The simplification of the insomnia severity index and epworth sleepiness scale using machine learning models

Insomnia and excessive daytime sleepiness (EDS) are the most common complaints in sleep clinics, and the cost of healthcare services associated with them have also increased significantly. Though the brief questionnaires such as the Insomnia Severity Index (ISI) and Epworth Sleepiness Scale (ESS) can be useful to assess insomnia and EDS, there are some limitations to apply for large numbers of patients. As the researches using the Internet of Things technology become more common, the need for the simplification of sleep questionnaires has been also growing. We aimed to simplify ISI and ESS using machine learning algorithms and deep neural networks with attention models. The medical records of 1,241 patients who examined polysomnography for insomnia or EDS were analyzed. All patients are classified into five groups according to the severity of insomnia and EDS. To develop the model, six machine learning algorithms were firstly applied. After going through normalization, the process with the CNN+ Attention model was applied. We classified a group with an accuracy of 93% even with only the results of 6 items (ISI1a, ISI1b, ISI3, ISI5, ESS4, ESS7). We simplified the sleep questionnaires with maintaining high accuracy by using machine learning models.

Point Cloud Deep Learning Network Based on Balanced Sampling and Hybrid Pooling

The automatic semantic segmentation of point cloud data is important for applications in the fields of machine vision, virtual reality, and smart cities. The processing capability of the point cloud segmentation method with PointNet++ as the baseline needs to be improved for extremely imbalanced point cloud scenes. To address this problem, in this study, we designed a weighted sampling method based on farthest point sampling (FPS), which adjusts the sampling weight value according to the loss value of the model to equalize the sampling process. We also introduced the relational learning of the neighborhood space of the sampling center point in the feature encoding process, where the feature importance is distinguished by using a self-attention model. Finally, the global-local features were aggregated and transmitted using the hybrid pooling method. The experimental results of the six-fold crossover experiment showed that on the S3DIS semantic segmentation dataset, the proposed network achieved 9.5% and 11.6% improvement in overall point-wise accuracy (OA) and mean of class-wise intersection over union (MIoU), respectively, compared with the baseline. On the Vaihingen dataset, the proposed network achieved 4.2% and 3.9% improvement in OA and MIoU, respectively, compared with the baseline. Compared with the segmentation results of other network models on public datasets, our algorithm achieves a good balance between OA and MIoU.

Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras

In this paper, an efficient normal estimation and filtering method for depth images acquired by Time-of-Flight (ToF) cameras is proposed. The method is based on a common feature pyramid networks (FPN) architecture. The normal estimation method is called ToFNest, and the filtering method ToFClean. Both of these low-level 3D point cloud processing methods start from the 2D depth images, projecting the measured data into the 3D space and computing a task-specific loss function. Despite the simplicity, the methods prove to be efficient in terms of robustness and runtime. In order to validate the methods, extensive evaluations on public and custom datasets were performed. Compared with the state-of-the-art methods, the ToFNest and ToFClean algorithms are faster by an order of magnitude without losing precision on public datasets.

Geometric Feature Extraction of Point Cloud of Chemical Reactor Based on Dynamic Graph Convolution Neural Network

Geometric features are an important factor for the classification of drugs and other transport objects in chemical reactors. The moving speed of drugs and other transport objects in chemical reactors is fast, and it is difficult to obtain their features by imaging and other methods. In order to avoid the mistaken and missed distribution of drugs and other objects, a method of extracting geometric features of the drug's point cloud in a chemical reactor based on a dynamic graph convolution neural network (DGCNN) is proposed. In this study, we first use MATLAB R2019a to add a random number of noise points in each point cloud file and label the point cloud. Second, k-nearest neighbor (KNN) is used to construct the adjacency relationship of all nodes, and the effect of DGCNN under different k values and the confusion matrix under the optimal k value are analyzed. Finally, we compare the effect of DGCNN with PointNet and PointNet++. The experimental results show that when k is 20, the accuracy, precision, recall, and F1 score of DGCNN are higher than those of other k values, while the training time is much shorter than that of k = 25, 30, and 35; in addition, the effect of DGCNN in extracting geometric features of the point cloud is better than that of PointNet and PointNet++. The results show that it is feasible to use DGCNN to analyze the geometric characteristics of drug point clouds in a chemical reactor. This study fills the gap of the end-to-end extraction method for a point cloud's corresponding geometric features without a data set. In addition, this study promotes the institutionalization, standardization, and intelligent design of safe production and management of drugs and other objects in the chemical reactor, and it has positive significance for the production cost and resource utilization of the whole pharmaceutical process. At the same time, it provides a new method for the intelligent processing of point cloud data.