Cephalometric analysis is a standard tool for assessment and prediction of craniofacial growth, orthodontic diagnosis, and oral-maxillofacial treatment planning. The aim of this study is to develop a fully automatic system of cephalometric analysis, including cephalometric landmark detection and cephalometric measurement in lateral cephalograms for malformation classification and assessment of dental growth and soft tissue profile. First, a novel method of multiscale decision tree regression voting using SIFT-based patch features is proposed for automatic landmark detection in lateral cephalometric radiographs. Then, some clinical measurements are calculated by using the detected landmark positions. Finally, two databases are tested in this study: one is the benchmark database of 300 lateral cephalograms from 2015 ISBI Challenge, and the other is our own database of 165 lateral cephalograms. Experimental results show that the performance of our proposed method is satisfactory for landmark detection and measurement analysis in lateral cephalograms.
Convolutional neural networks (CNNs) have been widely applied in the fields of medical tasks because they can achieve high accuracy in many fields using a large number of parameters and operations. However, many applications designed for auxiliary checks or help need to be deployed into portable devices, where the huge number of operations and parameters of a standard CNN can become an obstruction. MobileNet adopts a depthwise separable convolution to replace the standard convolution, which can greatly reduce the number of operations and parameters while maintaining a relatively high accuracy. Such highly structured models are very suitable for FPGA implementation in order to further reduce resource requirements and improve efficiency. Many other implementations focus on performance more than on resource requirements because MobileNets has already reduced both parameters and operations and obtained significant results. However, because many small devices only have limited resources they cannot run MobileNet-like efficient networks in a normal way, and there are still many auxiliary medical applications that require a high-performance network running in real-time to meet the requirements. Hence, we need to figure out a specific accelerator structure to further reduce the memory and other resource requirements while running MobileNet-like efficient networks. In this paper, a MobileNet accelerator is proposed to minimize the on-chip memory capacity and the amount of data that is transferred between on-chip and off-chip memory. We propose two configurable computing modules: Pointwise Convolution Accelerator and Depthwise Convolution Accelerator, to parallelize the network and reduce the memory requirement with a specific dataflow model. At the same time, a new cache usage method is also proposed to further reduce the use of the on-chip memory. We implemented the accelerator on Xilinx XC7Z020, deployed MobileNetV2 on it, and achieved 70.94 FPS with 524.25 KB on-chip memory usage under 150 MHz.
18 April 2022 in IEEE Transactions on Neural Networks and Learning Systems
This article studies the meaning of parameters of fully connected neural networks with single hidden layer from the perspective of spectrum. Under the constraints of numerical range, the corresponding relationship between parameters and the spectrum of network function can be established by the Fourier series coefficients of the activation function, which is truncated and periodically extended. This work is substantiated on the Mixed National Institute of Standards and Technology (MNIST) handwritten dataset and two illustrative examples with certain spectra. The simulations complete the conversion between spectrum and parameters with high precision and give the significance of hidden nodes to the spectrum of network function. Some algorithms derived from these properties, such as the parameter initialization method using spectrum and the pruning method by sorting amplification weights, are also presented to introduce how spectrum analysis affects neural network decision-making. Thus, spectrum analysis has great potential in network interpretation.
As a crucial part of ubiquitous networking and computing (UNC) technologies, low earth orbit (LEO) satellite communications aim at providing internet connectivity services everywhere. To improve the spectrum efficiency of satellite-to-ground communications, adaptive modulation and coding (AMC) are widely used, which can adjust the modulation and coding types according to the varying channel condition. However, satellite-to-ground communication channels have the characterizations such as fast dynamic change, fast switching, and significant fading. These characterizations make it challenging to predict the channel state information accurately and, thus, to perform accurate AMC. For example, rain loss is one of the crucial factors in satellite-to-ground channel fading. In general, it is difficult to build an integrated global model for rain loss because it varies in different regions around the world. Moreover, for the emerging applications of multiple antennas on satellites, the conventional look-up table method cannot cope with the high-dimensional inputs of the multiple antennas. To tackle the above challenges, we propose an AMC method based on deep learning (DL) and deep reinforcement learning (DRL) for ubiquitous satellite-to-ground networks. The proposed method directly processes real-time global weather and location information in the environment and intelligently selects encoding schemes to maximize system throughput. Simulation results show that the proposed method can increase the total throughput. The total number of correctly transmitted bits per unit time is improved, and the efficiency of the satellite-to-ground communication is enhanced.
1 December 2021 in Research in Astronomy and Astrophysics
Radio frequency interference (RFI) will pollute the weak astronomical signals receivedby radio telescopes, which in return will seriously affect the time-domain astronomical observation and research. In this paper, we use a deep learning method to identify RFI in frequency spectrum data, and propose a neural network based on Unet that combines the principles of depthwise separable convolution and residual, named DSC Based Dual-Resunet. Compared with the existing Unet network, DSC Based Dual-Resunet performs better in terms ofaccuracy, F1 score, and MIoU, and is also better in terms of computation cost where the model size and parameter amount are 12.5% of Unet and the amount of computation is 38%ofUnet. The experimental results show that the proposed network is a high-performance and lightweight network, and it is hopeful to be applied to RFI identification of radio telescopes on a large scale.
A future unmanned system needs the ability to perceive, decide and control in an open dynamic environment. In order to fulfill this requirement, it needs to construct a method with a universal environmental perception ability. Moreover, this perceptual process needs to be interpretable and understandable, so that future interactions between unmanned systems and humans can be unimpeded. However, current mainstream DNN (deep learning neural network)-based AI (artificial intelligence) is a ‘black box’. We cannot interpret or understand how the decision is made by these AIs. An SNN (spiking neural network), which is more similar to a biological brain than a DNN, has the potential to implement interpretable or understandable AI. In this work, we propose a neuron group-based structural learning method for an SNN to better capture the spatial and temporal information from the external environment, and propose a time-slicing scheme to better interpret the spatial and temporal information of responses generated by an SNN. Results show that our method indeed helps to enhance the environment perception ability of the SNN, and possesses a certain degree of robustness, enhancing the potential to build an interpretable or understandable AI in the future.