Over the past year, the world's attention has focused on combating COVID-19 disease, but the other threat waiting at the door—antimicrobial resistance should not be forgotten. Although making the diagnosis rapidly and accurately is crucial in preventing antibiotic resistance development, bacterial identification techniques include some challenging processes. To address this challenge, we proposed a deep neural network (DNN) that can discriminate antibiotic-resistant bacteria using surface-enhanced Raman spectroscopy (SERS). Stacked autoencoder (SAE)-based DNN was used for the rapid identification of methicillin-resistant Staphylococcus aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) bacteria using a label-free SERS technique. The performance of the DNN was compared with traditional classifiers. Since the SERS technique provides high signal-to-noise ratio (SNR) data, some subtle differences were found between MRSA and MSSA in relative band intensities. SAE-based DNN can learn features from raw data and classify them with an accuracy of 97.66%. Moreover, the model discriminates bacteria with an area under curve (AUC) of 0.99. Compared to traditional classifiers, SAE-based DNN was found superior in accuracy and AUC values. The obtained results are also supported by statistical analysis. These results demonstrate that deep learning has great potential to characterize and detect antibiotic-resistant bacteria by using SERS spectral data.

No abstract

No abstract

No abstract

1-3,4-Dihydroxy phenylalanine called as l-Dopa is a precursor of dopamine and an important neural message transmitter and it has been a preferred drug for the treatment of Parkinson's disease. In this study, with regards to the synthesis of l-Dopa two types of biosensors were designed by immobilizing tyrosinase on conducting polymers: thiophene capped poly(ethyleneoxide)/polypyrrole (PEO-co-PPy) and 3-methylthienyl methacrylate-cop -vinylbenzyloxy poly(ethyleneoxide)/polypyrrole (CP-co-PPy). PEO-co-PPy and CP-co-PPy were synthesized electrochemically and tyrosinase immobilized by entrapment during electropolymerization. l-Tyrosine was used as the substrate for l-Dopa synthesis. The kinetic parameters of the designed biosensors, maximum reaction rate of the enzyme (V max) and Michaelis Menten constant (K m) were determined. V max were found as 0.007 mol/(min electrode) for PEO-co-PPy matrix and 0.012 mol/(min electrode) for CP-co-PPy matrix. K m values were determined as 3.4 and 9.2 mM for PEO-co-PPy and CP-co-PPy matrices, respectively. Optimum temperature and pH, operational and shelf life stabilities of immobilized enzyme were also examined.

No abstract

Magnetoencephalography(MEG) is an emerging medical signal processing methodology that uses the magnetic field of brain to decode internal brain activity. However, MEG signals are very complicated and usually corrupted with significant amount of noise. Therefore, it is not easy to directly understand how the human brain responds to visual stimulus by analysing the MEG signals without utilizing advanced signal processing techniques such as feature extraction and classification. The feature extraction of MEG signals can be accomplished by applying the Riemannian approach. Moreover, the extracted features can be classified by classification algorithms such as SVM and KNN to complete the decoding process. However, these classification methods don't produce satisfying results as the number of features is very high. In this paper, the classification problem of MEG signals is addressed and a deep neural network based classifier is proposed to classify the MEG signals that were produced as the brain output for two different types of visual stimuli. The visual stimuli comprise a data base of faces and scrambled faces. Our experimental results demonstrate that the proposed classifier exhibits superior classification performance over the other competing methods used in the paper.

No abstract