A review of various calibration techniques of MEMS inertial sensors is presented in this paper. MEMS inertial sensors are subject to various sources of error, so it is essential to correct these errors through calibration techniques to improve the accuracy and reliability of these sensors. In this paper, we first briefly describe the main characteristics of MEMS inertial sensors and then discuss some common error sources and the establishment of error models. A systematic review of calibration methods for inertial sensors, including gyroscopes and accelerometers, is conducted. We summarize the calibration schemes into two general categories: autonomous and nonautonomous calibration. A comprehensive overview of the latest progress made in MEMS inertial sensor calibration technology is presented, and the current state of the art and development prospects of MEMS inertial sensor calibration are analyzed with the aim of providing a reference for the future development of calibration technology.

Compared with optical sensors, wearable inertial sensors have many advantages such as low cost, small size, more comprehensive application range, no space restrictions and occlusion, better protection of user privacy, and more suitable for sports applications. This article aims to solve irregular actions that table tennis enthusiasts do not know in actual situations. We use wearable inertial sensors to obtain human table tennis action data of professional table tennis players and non-professional table tennis players, and extract the features from them. Finally, we propose a new method based on multi-dimensional feature fusion convolutional neural network and fine-grained evaluation of human table tennis actions. Realize ping-pong action recognition and evaluation, and then achieve the purpose of auxiliary training. The experimental results prove that our proposed multi-dimensional feature fusion convolutional neural network has an average recognition rate that is 0.17 and 0.16 higher than that of CNN and Inception-CNN on the nine-axis non-professional test set, which proves that we can better distinguish different human table tennis actions and have a more robust generalization performance. Therefore, on this basis, we have better realized the enthusiast of table tennis the purpose of the action for auxiliary training.

In this paper, we present a new method to estimate ground reaction forces (GRF) from wearable sensors for a variety of real-world situations. We address the drawbacks of using force plates with limited activity range and high cost in previous work. We use a transformer encoder as a feature extractor to extract temporal and spatial features from wearable sensors more efficiently. Using the Mean Absolute Percentage Error (MAPE) as the evaluation criterion, the experimental results show that the average error of the predicted values using the transformer as a feature extractor improved by 32% compared to the RNN architecture and by 25% compared to the LSTM architecture. Finally, we use Gate_MSE to solve the problem of a large peak error in GRF prediction. Meanwhile, this paper explores the effect of the number of wearable sensors or wearable modes on GRF prediction.

Musculoskeletal injuries induced by high-intensity and repetitive physical activities represent one of the primary health concerns in the fields of public fitness and sports. Musculoskeletal injuries, often resulting from unscientific training practices, are particularly prevalent, with the tibia being especially vulnerable to fatigue-related damage. Current tibial load monitoring methods rely mainly on laboratory equipment and wearable devices, but datasets combining both sources are limited due to experimental complexities and signal synchronization challenges. Moreover, wearable-based algorithms often fail to capture deep signal features, hindering early detection and prevention of tibial fatigue injuries. In this study, we simultaneously collected data from laboratory equipment and wearable insole sensors during in-place running by volunteers, creating a dataset named WearLab-Leg. Based on this dataset, we developed a machine learning model integrating Temporal Convolutional Network (TCN) and Transformer modules to estimate vertical ground reaction force (vGRF) and tibia bone force (TBF) using insole pressure signals. Our model’s architecture effectively combines the advantages of local deep feature extraction and global modeling, and further introduces the Weight-MSELoss function to improve peak prediction performance. As a result, the model achieved a normalized root mean square error (NRMSE) of 7.33% for vGRF prediction and 10.64% for TBF prediction. Our dataset and proposed model offer a convenient solution for biomechanical monitoring in athletes and patients, providing reliable data and technical support for early warnings of fatigue-induced injuries.

We propose a novel pose estimation method that can predict the full-body pose from six inertial sensors worn by the user. This method solves problems encountered in vision, such as occlusion or expensive deployment. We address several complex challenges. First, we use the SRU network structure instead of the bidirectional RNN structure used in previous work to reduce the computational effort of the model without losing its accuracy. Second, our model does not require joint position supervision to achieve the best results of the previous work. Finally, since sensor data tend to be noisy, we use SmoothLoss to reduce the impact of inertial sensors on pose estimation. The faster deep inertial poser model proposed in this paper can perform online inference at 90 FPS on the CPU. We reduce the impact of each error by more than 10% and increased the inference speed by 250% compared to the previous state of the art.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.