Artificial neural network and convolutional neural network for prediction of dental caries.

Dental caries has high prevalence among kids and adults thus it has become one of the global health concerns. The current modern dentistry focused on the preventives measures to reduce the number of dental caries cases. The employment of machine learning coupled with UV spectroscopy plays a crucial role to detect the early stage of caries. Artificial neural network with hyperparameter tuning was employed to train spectral data for the classification based on the International Caries Detection and Assesment System (ICDAS). Spectra preprocessing namely mean center (MC), autoscale (AS) and Savitzky Golay smoothing (SG) were applied on the data for spectra correction. The best performance of ANN model obtained has accuracy of 0.85 with precision of 1.00. Convolutional neural network (CNN) combined with Savitzky Golay smoothing performed on the spectral data has accuracy, precision, sensitivity and specificity for validation data of 1.00 respectively. The result obtained shows that the application of ANN and CNN capable to produce robust model to be used as an early screening of dental caries.

Chemometrics analysis for the detection of dental caries via UV absorption spectroscopy.

Caries is one of the non-communicable diseases that has a high prevalence trend. The current methods used to detect caries require sophisticated laboratory equipment, professional inspection, and expensive equipment such as X-ray imaging device. A non-invasive and economical method is required to substitute the conventional methods for the detection of caries. UV absorption spectroscopy coupled with chemometrics analysis has emerged as a good potential candidate for such an application. Data preprocessing methods such as mean centre, autoscale and Savitzky-Golay smoothing were implemented to enhance the signal-to-noise ratio of spectra data. Various classification algorithms namely K-nearest neighbours (KNN), logistic regression (LR) and linear discriminant analysis (LDA) were implemented to classify the severity of dental caries into International Caries Detection and Assessment System (ICDAS) scores. The performance of the prediction model was measured and comparatively analysed based on the accuracy, precision, sensitivity, and specificity. The LDA algorithm combined with the Savitzky-Golay preprocessing method had shown the best result with respect to the validation data accuracy, precision, sensitivity and specificity, where each had values of 0.90, 1.00, 0.86 and 1.00 respectively. The area under the curve of the ROC plot computed for the LDA algorithm was 0.95, which indicated that the prediction algorithm was capable of differentiating normal and caries teeth excellently.

Classification and quantification of palm oil adulteration via portable NIR spectroscopy.

Short wave near infrared spectroscopy (NIR) method was used to detect the presence of lard adulteration in palm oil. MicroNIR was set up in two different scan modes to study the effect of path length to the performance of spectral measurement. Pure and adulterated palm oil sample were classified using soft independent modeling class analogy (SIMCA) algorithm with model accuracy more than 0.95 reported for both transflectance and transmission modes. Additionally, by employing partial least square (PLS) regression, the coefficient of determination (R2) of transflectance and transmission were 0.9987 and 0.9994 with root mean square error of calibration (RMSEC) of 0.5931 and 0.6703 respectively. In order to remove the uninformative variables, variable selection using cumulative adaptive reweighted sampling (CARS) has been performed. The result of R2 and RMSEC after variable selection for transflectance and transmission were improved significantly. Based on the result of classification and quantification analysis, the transmission mode has yield better prediction model compared to the transflectance mode to distinguish the pure and adulterated palm oil.

Substoichiometric two-dimensional molybdenum oxide flakes: a plasmonic gas sensing platform.

Two-dimensional (2D) molybdenum oxides at their various stoichiometries are promising candidates for generating plasmon resonances in visible light range. Herein, we demonstrate plasmonic 2D molybdenum oxide flakes for gas sensing applications, in which hydrogen (H2) is selected as a model gas. The 2D molybdenum oxide flakes are obtained using a grinding-assisted liquid exfoliation method and exposed to simulated sunlight to acquire its substoichiometric quasi-metallic form. After the exposure to H2 gas molecules, the quasi-metallic molybdenum oxide flakes are partially transformed into semiconducting states, thus gradually losing their plasmonic properties. The novel 2D plasmonic sensing platform is tested using different concentrations of H2 gas at various operating temperatures to comprehensively assess its sensing performance. The presented 2D plasmonic system offers great opportunities for future sensing and optical applications.

Reduced impurity-driven defect states in anodized nanoporous Nb2O5: the possibility of improving performance of photoanodes.

Anodized nanoporous Nb2O5 films are synthesized using two different types of electrolyte compositions onto transparent conductive glasses and their impurities induced during the anodization process are assessed. These films are incorporated as photoanodes in dye sensitized solar cells (DSSCs). The one with no traces of impurity-driven defects exhibits higher current density and longer electron lifetimes, and consequently, an improvement in photoconversion efficiencies compared to the one that contains impurities.

Engineering electrodeposited ZnO films and their memristive switching performance.

We report the influence of zinc oxide (ZnO) seed layers on the performance of ZnO-based memristive devices fabricated using an electrodeposition approach. The memristive element is based on a sandwich structure using Ag and Pt electrodes. The ZnO seed layer is employed to tune the morphology of the electrodeposited ZnO films in order to increase the grain boundary density as well as construct highly ordered arrangements of grain boundaries. Additionally, the seed layer also assists in optimizing the concentration of oxygen vacancies in the films. The fabricated devices exhibit memristive switching behaviour with symmetrical and asymmetrical hysteresis loops in the absence and presence of ZnO seed layers, respectively. A modest concentration of oxygen vacancy in electrodeposited ZnO films as well as an increase in the ordered arrangement of grain boundaries leads to higher switching ratios in Ag/ZnO/Pt devices.

The anodized crystalline WO3 nanoporous network with enhanced electrochromic properties.

We demonstrate that a three dimensional (3D) crystalline tungsten trioxide (WO(3)) nanoporous network, directly grown on a transparent conductive oxide (TCO) substrate, is a suitable working electrode material for high performance electrochromic devices. This nanostructure, with achievable thicknesses of up to 2 µm, is prepared at room temperature by the electrochemical anodization of a RF-sputtered tungsten film deposited on a fluoride doped tin oxide (FTO) conductive glass, under low applied anodic voltages and mild chemical dissolution conditions. For the crystalline nanoporous network with thicknesses ranging from 0.6 to 1 µm, impressive coloration efficiencies of up to 141.5 cm(2) C(-1) are achieved by applying a low coloration voltage of -0.25 V. It is also observed that there is no significant degradation of the electrochromic properties of the porous film after 2000 continuous coloration-bleaching cycles. The remarkable electrochromic characteristics of this crystalline and nanoporous WO(3) are mainly ascribed to the combination of a large surface area, facilitating increased intercalation of protons, as well as excellent continuous and directional paths for charge transfer and proton migration in the highly crystalline material.