Search for: All records

Abstract This paper proposed a collaborative neurodynamic optimization (CNO) method to solve traveling salesman problem (TSP). First, we construct a Hopfield neural network (HNN) with $$n \times n$$ n × n neurons for the n cities. Second, to ensure the convergence of continuous HNN (CHNN), we reformulate TSP to satisfy the convergence condition of CHNN and solve TSP by CHNN. Finally, a population of CHNNs is used to search for local optimal solutions of TSP and the globally optimal solution is obtained using particle swarm optimization. Experimental results show the effectiveness of the CNO approach for solving TSP. 

Abstract CdS nanowires and film Schottky diodes are fabricated and diode properties are compared. Effect of SnO 2 on CdS film diode properties is investigated. CdS film/Au on 100 nm SnO 2 substrate demonstrates like-resistor characteristics and increase in SnO 2 thickness corrects resistor behavior, however the effective reverse saturation current density J o is significantly high and shunt resistance are considerably low, implying that SnO 2 slightly prevents impurities migration from CdS films into ITO but cause additional issues. Thickness of CdS film on diode properties is further investigated and increasing CdS film thickness improved J o by one order of magnitude, however shunt resistance is obviously low, suggesting intrinsic issues in CdS film. 100 nm CdS nanowire/Au diodes reduce J o by three orders of magnitude in the dark and two orders of magnitude in the light respectively and their shunt resistance is significantly enhanced by 70 times when comparing with those of the CdS film diodes. The wide difference can be attributed to the fact that CdS nanowires overcome intrinsic issues in CdS film and thus demonstrate significantly well- defined diode behavior. Simulation found that CdS nanowire diodes have low compensating acceptor type traps and interface state density of 5.0 × 10 9 cm −2 , indicating that interface recombination is not a dominated current transport mechanism in the nanowire diodes. CdS film diodes are simulated with acceptor traps and interface state density increased by two order of magnitude and shunt resistance reduced by one order of magnitude, indicating that high density of interface states and shunt paths occur in the CdS film diodes. 

Hyperspectral imaging is an area of active research with many applications in remote sensing, mineral exploration, and environmental monitoring. Deep learning and, in particular, convolution-based approaches are the current state-of-the-art classification models. However, in the presence of noisy hyperspectral datasets, these deep convolutional neural networks underperform. In this paper, we proposed a feature augmentation approach to increase noise resistance in imbalanced hyperspectral classification. Our method calculates context-based features, and it uses a deep convolutional neuronet (DCN). We tested our proposed approach on the Pavia datasets and compared three models, DCN, PCA + DCN, and our context-based DCN, using the original datasets and the datasets plus noise. Our experimental results show that DCN and PCA + DCN perform well on the original datasets but not on the noisy datasets. Our robust context-based DCN was able to outperform others in the presence of noise and was able to maintain a comparable classification accuracy on clean hyperspectral images.