Anna Wang

When disasters such as earthquakes and collapses occur, rescuers must go deep into dangerous regions and rush to transport the wounded. Long-term rescue operations in dangerous environments challenge the rescuers’ physical strength and threaten their lives. We propose a human-body reconstruction method for autonomous rescue operations with a wounded rescue robot. This method constructs a human body model that can support a robot’s autonomous rescue operations given limited scans of the injured. Most casualties lie on the ground in supine positions, so this scanning limit is typical. We propose a scanning viewpoint planning method using deep reinforcement learning and change the viewpoint with the help of a 6-degree-of-freedom (DOF) robotic arm to obtain a complete scan of the visible surface. For successful autonomous casualty rescue, a robot must have access to a watertight human body mesh with precise surfaces and associated semantics. To this end, we develop a neural network that predicts a completely clothed body mesh from visible point clouds. The results of experiments show that our method can reconstruct a watertight body mesh with accurate surfaces and human semantics to satisfy the needs of autonomous robotic casualty rescue operations under scanning limitations.

In the aftermath of a disaster, such as an earthquake or the collapse of dilapidated buildings, it is necessary to enter the ruins to rescue the wounded, which is often accompanied by the casualties of rescuers. We propose a wounded body reconstruction system for rescue operations in disaster zones to replace humans with robots for rescue in hazardous environments. However, many limitations such as self-scanning constraints, reliable human semantic parsing, accurate surface reconstruction, and plausible motion tracking make this work even more challenging. We employ a parametric model to break the self-scanning constraints and obtain human semantic parsing fundamentally. To enable the parametric model to present human detail, we improved the human parametric model by defining a detail layer applying to the template as an additional offset. We propose automatically changing the viewpoint according to the human pose with the help of a robotic arm to obtain a dense and complete observation and achieve a high precision surface reconstruction. To meet the requirements of the rescue operation, we propose a new pipeline to track the wounded motion accurately. The experiments demonstrate that our method can accurately recover the surface of the human body and achieve accurate motion tracking free from the constraints of self-scanning and preserving reliable human semantic parsing.

Most current research on Alzheimer’s disease (AD) is based on transverse measurements. Given the nature of neurodegeneration in AD progression, observing longitudinal changes in the structural features of brain networks over time may improve the accuracy of the predicted transformation and provide a good measure of the progression of AD. Currently, there is no cure for patients with existing AD dementia, but patients with mild cognitive impairment (MCI) in the prodromal stage of AD dementia may be diagnosed. The study of the early diagnosis of MCI and the prediction of MCI to AD transformation is of great significance for the monitoring of the MCI to AD transformation process. Despite the high rate of MCI conversion to AD, the neuropathological cause of MCI is heterogeneous. However, many people with MCI remain stable. Treatment options are different for patients with stable MCI and those with underlying dementia. Therefore, it is of great significance for clinical practice to predict whether patients with MCI will develop AD dementia. This paper proposes an improved algorithm that is based on a convolution neural network (CNN) with residuals combined with multi-layer long short-term memory (LSTM) to diagnose AD and predict MCI. Firstly, multi-time resting-state fMRI images were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database for preprocessing, and then an AAL brain partition template was used to construct a 90 × 90 functional connectivity (FC) network matrix of a whole-brain region of interest (ROI). Secondly, the diversity of training samples was increased by generating an adversarial network (GAN). Finally, a CNN with residuals and a multi-layer LSTM model were constructed to automatically classify and predict the functional adjacency matrix. This method can not only distinguish Alzheimer’s disease from normal health conditions at multiple time points, but can also predict progressive MCI (pMCI) and stable MCI (sMCI) at multiple time points. The classification accuracies in AD vs. NC and sMCI vs.pMCI reached 93.5% and 75.5%, respectively.

In this paper, the trajectory tracking problem of industrial manipulator with fixed periodic external force on human-robot cooperative assembly line is studied. An advanced fuzzy adaptive supertwisting sliding mode control (FASTSMC) algorithm is proposed to realize the rapid convergence and continuous control of nonlinear control system. In order to enhance the robustness of the system, an arctangent terminal sliding mode surface is designed to deal with the concentrated uncertain disturbance. The supertwisting method is used to overcome the chattering problem in the control law. The fuzzy adaptive technique is used to compensate the centralized disturbance with unknown upper bound. A stiffness identification model is designed to estimate the deviation of the manipulator under external force. Finally, the feasibility of the proposed control scheme is verified by a simulation example of a 4-DOF manipulator.

The early diagnosis of Alzheimer’s disease (AD) can allow patients to take preventive measures before irreversible brain damage occurs. It can be seen from cross-sectional imaging studies of AD that the features of the lesion areas in AD patients, as observed by magnetic resonance imaging (MRI), show significant variation, and these features are distributed throughout the image space. Since the convolutional layer of the general convolutional neural network (CNN) cannot satisfactorily extract long-distance correlation in the feature space, a deep residual network (ResNet) model, based on spatial transformer networks (STN) and the non-local attention mechanism, is proposed in this study for the early diagnosis of AD. In this ResNet model, a new Mish activation function is selected in the ResNet-50 backbone to replace the Relu function, STN is introduced between the input layer and the improved ResNet-50 backbone, and a non-local attention mechanism is introduced between the fourth and the fifth stages of the improved ResNet-50 backbone. This ResNet model can extract more information from the layers by deepening the network structure through deep ResNet. The introduced STN can transform the spatial information in MRI images of Alzheimer’s patients into another space and retain the key information. The introduced non-local attention mechanism can find the relationship between the lesion areas and normal areas in the feature space. This model can solve the problem of local information loss in traditional CNN and can extract the long-distance correlation in feature space. The proposed method was validated using the ADNI (Alzheimer’s disease neuroimaging initiative) experimental dataset, and compared with several models. The experimental results show that the classification accuracy of the algorithm proposed in this study can reach 97.1%, the macro precision can reach 95.5%, the macro recall can reach 95.3%, and the macro F1 value can reach 95.4%. The proposed model is more effective than other algorithms.

The sub-module capacitor voltage equalization of modular multilevel converters is the key to their stable operation. Aiming at the computation complexity and high switching frequency existing in conventional voltage balancing method of high-level modular multilevel converter, an optimal equalization control strategy based on sub-modules(SMs) priority with variable threshold interval is proposed. The number of current input modules is calculated by the nearest level modulation, then the reference value is adjusted according to the number of input modules, and based on this reference value, sets the SMs capacitance voltage threshold range to constrain the voltage distribution of SMs. The grouping order of each SM in current control cycle were determined by comparing the voltage values of SMs switched IN or OUT in last control cycle with the upper and lower limits of threshold interval. According to the direction of the bridge arm current, the sequencing order of the groups is determined, and the information of the input module is finally determined. A simulation model of three-phase inverter based on MMC is set up in MATLAB/Simulink to verify the proposed strategy can reduce the switching frequency of power devices significantly when maintaining high capacitor voltage consistency, whether in steady or transient process.

High-quality and complete human motion 4D reconstruction is of great significance for immersive VR and even human operation. However, it has inevitable self-scanning constraints, and tracking under monocular settings also has strict restrictions. In this paper, we propose a human motion capture system combined with human priors and performance capture that only uses a single RGB-D sensor. To break the self-scanning constraint, we generated a complete mesh only using the front view input to initialize the geometric capture. In order to construct a correct warping field, most previous methods initialize their systems in a strict way. To maintain high fidelity while increasing the easiness of the system, we updated the model while capturing motion. Additionally, we blended in human priors in order to improve the reliability of model warping. Extensive experiments demonstrated that our method can be used more comfortably while maintaining credible geometric warping and remaining free of self-scanning constraints.

In this paper, a repetitive control scheme of a 2‐DOF robotic manipulator based on the improved cubic B‐spline curve is proposed. Firstly, a repetitive controller for robotic manipulator is designed, which is composed of an iterative controller and disturbance observer. Then, an improved B‐spline optimization scheme is introduced to divide the task of the robotic manipulator into three intervals. A correction function is added to each interval of cubic spline interpolation. Finally, a variety of cases are designed and simulated by MATLAB. The experimental results show that, compared with the conventional B‐spline, the improved B‐spline has better performance in tracking accuracy and smoothness of motion trajectory. By changing the mechanism of the manipulator, the cases of different weights and lengths are designed. The experimental results in these cases show that the proposed scheme can be applied to most of the 2‐DOF robotic manipulator control systems.

Multi-label learning is a meaningful supervised learning task in which each sample may belong to multiple labels simultaneously. Due to this characteristic, multi-label learning is more complicated and more difficult than multi-class classification learning. The multi-label twin support vector machine (MLTSVM) [], which is an effective multi-label learning algorithm based on the twin support vector machine (TSVM), has been widely studied because of its good classification performance. To obtain good generalization performance, the MLTSVM often needs a large number of labelled samples. In practical engineering problems, it is very time consuming and difficult to obtain all labels of all samples for multi-label learning problems, so we can only obtain a large number of partially labelled and unlabelled samples and a small number of labelled samples. However, the MLTSVM can use only expensive labelled samples and ignores inexpensive partially labelled and unlabelled samples. Because of the MLTSVM’s disadvantages, we propose an alternative novel semi-supervised multi-label twin support vector machine, named SS-MLTSVM, which can take full advantage of the geometric information of the edge distribution embedded in partially labelled and unlabelled samples by introducing a manifold regularization term into each sub-classifier and use the successive overrelaxation (SOR) method to speed up the solving process. Experimental results on several publicly available benchmark multi-label datasets show that, compared with the classical MLTSVM, our proposed SS-MLTSVM has better classification performance.

Multi-label twin support vector machine (MLTSVM), being an effective multi-label classifier based on twin support vector machine (TSVM), has been widely studied and applied due to its excellent classification performance. However, there are some disadvantages in classical MLTSVM: (a) MLTSVM needs to solve a series of quadratic programming problems (QPPs), which makes its learning speed lower. (b) For multi-label learning problems, it is very difficult to obtain all labels of all samples. In fact, the datasets that we can obtain only contain a small amount of labeled samples and a large amount of partially labeled and unlabeled samples. However, MLTSVM can only use expensive labeled samples and ignore cheap unlabeled and partially labeled samples. For the drawbacks, we propose a novel semi-supervised multi-label least squares twin support vector machine, called SS-MLLSTSVM. Firstly, to speed up solving, SS-MLLSTSVM introduces the least squares idea into each sub-classifier of MLTSVM, which makes each sub-classifier only need to solve a system of linear equations, instead of one QPP. Secondly, SS-MLLSTSVM can make full use of the geometric information in unlabeled and partially labeled samples by introducing manifold regularization term into each sub-classifier. The experimental results on the benchmark datasets show that, compared with the existing multi-label classification algorithms, our SS-MLLSTSVM has better classification performance.