An accurate and efficient automatic brain tumor segmentation algorithm is important for clinical practice. In recent years, there has been much interest in automatic segmentation algorithms that use convolutional neural networks. In this paper, we propose a novel hierarchical multi-scale segmentation network (HMNet), which contains a high-resolution branch and parallel multi-resolution branches. The high-resolution branch can keep track of the brain tumor’s spatial details, and the multi-resolution feature exchange and fusion allow the network’s receptive fields to adapt to brain tumors of different shapes and sizes. In particular, to overcome the large computational overhead caused by expensive 3D convolution, we propose a lightweight conditional channel weighting block to reduce GPU memory and improve the efficiency of HMNet. We also propose a lightweight multi-resolution feature fusion (LMRF) module to further reduce model complexity and reduce the redundancy of the feature maps. We run tests on the BraTS 2020 dataset to determine how well the proposed network would work. The dice similarity coefficients of HMNet for ET, WT, and TC are 0.781, 0.901, and 0.823, respectively. Many comparative experiments on the BraTS 2020 dataset and other two datasets show that our proposed HMNet has achieved satisfactory performance compared with the SOTA approaches.

As a powerful global registration method for point clouds, the 4-points congruent sets (4PCS) algorithm has been wildly used in the 3D scene reconstruction field. In this paper, we propose an adaptive 4PCS (A4PCS), which aims to provide a robustness rigid transformation for two or more overlapping laser scans. The proposed method only incorporates the distance information of the stereoscopic base set and a fast mechanism for congruent base extraction into 4PCS. To ensure the registration accuracy when dealing with restrictive situations, such as point clouds with small overlaps or scenes with symmetrical structures, a non-coplanar 4-points base set is adopted without extra time consumption. Besides, the adaptive set fine-tuning is introduced to the point pair searching process to accelerate the convergence of the algorithm. In addition, we replace the binary cost function of the original 4PCS with a modified estimator to strengthen the robustness of the proposed method. Experiments on thirteen pairs of point clouds for 3D indoor scenes, including ten regular size models and three scenes of one large-scale model, can demonstrate the accuracy and efficiency of the proposed method.

Pedestrian dead reckoning is a challenging task due to the low-cost inertial sensor error accumulation. Recent research has shown that deep learning methods can achieve impressive performance in handling this issue. In this letter, we propose inertial odometry using a deep learning-based velocity estimation method. The deep neural network based on Res2Net modules and two convolutional block attention modules is leveraged to restore the potential connection between the horizontal velocity vector and raw inertial data from a smartphone. Our network is trained using only fifty percent of the public inertial odometry dataset (RoNIN) data. Then, it is validated on the RoNIN testing dataset and another public inertial odometry dataset (OXIOD). Compared with the traditional step-length and heading system-based algorithm, our approach decreases the absolute translation error (ATE) by 76%-86%. In addition, compared with the state-of-the-art deep learning method (RoNIN), our method improves its ATE by 6%-31.4%.

With the widespread application of machine learning techniques in time series analysis, the interpretability of models trained on time series data has attracted increasing attention. Most existing explanation methods are based on time-domain features, making it difficult to reveal how complex models focus on time–frequency information. To address this, this paper proposes a time–frequency domain-based time series interpretation method aimed at enhancing the interpretability of models at the time–frequency domain. This method extends the traditional LIME algorithm by combining the ideas of short-time Fourier transform (STFT), inverse STFT, and local interpretable model-agnostic explanations (LIME), and introduces a self-designed TFHS (time–frequency homogeneous segmentation) algorithm. The TFHS algorithm achieves precise homogeneous segmentation of the time–frequency matrix through peak detection and clustering analysis, incorporating the distribution characteristics of signals in both frequency and time dimensions. The experiment verified the effectiveness of the TFHS algorithm on Synthetic Dataset 1 and the effectiveness of the TF-LIME algorithm on Synthetic Dataset 2, and then further evaluated the interpretability performance on the MIT-BIH dataset. The results demonstrate that the proposed method significantly improves the interpretability of time-series models in the time–frequency domain, exhibiting strong generalization capabilities and promising application prospects.

Accurately estimating human pose is crucial for providing feedback during exercises or musical performances, but the complex and flexible nature of human joints makes it challenging. Additionally, traditional methods often neglect pixel coordinates, which are naturally present in high-resolution images of the human body. To address this issue, we propose a novel human pose estimation method that directly incorporates pixel coordinates. Our method adds a coordinate channel to the convolution process and embeds pixel coordinates into the feature map, while also using coordinate attention to capture position- and structure-sensitive features. We further reduce the network parameters and computational cost by using small-scale convolution kernels and a smooth activation function in residual blocks. We evaluate our model on the MPII Human Pose and COCO Keypoint Detection datasets and demonstrate improved accuracy, highlighting the importance of directly incorporating coordinate location information in position-sensitive tasks.