As a data-driven dimensionality reduction and visualization tool, t-distributed stochastic neighborhood embedding (t-SNE) has been successfully applied to a variety of fields. In recent years, it has also received increasing attention for classification and regression analysis. This study presented a t-SNE based classification approach for compositional microbiome data, which enabled us to build classifiers and classify new samples in the reduced dimensional space produced by t-SNE. The Aitchison distance was employed to modify the conditional probabilities in t-SNE to account for the compositionality of microbiome data. To classify a new sample, its low-dimensional features were obtained as the weighted mean vector of its nearest neighbors in the training set. Using the low-dimensional features as input, three commonly used machine learning algorithms, logistic regression (LR), support vector machine (SVM), and decision tree (DT) were considered for classification tasks in this study. The proposed approach was applied to two disease-associated microbiome datasets, achieving better classification performance compared with the classifiers built in the original high-dimensional space. The analytic results also showed that t-SNE with Aitchison distance led to improvement of classification accuracy in both datasets. In conclusion, we have developed a t-SNE based classification approach that is suitable for compositional microbiome data and may also serve as a baseline for more complex classification models.

The deflectometry enables high-precision wavefront measurement with large dynamic range. Traditional multi-step phase-shifting fringe-illumination deflectometric methods involve at least three sinusoidal phase-shifting fringe patterns and require a sequential projection, making it not feasible for the instantaneous measurement. In this paper, a colorcoded method with frequency-carrier patterns is proposed to achieve the instantaneous wavefront measurement based on deflectometry. With the color extraction from different channels, composite patterns in x and y directions can be well separated with a single shot. Then, the phase-shifting patterns encoded in different frequencies can be demodulated with the designed filters, by which the local wavefront slopes can be obtained simultaneously to reconstruct the wavefront under test. Both the numerical simulation and experiments are performed to validate the feasibility of proposed method. The proposed method provides a feasible way for the real-time and instantaneous measurement with large dynamic range based on deflectometry.

With the development of intelligent lighting technology and green lighting, energy-saving has become an important direction of research and development. A lighting energy consumption monitoring platform has been designed and described in the paper based on Model-View-Controller (MVC) software architecture and Entity framework on .Net platform. The energy consumption of the lighting system before and after the using of energy-saving equipment can be monitored, compared and analyzed, which can provide detailed numerical basis for the analyzing of energy-saving performance of the equipments. The system has been deployed by a lighting company in Suzhou. The practical results show that the system has high stability, scalability and significant energy savings.

No abstract

The deflectometry provides an optical testing method with ultra-high dynamic range. In this paper, a microscopic testing method based on deflectometric technique is proposed to quantitatively evaluate the microstructures according to the wavefront aberration. To achieve the real-time and accurate wavefront testing for microstructure evaluation, a colorcoded phase-shifting fringe pattern is applied to illuminate the test object. It avoids the sequential projection of multistep phase-shifting fringes in traditional deflectometry, enabling the transient wavefront testing. The feasibility of the proposed transient microscopic testing method is demonstrated by the experiment. The proposed method enables accurate and transient testing of microstructures with high dynamic range, minimizing the environmental disturbance.