The Internet of Things (IoT) boom has revolutionized almost every corner of people’s daily lives: healthcare, environment, transportation, manufacturing, supply chain, and so on. With the recent development of sensor and communication technology, IoT artifacts including smart wearables, cameras, smartwatches, and autonomous systems can accurately measure and perceive their surrounding environment. Continuous sensing generates massive amounts of data and presents challenges for machine learning. Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data. Graph neural networks (GNNs), an emerging and fast-growing family of neural network models, can capture complex interactions within sensor topology and have been demonstrated to achieve state-of-the-art results in numerous IoT learning tasks. In this survey, we present a comprehensive review of recent advances in the application of GNNs to the IoT field, including a deep dive analysis of GNN design in various IoT sensing environments, an overarching list of public data and source codes from the collected publications, and future research directions. To keep track of newly published works, we collect representative papers and their open-source implementations and create a Github repository at GNN4IoT.
Mobile sensing appears as a promising solution for health inference problem (e.g., influenza-like symptom recognition) by leveraging diverse smart sensors to capture fine-grained information about human behaviors and ambient contexts. Centralized training of machine learning models can place mobile users' sensitive information under privacy risks due to data breach and misexploitation. Federated Learning (FL) enables mobile devices to collaboratively learn global models without the exposure of local private data. However, there are challenges of on-device FL deployment using mobile sensing: 1) long-term and continuously collected mobile sensing data may exhibit domain shifts as sensing objects (e.g. humans) have varying behaviors as a result of internal and/or external stimulus; 2) model retraining using all available data may increase computation and memory burden; and 3) the sparsity of annotated crowd-sourced data causes supervised FL to lack robustness. In this work, we propose FedMobile, an incremental semi-supervised federated learning algorithm, to train models semi-supervisedly and incrementally in a decentralized online fashion. We evaluate FedMobile using a real-world mobile sensing dataset for influenza-like symptom recognition. Our empirical results show that FedMobile-trained models achieve the best results in comparison to the selected baseline methods.
Dipeptide-conjugated nucleosides were efficiently synthesized from the intermediates of 3'-amino-3'-deoxy-nucleosides by using the solid-phase synthetic strategy with HOBt/HBTU (1-hydroxy-1H-benzotriazole/ 2-(1H-benzotriazol-1-yl)-1,1,3,3-tetramethyluronium hexafluoroborate) as the coupling reagents (Schemes 1 ± 3). CD Spectra and thermal melting studies showed that the synthesized hydrophobic dipeptideÀthymidine and Àuridine derivatives 8a ± 8d, 13a ± d, and 18 had a mild affinity with the polyA ¥ polyU duplex and could induce the change of RNA conformation. The results also implied that the interaction of conjugates with RNA might be related to the sugar pucker conformation of the nucleoside.Introduction. ± The functional and structural diversities of RNA provide numerous opportunities for academic researchers and pharmaceutical industry to develop small molecules to target specific RNA for treating a variety of diseases, such as bacteria or virus infections [1]. The RNA secondary structure of base pairing is more conservative than its primary sequence, so the potential for slower development of drug resistance against small molecules is one of the advantages of targeting RNA over traditional protein targets. Aminoglycosides, a class of structurally diverse aminocyclitols with potent antibiotic and antiviral activities are intensively and well-studied RNA binders. They can selectively and stoichiometrically bind with functional RNA motifs and disrupt the proteinÀRNA, RNPÀRNA, or RNAÀRNA interaction [2]. On the basis of the study of RNA in the presence of aminoglycosides and other small molecules, the interactions of RNA with small molecules are affected by the distribution of charged, aromatic, and H-bonding groups of a relatively rigid scaffold [1]. Considering the interaction of proteinÀRNA, the a-helix conformation of the protein provides a scaffold for H-bonding with RNA bases, the b-sheet form is suitable for binding aromatic groups with unstacked bases, and the negative phosphodiester moiety of RNA supplies a function for the electrostatic interaction. Furthermore, the structure of RNA is dynamic, and the conformational change can be induced by a small molecule [2]. The structural and functional features of RNA stimulated our enthusiasm to find moreselective and potent small molecules, and the adoption of virtual screening, surface plasmon resonance (SPR), and other technologies also speeded up the process [3].Our previous findings indicated that aminoglycosyl-nucleosides could bind to RNA with high affinity [4]. Besides that the configuration of the glycosyl moiety could affect their interaction, the heterocyclic-base moiety also showed an effect on the base stacking of the RNA duplex. Peptides have a relatively flexible conformation as compared to a glycosyl moiety. The diverse functional groups of a peptide, such as
Background: Only few studies have yet investigated whether perioperative administration of pregabalin can reduce the incidence of postoperative chronic neuropathic pain after total hip arthroplasty (THA). This prospective, randomized study compared placebo with pregabalin in the hope that a lower pregabalin dose would improve analgesia without increasing side-effects after THA. Methods: This study was a prospective randomized blinded study, with a parallel design and an allocation ratio of 1:1 for the treatment groups. The study was approved by the Institutional Review Board in Weifang People's Hospital and written informed consent was obtained from all subjects before enrolment. A total of 120 patients who meet inclusion criteria are randomized to either pregabalin or placebo group. The primary objective of the study was visual analog scale score. As secondary outcomes, opioid consumption measurement, Harris Hip Score, hip range of motion, patient satisfaction, and complications were made at different time points throughout the study for comparison. Results: The null hypothesis of this study was that pregabalin would reduce pain after THA. Trial registration: This study protocol was registered in Research Registry (researchregistry5669).
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.