This paper proposes a novel method for supervised subspace learning based on Single-hidden Layer Feedforward Neural networks. The proposed method calculates appropriate network target vectors by formulating a Bayesian model exploiting both the labeling information available for the training data and geometric properties of the training data, when represented in the feature space determined by t...

The prediction of travel time is challenging given the sparseness of real-time traffic data and the uncertainty of travel, because it is influenced by multiple factors on the congested urban road networks. In our paper, we propose a three-layer neural network from big probe vehicles data incorporating multi-factors to estimate travel time. The procedure includes the following three steps. First...

background: motorcycle accidents and sport accidents lead yearly to many head injuries like head fractures and concussion. so finding the most proper helmet for reducing the injuries to head can be very helpful for head protection in such cases. methods: after 3d modeling of the helmet and head and meshing the model, a compressive impacting load of 1.31mpa was exerted on head and the model was ...

In this paper, quality-of-service (QoS) guarantees for multiclass code division multiple access networks are provided by means of cross-layer optimization across the physical and network layers. At the physical layer, the QoS requirements are specified in terms of a target signal-to-interference ratio (SIR) requirement, and optimal target powers are dynamically adjusted according to the current...

In order to accurately and efficiently analyze the reliability of distribution network, this paper proposes a method analyzing network based on deep belief network. The Deep Belief Network (DBN) is composed limiting Boltzmann machine layer-by-layer stacking. It has strong advantage automatic feature extraction, which overcomes shortcomings traditional neural networks in extracting data features...

Quantum Neural Networks is one of the new concept which exploits the advantages of both traditional neural networks and concept of quantum computation. A simple hybrid three layer quantum neural networks model is studied, which is composed of both quantum and traditional neurons. The weight of the quantum neuron is quantum bits and its transforming function is an inner product operator. The inp...

To enhance the approximation ability of neural networks, by introducing quantum rotation gates to the traditional BP networks, a novel quantum-inspired neural network model is proposed in this paper. In our model, the hidden layer consists of quantum neurons. Each quantum neuron carries a group of quantum rotation gates which are used to update the quantum weights. Both input and output layer a...

Mercure is an information retrieval system based on a connexionist approach and modeled by a multi-layer network. The network is composed of a query layer (set of query terms), of a term layer (representing the indexing terms) and of a document layer [Bougha 99]. Mercure includes the implementation of retrieval process based on spreading activation forward and backward through the weighted link...

The paper presents a method of image recognition, which is inspired by research in visual cortex. The architecture of our model called CaNN is similar to the one proposed in neocognitron, LeNet or HMAX networks. It is composed of many consecutive layers with various number of planes (receptive fields). Units in the corresponding positions of the planes in one layer receive input from the same r...

TThe uncertainty estimation and compensation are challenging problems for the robust control of robot manipulators which are complex systems. This paper presents a novel decentralized model-free robust controller for electrically driven robot manipulators. As a novelty, the proposed controller employs a simple Gaussian Radial-Basis-Function Network as an uncertainty estimator. The proposed netw...