Long Liu

Finding ways to enable seamless communication between deaf and able-bodied individuals has been a challenging and pressing issue. This paper proposes a solution to this problem by designing a low-cost data glove that utilizes multiple inertial sensors with the purpose of achieving efficient and accurate sign language recognition. In this study, four machine learning models—decision tree (DT), support vector machine (SVM), K-nearest neighbor method (KNN), and random forest (RF)—were employed to recognize 20 different types of dynamic sign language data used by deaf individuals. Additionally, a proposed attention-based mechanism of long and short-term memory neural networks (Attention-BiLSTM) was utilized in the process. Furthermore, this study verifies the impact of the number and position of data glove nodes on the accuracy of recognizing complex dynamic sign language. Finally, the proposed method is compared with existing state-of-the-art algorithms using nine public datasets. The results indicate that both the Attention-BiLSTM and RF algorithms have the highest performance in recognizing the twenty dynamic sign language gestures, with an accuracy of 98.85% and 97.58%, respectively. This provides evidence for the feasibility of our proposed data glove and recognition methods. This study may serve as a valuable reference for the development of wearable sign language recognition devices and promote easier communication between deaf and able-bodied individuals.

The symmetry of rowing movement is essential for injury prevention and motion effectiveness. Much effort has been dedicated to developing low-cost and intuitive methods for assessing kayaking athletes’ posture. This study proposes a design of motion capture and kinematic analysis based on inertial sensors under real on-water conditions. Athletes with different proficient level are recruited to participate in the experiments. Motion data is collected by self-made devices. The indirect Kalman filter algorithm is used to fuse multiple sensor data after calibrations. The whole body posture and multi-joint coordination can be calculated accordingly. Wavelet scattering is used for automatic feature extraction, and various machine learning algorithms are used for phase recognition. Symmetry analysis is achieved based on the results of phase segmentation in one paddling stroke cycle. Postural control strategy of symmetry is assessed from the perspective of joint angles. The results show that the parameters, which represent the orientation of inertia’s principal axis of the cyclogram based on joint angle can reflect the symmetric difference between elite and novice.

Gesture recognition has found widespread applications in various fields, such as virtual reality, medical diagnosis, and robot interaction. The existing mainstream gesture-recognition methods are primarily divided into two categories: inertial-sensor-based and camera-vision-based methods. However, optical detection still has limitations such as reflection and occlusion. In this paper, we investigate static and dynamic gesture-recognition methods based on miniature inertial sensors. Hand-gesture data are obtained through a data glove and preprocessed using Butterworth low-pass filtering and normalization algorithms. Magnetometer correction is performed using ellipsoidal fitting methods. An auxiliary segmentation algorithm is employed to segment the gesture data, and a gesture dataset is constructed. For static gesture recognition, we focus on four machine learning algorithms, namely support vector machine (SVM), backpropagation neural network (BP), decision tree (DT), and random forest (RF). We evaluate the model prediction performance through cross-validation comparison. For dynamic gesture recognition, we investigate the recognition of 10 dynamic gestures using Hidden Markov Models (HMM) and Attention-Biased Mechanisms for Bidirectional Long- and Short-Term Memory Neural Network Models (Attention-BiLSTM). We analyze the differences in accuracy for complex dynamic gesture recognition with different feature datasets and compare them with the prediction results of the traditional long- and short-term memory neural network model (LSTM). Experimental results demonstrate that the random forest algorithm achieves the highest recognition accuracy and shortest recognition time for static gestures. Moreover, the addition of the attention mechanism significantly improves the recognition accuracy of the LSTM model for dynamic gestures, with a prediction accuracy of 98.3%, based on the original six-axis dataset.

Synchronized canoeing is a cyclically repetitive sport, and two canoeists need to work in concert with each other’s power patterns and paddle movements to achieve great results. Most of the analysis of synchronized canoeing focuses on the mechanics and work output of oars. This paper proposes a motion capture method based on inertial sensors. The extended Kalman filter method is used to fuse the sensor information and reconstruct human movements. Four sets of joint angular movement data of shoulders and elbows of two canoeists are extracted respectively for kinematics analysis with correlation coefficient and dynamic time warping method. The experimental results show that there is a significant correlation (r=0.9605) between the shoulder joint angles of the synchronized canoeists. The dynamic time warping method can also clearly analyze the posture coordination of two canoeists. According to the analysis results of upper limb kinematics, this research can evaluate the synchronization effect of synchronized canoeing from the perspective of kinematics, help canoeists to improve their technical movements and help coaches to reasonably select athletes with matching skills and styles.

This paper presents a design method for a high-power optical system with multiple channels to achieve high-quality color-mixing and uniform lighting. The high-power optical system consists of a multi-channel reflector and a color-mixing component. The optical systems with different parameters are simulated to analyze the color-mixing performance. Simulation results show that the illumination uniformity of all optical systems is greater than 0.77, and the maximum color difference is 0.014. This optical system can be introduced into applications, such as illumination of machine vision, simulating daylight, smart lighting, and so on.

According to the working scenes, a proper light environment can enable people to maintain greater attention and meditation. A posture detection system in different working scenes is proposed in this paper, and different lighting conditions are provided for changes in body posture. This aims to stimulate the nervous system and improve work efficiency. A brainwave acquisition system was used to capture the participants’ optimal attention and meditation. The posture data are collected by ten miniature inertial measurement units (IMUs). The gradient descent method is used for information fusion and updating the participant’s attitude after sensor calibration. Compared with the optical capture system, the reliability of the system is verified, and the correlation coefficient of both joint angles is as high as 0.9983. A human rigid body model is designed for reconstructing the human posture. Five classical machine learning algorithms, including logistic regression, support vector machine (SVM), decision tree, random forest, and k-nearest neighbor (KNN), are used as classification algorithms to recognize different postures based on joint angles series. The results show that SVM and random forest achieve satisfactory classification effects. The effectiveness of the proposed method is demonstrated in the designed systematic experiment.

Rationale: The management of retrograde type A dissection (RTAD) after thoracic endovascular aortic repair (TEVAR) for type A aortic dissection (TAAD) has rarely been reported. We report the management of RTAD after TEVAR with in situ fenestration for TAAD. Patient concerns: A 59-year-old man with TAAD had undergone TEVAR with in situ fenestration 4 months prior to presenting to our emergency room complaining of acute chest and back pain. Computed tomography angiography showed RTAD starting from the proximal endograft and extending to the aortic root. Diagnosis: The patient was diagnosed with RTAD. Interventions: We performed only the Bentall procedure, and the patient did not require total arch replacement. We removed the bare spring of the proximal endograft and anastomosed the prosthetic graft with the endograft and the native ascending aortic wall. Outcomes: The postoperative course was uneventful, and the patient remained asymptomatic for 3 years after surgery. Computed tomography angiography at the 3-year follow-up showed no perivalvular or anastomotic leakage. Lessons: RTAD after TEVAR for TAAD was safely and effectively treated by anastomosing the prosthetic graft with the endograft and the native ascending aortic wall instead of total arch replacement.

Despite encouraging results have been achieved in human pose estimation in recent years, it remains challenging problems. When the background is similar to the human body parts, and there are small persons with low-resolution in the image, the performance may degrade dramatically. This paper addresses problems in background-inference and small-person pose estimation. To achieve this, a novel pose estimation algorithm is proposed on the basis of person semantic segmentation deep neural network. Different from most previous methods with a single pose estimation model, we generate mixture models with pose estimation and semantic segmentation. We introduce novel generative adversarial model and auxiliary model to realize the semantic segmentation network, which can handle the confusion of the similar regions in the background. In addition, to address the problem of the scale differences between big and small persons’ keypoints, we add additional position and channel attention modules to the first two stages of OpenPose. We conduct extensive experiments on COCO and VOC datasets. And we compare the proposed method with the most popular state-of-the-art human pose estimation and semantic segmentation frameworks, including MultiPoseNet, Deterton2 and DeepLab V3. Our experimental results show that the proposed method is more accurate than the state-of-the-art algorithms and performs effectively in tackling the complex situations.