Cognitive Computation and Systems最新文献

Human motion prediction is an important and challenging task in computer vision with various applications. Recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been proposed to address this challenging task. However, RNNs exhibit their limitations on long-term temporal modelling and spatial modelling of motion signals. CNNs show their inflexible spatial and temporal modelling capability that mainly depends on a large convolutional kernel and the stride of convolutional operation. Moreover, those methods predict multiple future poses recursively, which easily suffer from noise accumulation. The authors present a new encoder–decoder framework based on the residual convolutional block with a small filter to predict future human poses, which can flexibly capture the hierarchical spatial and temporal representation of the human motion signals from the motion capture sensor. Specifically, the encoder is stacked by multiple residual convolutional blocks to hierarchically encode the spatio-temporal features of previous poses. The decoder is built with two fully connected layers to automatically reconstruct the spatial and temporal information of future poses in a non-recursive manner, which can avoid noise accumulation that differs from prior works. Experimental results show that the proposed method outperforms baselines on the Human3.6M dataset, which shows the effectiveness of the proposed method. The code is available at https://github.com/lily2lab/residual_prediction_network.

In this study, the manoeuvering target tracking problem is addressed by using the unbiased converted measurements from a two-dimensional radar system. Due to the fact that radar measurements are usually expressed in polar coordinates while the target motion is described in the Cartesian coordinates, the unbiased converted measurements are utilised to linearise the system model of the manoeuvering target tracking problem in the Cartesian coordinates. The manoeuver acceleration is modelled as the unknown input of the constant velocity kinematic model of the target. First, it is pointed out that the converted measurement noise no longer satisfies Gaussian distribution, even if the raw radar measurement noise is Gaussian noise. In order to solve the manoeuvering target tracking problem with non-Gaussian disturbances, a joint estimation method for the target state and the unknown input is presented under the maximum correntropy criterion. In the simulation, the proposed manoeuvering target tracking method is compared with the one developed on the basis of the traditional Kalman filter. The simulation results verify the effectiveness of the method proposed in this study.

Echography imaging is an important technique frequently used in medical diagnostics due to low-cost, non-ionising characteristics, and pragmatic convenience. Due to the shortage of skilful technicians and injuries of physicians sustained from diagnosing several patients, robot-assisted echography (RAE) system is gaining great attention in recent decades. A thorough study of the recent research advances in the field of perception, control and cognition techniques used in RAE systems is presented in this study. This survey introduces the representative system structure, applications and projects, and products. Challenges and key technological issues faced by the traditional RAE system and how the current artificial intelligence and cobots attempt to overcome these issues are summarised. Furthermore, significant future research directions in this field have been identified by this study as cognitive computing, operational skills transfer, and commercially feasible system design.

Epilepsy is a neurological disorder and generally detected by electroencephalogram (EEG) signals. The manual inspection of epileptic seizures is a time-consuming and laborious process. Extensive automatic detection algorithms were proposed by using traditional approaches, which show good accuracy for several specific EEG classification problems but perform poorly in others. To address this issue, the authors present a novel model, named SeizureNet, for robust detection of epileptic seizures using EEG signals based on convolutional neural network. Firstly, they utilise two convolutional neural networks to extract time-invariant features from single-channel EEG signals. Then, a fully connected layer is employed to learn high-level features. Finally, these features are supplied to a softmax layer to classify. They evaluated the model on a benchmark database provided by the University of Bonn and adopted a ten-fold cross-validation approach. The proposed model has achieved the accuracy of 98.50–100.00% in classifying non-seizure and seizure, 97.00–99.00% in classifying healthy, inter-ictal and ictal, and 95.84% in classifying among five-class EEG states.

This study aims to offer multiple-model informed predictions of COVID-19 in Canada, specifically through the use of deep learning strategy and mathematical prediction models including long-short term memory network, logistic regression model, Gaussian model, and susceptible-infected-removed model. Using the published data as of the 10th of April 2020, the authors forecast that the daily increased number of infective cases in Canada has not reached the peak turning point and will continue to increase. Therefore, Canada's healthcare services need to be ready for the magnitude of this pandemic.

The pressing demand for workload along with social media interaction leads to diminished alertness during work hours. Researchers attempted to measure alertness level from various cues like EEG, EOG, video-based eye movement analysis, etc. Among these, video-based eyelid and iris motion tracking gained much attention in recent years. However, most of these implementations are tested on video data of subjects without spectacles. These videos do not pose a challenge for eye detection and tracking. In this work, the authors have designed an experiment to yield a video database of 58 human subjects wearing spectacles and are at different levels of alertness. Along with spectacles, they introduced variation in session, recording frame rate (fps), illumination, and time of the experiment. They carried out an analysis to detect the reliableness of facial and ocular features like yawning and eye-blinks in the context of alertness level detection capability. Also, they observe the influence of spectacles on ocular feature detection performance under spectacles and propose a simple preprocessing step to alleviate the specular reflection problem. Extensive experiments on real-world images demonstrate that the authors’ approach achieves desirable reflection suppression results within minimum execution time compared to the state-of-the-art.

For patients with ankle injuries, rehabilitation training is an important and effective way to help patients restore their ankle complex's motor abilities. Aiming to improve the accuracy and performance of ankle rehabilitation, the authors focus on the control strategies of the developed parallel ankle rehabilitation robot with novel 2-UPS/RRR mechanism. Firstly, the kinematics model of the mechanism is established, and they deduce the inverse solution of positions as well as the velocity mapping between the driving speed and the robot's angular velocity, based on which they realise the trajectory tracking control in the process of passive rehabilitation training. Secondly, they set up experiments to determine the torque threshold that can be used to detect the motion intention of ankle joint, and then they propose the active rehabilitation training strategy according to the motion intention detection. Finally, experiments were carried out with healthy subjects, with results showing that the trajectory tracking error during passive rehabilitation training is very small, and the moving platform of the ankle rehabilitation robot can drive the ankle joint to the detected motion intention direction at a constant speed flexibly and smoothly, which verifies the effectiveness of the control strategies for ankle rehabilitation training.

The distributed online algorithms which are based on the Frank-Wolfe method can effectively deal with constrained optimisation problems. However, the calculation of the full (sub)gradient vector in those algorithms leads to a huge computational cost at each iteration. To reduce the computational cost of the algorithms mentioned above, the authors present a distributed online randomised block-coordinate Frank-Wolfe algorithm over networks. Each agent in the networks only needs to calculate a subset of the coordinates of its (sub)gradient vector in this algorithm. Furthermore, they make a detailed theoretical analysis of the regret bound of this algorithm. When all local objective functions satisfy the conditions of strongly convex functions, the authors’ algorithm attains the regret bound of , where T is the total number of iterations. Furthermore, the theorem results are verified via simulation experiments, which show that the algorithm is effective and efficient.

A feature cognitive model combined with an improved variational mode and singular value decomposition is presented to recognise the characteristics of the fault signals from vibration signals of mechanical equipment in this study. Specifically, the variational mode model is constructed firstly to decompose the known fault signals for mechanical equipment with the same load. Singular value decomposition approach is applied to recognise further the inherent modal features of the fault signals and construct the feature set. The supervised learning-support vector machine and the unsupervised learning-fuzzy c-means clustering are used to verify the effectiveness of the presented method. Finally, the provided feature cognitive model is used to recognise the bearing faults to verify its effectiveness. From simulation results, it can be seen that compared to the complete integration empirical mode decomposition method, the feature cognitive model combined by an improved variational mode and singular value decomposition can obtain more higher accuracy and larger evaluation coefficients. It is worth mentioning that the presented method can also be applied to recognise the key characteristics of the other signals.

A novel variable stiffness soft robotic hand (SRH) consists of three pieces of layer jamming structure (LJS) is proposed. The mechanism is driven by the motor-based tendon along the surface of the pieces that connect to individual gas channel. Each LJS is optimised by adhering a thin layer of hot melt adhesive and overlapping the spring steel sheet as inner layer material. It can be switched between rigid and compliant independently. The structures of variable stiffness and tendon-driven lead to various deformation poses. Then the control system of SRH and the performance analysis of the LJS are introduced. Finally, the experiments are implemented to prove the superiority of the proposed LJS and the demonstrations show that the designed robotic hand has multiple configurations to successfully grasp various objects.