Arcobacter Identification and Species Determination Using Raman Spectroscopy Combined with Neural Networks.

Rapid and accurate identification of Arcobacter is of great importance because it is considered an emerging food- and waterborne pathogen and potential zoonotic agent. Raman spectroscopy can differentiate bacteria based on Raman scattering spectral patterns of whole cells in a fast, reagentless, and easy-to-use manner. We aimed to detect and discriminate Arcobacter bacteria at the species level using confocal micro-Raman spectroscopy (785 nm) coupled with neural networks. A total of 82 reference and field isolates of 18 Arcobacter species from clinical, environmental, and agri-food sources were included. We determined that the bacterial cultivation time and growth temperature did not significantly influence the Raman spectral reproducibility and discrimination capability. The genus Arcobacter could be successfully differentiated from the closely related genera Campylobacter and Helicobacter using principal-component analysis. For the identification of Arcobacter to the species level, an accuracy of 97.2% was achieved for all 18 Arcobacter species using Raman spectroscopy combined with a convolutional neural network (CNN). The predictive capability of Raman-CNN was further validated using an independent data set of 12 Arcobacter strains. Furthermore, a Raman spectroscopy-based fully connected artificial neural network (ANN) was constructed to determine the actual ratio of a specific Arcobacter species in a bacterial mixture ranging from 5% to 100% by biomass (regression coefficient >0.99). The application of both CNN and fully connected ANN improved the accuracy of Raman spectroscopy for bacterial species determination compared to the conventional chemometrics. This newly developed approach enables rapid identification and species determination of Arcobacter within an hour following cultivation.IMPORTANCE Rapid identification of bacterial pathogens is critical for developing an early warning system and performing epidemiological investigation. Arcobacter is an emerging foodborne pathogen and has become more important in recent decades. The incidence of Arcobacter species in the agro-ecosystem is probably underestimated mainly due to the limitation in the available detection and characterization techniques. Raman spectroscopy combined with machine learning can accurately identify Arcobacter at the species level in a rapid and reliable manner, providing a promising tool for epidemiological surveillance of this microbe in the agri-food chain. The knowledge elicited from this study has the potential to be used for routine bacterial screening and diagnostics by the government, food industry, and clinics.

An Improved Load Forecasting Method Based on the Transfer Learning Structure under Cyber-Threat Condition.

Smart grid is regarded as an evolutionary regime of existing power grids. It integrates artificial intelligence and communication technologies to fundamentally improve the efficiency and reliability of power systems. One serious challenge for the smart grid is its vulnerability to cyber threats. In the event of a cyber attack, grid data may be missing; subsequently, load forecast and power planning that rely on these data cannot be processed by generation centers. To address this issue, this paper proposes a transfer learning-based framework for smart grid scheduling that is less reliant on local data while capable of delivering schedules with low operating cost. Specifically, the proposed framework contains (1) a power forecasting model based on transfer learning which can provide high quality load prediction with limited training data, (2) a novel adaptive time series prediction method with modeling time series from a covariate shift perspective that aims to train the forecasting model with a strong generalization capability, and (3) a day-ahead optimal economic power scheduling model considering a shared energy storage station.

Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation.

Accurate capacity estimation is crucial for the reliable and safe operation of lithium-ion batteries. In particular, exploiting the relaxation voltage curve features could enable battery capacity estimation without additional cycling information. Here, we report the study of three datasets comprising 130 commercial lithium-ion cells cycled under various conditions to evaluate the capacity estimation approach. One dataset is collected for model building from batteries with LiNi0.86Co0.11Al0.03O2-based positive electrodes. The other two datasets, used for validation, are obtained from batteries with LiNi0.83Co0.11Mn0.07O2-based positive electrodes and batteries with the blend of Li(NiCoMn)O2 - Li(NiCoAl)O2 positive electrodes. Base models that use machine learning methods are employed to estimate the battery capacity using features derived from the relaxation voltage profiles. The best model achieves a root-mean-square error of 1.1% for the dataset used for the model building. A transfer learning model is then developed by adding a featured linear transformation to the base model. This extended model achieves a root-mean-square error of less than 1.7% on the datasets used for the model validation, indicating the successful applicability of the capacity estimation approach utilizing cell voltage relaxation.

Machine Learning Algorithms for Liquid Crystal-Based Sensors.

We present a machine learning (ML) framework to optimize the specificity and speed of liquid crystal (LC)-based chemical sensors. Specifically, we demonstrate that ML techniques can uncover valuable feature information from surface-driven LC orientational transitions triggered by the presence of different gas-phase analytes (and the corresponding optical responses) and can exploit such feature information to train accurate and automatic classifiers. We demonstrate the utility of the framework by designing an experimental LC system that exhibits similar optical responses to a stream of nitrogen containing either 10 ppmv dimethyl-methylphosphonate (DMMP) or 30% relative humidity (RH). The ML framework is used to process and classify thousands of images (optical micrographs) collected during the LC responses and we show that classification (sensing) accuracies of over 99% can be achieved. For the same experimental system, we demonstrate that traditional feature information used in characterizing LC responses (such as average brightness) can only achieve sensing accuracies of 60%. We also find that high accuracies can be achieved by using time snapshots collected early in the LC response, thus providing the ability to create fast sensors. We also show that the ML framework can be used to systematically analyze the quality of information embedded in LC responses and to filter out noise that arises from imperfect LC designs and from sample variations. We evaluate a range of classifiers and feature extraction methods and conclude that linear support vector machines are preferred and that high accuracies can only be achieved by simultaneously exploiting multiple sources of feature information.