Assembled draft genomes usually contain many gaps because of the length limit of next-generation sequencing. Although many gap-closing tools have been developed, most of them still attempt to fill gaps on the basis of next-generation sequencing reads (always < 200 bp). Hence, the gap-filling effect is inferior. Several tools that use long-reads to close gaps have recently been created. However, they require extensive runtimes, which may not be suitable for large genomes. We describe a gap-closing tool called PGcloser, which supports parallel mode and adopts long-reads/contigs to fill gaps in genome sequences. Three tests show that PGcloser is faster than other tools but exhibits similar accuracy. PGcloser is free open-source software that is available at http://software.tobaccodb.org/software/pgcloser .
Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. The remaining challenges are the obvious scale difference between different types of COVID-19 lesions and the similarity between the lesions and normal tissues. This work aims to segment lesions of different scales and lesion boundaries correctly by utilizing multiscale and multilevel features. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features for better segmentation of lesions at different scales. Furthermore, a multilevel feature aggregate (MLFA) module is proposed to reduce the information loss in the downsampling process. Experiments on the publicly available COVID-19 CT Segmentation dataset demonstrate that the proposed MSDC-Net is superior to other existing methods in segmenting lesion boundaries and large, medium, and small lesions, and achieves the best results in Dice similarity coefficient, sensitivity and mean intersection-over-union (mIoU) scores of 82.4%, 81.1% and 78.2%, respectively. Compared with other methods, the proposed model has an average improvement of 10.6% and 11.8% on Dice and mIoU. Compared with the existing methods, our network achieves more accurate segmentation of lesions at various scales and lesion boundaries, which will facilitate further clinical analysis. In the future, we consider integrating the automatic detection and segmentation of COVID-19, and conduct research on the automatic diagnosis system of COVID-19.
Due to the great success of Vision Transformer (ViT) in image classification tasks, many pure Transformer architectures for human action recognition have been proposed. However, very few works have attempted to use Transformer to conduct bimodal action recognition, i.e., both skeleton and RGB modalities for action recognition. As proved in many previous works, RGB modality and skeleton modality are complementary to each other in human action recognition tasks. How to use both RGB and skeleton modalities for action recognition in a Transformer-based framework is a challenge. In this paper, we propose RGBSformer, a novel two-stream pure Transformer-based framework for human action recognition using both RGB and skeleton modalities. Using only RGB videos, we can acquire skeleton data and generate corresponding skeleton heatmaps. Then, we input skeleton heatmaps and RGB frames to Transformer at different temporal and spatial resolutions. Because the skeleton heatmaps are primary features compared to the original RGB frames, we use fewer attention layers in the skeleton stream. At the same time, two ways are proposed to fuse the information of two streams. Experiments demonstrate that the proposed framework achieves the state of the art on four benchmarks: three widely used datasets, Kinetics400, NTU RGB+D 60, and NTU RGB+D 120, and the fine-grained dataset FineGym99.
Physical layer secret key generation (PLKG) is a promising technology for establishing effective secret keys. Current works for PLKG mostly study key generation schemes in ideal communication environments with little or even no signal interference. In terms of this issue, exploiting the reconfigurable intelligent reflecting surface (IRS) to assist PLKG has caused an increasing interest. Most IRS-assisted PLKG schemes focus on the single-input-single-output (SISO), which is limited in future communications with multi-input-multi-output (MIMO). However, MIMO could bring a serious overhead of channel reciprocity extraction. To fill the gap, this paper proposes a novel low-overhead IRS-assisted PLKG scheme with deep learning in the MIMO communications environments. We first combine the direct channel and the reflecting channel established by the IRS to construct the channel response function, and we propose a theoretically optimal interaction matrix to approach the optimal achievable rate. Then we design a channel reciprocity-learning neural network with an IRS introduced (IRS-CRNet), which is exploited to extract the channel reciprocity in time division duplexing (TDD) systems. Moreover, a PLKG scheme based on the IRS-CRNet is proposed. Final simulation results verify the performance of the PLKG scheme based on the IRS-CRNet in terms of key generation rate, key error rate and randomness.
As the development of the Internet of Things (IoT) continues, Federated Learning (FL) is gaining popularity as a distributed machine learning framework that does not compromise the data privacy of each participant. However, the data held by enterprises and factories in the IoT often have different distribution properties (Non-IID), leading to poor results in their federated learning. This problem causes clients to forget about global knowledge during their local training phase and then tends to slow convergence and degrades accuracy. In this work, we propose a method named FedRAD, which is based on relational knowledge distillation that further enhances the mining of high-quality global knowledge by local models from a higher-dimensional perspective during their local training phase to better retain global knowledge and avoid forgetting. At the same time, we devise an entropy-wise adaptive weights module (EWAW) to better regulate the proportion of loss in single-sample knowledge distillation versus relational knowledge distillation so that students can weigh losses based on predicted entropy and learn global knowledge more effectively. A series of experiments on CIFAR10 and CIFAR100 show that FedRAD has better performance in terms of convergence speed and classification accuracy compared to other advanced FL methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.