Trajectory tracking control for quadrotors is important for applications ranging from surveying and inspection, to film making. However, designing and tuning classical controllers, such as proportional-integral-derivative (PID) controllers, to achieve high tracking precision can be timeconsuming and difficult, due to hidden dynamics and other non-idealities. The Deep Neural Network (DNN), with its superior capability of approximating abstract, nonlinear functions, proposes a novel approach for enhancing trajectory tracking control. This paper presents a DNN-based algorithm as an addon module that improves the tracking performance of a classical feedback controller. Given a desired trajectory, the DNNs provide a tailored reference input to the controller based on their gained experience. The input aims to achieve a unity map between the desired and the output trajectory. The motivation for this work is an interactive "fly-as-you-draw" application, in which a user draws a trajectory on a mobile device, and a quadrotor instantly flies that trajectory with the DNNenhanced control system. Experimental results demonstrate that the proposed approach improves the tracking precision for user-drawn trajectories after the DNNs are trained on selected periodic trajectories, suggesting the method's potential in realworld applications. Tracking errors are reduced by around 40-50% for both training and testing trajectories from users, highlighting the DNNs' capability of generalizing knowledge. Accepted final version.

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches. However, acquiring additional clinical data can be expensive, and handcrafting features is burdensome. In this paper, we take a third approach, proposing Consensus Networks (CNs), a framework to classify after reaching agreements between modalities. We divide linguistic features into non-overlapping subsets according to their modalities, and let neural networks learn low-dimensional representations that agree with each other. These representations are passed into a classifier network. All neural networks are optimized iteratively.In this paper, we also present two methods that improve the performance of CNs. We then present ablation studies to illustrate the effectiveness of modality division. To understand further what happens in CNs, we visualize the representations during training. Overall, using all of the 413 linguistic features, our models significantly outperform traditional classifiers, which are used by the state-of-the-art papers.

Background Gastric cancer (GC) is a common type of gastrointestinal tumor in the world. Transfer RNA (tRNA) derived fragments (tsRNAs) implicate various cancers, but their roles in GC remain unclear. Our study aimed to investigate the potential biological functions and molecular mechanisms of tsRNAs in GC. Methods Differentially expressed tsRNAs were identified using high-throughput sequencing. The expression levels of tsRNAs were validated in 62 paired GC tissues and adjacent normal tissues using RT-qPCR. In vitro functional assays were used to evaluate the influences of tsRNAs on GC cells. The potential mechanisms underlying tsRNAs were explored using bioinformatics analysis,RT-qPCR, RNA immunoprecipitation assays and Western blot. Results We found that tiRNA-Val-CAC-001 was downregulated in GC tissues and cells, and demonstrated that tiRNA-Val-CAC-001 was a tsRNA sheared from mature tRNA-Val and mainly localized in the cytoplasm. tiRNA-Val-CAC-001 overexpression inhibited metastasis and proliferation but promoted apoptosis of GC cells; nevertheless, tiRNA-Val-CAC-001 knockdown increased metastasis and proliferation and reduced apoptosis ( P <0.05). GO and KEGG analyses indicated tiRNA-Val-CAC-001 may exert its effects via Wnt/β-catenin signaling pathway by targeting LRP6. Following experiments showed that tiRNA-Val-CAC-001 could downregulated the protein levels of LRP6 and β-catenin, but up-regulated p-β-catenin, which confirmed the findings in bioinformatics analysis. Conclusion In conclusion, tiRNA-Val-CAC-001 works as a cancer suppressor in GC by targeting LRP6 via Wnt/β-catenin signaling pathway. tiRNA-Val-CAC-001 may serve as a therapy target and a biomarker of GC in the future. Key Points tiRNA-Val-CAC-001 is downregulated in gastric cancer tissues and cell lines, tiRNA-Val-CAC-001 has potential to become a novel diagnostic biomarker in gastric cancer, and tiRNA-Val-CAC-001 regulates gastric cancer cells by targeting LRP6.

Recently, neural language models (LMs) have demonstrated impressive abilities in generating high-quality discourse. While many recent papers have analyzed the syntactic aspects encoded in LMs, to date, there has been no analysis of the inter-sentential, rhetorical knowledge. In this paper, we propose a method that quantitatively evaluates the rhetorical capacities of neural LMs. We examine the capacities of neural LMs understanding the rhetoric of discourse by evaluating their abilities to encode a set of linguistic features derived from Rhetorical Structure Theory (RST). Our experiments show that BERT-based LMs outperform other Transformer LMs, revealing the richer discourse knowledge in their intermediate layer representations. In addition, GPT-2 and XLNet apparently encode less rhetorical knowledge, and we suggest an explanation drawing from linguistic philosophy. Our method presents an avenue towards quantifying the rhetorical capacities of neural LMs.

No abstract