The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Biological system such as neural networks and genetic algorithms are adapted to improve the doctors experience for diagnosis of illnesses. This work is introduced an approach for diagnosing breast cancer via classifying a well-known WBCD dataset based on a hybrid neurogenetic system. The suggested approach showed a good behavior and excellent classification accuracy through the implementation of several...
Neural Network (NN) based acoustic frontends, such as denoising autoencoders, are actively being investigated to improve the robustness of NN based acoustic models to various noise conditions. In recent work the joint training of such frontends with backend NNs has been shown to significantly improve speech recognition performance. In this paper, we propose an effective algorithm to jointly train...
Non-cosmic, non-Gaussian disturbances known as “glitches”, show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their...
This paper presents a framework for modeling neural decoding using electromyogram (EMG) and electrocorticogram (ECoG) signals to interpret human intent and control prosthetic arms. Specifically, the method of this paper employs Markov Decision Processes (MDP) for neural decoding, parameterizing the policy using an artificial neural network. The system is trained using a modification of the Dataset...
A multi-stream framework with deep neural network (DNN) classifiers has been applied in this paper to improve automatic speech recognition (ASR) performance in environments with different reverberation characteristics. We propose a room parameter estimation model to determine the stream weights for DNN posterior probability combination with the aim of obtaining reliable log-likelihoods for decoding...
Though the classical robotics is highly proficient in accomplishing a lot of complex tasks, still it is far from exhibiting the human-like natural intelligence in terms of flexibility and reliability to work in dynamic scenarios. In order to render these qualities in the robots, reinforcement learning could prove to be quite effective. By employing learning based training provided by reinforcement...
Unintended lane departure accidents are due to driver's inattention, incapacitation, and drowsiness. Lane departure warning systems have been developed to enhance traffic safety by predicting/detecting driving situation and alerting drivers to avoid or mitigate traffic accidents. This paper explores effectiveness of a three-layer perceptron neural network in predicting an unintentional lane departure,...
Neural networks generally require significant memory capacity/bandwidth to store/access a large number of synaptic weights. This paper presents an application of JPEG image encoding to compress the weights by exploiting the spatial locality and smoothness of the weight matrix. To minimize the loss of accuracy due to JPEG encoding, we propose to adaptively control the quantization factor of the JPEG...
This paper presents the ideal approach to how to minimize the time taken by reinforcement learning to train the model. Similar to Computer vision the progress in reinforcement learning is not influenced by new ideas but mostly by the computation, large data, infrastructure and efficiency of algorithm. These 4 things only influenced the reinforcement learning RL model. How much time it will take to...
Deep neural networks (DNNs), which show outstanding performance in various areas, consume considerable amounts of memory and time during training. Our research led us to propose a controlled dropout technique with the potential of reducing the memory space and training time of DNNs. Dropout is a popular algorithm that solves the overfitting problem of DNNs by randomly dropping units in the training...
By the number of people aged 60 or over and people with disabilities growing, homecare mobile robot draws increasing attention. However, there are challenges of autonomous navigation for homecare robot such as frequent changes of environment, obstacles and goal position. In this paper, we focus on verifying potential of neural network-based autonomous navigation for homecare mobile. And we compare...
Usage of inercial sensors is widespread in many areas, especially in aueronautics. Another field of use for such sensors is capturing and recognizing gestures from sensors placed on human body parts, for example hand or shoulder. This article is dealing with a proposal of weareable sensors, capable of detecting simple gestures such as rotation, elevation, movement etc. System will be based on STM32...
A targeted approach to soot blow operation based on boiler operating conditions involves estimation of cleanliness factor. The present work introduces a way of estimating the cleanliness factor of thermal power plant reheater by artificial neural network (ANN). Three different algorithms used to train NN and their performance is compared. Based on the simulation studies it was observed that although...
Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC-called a Tensor Processing Unit (TPU)-deployed in datacenters since 2015 that accelerates the inference phase of neural networks (NN). The heart of the TPU is a 65,536 8-bit MAC matrix multiply unit that offers a peak throughput of 92 TeraOps/second...
In this Research Experience for Undergraduate (REU) project, we develop and implement deep neural network algorithms for change detection of synthetic aperture radar (SAR) images. Deep neural networks represent a powerful data processing methodology that integrates recent deep learning techniques on neural network computing frameworks to undercover underlying features and structures of observational...
In this paper, a sequential and partially parallel Fuzzy Adaptive Resonance Theory (ART) neural network (NN) are simulated. Simulations are performed in Matlab environment. According to simulation results, partially parallel Fuzzy ART NN is capable to reach by order higher speed of data processing than its sequential counterpart.
With the cloud computing development, elastic scaling capability is an important factor to ensure the quality of cloud services. In this paper, the author designed resource requirement model about web system based on neural network under the certain quality of service on cloud platforms. According to the model, the method and mechanism for elastic scaling is realized by BP algorithm on cloud platforms.
This paper proposes a model for an offline handwritten Khmer character recognition. We make use of two dimensional Fourier transformation for feature selection and feed-forward Artificial Neural Net as classification tool. The recognition system allows using the nature of Khmer writing, which is an example of alphasyllabary (Abugida) writing systems. The recognition of the normalized handwritten images...
Recently, more neuroscience researches focus on the role of dendritic structure during the neural computation. Inspired by the specified topologies of numerous dendritic trees, we proposed a single neural model with a particular dendritic structure. The dendrites are composed of several branches, and these branches correspond to three distributions in coordinate, which are used to classify the training...
We present staff notation recognition using deep learning technique. To satisfy the purpose, the application requires a user to provide input image of the staff notations. As the staff notations are predominantly black in color, algorithms like desaturation and decomposition can be used to convert colored images into gray scale equivalent (Image Processing). The converted images will undergo the processing...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.