A new technique for facial expression recognition is proposed, which uses the two-dimensional (2-D) discrete cosine transform (DCT) over the entire face image as a feature detector and a constructive one-hidden-layer feedforward neural network as a facial expression classifier. An input-side pruning technique, proposed previously by the authors, is also incorporated into the constructive learning process to reduce the network size without sacrificing the performance of the resulting network. The proposed technique is applied to a database consisting of images of 60 men, each having five facial expression images (neutral, smile, anger, sadness, and surprise). Images of 40 men are used for network training, and the remaining images of 20 men are used for generalization and testing. Confusion matrices calculated in both network training and generalization for four facial expressions (smile, anger, sadness, and surprise) are used to evaluate the performance of the trained network. It is demonstrated that the best recognition rates are 100% and 93.75% (without rejection), for the training and generalizing images, respectively. Furthermore, the input-side weights of the constructed network are reduced by approximately 30% using our pruning method. In comparison with the fixed structure back propagation-based recognition methods in the literature, the proposed technique constructs one-hidden-layer feedforward neural network with fewer number of hidden units and weights, while simultaneously provide improved generalization and recognition performance capabilities.

In this paper, a constructive one-hidden-layer network is introduced where each hidden unit employs a polynomial function for its activation function that is different from other units. Specifically, both a structure level as well as a function level adaptation methodologies are utilized in constructing the network. The functional level adaptation scheme ensures that the "growing" or constructive network has different activation functions for each neuron such that the network may be able to capture the underlying input-output map more effectively. The activation functions considered consist of orthonormal Hermite polynomials. It is shown through extensive simulations that the proposed network yields improved performance when compared to networks having identical sigmoidal activation functions.

No abstract

No abstract

Developing cheap and earth-abundant electrocatalysts with high activity and stability for oxygen reduction reactions (ORRs) is highly desired for the commercial implementation of fuel cells and metal-air batteries. Tremendous efforts have been made on doped-graphene catalysts. However, the progress of phosphorus-doped graphene (P-graphene) for ORRs has rarely been summarized until now. This review focuses on the recent development of P-graphene-based materials, including the various synthesis methods, ORR performance, and ORR mechanism. The applications of single phosphorus atom-doped graphene, phosphorus, nitrogen-codoped graphene (P, N-graphene), as well as phosphorus, multi-atoms codoped graphene (P, X-graphene) as catalysts, supporting materials, and coating materials for ORR are discussed thoroughly. Additionally, the current issues and perspectives for the development of P-graphene materials are proposed.