Objectives-Tone production is particularly important for communicating in tone languages such as Mandarin Chinese. In the present study, an artificial neural network was used to recognize tones produced by adult native speakers. The purposes of the study were (1) to test the sensitivity of the neural network to speaker variation typically in adult speaker groups, (2) to evaluate two normalization procedures to overcome the effects of speaker variation, and (3) to compare tone recognition performance of the neural network with that of the human listeners.Design-A feedforward multilayer neural network was used. Twenty-nine adult native Mandarin Chinese speakers were recruited to record tone samples. The F0 contours of the vowel part of the 1044 monosyllabic words recorded were extracted using an autocorrelation method. Samples from the F0 contours were used as inputs to the neural network. The efficacy of the neural network was first tested by varying the number of inputs and the number of neurons in the hidden layer from 1 to 16. The sensitivity of the neural network to speaker variation was tested by (1) using the raw F0 data from speech tokens of a number of randomly drawn speakers that varied from 1 to 29, (2) using the raw F0 data from speech tokens of either male-only or female-only speakers, and (3) using two sets of normalized F0 data (i.e., tone 1-based normalization and first-order derivative) from speech tokens from a number of randomly drawn speakers that varied from 1 to 29. The recognition performance of the neural network under several experimental conditions was compared with the corresponding recognition performance of 10 normal-hearing, native Mandarin Chinese speaking adult listeners.Results-Three inputs and four hidden neurons were found to be sufficient for the neural network to perform at about 85% correct using speech samples without normalization. The performance of the neural network was affected by variation across speakers particularly between genders. Using the tone 1-based normalization procedure, the performance of the neural network improved significantly. The recognition accuracy of the neural network as a whole or for each tone was comparable with that of the human listeners.Conclusions-The neural network can be used to evaluate the tone production of Mandarin Chinese speaking adults with human listener-like recognition accuracy. The tone 1-based normalization procedure improves the performance of the neural network to human listener-like accuracy. The success of our neural network in recognizing tones from multiple speakers supports its utility for evaluating tone production. Further testing of the neural network with hearing-impaired speakers might reveal its potential use for clinical evaluation of tone production.
As typical discrete event systems, flexible manufacturing systems have been extensively studied in such aspects as modeling, control and performance analysis. One important topic in the study of such systems is the deadlock detection, prevention and avoidance. In the past decade, two major modeling formalisms, i.e., Petri nets and digraphs, have been adopted for developing deadlock control policies for flexible manufacturing systems. In this paper, the concepts of slack, knot, order and effective free space of circuits in the digraph are established and used to concisely and precisely quantify the sufficient conditions for a system state to be live. Necessary conditions for this liveness is quantified for a special class of system states -called evaluation states. The significance of the result is that the conditions are true for avoiding both primary deadlocks and impending deadlocks that are arbitrary steps away from a primary one, whereas only second level deadlocks have been studied in the literature. Examples are provided to illustrate the method.
A simple, rapid and accurate method for simultaneous determination of melamine and dicyandiamide in milk by UV spectroscopy coupled with chemometrics was proposed. In total, 1728 sample solutions were designed and prepared with 3 kinds of milk powder samples and 3 kinds of liquid milk samples to demonstrate this method. Six spectral pretreatment methods, including the smoothing method of Savitzky-Golay (Smoothing-SG), area normalization (Nor), standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative Savitzky-Golay (1d + SG) and second derivative gap-segment (2d + GS) were used to preprocess the raw spectra for building regression models by partial least squares (PLS) regression, support vector machine (SVM) and least-squares support vector machine (LS-SVM). For milk powder samples, the LS-SVM algorithm gave the best prediction of melamine and dicyandiamide with RSDs of 8.53% and 5.31%, respectively, and LODs of 14.2 mg kg À1 and 8.84 mg kg À1 , respectively. For liquid milk samples, the best prediction of melamine and dicyandiamide was obtained by the SVM algorithm with RSDs of 4.97% and 3.46%, respectively, and LODs of 9.94 mg L À1 and 6.91 mg L À1 , respectively.
some 2D materials translocate into living cells via endocytosis, offering a promising platform that enables intracellular bioimaging, [1][2][3] biosensing, [4][5][6] or disease theranostics. [7][8][9][10] Despite encouraging advances in this emerging field, one major challenge lies in managing the trade-off between lateral size of the 2D platform and their cellular uptake. In general, 2D materials with a small lateral dimension are easily taken up by cells but clear fast. One typical example [11] is doxorubicinloaded 2D molybdenum disulfide (MoS 2 ) nanosheets recently reported for synergistic chemo-photothermal cancer therapy. The drug-loaded MoS 2 platform, due to its small lateral size (≈116 nm), could be well internalized by cancer cells, but suffered from exocytosis that compromised the therapeutic effect unless exocytosis inhibitor was added. In comparison, large 2D materials have longer retention time in cells, thus affording greater potency to serve as intracellular functional platforms than small counterparts of the same composition. However, an ultrahigh-aspect-ratio makes the endocytosis of very large 2D materials extremely difficult. [12,13] Having this dilemma in mind, previous researchers had to employ relatively small 2D materials (lateral dimension < 200 nm) as intracellular signaling or theranostic platforms, [2][3][4][5][6][7][8][9][10][11] simply because they were readily endocytosable compared with micrometer-sized counterparts, even though the latter were conceivably more qualifying candidates.Indeed, 2D materials, regardless of chemical composition, can invariably be regarded as an assembly composed of laterally connected areal monomeric units that extend in two orthogonal directions. [14,15] These monomers are typically less than 1 nm in size, thus having no trouble being internalized and enriched inside living cells. Bearing this in mind, we envision unprecedentedly large 2D materials can be directly generated in cell milieu provided that the internalized monomers in situ polymerize efficiently with the inter-monomer connections being strictly confined to lateral directions. As such, the otherwise non-endocytosable large 2D materials can eventually enter the cells, addressing the lateral size versus cellular uptake trade-off aforementioned.An areal monomeric unit designed for such a purpose then must meet several demanding requirements: 1) it should be The unique structural advantage and physicochemical properties render some 2D materials emerging platforms for intracellular bioimaging, biosensing, or disease theranostics. Despite recent advances in this field, one major challenge lies in bypassing the endocytic uptake barrier to allow internalization of very large 2D materials that have longer retention time in cells, and hence greater potency as intracellular functional platforms than small, endocytosable counterparts. Here, an engineered cucurbit[6]uril carrying at its periphery multiple spiropyran pendants that readily translocates into cytosol, and then polymerizes laterally and non-c...
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.