Semantic Segmentation of 3D Point Cloud Based on Spatial Eight-Quadrant Kernel Convolution

In order to deal with the problem that some existing semantic segmentation networks for 3D point clouds generally have poor performance on small objects, a Spatial Eight-Quadrant Kernel Convolution (SEQKC) algorithm is proposed to enhance the ability of the network for extracting fine-grained features from 3D point clouds. As a result, the semantic segmentation accuracy of small objects in indoor scenes can be improved. To be specific, in the spherical space of the point cloud neighborhoods, a kernel point with attached weights is constructed in each octant, the distances between the kernel point and the points in its neighborhood are calculated, and the distance and the kernel points’ weights are used together to weight the point cloud features in the neighborhood space. In this case, the relationship between points are modeled, so that the local fine-grained features of the point clouds can be extracted by the SEQKC. Based on the SEQKC, we design a downsampling module for point clouds, and embed it into classical semantic segmentation networks (PointNet++, PointSIFT and PointConv) for semantic segmentation. Experimental results on benchmark dataset ScanNet V2 show that SEQKC-based PointNet++, PointSIFT and PointConv outperform the original networks about 1.35–2.12% in terms of MIoU, and they effectively improve the semantic segmentation performance of the networks for small objects of indoor scenes, e.g., the segmentation accuracy of small object “picture” is improved from 0.70% of PointNet++ to 10.37% of SEQKC-PointNet++.

Tsunami propagation kernel and its applications

Tsunamis rarely occur in a specific area, and their occurrence is highly uncertain. Suddenly generated from their sources in deep water, they occasionally undergo tremendous amplification in shallow water to devastate low-lying coastal areas. Despite the advancement of computational power and simulation algorithms, there is a need for novel and rigorous approaches to efficiently predict coastal amplification of tsunamis during different disaster management phases, such as tsunami risk assessment and real-time forecast. This study presents convolution kernels that can instantly predict onshore waveforms of water surface elevation and flow velocity from observed/simulated wave data away from the shore. Kernel convolution involves isolating an incident-wave component from the offshore wave data and transforming it into the onshore waveform. Moreover, unlike previously derived ones, the present kernels are based on shallow-water equations with a damping term and can account for tsunami attenuation on its path to the shore with a damping parameter. Kernel convolution can be implemented at a low computational cost compared to conventional numerical models that discretise the spatial domain. The prediction capability of the kernel method was demonstrated through application to real-world tsunami cases.

Multi-kernel CNN block-based detection for COVID-19 with imbalance dataset

COVID-19, which originated from Wuhan, rapidly spread throughout the world and became a public health crisis. Recognizing the positive cases at the earliest stage was crucial in order to restrain the spread of this virus and to perform medical treatment quickly for patients affected. However, the limited supply of RT-PCR as a diagnosis tool caused greatly delay in obtaining examination results of the suspected patients. Previous research stated that using radiologic images could be utilized to detect COVID-19 before the symptoms appeared. With the rapid development of Artificial intelligence in medical imaging in recent years, deep learning as the core of this technology could achieve human-level-performance in diagnostic accuracy. In this paper, deep learning was implemented to detect COVID-19 using a chest X-ray dataset. The proposed model employed a multi-kernel convolution neural network (CNN) block combined with pre-trained ResNet-34 to overcome an imbalanced dataset. The model block adopted different kernel sizes as follows 1x1, 3x3, 5x5, and 7x7. The findings show that the proposed model is capable of performing binary and three class classification tasks with an accuracy of 100% and 93.51% in the validation phase and 95% and 83% in the test phase, respectively.

Integrating Extracted Information from Bert and Multiple Embedding Methods with the Deep Neural Network for Humour Detection

Humour detection from sentences has been an interesting and challenging task in the last few years. In attempts to highlight humour detection, most research was conducted using traditional approaches of embedding, e.g., Word2Vec or Glove. Recently BERT sentence embedding has also been used for this task. In this paper, we propose a framework for humour detection in short texts taken from news headlines. Our proposed framework (IBEN) attempts to extract information from written text via the use of different layers of BERT. After several trials, weights were assigned to different layers of the BERT model. The extracted information was then sent to a Bi-GRU neural network as an embedding matrix. We utilized the properties of some external embedding models. A multi-kernel convolution in our neural network was also employed to extract higher-level sentence representations. This framework performed very well on the task of humour detection.

Tsunami propagation kernel and its applications

Tsunamis rarely occur in a specific area, and their occurrence is highly uncertain. Generated from their sources in deep water, they occasionally undergo tremendous amplification over decreasing water depth to devastate low-lying coastal areas. Despite the advancement of computational power and simulation algorithms, there is a need for novel and rigorous approaches to efficiently predict coastal amplification of tsunamis during different disaster management phases, such as tsunami risk assessment and real-time forecast. This study presents convolution kernels that can instantly predict onshore waveforms of water surface elevation and flow velocity from observed/simulated wavedata apart from the shore. Kernel convolution involves isolating an incident-wave component from the offshore wavedata and transforming it into the onshore waveform. Moreover, unlike previous derived ones, the present kernels are based on shallow-water equations with a damping term and can account for tsunami attenuation on its path to the shore with a damping parameter. Kernel convolution can be implemented at a low computational cost compared to conventional numerical models that discretise the spatial domain. The prediction capability of the kernel method was demonstrated through application to real-world tsunami cases.