The pre-diagnosis to type 2 Diabetes, and the effective prophylaxis and treatment of its complication is to be worthy paying attention to. So an intelligent diagnosis based on Quantum Particle Swarm Optimization (QPSO) algorithm and Weighted Least Squares Support Vector Machines (WLS-SVM) is presented, which can overcome the disadvantage of large sample data, slow model-building and rather large deviation in real-time diagnosis. The detailed improvement of the method is to build a mixed kernel function instead of the single one, add self adapting weights, and solve the linear system of equations in the training model of the WLS-SVM with QPSO algorithm, which can increase the performance of diagnostic model. Applied the method in type 2 diabetes, it shows that the velocity of the model-building is quick and the diagnosis accuracy is high, and the result of the improved WLS-SVM is superior to the improved BP algorithm, LM algorithm neural network and the single-kernel function SVM.

No abstract

Background Intrinsically disordered proteins possess flexible 3-D structures, which makes them play an important role in a variety of biological functions. Molecular recognition features (MoRFs) act as an important type of functional regions, which are located within longer intrinsically disordered regions and undergo disorder-to-order transitions upon binding their interaction partners. Results We develop a method, MoRFCNN, to predict MoRFs based on sequence properties and convolutional neural networks (CNNs). The sequence properties contain structural and physicochemical properties which are used to describe the differences between MoRFs and non-MoRFs. Especially, to highlight the correlation between the target residue and adjacent residues, three windows are selected to preprocess the selected properties. After that, these calculated properties are combined into the feature matrix to predict MoRFs through the constructed CNN. Comparing with other existing methods, MoRFCNN obtains better performance. Conclusions MoRFCNN is a new individual MoRFs prediction method which just uses protein sequence properties without evolutionary information. The simulation results show that MoRFCNN is effective and competitive.

No abstract

This paper proposes an improved Criminisi image restoration algorithm that produces better repairs and reduces the computational time. First, we improved the priority calculation and included a step that transforms the original confidence term into an index to achieve a more precise repair. Second, in large damaged areas of an image, we use a local searching method to find the optimal matching block to speed up the repair process. Our experimental results show that the improved method significantly increased the speed of the method, effectively retained image structures, and produced better visual effects.