Background: To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. Results: A convolutional neural network (CNN) with transfer learning capability is proposed and appropriate hyperparameters are selected for classifying optical coherence tomography (OCT) images of AMD and DME. To perform transfer learning, a pre-trained CNN model is used as the starting point for a new CNN model for solving related problems. The hyperparameters (parameters that have set values before the learning process begins) in this study were algorithm hyperparameters that affect learning speed and quality. During training, different CNN-based models require different algorithm hyperparameters (e.g., optimizer, learning rate, and mini-batch size). Experiments showed that, after transfer learning, the CNN models (8-layer Alexnet, 22-layer Googlenet, 16-layer VGG, 19-layer VGG, 18-layer Resnet, 50-layer Resnet, and a 101-layer Resnet) successfully classified OCT images of AMD and DME. Conclusions: The experimental results further showed that, after transfer learning, the VGG19, Resnet101, and Resnet50 models with appropriate algorithm hyperparameters had excellent capability and performance in classifying OCT images of AMD and DME.

Nanofluid/ultrasonic atomization minimal quantity lubrication (MQL) was used in an SKD11 steel micro-milling process with ultrasonic dispersion. The nanofluid atomizer substantially improved nanofluid reunification and delivery to the cutting zone. The micro-milling cutting force and temperature were used to calculate the signal-to-noise ratio (S/N). Normalization of the S/N in a grey relational analysis obtained a grey correlation coefficient, which was used in a fuzzy analysis to obtain a multiple performance characteristic indexes (MPCI). The MPCI was maximized by optimizing the process parameters for multiple quality characteristics and then comparing the optimized parameters with those in the MQL system. Experimental results indicate that the nanofluid parameters containing the density of nanofluid, feed rate, and distance of nozzle are the most influential control factors, while 3.617 Newton and 117.1 degrees Celsius, respectively, are the optimal combination of parameters. Different lubricating methods were also compared in terms of effects on micro-milling cutting force, micro-milling temperature, micro-milling tool wear, and surface burr. Experiments showed that nanofluid (MWCNTs)/ultrasonic atomization MQL obtained the best results.

An adaptive network-based fuzzy inference system (ANFIS) with a sliding-level particle swarm optimization (SL-PSO) is proposed for optimizing parameters of a chemical-mechanical process for polishing a color filter (CMP-CF). The SL-PSO is used not only to find the best membership function types, but also to optimize the premise and consequent parameters for ANFIS. The important process parameters for CMP-CF included the initial time, polishing time, polishing pad weight (down force), slurry chemicals, and rotation speed. The output targets were red pixels, green pixels, blue pixels, and the surface roughness. First, the performance of the SL-PSO was tested with 18 continuous global numerical optimization problems, including six unimodal functions, seven multimodal functions, and five complex rotated and shifted functions. Nonparametric Wilcoxon tests were also used in multiple-problem analysis for simultaneous comparison of various algorithms over a problem set. The computational experiments showed that the proposed SL-PSO approach outperforms PSO-based methods reported in the literature. Finally, the proposed SL-PSO method was used to optimize CMP-CF parameters. The experimental results showed that the ANFIS with SL-PSO outperforms the conventional ANFIS method and conventional back propagation neural network in terms of prediction accuracy. A practical industrial application in a CF manufacturer showed that the ANFIS with SL-PSO obtained superior results compared to the previous method and immediately enhanced production efficiency. Together, these experimental results indicate that the proposed ANFIS with SL-PSO is a reliable method for optimizing CMP-CF processes.

Background: Researchers have attempted to apply deep learning methods of artificial intelligence for rapidly and accurately detecting acute lymphoblastic leukemia (ALL) in microscopic images. Results: A Resnet101-9 ensemble model was developed for classifying ALL in microscopic images. The proposed Resnet101-9 ensemble model combined the use of the nine trained Resnet-101 models with a majority voting strategy. Each trained Resnet-101 model integrated the well-known pre-trained Resnet-101 model and its algorithm hyperparameters by using transfer learning method to classify ALL in microscopic images. The best combination of algorithm hyperparameters for the pre-trained Resnet-101 model was determined by Taguchi experimental method. The microscopic images used for training of the pre-trained Resnet-101 model and for performance tests of the trained Resnet-101 model were obtained from the C-NMC dataset. In experimental tests of performance, the Resnet101-9 ensemble model achieved an accuracy of 85.11% and an F₁-score of 88.94 in classifying ALL in microscopic images. The accuracy of the Resnet101-9 ensemble model was superior to that of the nine trained Resnet-101 individual models. All other performance measures (i.e., precision, recall, and specificity) for the Resnet101-9 ensemble model exceeded those for the nine trained Resnet-101 individual models. Conclusion: Compared to the nine trained Resnet-101 individual models, the Resnet101-9 ensemble model had superior accuracy in classifying ALL in microscopic images obtained from the C-NMC dataset.

The modeling and optimization method (MAOM) proposed in this study finds the best combination of parameters for a multi-layer convolutional neural network (MCNN). This study emphasizes that in addition to the importance of the MCNN structure, the parameter design within the layers is also very important. After determining the structure of the MCNN, the parameter optimization in the layer can improve the performance of the MCNN. The MCNN parameters for convolutional layers include filter size, number of filters, padding, and filter stride. Parameters for max-pooling layers also include pooling size and pooling stride. After the MCNN architecture is designed, the major challenge is finding the combination of parameters that enhances the MCNN performance. The proposed MAOM optimizes the MCNN parameters by integrating uniform experimental design (UED), multiple regression (MR), and optimization method. After the MCNN architecture is designed, UED is used to design the MCNN parameters. The parameter layout obtained by UED is then used in experiments to collect data that can be used for modeling. Next, MR is performed using the parameters with the average correct rate to build an MCNN parameter model. Finally, a full-factorial search algorithm is used to find the best combination of MCNN parameters for obtaining maximum average correct rate. Images from the modified National Institute of Standards and Technology (modified NIST or MNIST) resources, Fashion-MNIST and PhysioNet databases are used to test the performance of the architecture and parameters of the MCNN. The experimental results demonstrate the excellent performance of the MAOM in obtaining the best combination of MCNN parameters and maximum average correct rate. The main advantage of the proposed MAOM is its systematic method of finding the best combination of MCNN parameters for image identification and obtaining high correct rate.