingernail images.
problem Estimating fingertip forces and curvatures in various contact scenarios.
method Deformation and color distribution analysis of fingernail images using neural networks.
result High accuracy in predicting fingertip forces, torques, and curvatures.
Paper teaches robots to play piano with touch and learning.
problem Teaching robots to play piano with touch and emotion.
method Reinforcement learning from scratch with touch-augmented reward and curriculum.
result Robots can play piano with correct key positions and various requirements.
Developed a simulator and dataset for deep learning in robotic grasping.
problem Lack of sufficient data for deep learning in robotic grasping.
method Created a simulator and dataset for precise cylindrical grasps.
result Demonstrated the feasibility of deep learning for robotic grasping.
Construction of (colored) knot polynomials for double-fat graphs is further generalized to the case when "fingers" and "propagators" are substituting R-matrices in arbitrary closed braids with m-strands. Original version of arXiv:1504.00371 corresponds to the case m=2, and our generalizations sheds additional light on …
Link concordance equals homotopy for high-dimensional spheres.
problem Understanding when immersions of high-dimensional spheres are homotopically trivial.
method Developed stratified Morse theory for generic immersions, using gradient-like vector fields and Cerf theory.
result Every link of high-dimensional spheres is homotopically trivial, resolving a long-standing conjecture.
Paper explores deep learning for translating motor imagery to robotic grasp synthesis.
problem Challenges in equipping machines with the ability to grasp objects based on sensory information.
method Investigates deep conditional generative models for learning integrated object-action representations.
result Demonstrates the capacity of generative models to capture and generate multimodal, multi-finger grasp configurations.
This paper starts a systematic description of colored knot polynomials, beginning from the first non-(anti)symmetric representation R=[2,1]. The project involves several steps: (i) parametrization of big families of knots a la arXiv:1506.00339, (ii) evaluating Racah/mixing matrices for various numbers of strands in var…
Let X be a finite 2-complex with unfree fundamental group. We prove lower bounds for the area of a metric on X, in terms of the square of the least length of a noncontractible loop in X. We thus establish a uniform systolic inequality for all unfree 2-complexes. Our inequality improves the constant in M. Gromov's inequ…
Adaptive smoothing in fMRI improves brain activity analysis.
problem Optimizing spatial smoothing in fMRI data processing pipelines.
method Integrating adaptive spatial smoothing as a neural network layer.
result Adaptive smoothing enhances brain activity analysis accuracy.
Simple attention model outperforms complex sEMG classifiers.
problem Improving myoelectric control for robotic prosthetics.
method Attention-based model for sEMG signal classification.
result Simple model achieves benchmark results on multiple datasets.
Paper monitors population migration across China weekly using Didi data.
problem Lack of timely data on population migration across China.
method Developed a monitoring system leveraging Didi's positioning data.
result Timely detection of population migration from community to provincial scale.
Graph neural network predicts grasp stability from tactile sensor data.
problem Predicting grasp stability from tactile sensor data.
method Graph Convolutional Network (GCN) trained on tactile sensor data.
result Graph neural network effectively predicts grasp stability.
The paper develops GPR models for hyperelastic materials, improving accuracy and rotational invariance.
problem Modeling stress tensors of hyperelastic materials with fewer training examples and higher accuracy.
method Developed three approaches: direct stress tensor modeling, embedding rotational invariance, and recovering strain-energy density.
result Improved GPR models achieve higher accuracy and rotational invariance with fewer training examples.
We analyse the dynamics of the Warsaw Stock Exchange index WIG at a daily time horizon before and after its well defined local maxima of the cusp-like shape decorated with oscillations. The rising and falling paths of the index peaks can be described by the Mittag-Leffler function superposed with various types of oscil…
A framework for real-time gesture recognition in tomato grafting.
problem Efficiently recognizing and tracking hand gestures for manual tasks.
method Sliding window filtering and decision tree model for real-time recognition.
result Average accuracy of 91% in recognizing gestures in real time.
Study surfaces in 4-manifolds using banded unlink diagrams.
problem Representing and manipulating immersed surfaces in 4-manifolds.
method Singular banded unlink diagrams and associated moves.
result Every immersed surface can be represented uniquely by a singular banded unlink diagram.
Method learns gestures from touch devices, outperforming state of the art.
problem Automatic gesture recognition on touch devices with multi-user variability.
method Dynamic sampling, convolutional model, recurrent vs. convolutional features.
result Outperforms state of the art on MMG dataset.
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
ROBEL platform accelerates reinforcement learning with low-cost robots.
problem Accelerating reinforcement learning research in robotics.
method Open-source platform of cost-effective robots for real-world reinforcement learning.
result Robots D'Claw and D'Kitty facilitate learning dexterous manipulation and agile locomotion tasks.
New system uses wearable bio-signals for easy authentication.
problem Security of private information on wearables is a concern.
method Context-dependent soft-biometric authentication using heart rate, gait, and breathing audio.
result Binary SVM with RBF kernel achieves high accuracy and low EER.
ARCHER counters bias in HER to improve sample efficiency in RL.
problem Sample inefficiency in deep RL due to biased replay buffer experiences.
method ARCHER extends HER with aggressive hindsight rewards to counter bias.
result ARCHER increases sample efficiency in RL applications with limited computing budget.
Robotic manipulation learns synergies between pushing and grasping from scratch.
problem Discovering complex synergies between pushing and grasping for efficient robotic manipulation.
method Self-supervised deep reinforcement learning with two convolutional networks.
result System learns pushing and grasping motions that improve picking success rates and efficiency.
Paper proves existence of anisotropic dynamical horizons in gravitational collapse.
problem Existence of apparent horizons in gravitational collapse.
method Scale-critical hyperbolic method and non-perturbative elliptic techniques.
result Smooth and spacelike apparent horizons emerge from general initial data in gravitational collapse.
Paper tackles cross-modal anomalies in multi-source data.
problem Detect anomalies in multi-modal data where patterns are inconsistent across different sources.
method Proposes a deep structured anomaly detection framework.
result Demonstrates effectiveness on real-world datasets.
CUDA optimized neural network predicts HbA1c from joint mobility and anthropometrics.
problem Early detection and accurate diagnosis of diabetes.
method Parallelized neural network using CUDA and C++ on Nvidia GPUs.
result Achieved high accuracy (95.65% on training, 86.67% on testing for males; 97.73% on training, 66.67% on testing for females).
Resource-efficient oblique trees reduce neural signal classification costs.
problem Implementing efficient neural signal classifiers on resource-constrained devices.
method Integrating model compression, probabilistic routing, and cost-aware learning.
result Significant reduction in model size and feature extraction cost compared to state-of-the-art models.
New sEMG dataset for ADL activities recognized with high accuracy.
problem Developing a robust dataset for sEMG-based ADL activity recognition.
method Acquired sEMG data from 25 subjects performing 22 ADL activities. Used 4 classifiers with various feature sets.
result SVM classifier achieved 83.21% accuracy on 5 FAABOS categories.
AWAC combines offline and online data to accelerate RL learning.
problem Challenges in applying RL to real-world robotic control due to exploration and sample complexity.
method Combines sample-efficient dynamic programming with maximum likelihood policy updates.
result AWAC enables rapid learning of robotic skills with prior data and online experience.
Extends positive and almost positive links to successively almost positive ones.
problem Extending properties of positive and almost positive diagrams and links.
method Introducing successively almost positive diagrams and links, and analyzing their properties.
result Improves known results of positive and almost positive links.
The paper extends positivity results from vector bundles to Kobayashi positive ones.
problem Extending positivity results from vector bundles to Kobayashi positive ones.
method Using convexity of Kobayashi positive Finsler metrics and duality for convex Finsler metrics.
result The quotient and tensor product of Kobayashi positive vector bundles are also Kobayashi positive.
The study establishes conditions for positive and quasi-positive links.
problem Characterizing and testing positive and quasi-positive links.
method Proves necessary conditions for link concordance and positivity.
result Characterizes positive links with unlinking number 1 and 2, and tests positive links as closures of positive braids.
The paper defines new types of positivity and proves properties of Schur forms for vector bundles.
problem Defining and characterizing new types of positivity for vector bundles.
method Introducing and characterizing two types of strongly decomposable positivity, proving properties of Schur forms.
result Schur forms of strongly decomposable positive vector bundles are positive or weakly positive, answering a question of Griffiths.
New characterizations of partial positivity using Hörmander's L2-estimate.
problem Characterizing partial positivity in complex geometry.
method Using a twisted version of Hörmander's L2-estimate. result New characterizations of partial positivity, including uniform q-positivity and RC-positivity. Introduces Θ-positivity in Lie groups, generalizing Lusztig's positivity.
problem Generalizing Lusztig's total positivity to a broader class of Lie groups.
method Introduces and studies Θ-positivity in real simple Lie groups. result Four families of Lie groups admit Θ-positive structures. Uniform RC-positivity results for direct image bundles.
problem Understanding the relation between rational connectedness and RC-positivity.
method Analyzing vector bundles and their direct images, using weak RC-positivity as a starting point.
result Uniform RC-positivity of direct image bundles under weak RC-positivity conditions.