Raman optical spectroscopy promises label-free bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and ...accuracies remains challenging due to weak Raman signal from bacterial cells and numerous bacterial species and phenotypes. Here we generate an extensive dataset of bacterial Raman spectra and apply deep learning approaches to accurately identify 30 common bacterial pathogens. Even on low signal-to-noise spectra, we achieve average isolate-level accuracies exceeding 82% and antibiotic treatment identification accuracies of 97.0±0.3%. We also show that this approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) with 89±0.1% accuracy. We validate our results on clinical isolates from 50 patients. Using just 10 bacterial spectra from each patient isolate, we achieve treatment identification accuracies of 99.7%. Our approach has potential for culture-free pathogen identification and antibiotic susceptibility testing, and could be readily extended for diagnostics on blood, urine, and sputum.
Separation of enantiomers is crucial to the pharmaceutical and chemical industries, but prevailing chemical methods are economically costly and time-consuming. Illumination with circularly polarized ...light (CPL) provides a potentially cost-effective and versatile alternative but can achieve only 2% enantiomeric excesses with substantial yield. Here, we theoretically show that high-index dielectric nanoparticles can increase enantiomeric excesses 7 times beyond CPL in free space. Mie theory and a local optimization algorithm indicate that magnetic multipolar Mie resonances supported by submicrometer silicon spheres increase Kuhn’s dissymmetry factor 7-fold, compared to CPL in free space. Further, the circular dichroism signal can be enhanced 170-fold. Importantly, these local enhancements maintain the total molecular absorption rate, enabling efficient selective photoexcitation. Even greater enhancements in Kuhn’s dissymmetry factor can be achieved with lower loss and higher refractive index nanoparticles. Our results provide a path toward more efficient all-optical chiral resolution techniques.
In a pandemic era, rapid infectious disease diagnosis is essential. Surface-enhanced Raman spectroscopy (SERS) promises sensitive and specific diagnosis including rapid point-of-care detection and ...drug susceptibility testing. SERS utilizes inelastic light scattering arising from the interaction of incident photons with molecular vibrations, enhanced by orders of magnitude with resonant metallic or dielectric nanostructures. While SERS provides a spectral fingerprint of the sample, clinical translation is lagged due to challenges in consistency of spectral enhancement, complexity in spectral interpretation, insufficient specificity and sensitivity, and inefficient workflow from patient sample collection to spectral acquisition. Here, we highlight the recent, complementary advances that address these shortcomings, including (1) design of label-free SERS substrates and data processing algorithms that improve spectral signal and interpretability, essential for broad pathogen screening assays; (2) development of new capture and affinity agents, such as aptamers and polymers, critical for determining the presence or absence of particular pathogens; and (3) microfluidic and bioprinting platforms for efficient clinical sample processing. We also describe the development of low-cost, point-of-care, optical SERS hardware. Our paper focuses on SERS for viral and bacterial detection, in hopes of accelerating infectious disease diagnosis, monitoring, and vaccine development. With advances in SERS substrates, machine learning, and microfluidics and bioprinting, the specificity, sensitivity, and speed of SERS can be readily translated from laboratory bench to patient bedside, accelerating point-of-care diagnosis, personalized medicine, and precision health.
A Limitation of Gradient Descent Learning Sum, John; Leung, Chi-Sing; Ho, Kevin
IEEE transaction on neural networks and learning systems,
06/2020, Letnik:
31, Številka:
6
Journal Article
Over decades, gradient descent has been applied to develop learning algorithm to train a neural network (NN). In this brief, a limitation of applying such algorithm to train an NN with persistent ...weight noise is revealed. Let <inline-formula> <tex-math notation="LaTeX">V({\mathbf w}) </tex-math></inline-formula> be the performance measure of an ideal NN. <inline-formula> <tex-math notation="LaTeX">V({\mathbf w}) </tex-math></inline-formula> is applied to develop the gradient descent learning (GDL). With weight noise, the desired performance measure (denoted as <inline-formula> <tex-math notation="LaTeX">{\mathcal{ J}}({\mathbf w}) </tex-math></inline-formula>) is <inline-formula> <tex-math notation="LaTeX">EV(\tilde {\mathbf w})|{\mathbf w} </tex-math></inline-formula>, where <inline-formula> <tex-math notation="LaTeX">\tilde {\mathbf w} </tex-math></inline-formula> is the noisy weight vector. Applying GDL to train an NN with weight noise, the actual learning objective is clearly not <inline-formula> <tex-math notation="LaTeX">V({\mathbf w}) </tex-math></inline-formula> but another scalar function <inline-formula> <tex-math notation="LaTeX">{\mathcal{ L}}({\mathbf w}) </tex-math></inline-formula>. For decades, there is a misconception that <inline-formula> <tex-math notation="LaTeX">{\mathcal{ L}}({\mathbf w}) = {\mathcal{ J}}({\mathbf w}) </tex-math></inline-formula>, and hence, the actual model attained by the GDL is the desired model. However, we show that it might not: 1) with persistent additive weight noise, the actual model attained is the desired model as <inline-formula> <tex-math notation="LaTeX">{\mathcal{ L}}({\mathbf w}) = {\mathcal{ J}}({\mathbf w}) </tex-math></inline-formula>; and 2) with persistent multiplicative weight noise, the actual model attained is unlikely the desired model as <inline-formula> <tex-math notation="LaTeX">{\mathcal{ L}}({\mathbf w}) \neq {\mathcal{ J}}({\mathbf w}) </tex-math></inline-formula>. Accordingly, the properties of the models attained as compared with the desired models are analyzed and the learning curves are sketched. Simulation results on 1) a simple regression problem and 2) the MNIST handwritten digit recognition are presented to support our claims.
Polycyclic aromatic hydrocarbons (PAHs) and their polar derivatives (oxygenated PAHs: OPAHs and azaarenes: AZAs) were characterized in fine particulates (PM2.5) emitted from indoor coal combustion. ...Samples were collected in Xuanwei (Yunnan Province), a region in China with a high rate of lung cancer. A sample from the community with the highest mortality contained the highest total concentration of PAHs, OPAHs and AZAs and posed the highest excess cancer risk from a lifetime of inhaling fine particulates. Positive correlations between total carbonyl-OPAHs, total AZAs and total PAHs implied that the emissions were dependent on similar factors, regardless of sample location and type. The calculated cancer risk ranged from 5.23–10.7 × 10−3, which is higher than the national average. The risk in each sample was ∼1–2 orders of magnitude higher than that deemed high risk, suggesting that the safety of these households is in jeopardy. The lack of potency equivalency factors for the PAH derivatives could possibly have underestimated the overall cancer risk.
•Sample shows highest total PAHs concentration at highest cancer mortality community.•Strong correlation between total polar-PACs and PAHs.•Sample from highest cancer mortality community poses highest cancer risk.•The risk in all samples were ∼1–2 orders of magnitude higher than deemed high risk.
Surface-enhanced Raman spectroscopy (SERS) is a promising cellular identification and drug susceptibility testing platform, provided it can be performed in a controlled liquid environment that ...maintains cell viability. We investigate bacterial liquid-SERS, studying plasmonic and electrostatic interactions between gold nanorods and bacteria that enable uniformly enhanced SERS. We synthesize five nanorod sizes with longitudinal plasmon resonances ranging from 670 to 860 nm and characterize SERS signatures of Gram-negative Escherichia coli and Serratia marcescens and Gram-positive Staphylococcus aureus and Staphylococcus epidermidis bacteria in water. Varying the concentration of bacteria and nanorods, we achieve large-area SERS enhancement that is independent of nanorod resonance and bacteria type; however, bacteria with higher surface charge density exhibit significantly higher SERS signal. Using cryo-electron microscopy and zeta potential measurements, we show that the higher signal results from attraction between positively charged nanorods and negatively charged bacteria. Our robust liquid-SERS measurements provide a foundation for bacterial identification and drug testing in biological fluids.
•This paper develops a noise/fault aware training objective for incremental ELM.•This paper uses two representative algorithms to develop two noise aware ELM.•The two proposed algorithms are much ...better than existing ones.•The multiple set concept can further enhance the performance.•We can make other non-noise tolerant algorithms to be noise tolerant.
This paper investigates noise/fault tolerant incremental algorithms for the extreme learning machine (ELM) concept. Existing incremental ELM algorithms can be classified into two approaches: non-recomputation and recomputation. This paper first formulates a noise/fault aware objective function for nonlinear regression problems. Instead of developing noise/fault aware algorithms for the two computational approaches in a one-by-one manner, this paper uses two representative incremental algorithms, namely incremental ELM (I-ELM) and error minimized ELM (EM-ELM), to develop two noise/fault aware incremental algorithms. The proposed algorithms are called generalized I-ELM (GI-ELM) and generalized EM-ELM (GEM-ELM). The GI-ELM adds k hidden nodes into the existing network at each incremental step without recomputing the existing weights. To have a fair comparison, we consider a modified version of I-ELM as a comparison algorithm. The simulation demonstrates that the noise/fault tolerance of the proposed GI-ELM is better than that of the modified I-ELM. In the GEM-ELM, k hidden nodes are added into the existing network at each incremental step. Meanwhile, all output weights are recomputed based on a recursive formula. We also consider a modified version of EM-ELM as a comparison algorithm. The simulation demonstrates that the noise/fault tolerance of the proposed GEM-ELM is better than that of the modified EM-ELM. Moreover, we demonstrate that the multiple set concept can further enhance the performance of the two proposed algorithms. Following our research results, one can make some non-noise/fault tolerant incremental algorithms to be noise/fault tolerant.
•This paper formally analyzes the properties of multi-bit quanta image sensor (QIS) systems. It derives the log likelihood function of the received photon counts in a spatiotemporal jot kernel, and ...introduces the concept of the probability of all jots being saturated.•From the likelihood function result, we can have a maximum likelihood (ML) estimate for the exposure level and present a construction algorithm, namely ML multi-bit (MLM). As our estimate is ML based, the variance of the estimated exposure achieves the Cramér-Rao bound (CRB) asymptotically.•From the Fisher information concept, this paper derives the CRB on the variance of the estimated exposure. This CRB value can be considered as a performance indicator for different hardware settings.•From the jot saturation result, we can accurately formulate the relationship between maximum exposure and the kernel size, as well as i.e., the relationship between dynamic range and the kernel size.•From two analysis results, we can model the relationships between sensor design parameters and performance metrics (variance of the estimated exposure and the dynamic range). Since the analysis results are independent of the construction algorithm used, they give us some guidelines to vary the spatiotemporal jot kernel size and the bit resolution of QIS jots to control dynamic range, and signal to noise ratio of constructed images.•This paper empirically studies the effect of readout Gaussian noise.•With our framework in likelihood function, we can develop some joint-construction-and-denosing algorithms for MBQIS. We use an enhanced version of MLM, namely MLM with denoising (MLMDN), to demonstrate this joint-construction-and-denosing concept.
A new breed of photon-counting sensors, called quanta image sensor (QIS), enables the detection of light with precision represented by the number of photons arriving within a time period. However, most existing analysis results on QIS systems are formulated for the single-bit case only. Directly extending the existing single-bit analysis to the multi-bit case leads to the situation that the variance of the estimated exposure is greater than the Cramér-Rao bound (CRB). Also, the existing dynamic range analysis leads to a strange situation that the maximum exposure level is not a function of the spatiotemporal jot kernel size. This paper formally analyzes the properties of multi-bit QIS (MBQIS) systems. It derives the log likelihood function of the received photon counts in a spatiotemporal jot kernel, and introduces the concept of the probability of all jots being saturated. From the likelihood function result, we can obtain a maximum likelihood (ML) estimate for the exposure level and present an image construction algorithm, namely ML multi-bit (MLM). Since the estimate is ML based, the variance of the estimated exposure achieves the CRB asymptotically and the MLM is an asymptotically unbiased estimator. Also, based on the Fisher information concept, this paper derives the CRB on the variance of the estimated exposure. Hence the CRB given by this paper can be considered as a performance indicator for all algorithms. From the jot saturation analysis result, we can accurately formulate the relationship between dynamic range and spatiotemporal kernel size. Specifically, with our two analysis results, we can model the relationships between sensor design parameters and performance metrics (variance of the estimated exposure and the dynamic range). Since the two analysis results are independent of the construction algorithms used, they give us some guidelines to design a QIS system. In addition, this paper empirically studies the effect of the readout Gaussian noise. Finally, to demonstrate another application of the likelihood analysis result, we develop an enhanced version of MLM, namely MLM with denoising (MLMDN), based on the proposed likelihood function and the regularization concept.
A rapid and convenient detection method for biogenic polyamines is of great importance for early diagnosis of many diseases. In this work, a tetraphenyl ethylene (TPE) conjugated pentiptycene has ...been synthesized and showed to be a highly responsive fluorescent sensor toward polyamines. The detection limit of this probe is in the sub-micromolar level, and it also shows good selectivity for spermine. This small organic molecular bio-indicator can be used to detect spermine in artificial urine, demonstrating the potential application in clinical practice.
•A TPE conjugated pentiptycene derivative SS-1 was synthesized and characterized.•The synergistic effects between the pentiptycene core and the TPE moiety was studied.•SS-1 selectively binds with spermine without interference from various amines and cations.•SS-1 can be applied for spermine detection in artificial urine solutions.
Efficient external luminescence is a prerequisite for high-voltage solar cells. To approach the Shockley-Queisser limit, a highly reflective rear mirror is required. This mirror enhances the voltage ...of the solar cell by providing internally luminescent photons with multiple opportunities for escaping out the front surface. Likewise, intermediate reflectors in a multibandgap solar cell can assist external luminescence to enhance the voltage for each cell in a stack. These intermediate reflectors must also transmit the subbandgap photons to the next cell in the stack. A practical implementation of an intermediate selective reflector is an air gap sandwiched by antireflection coatings. The air gap provides perfect reflection for angles outside the escape cone, and the antireflection coating transmits angles inside the escape cone. As the incoming sunlight is within the escape cone, it is transmitted on to the next cell, while most of the internally trapped luminescence is reflected. We calculate that air gap intermediate reflectors, along with a rear mirror, can provide an absolute efficiency increase of ≈5% in multibandgap cells.