Cloud Computing provides an effective platform for executing large-scale and complex workflow applications with a pay-as-you-go model. Nevertheless, various challenges, especially its optimal scheduling for multiple conflicting objectives, are yet to be addressed properly. The existing multi-objective workflow scheduling approaches are still limited in many ways, e.g., encoding is restricted by prior experts' knowledge when handling a dynamic real-time problem, which strongly influences the performance of scheduling. In this paper, we apply a deep-Q-network model in a multi-agent reinforcement learning setting to guide the scheduling of multi-workflows over infrastructure-as-a-service clouds. To optimize multi-workflow completion time and user's cost, we consider a Markov game model, which takes the number of workflow applications and heterogeneous virtual machines as state input and the maximum completion time and cost as rewards. The game model is capable of seeking for correlated equilibrium between make-span and cost criteria without prior experts' knowledge and converges to the correlated equilibrium policy in a dynamic real-time environment. To validate our proposed approach, we conduct extensive case studies based on multiple well-known scientific workflow templates and Amazon EC2 cloud. The experimental results clearly suggest that our proposed approach outperforms traditional ones, e.g., non-dominated sorting genetic algorithm-II, multi-objective particle swarm optimization, and game-theoretic-based greedy algorithms, in terms of optimality of scheduling plans generated. INDEX TERMS Multi-objective workflow scheduling, deep-Q-network (DQN), multi-agent reinforcement learning (MARL), infrastructure-as-a-service (IaaS) cloud, quality-of-service (QoS).
In this study we simultaneously collected ultrasound images, EMG, MMG from the rectus femoris (RF) muscle and torque signal from the leg extensor muscle group of nine male subjects (mean±SD, age=30.7±.4.9 years; body weight=67.0±8.4kg; height=170.4±6.9cm) during step, ramp increasing, and decreasing at three different rates (50%, 25% and 17% MVC/s). The muscle architectural parameters extracted from ultrasound imaging, which reflect muscle contractions, were defined as sonomyography (SMG) in this study. The cross-sectional area (CSA) and aspect ratio between muscle width and thickness (width/thickness) were extracted from ultrasound images. The results showed that the CSA of RF muscles decreased by 7.25±4.07% when muscle torque output changed from 0% to 90% MVC, and the aspect ratio decreased by 41.66±7.96%. The muscle contraction level and SMG data were strongly correlated (R(2)=0.961, P=0.003, for CSA and R(2)=0.999, P<0.001, for width/thickness ratio). The data indicated a significant difference (P<0.05) in percentage changes for CSA and aspect ratio among step, ramp increasing, and decreasing contractions. The normalized EMG RMS in ramp increasing was 8.25±4.00% higher than step (P=0.002). The normalized MMG RMS of step contraction was significantly lower than ramp increasing and decreasing, with averaged differences of 12.22±3.37% (P=0.001) and 12.06±3.37% (P=0.001), respectively. The results of this study demonstrated that the CSA and aspect ratio, i.e., SMG signals, can provide useful information about muscle contractions. They may therefore complement EMG and MMG for studying muscle activation strategies under different conditions.
A highly transparent cellulose film with a high built-in haze is emerging as a green photonic material for optoelectronics. Unfortunately, attaining its theoretical haze still remains a challenge. Here, we demonstrate an all-cellulose composite film with a 90.1% transmittance and a maximal transmission haze of 95.2% close to the theoretical limit (∼100%), in which the entangled network of softwood cellulose fibers works as strong light scattering sources and regenerated cellulose (RC) with undissolved fibril bundles functions as a matrix to simultaneously improve the optical transparency and transmission haze. The underlying mechanism for the ultrahigh haze is attributed to microsized irregularities in the refractive index, arising primarily from the crystalline structure of softwood fibers, undissolved nanofibril bundles in RC, and a small number of internal cavities. Moreover, the resulting composite film presents a folding resistance of over 3500 times and good water resistance, and its application in a perovskite solar cell as an advanced light management layer is demonstrated. This work sheds light on the design of a highly transparent cellulose film with a haze approaching the theoretical limit for optoelectronics and brings us a step further toward its industrial production.
The salt-tolerant unicellular alga Dunaliella bardawil FACHB-847 can accumulate large amounts of lutein, but the underlying cause of massive accumulation of lutein is still unknown. In this study, genes encoding two types of carotene hydroxylases, i.e., β-carotene hydroxylase (DbBCH) and cytochrome P450 carotenoid hydroxylase (DbCYP97s; DbCYP97A, DbCYP97B, and DbCYP97C), were cloned from D. bardawil. Their substrate specificities and enzyme activities were tested through functional complementation assays in Escherichia coli. It was showed that DbBCH could catalyze the hydroxylation of the β-rings of both βand α-carotene, and displayed a low level of εhydroxylase. Unlike CYP97A from higher plants, DbCYP97A could not hydroxylate β-carotene. DbCYP97A and DbCYP97C showed high hydroxylase activity toward the β-ring and ε-ring of α-carotene, respectively. DbCYP97B displayed minor activity toward the β-ring of α-carotene. The high accumulation of lutein in D. bardawil may be due to the multiple pathways for lutein biosynthesis generated from α-carotene with zeinoxanthin or α-cryptoxanthin as intermediates by DbBCH and DbCYP97s. Taken together, this study provides insights for understanding the underlying reason for high production of lutein in the halophilic green alga D. bardawil FACHB-847.
BackgroundSurface electromyography (SEMG) is an electrical manifestation of the neuromuscular activation associated with contracting muscle. 1 It has been widely used to control powered upper limb prosthetic devices. Although controlled studies suggest that expert users of EMG driven powered prostheses can perform a wide range of tasks, the high rejection rates 2 and the high incidence of overuse injuries in the contralateral arm of unilateral amputees, 3 suggest that full functionality of EMG-based powered prosthesis is often not exploited in everyday life. The use of EMG driven powered prostheses is limited by some of its inherent properties. SEMG is a noisy, non-stationary and non-linear signal, which is susceptible to interference (e.g. socket movement and sweat-related skin impedance changes). It is also difficult to use SEMG to discriminate superficial and Towards the application of one-dimensional sonomyography for powered upper-limb prosthetic control using machine learning models Jing-Yi Guo 1 , Yong-Ping Zheng 2 , Hong-Bo Xie 3 and Terry K Koo 1 Abstract Background: The inherent properties of surface electromyography limit its potential for multi-degrees of freedom control. Our previous studies demonstrated that wrist angle could be predicted by muscle thickness measured from B-mode ultrasound, and hence, it could be an alternative signal for prosthetic control. However, an ultrasound imaging machine is too bulky and expensive. Objective: We aim to utilize a portable A-mode ultrasound system to examine the feasibility of using one-dimensional sonomyography (i.e. muscle thickness signals detected by A-mode ultrasound) to predict wrist angle with three different machine learning models -(1) support vector machine (SVM), (2) radial basis function artificial neural network (RBF ANN), and (3) back-propagation artificial neural network (BP ANN). Study Design: Feasibility study using nine healthy subjects. Methods: Each subject performed wrist extension guided at 15, 22.5, and 30 cycles/minute, respectively. Data obtained from 22.5 cycles/minute trials was used to train the models and the remaining trials were used for cross-validation. Prediction accuracy was quantified by relative root mean square error (RMSE) and correlation coefficients (CC). Results: Excellent prediction was noted using SVM (RMSE = 13%, CC = 0.975), which outperformed the other methods.Conclusion: It appears that one-dimensional sonomyography could be an alternative signal for prosthetic control. Clinical relevanceSurface electromyography has inherent limitations that prohibit its full functional use for prosthetic control. Research that explores alternative signals to improve prosthetic control (such as the one-dimensional sonomyography signals evaluated in this study) may revolutionize powered prosthesis design and ultimately benefit amputee patients.
Electromyographic (EMG) is a bio-signal collected on human skeletal muscle. Analysis of EMG signals has been widely used to detect human movement intent, control various human-machine interfaces, diagnose neuromuscular diseases, and model neuromusculoskeletal system. With the advances of artificial intelligence and soft computing, many sophisticated techniques have been proposed for such purpose. Hybrid soft computing system (HSCS), the integration of these different techniques, aims to further improve the effectiveness, efficiency, and accuracy of EMG analysis. This paper reviews and compares key combinations of neural network, support vector machine, fuzzy logic, evolutionary computing, and swarm intelligence for EMG analysis. Our suggestions on the possible future development of HSCS in EMG analysis are also given in terms of basic soft computing techniques, further combination of these techniques, and their other applications in EMG analysis.
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
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.