Downloads & Free Reading Options - Results

This paper presented neural network based maximum power point tracking on the design of photovoltaic power input to a DC DC boot converter to the load. Simulink model of photovoltaic array tested the neural network with different temperature and irradiance for maximum power point of a photovoltaic system. DC DC boot converter is used in load when an average output voltage is stable required which can be lower than the input voltage. At the end, the different temperature and irradiance of the data collected from the photovoltaic array system is used to train the neutral network and output efficiency of the designed DC DC boot converter with MPPT control strategy is accepted the maximum power amount to show the result voltage, current and power output for each different have been presented. And also demonstrated that the neural network based MPPT tracking require less time and more accurate results than the other algorithm based MPPT. By Myint Thuzar | Cho Hnin Moh Moh Aung "Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd27867.pdf Paper URL https://www.ijtsrd.com/engineering/electrical-engineering/27867/artificial-neural-network-for-solar-photovoltaic-system-modeling-and-simulation/myint-thuzar

This paper presented neural network based maximum power point tracking on the design of photovoltaic power input to a DC DC boot converter to the load. Simulink model of photovoltaic array tested the neural network with different temperature and irradiance for maximum power point of a photovoltaic system. DC DC boot converter is used in load when an average output voltage is stable required which can be lower than the input voltage. At the end, the different temperature and irradiance of the data collected from the photovoltaic array system is used to train the neutral network and output efficiency of the designed DC DC boot converter with MPPT control strategy is accepted the maximum power amount to show the result voltage, current and power output for each different have been presented. And also demonstrated that the neural network based MPPT tracking require less time and more accurate results than the other algorithm based MPPT. By Myint Thuzar | Cho Hnin Moh Moh Aung "Artificial Neural Network for Solar Photovoltaic System Modeling and Simulation" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd27867.pdf Paper URL https://www.ijtsrd.com/engineering/electrical-engineering/27867/artificial-neural-network-for-solar-photovoltaic-system-modeling-and-simulation/myint-thuzar

This article is from Frontiers in Computational Neuroscience , volume 8 . Abstract None

In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members of the pair. The matches are encoded as embeddings with additional parameters (dimensions), which are tuned by the network. These allows for better capturing interactions between questions and answers, resulting in a significant boost in accuracy. We test our models on two widely used answer sentence selection benchmarks. The results clearly show the effectiveness of our relational information, which allows our relatively simple network to approach the state of the art.

We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously investigated matrix-space models for compositionality, and show they are special cases of the multiplicative recurrent net. Our experiments show that these models perform comparably or better than Elman-type additive recurrent neural networks and outperform matrix-space models on a standard fine-grained sentiment analysis corpus. Furthermore, they yield comparable results to structural deep models on the recently published Stanford Sentiment Treebank without the need for generating parse trees.

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological information, though character-level embeddings have proven valuable to NLP tasks. We propose a new neural language model incorporating both word order and character order in its embedding. The model produces several vector spaces with meaningful substructure, as evidenced by its performance of 85.8% on a recent word-analogy task, exceeding best published syntactic word-analogy scores by a 58% error margin. Furthermore, the model includes several parallel training methods, most notably allowing a skip-gram network with 160 billion parameters to be trained overnight on 3 multi-core CPUs, 14x larger than the previous largest neural network.

When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet benchmark, where we demonstrate a 51.5% relative improvement in the state of the art for object classification.

Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs need to consider longer history of tokens to properly predict the next one. We address this problem by proposing hierarchical RNN architectures, which consist of multiple modules with different timescales. Despite the multi-timescale structures, the input and output layers operate with the character-level clock, which allows the existing RNN CLM training approaches to be directly applicable without any modifications. Our CLM models show better perplexity than Kneser-Ney (KN) 5-gram WLMs on the One Billion Word Benchmark with only 2% of parameters. Also, we present real-time character-level end-to-end speech recognition examples on the Wall Street Journal (WSJ) corpus, where replacing traditional mono-clock RNN CLMs with the proposed models results in better recognition accuracies even though the number of parameters are reduced to 30%.

Field-programmable gate array (FPGA) is a prominent device in developing the internet of things (IoT) application since it offers parallel computation, power efficiency, and scalability. The identification and authentication of these FPGAbased IoT applications are crucial to secure the user-sensitive data transmitted over IoT networks. Physical unclonable function (PUF) technology provides a great capability to be used as device identification and authentication for FPGAbased IoT applications. Nevertheless, conventional PUF-based authentication suffers a huge overhead in storing the challenge-response pairs (CRPs) in the verifier’s database. Therefore, in this paper, the FPGA implementation of the Arbiter-PUF model using an artificial neural network (ANN) is presented. The PUF model can generate the CRPs on-the-fly upon the authentication request (i.e., by a prover) to the verifier and eliminates huge storage of CRPs database in the verifier. The architecture of ANN (i.e., Arbiter-PUF model) is designed in Xilinx system generator and subsequently converted into intellectual property (IP). Further, the IP is programmed in Xilinx Artix-7 FPGA with other peripherals for CRPs generation and validation. The findings show that the Arbiter-PUF model implementation on FPGA using the ANN technique achieves approximately 98% accuracy. The model consumes 12,196 look-up tables (LUTs) and 67 mW power in FPGA.

Click here to view the University of Florida catalog record

The brain is one of the most studied and highly complex systems in the biological world. It is the information center behind all vertebrate and most invertebrate life, and thus has become a major focus in current research. While many of these studies have concentrated on studying the brain directly, our focus is the structure of the brain itself: at its core an interconnected network of nodes (neurons). A better understanding of the structural aspects of the brain should elucidate some of its functional properties. In this paper we analyze the brain of the nematode Caenorhabditis elegans. Consisting of only 302 neurons, it is one of the better-understood neural networks. Using a Laplacian matrix of the 279-neuron "giant component" of the network, we use an eigenvalue counting function to look for fractal-like self similarity. This matrix representation is also used to plot (in eigenfunction coordinates) both 2 and 3 dimensional visualizations of the neural network. Further analysis examines the small-world properties of the system, including average path length and clustering coefficient. We then test for localization of eigenfunctions, using graph energy and spacial variance. To better understand these results, all of these calculations are also performed on random networks, branching trees, and known fractals, as well as fractals which have been "rewired" to have small-world properties. This analysis is one of many stepping-stones in the research of neural networks. While many of the structures and functions within the brain are known, understanding how the two interact is also important. A firmer grasp on the structural properties of the neural network is a key step in this process

How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection (AS), paraphrase identification (PI) and textual entailment (TE). Most prior work (i) deals with one individual task by fine-tuning a specific system; (ii) models each sentence's representation separately, rarely considering the impact of the other sentence; or (iii) relies fully on manually designed, task-specific linguistic features. This work presents a general Attention Based Convolutional Neural Network (ABCNN) for modeling a pair of sentences. We make three contributions. (i) ABCNN can be applied to a wide variety of tasks that require modeling of sentence pairs. (ii) We propose three attention schemes that integrate mutual influence between sentences into CNN; thus, the representation of each sentence takes into consideration its counterpart. These interdependent sentence pair representations are more powerful than isolated sentence representations. (iii) ABCNN achieves state-of-the-art performance on AS, PI and TE tasks.

This was a short-term proof-of-concept project with the goal of demonstrating the feasibility of, and lay the theoretical foundations for, integration of predictive neural networks into Bayesian networks as a means of generating probability distribution functions and likelihood tables. The challenges were two-fold: first, developing a way to convert XY data output from an instrument to a probability density functionusing a neural network and secondly, fusing this and other types of sensor output into a single probabilistic evaluation of multiple sensor outputs. Ultimately, this would be useful in application such as networked sensor arrays such as might be deployed to detect chemical agentsin a subway system for example.

The problem of modeling forest tree growth curves with an artificial neural network (NN) is examined. The NN parametric form is shown to be a suitable model if each forest tree plot is assumed to consist of several differently growing sub-plots. The predictive Bayesian approach is used in estimating the NN output. Data from the correlated curve trend (CCT) experiments are used. The NN predictions are compared with those of one of the best parametric solutions, the Schnute model. Analysis of variance (ANOVA) methods are used to evaluate whether any observed differences are statistically significant. From a Frequentist perspective the differences between the Schnute and NN approach are found not to be significant. However, a Bayesian ANOVA indicates that there is a 93% probability of the NN approach producing better predictions on average.

Neural networks provide an alternative method of building models of human performance. They can learn behavior from examples, reducing the need for many identical repetitions and intensive analysis. A properly trained net can be very robust in its response to a novel stimulus. This opens the door to modeling performance in the presence of an interactive stimulus. Neural networks provide the possibility of robust models that can operate interactively in real time, depending on the size and architecture of the net and the application. A neural network architecture derived from recurrent back propagation is presented which learns to mimic human behavior and performance in a sample task. It shows operating characteristics similar to those of human subjects, and even makes the same kinds of mistakes. Possible applications are discussed.

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some context information that cycles in the network. This paper presents a novel approach, which bridges the gap between these two categories of networks. In particular, we propose an architecture which takes advantage of the explicit, sequential enumeration of the word history in FNN structure while enhancing each word representation at the projection layer through recurrent context information that evolves in the network. The context integration is performed using an additional word-dependent weight matrix that is also learned during the training. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.

Many important NLP problems can be posed as dual-sequence or sequence-to-sequence modeling tasks. Recent advances in building end-to-end neural architectures have been highly successful in solving such tasks. In this work we propose a new architecture for dual-sequence modeling that is based on associative memory. We derive AM-RNNs, a recurrent associative memory (AM) which augments generic recurrent neural networks (RNN). This architecture is extended to the Dual AM-RNN which operates on two AMs at once. Our models achieve very competitive results on textual entailment. A qualitative analysis demonstrates that long range dependencies between source and target-sequence can be bridged effectively using Dual AM-RNNs. However, an initial experiment on auto-encoding reveals that these benefits are not exploited by the system when learning to solve sequence-to-sequence tasks which indicates that additional supervision or regularization is needed.

Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et al. (2014) by explicitly modeling the relationship between previous and subsequent attention levels for each word using one recurrent network per input word. This architecture easily captures informative features, such as fertility and regularities in relative distortion. In experiments, we show our parameterization of attention improves translation quality.

Book Source: Digital Library of India Item 2015.194930 dc.contributor.author: Madhav Kumar.a dc.date.accessioned: 2015-07-08T05:19:38Z dc.date.available: 2015-07-08T05:19:38Z dc.date.digitalpublicationdate: 2005-09-27 dc.identifier.barcode: 1990010093680 dc.identifier.origpath: /rawdataupload/upload/0093/680 dc.identifier.copyno: 1 dc.identifier.uri: http://www.new.dli.ernet.in/handle/2015/194930 dc.description.scannerno: 14 dc.description.scanningcentre: IIIT, Allahabad dc.description.main: 1 dc.description.tagged: 0 dc.description.totalpages: 85 dc.format.mimetype: application/pdf dc.language.iso: English dc.publisher: Indian Institute Of Technology Kanpur dc.rights: Out_of_copyright dc.source.library: Indian Institute Of Technology Kanpur dc.subject.classification: Technology dc.subject.classification: Engineering. Technology In General dc.subject.classification: Civil Engineering dc.title: Modeling Of Monthly Run Off Time Series Using Artifical Neural Networks

Book Source: Digital Library of India Item 2015.194930 dc.contributor.author: Madhav Kumar.a dc.date.accessioned: 2015-07-08T05:19:38Z dc.date.available: 2015-07-08T05:19:38Z dc.date.digitalpublicationdate: 2005-09-27 dc.identifier.barcode: 1990010093680 dc.identifier.origpath: /rawdataupload/upload/0093/680 dc.identifier.copyno: 1 dc.identifier.uri: http://www.new.dli.ernet.in/handle/2015/194930 dc.description.scannerno: 14 dc.description.scanningcentre: IIIT, Allahabad dc.description.main: 1 dc.description.tagged: 0 dc.description.totalpages: 85 dc.format.mimetype: application/pdf dc.language.iso: English dc.publisher: Indian Institute Of Technology Kanpur dc.rights: Out_of_copyright dc.source.library: Indian Institute Of Technology Kanpur dc.subject.classification: Technology dc.subject.classification: Engineering. Technology In General dc.subject.classification: Civil Engineering dc.title: Modeling Of Monthly Run Off Time Series Using Artifical Neural Networks

Book Source: Digital Library of India Item 2015.194930 dc.contributor.author: Madhav Kumar.a dc.date.accessioned: 2015-07-08T05:19:38Z dc.date.available: 2015-07-08T05:19:38Z dc.date.digitalpublicationdate: 2005-09-27 dc.identifier.barcode: 1990010093680 dc.identifier.origpath: /rawdataupload/upload/0093/680 dc.identifier.copyno: 1 dc.identifier.uri: http://www.new.dli.ernet.in/handle/2015/194930 dc.description.scannerno: 14 dc.description.scanningcentre: IIIT, Allahabad dc.description.main: 1 dc.description.tagged: 0 dc.description.totalpages: 85 dc.format.mimetype: application/pdf dc.language.iso: English dc.publisher: Indian Institute Of Technology Kanpur dc.rights: Out_of_copyright dc.source.library: Indian Institute Of Technology Kanpur dc.subject.classification: Technology dc.subject.classification: Engineering. Technology In General dc.subject.classification: Civil Engineering dc.title: Modeling Of Monthly Run Off Time Series Using Artifical Neural Networks

The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN) as a general-purpose classification system for both sentences and documents. DSCNN hierarchically builds textual representations by processing pretrained word embeddings via Long Short-Term Memory networks and subsequently extracting features with convolution operators. Compared with existing recursive neural models with tree structures, DSCNN does not rely on parsers and expensive phrase labeling, and thus is not restricted to sentence-level tasks. Moreover, unlike other CNN-based models that analyze sentences locally by sliding windows, our system captures both the dependency information within each sentence and relationships across sentences in the same document. Experiment results demonstrate that our approach is achieving state-of-the-art performance on several tasks, including sentiment analysis, question type classification, and subjectivity classification.

Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word from scratch without using any part of the original content. Many deep learning approaches for headline generation from text document have been proposed recently, all requiring huge quantities of training data, which is difficult for spoken document summarization. In this paper, we propose an ASR error modeling approach to learn the underlying structure of ASR error patterns and incorporate this model in an Attentive Recurrent Neural Network (ARNN) architecture. In this way, the model for abstractive headline generation for spoken content can be learned from abundant text data and the ASR data for some recognizers. Experiments showed very encouraging results and verified that the proposed ASR error model works well even when the input spoken content is recognized by a recognizer very different from the one the model learned from.

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, slot filling, and language modeling. The neural network model keeps updating the intent estimation as word in the transcribed utterance arrives and uses it as contextual features in the joint model. Evaluation of the language model and online SLU model is made on the ATIS benchmarking data set. On language modeling task, our joint model achieves 11.8% relative reduction on perplexity comparing to the independent training language model. On SLU tasks, our joint model outperforms the independent task training model by 22.3% on intent detection error rate, with slight degradation on slot filling F1 score. The joint model also shows advantageous performance in the realistic ASR settings with noisy speech input.

Large amount of small Unmanned Aerial Vehicles (sUAVs) are projected to operate in the near future. Potential sUAV applications include, but not limited to, search and rescue, inspection and surveillance, aerial photography and video, precision agriculture, and parcel delivery. sUAVs are expected to operate in the uncontrolled Class G airspace, which is at or below 500 feet above ground level (AGL), where many static and dynamic constraints exist, such as ground properties and terrains, restricted areas, various winds, manned helicopters, and conflict avoidance among sUAVs. How to enable safe, efficient, and massive sUAV operations at the low altitude airspace remains a great challenge. NASA's Unmanned aircraft system Traffic Management (UTM) research initiative works on establishing infrastructure and developing policies, requirement, and rules to enable safe and efficient sUAVs' operations. To achieve this goal, it is important to gain insights of future UTM traffic operations through simulations, where the accurate trajectory model plays an extremely important role. On the other hand, like what happens in current aviation development, trajectory modeling should also serve as the foundation for any advanced concepts and tools in UTM. Accurate models of sUAV dynamics and control systems are very important considering the requirement of the meter level precision in UTM operations. The vehicle dynamics are relatively easy to derive and model, however, vehicle control systems remain unknown as they are usually kept by manufactures as a part of intellectual properties. That brings challenges to trajectory modeling for sUAVs. How to model the vehicle's trajectories with unknown control system? This work proposes to use a neural network to model a vehicle's trajectory. The neural network is first trained to learn the vehicle's responses at numerous conditions. Once being fully trained, given current vehicle states, winds, and desired future trajectory, the neural network should be able to predict the vehicle's future states at next time step. A complete 4-D trajectory are then generated step by step using the trained neural network. Experiments in this work show that the neural network can approximate the sUAV's model and predict the trajectory accurately.

Large amount of small Unmanned Aerial Vehicles (sUAVs) are projected to operate in the near future. Potential sUAV applications include, but not limited to, search and rescue, inspection and surveillance, aerial photography and video, precision agriculture, and parcel delivery. sUAVs are expected to operate in the uncontrolled Class G airspace, which is at or below 500 feet above ground level (AGL), where many static and dynamic constraints exist, such as ground properties and terrains, restricted areas, various winds, manned helicopters, and conflict avoidance among sUAVs. How to enable safe, efficient, and massive sUAV operations at the low altitude airspace remains a great challenge. NASA's Unmanned aircraft system Traffic Management (UTM) research initiative works on establishing infrastructure and developing policies, requirement, and rules to enable safe and efficient sUAVs' operations. To achieve this goal, it is important to gain insights of future UTM traffic operations through simulations, where the accurate trajectory model plays an extremely important role. On the other hand, like what happens in current aviation development, trajectory modeling should also serve as the foundation for any advanced concepts and tools in UTM. Accurate models of sUAV dynamics and control systems are very important considering the requirement of the meter level precision in UTM operations. The vehicle dynamics are relatively easy to derive and model, however, vehicle control systems remain unknown as they are usually kept by manufactures as a part of intellectual properties. That brings challenges to trajectory modeling for sUAVs. How to model the vehicle's trajectories with unknown control system? This work proposes to use a neural network to model a vehicle's trajectory. The neural network is first trained to learn the vehicle's responses at numerous conditions. Once being fully trained, given current vehicle states, winds, and desired future trajectory, the neural network should be able to predict the vehicle's future states at next time step. A complete 4-D trajectory are then generated step by step using the trained neural network. Experiments in this work show that the neural network can approximate the sUAV's model and predict the trajectory accurately.

Research works are ongoing in mixing the biologically synthesized oil with the diesel for reducing the effect of global warming and climate change. From the review study, it is noted that the blended biodiesels require more assert about their practical viability. So, the non-edible Tamanu oil is synthesized and it is blended with diesel and its emission characteristics, engine performance and combustion characteristics are studied in our previous work. This paper attempts to model the diesel engine fueled with tamanu oil biodiesel blend. The proposed model exploits the context of neural network and the firefly algorithm is used to train it. After analyzing the various characteristics of the diesel engine, the acquired data is subjected to a proposed FF-NM method. The simulated results are statistically evaluated and the proposed modeling method is proved to be better than the other NM.

Models to predict tree survival and mortality can help to understand vegetation dynamics and to predict effects of climate change on native forests. The objective of the present study was to use Artificial Neural Networks, based on the competition index and climatic and categorical variables, to predict tree survival and mortality in Semideciduous Seasonal Forests in the Atlantic Forest biome. Numerical and categorical trees variables, in permanent plots, were used. The Agricultural Reference Index for Drought (ARID) and the distance-dependent competition index were the variables used. The overall efficiency of classification by ANNs was higher than 92% and 93% in the training and test, respectively. The accuracy for classification and number of surviving trees was above 99% in the test and in training for all ANNs. The classification accuracy of the number of dead trees was low. The mortality accuracy rate (10.96% for training and 13.76% for the test) was higher with the ANN 4, which considers the climatic variable and the competition index. The individual tree-level model integrates dendrometric and meteorological variables, representing a new step for modeling tree survival in the Atlantic Forest biome.

Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the "bursty" distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus, MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.

Statistical Analysis Plan (SAP) As part of the larger TIP project, 61 SAD patients and 41 healthy controls underwent an emotion regulation task with negative and neutral faces during fMRI scanning. We will use dynamic causal modeling (DCM) to shed light on potential disturbances in the effective connectivity of emotion regulation networks in social anxiety disorder (SAD).

Book Source: Digital Library of India Item 2015.225022 dc.contributor.author: Om Prakash dc.date.accessioned: 2015-07-10T15:28:14Z dc.date.available: 2015-07-10T15:28:14Z dc.date.digitalpublicationdate: 2005-09-08 dc.identifier.barcode: 5990010120112 dc.identifier.origpath: /rawdataupload/upload/0120/114 dc.identifier.copyno: 1 dc.identifier.uri: http://www.new.dli.ernet.in/handle/2015/225022 dc.description.scannerno: 15 dc.description.scanningcentre: IIIT, Allahabad dc.description.main: 1 dc.description.tagged: 0 dc.description.totalpages: 66 dc.format.mimetype: application/pdf dc.language.iso: English dc.publisher: Indian Institute Of Technology Kanpur dc.rights: Out_of_copyright dc.source.library: Indian Institute Of Technology Kanpur dc.subject.classification: Technology dc.subject.classification: Engineering. Technology In General dc.subject.classification: Mechanical Engineering In General. Nuclear Technology. Electrical Engineering. Machinery dc.title: Modeling Of Performence Of An Artillery Rocket Using Neural Networks

Introduction Microwave drying compared to conventional hot air drying has many benefits to apply in food drying processes such as volumetric heating, high thermal efficiency, shorter drying time and improved product quality. In conventional microwave drying method, a fixed microwave power was used during the drying process. However, the water of the product evaporated and mass of product decreased over the time that resulted in microwave power density (MPD) increasing during the drying process. Increasing the power density, especially at the end of the process, sharply increased the product temperature. High temperature of products led to the deterioration of the product quality. Most research used variable microwave power program for preventing the risk of overheating and charring of product. The evaporation of the water causes the shrinkage of product. Therefore, many studies have used machine vision for measuring the shrinkage and this technology has been used in modeling and predicting the MC. Materials and Methods The fresh potato samples ( Solanum tuberosum cv. Santana) with 83% (w.b.) of initial MC were sliced into the chips of 5mm thickness. The developed drying systems consisted of microwave oven, lighting unit and imaging unit, temperature sensor, microwave power adjusting unit and a data acquisition unit (DAQ). A LabVIEW (V17.6, 2017) program was developed to integrate all measurements and adjusting the microwave power during the drying process. In this study, two sets of experiment with different aims have done. The first set of experiments was used for calculating the shrinkage by developed image processing algorithm and MC by offline mass measurement and then data sets were used to investigate the artificial neural networks (ANNs). The second set was used for evaluating the reliability of investigating models. The experiments, in the first set, were done with 8, 4 and 2.67 W g -1 . In the variable mode, the power varied in two/three steps with respect to the MC of samples during the drying process. Second set of experiments was done in two variable and constant power modes with 5 and 3 W g -1 . An image processing algorithm was developed to measure the shrinkage of potato slice during the drying process. In this study the feed forward ANN with back propagation algorithm was used. Two structures of ANN were used for modeling of MC. In the first model time and power density and the second model shrinkage and power density were used as input. Also moisture ratio was used as an output parameter in two models. Results and Discussion The obtained results indicated that for the first model the ANN with 2-3-1 structure had better results than others structures. This structure had 0.0713, 0.0337 and 0.0640 of RMSE and 0.9764, 0.9973 and 0.9800 of R for train, validation and test, respectively. For the second model, the 2-2-2-1 structure of ANN with 0.0780, 0.0816 and 0.0908 of RMSE and 0.9598, 0.9799 and 0.9746 of R for train, validation and test, respectively had better results than other structures. The evaluation of these models with a second data set showed that the second model with shrinkage and power density as input with 0.067 of RMSE and 0.994 of R had better results than the first model with 0.173 of RMSE and 0.961 of R. These consequences expressed that the second model had higher reliability for prediction of MC based on shrinkage and power density during drying process. Conclusion In this study, a microwave dryer was developed with a real-time image recording system and a microwave power level program during the drying process. Two ANN models were used for modeling of drying kinetics of the potato slices. Also image processing algorithm was investigated by measuring the shrinkage of potato slice during the drying process. The outcomes revealed that shrinkage as input in the ANN had great effect on MC prediction during the drying process.

Introduction Microwave drying compared to conventional hot air drying has many benefits to apply in food drying processes such as volumetric heating, high thermal efficiency, shorter drying time and improved product quality. In conventional microwave drying method, a fixed microwave power was used during the drying process. However, the water of the product evaporated and mass of product decreased over the time that resulted in microwave power density (MPD) increasing during the drying process. Increasing the power density, especially at the end of the process, sharply increased the product temperature. High temperature of products led to the deterioration of the product quality. Most research used variable microwave power program for preventing the risk of overheating and charring of product. The evaporation of the water causes the shrinkage of product. Therefore, many studies have used machine vision for measuring the shrinkage and this technology has been used in modeling and predicting the MC. Materials and Methods The fresh potato samples ( Solanum tuberosum cv. Santana) with 83% (w.b.) of initial MC were sliced into the chips of 5mm thickness. The developed drying systems consisted of microwave oven, lighting unit and imaging unit, temperature sensor, microwave power adjusting unit and a data acquisition unit (DAQ). A LabVIEW (V17.6, 2017) program was developed to integrate all measurements and adjusting the microwave power during the drying process. In this study, two sets of experiment with different aims have done. The first set of experiments was used for calculating the shrinkage by developed image processing algorithm and MC by offline mass measurement and then data sets were used to investigate the artificial neural networks (ANNs). The second set was used for evaluating the reliability of investigating models. The experiments, in the first set, were done with 8, 4 and 2.67 W g -1 . In the variable mode, the power varied in two/three steps with respect to the MC of samples during the drying process. Second set of experiments was done in two variable and constant power modes with 5 and 3 W g -1 . An image processing algorithm was developed to measure the shrinkage of potato slice during the drying process. In this study the feed forward ANN with back propagation algorithm was used. Two structures of ANN were used for modeling of MC. In the first model time and power density and the second model shrinkage and power density were used as input. Also moisture ratio was used as an output parameter in two models. Results and Discussion The obtained results indicated that for the first model the ANN with 2-3-1 structure had better results than others structures. This structure had 0.0713, 0.0337 and 0.0640 of RMSE and 0.9764, 0.9973 and 0.9800 of R for train, validation and test, respectively. For the second model, the 2-2-2-1 structure of ANN with 0.0780, 0.0816 and 0.0908 of RMSE and 0.9598, 0.9799 and 0.9746 of R for train, validation and test, respectively had better results than other structures. The evaluation of these models with a second data set showed that the second model with shrinkage and power density as input with 0.067 of RMSE and 0.994 of R had better results than the first model with 0.173 of RMSE and 0.961 of R. These consequences expressed that the second model had higher reliability for prediction of MC based on shrinkage and power density during drying process. Conclusion In this study, a microwave dryer was developed with a real-time image recording system and a microwave power level program during the drying process. Two ANN models were used for modeling of drying kinetics of the potato slices. Also image processing algorithm was investigated by measuring the shrinkage of potato slice during the drying process. The outcomes revealed that shrinkage as input in the ANN had great effect on MC prediction during the drying process.

When humans read text, they fixate some words and skip others. However, there have been few attempts to explain skipping behavior with computational models, as most existing work has focused on predicting reading times (e.g.,~using surprisal). In this paper, we propose a novel approach that models both skipping and reading, using an unsupervised architecture that combines a neural attention with autoencoding, trained on raw text using reinforcement learning. Our model explains human reading behavior as a tradeoff between precision of language understanding (encoding the input accurately) and economy of attention (fixating as few words as possible). We evaluate the model on the Dundee eye-tracking corpus, showing that it accurately predicts skipping behavior and reading times, is competitive with surprisal, and captures known qualitative features of human reading.

During the past decade, machine learning has become extremely popular and can be found in many aspects of our every day life. Nowayadays with explosion of data while rapid growth of computation capacity, Distributed Deep Neural Networks (DDNNs) which can improve their performance linearly with more computation resources, have become hot and trending. However, there has not been an in depth study of the performance of these systems, and how well they scale. In this paper we analyze CNTK, one of the most commonly used DDNNs, by first building a performance model and then evaluating the system two settings: a small cluster with all nodes in a single rack connected to a top of rack switch, and in large scale using Blue Waters with arbitary placement of nodes. Our main focus was the scalability of the system with respect to adding more nodes. Based on our results, this system has an excessive initialization overhead because of poor I/O utilization which dominates the whole execution time. Because of this, the system does not scale beyond a few nodes (4 in Blue Waters). Additionally, due to a single server-multiple worker design the server becomes a bottleneck after 16 nodes limiting the scalability of the CNTK.

Here we demonstrate that the activity of neural ensembles can be quantitatively modeled. We first show that an ensemble dynamical model (EDM) accurately approximates the distribution of voltages and average firing rate per neuron of a population of simulated integrate-and-fire neurons. EDMs are high-dimensional nonlinear dynamical models. To faciliate the estimation of their parameters we present a dimensionality reduction method and study its performance with simulated data. We then introduce and evaluate a maximum-likelihood method to estimate connectivity parameters in networks of EDMS. Finally, we show that this model an methods accurately approximate the high-gamma power evoked by pure tones in the auditory cortex of rodents. Overall, this article demonstrates that quantitatively modeling brain activity at the ensemble level is indeed possible, and opens the way to understanding the computations performed by neural ensembles, which could revolutionarize our understanding of brain function.

The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, which is fundamentally different from the commonly used discriminative gradient, and yet has the same computational architecture and cost as the latter. (3) We propose a generative visualization method for the CNNs by sampling from an explicit parametric image distribution. The proposed visualization method can directly draw synthetic samples for any given node in a trained CNN by the Hamiltonian Monte Carlo (HMC) algorithm, without resorting to any extra hold-out images. Experiments on the challenging ImageNet benchmark show that the proposed generative gradient pre-training consistently helps improve the performances of CNNs, and the proposed generative visualization method generates meaningful and varied samples of synthetic images from a large-scale deep CNN.

Neural networks were used to model wing bending-moment loads, torsion loads, and control surface hinge-moments of the Active Aeroelastic Wing (AAW) aircraft. Accurate loads models are required for the development of control laws designed to increase roll performance through wing twist while not exceeding load limits. Inputs to the model include aircraft rates, accelerations, and control surface positions. Neural networks were chosen to model aircraft loads because they can account for uncharacterized nonlinear effects while retaining the capability to generalize. The accuracy of the neural network models was improved by first developing linear loads models to use as starting points for network training. Neural networks were then trained with flight data for rolls, loaded reversals, wind-up-turns, and individual control surface doublets for load excitation. Generalization was improved by using gain weighting and early stopping. Results are presented for neural network loads models of four wing loads and four control surface hinge moments at Mach 0.90 and an altitude of 15,000 ft. An average model prediction error reduction of 18.6 percent was calculated for the neural network models when compared to the linear models. This paper documents the input data conditioning, input parameter selection, structure, training, and validation of the neural network models.

In this study, the Artificial Neural Network (ANN) application is implemented for predicting the required concrete volume and amount of the steel reinforcement within the inversed-T-shaped and stem-stepped reinforced concrete (RC) walls. For this aim, seven-different RC wall designs were approached differentiated within the wall heights and various internal friction angles of backfill materials. Each RC wall is proportionally designed and subjected to active lateral earth pressure defined with the Mononobe-Okabe approach foreseen by Turkish Specification for Building to be Built in Seismic Zones (TSC-2007). Following the stability analysis of the RC retaining walls, the structural and reinforced concrete analyses are performed according to the Turkish Standard on Requirements for Design and Construction in Reinforced Concrete Structures (TS500-2000). Input parameters such as concrete volumes, weights of the steel bars, soil and wall material properties are subjected to the ANN modeling. The prediction of the concrete volume and amount of the steel bars are achieved with the implementation of the ANN model trained with the Artificial Bee Colony (ABC) algorithm. As a result of this study, it is revealed that ANN models are useful for verifying the existing RC retaining wall designs or performing preliminary designs for the L-shaped and stem-stepped cantilever retaining walls.

Massive small unmanned aerial vehicles are envisioned to operate in the near future. While there are lots of research problems need to be addressed before dense operations can happen, trajectory modeling remains as one of the keys to understand and develop policies, regulations, and requirements for safe and efficient unmanned aerial vehicle operations. The fidelity requirement of a small unmanned vehicle trajectory model is high because these vehicles are sensitive to winds due to their small size and low operational altitude. Both vehicle control systems and dynamic models are needed for trajectory modeling, which makes the modeling a great challenge, especially considering the fact that manufactures are not willing to share their control systems. This work proposed to use a neural network approach for modelling small unmanned vehicle's trajectory without knowing its control system and bypassing exhaustive efforts for aerodynamic parameter identification. As a proof of concept, instead of collecting data from flight tests, this work used the trajectory data generated by a mathematical vehicle model for training and testing the neural network. The results showed great promise because the trained neural network can predict 4D trajectories accurately, and prediction errors were less than 2:0 meters in both temporal and spatial dimensions.

The goal of this work was to analyze the potential of neural networks and fuzzy logic methods to develop approximate response surfaces as process modeling, that is for mapping of input into output. Structural response was chosen as an example. Each of the many methods surveyed are explained and the results are presented. Future research directions are also discussed.

We present a new convolutional neural network-based time-series model. Typical convolutional neural network (CNN) architectures rely on the use of max-pooling operators in between layers, which leads to reduced resolution at the top layers. Instead, in this work we consider a fully convolutional network (FCN) architecture that uses causal filtering operations, and allows for the rate of the output signal to be the same as that of the input signal. We furthermore propose an undecimated version of the FCN, which we refer to as the undecimated fully convolutional neural network (UFCNN), and is motivated by the undecimated wavelet transform. Our experimental results verify that using the undecimated version of the FCN is necessary in order to allow for effective time-series modeling. The UFCNN has several advantages compared to other time-series models such as the recurrent neural network (RNN) and long short-term memory (LSTM), since it does not suffer from either the vanishing or exploding gradients problems, and is therefore easier to train. Convolution operations can also be implemented more efficiently compared to the recursion that is involved in RNN-based models. We evaluate the performance of our model in a synthetic target tracking task using bearing only measurements generated from a state-space model, a probabilistic modeling of polyphonic music sequences problem, and a high frequency trading task using a time-series of ask/bid quotes and their corresponding volumes. Our experimental results using synthetic and real datasets verify the significant advantages of the UFCNN compared to the RNN and LSTM baselines.

We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundamental problem is to model and predict such kind of marked temporal dynamics, i.e., when the next event will take place and what its mark will be. Existing methods either predict only the mark or the time of the next event, or predict both of them, yet separately. Indeed, in marked temporal dynamics, the time and the mark of the next event are highly dependent on each other, requiring a method that could simultaneously predict both of them. To tackle this problem, in this paper, we propose to model marked temporal dynamics by using a mark-specific intensity function to explicitly capture the dependency between the mark and the time of the next event. Extensive experiments on two datasets demonstrate that the proposed method outperforms state-of-the-art methods at predicting marked temporal dynamics.

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing a spoken utterance, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and word-based prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together improve parse F1 scores significantly over a strong text-only baseline. For this study with known sentence boundaries, error analysis shows that the main benefit of acoustic-prosodic features is in sentences with disfluencies and that attachment errors are most improved.

http://uf.catalog.fcla.edu/uf.jsp?st=UF002056070&ix=pm&I=0&V=D&pm=1

Microelectromechanical systems (MEMS) are a broad and rapidly expanding field that is currently receiving a great deal of attention because of the potential to significantly improve the ability to sense, analyze, and control a variety of processes, such as heating and ventilation systems, automobiles, medicine, aeronautical flight, military surveillance, weather forecasting, and space exploration. MEMS are very small and are a blend of electrical and mechanical components, with electrical and mechanical systems on one chip. This research establishes reliability estimation and prediction for MEMS devices at the conceptual design phase using neural networks. At the conceptual design phase, before devices are built and tested, traditional methods of quantifying reliability are inadequate because the device is not in existence and cannot be tested to establish the reliability distributions. A novel approach using neural networks is created to predict the overall reliability of a MEMS device based on its components and each component's attributes. The methodology begins with collecting attribute data (fabrication process, physical specifications, operating environment, property characteristics, packaging, etc.) and reliability data for many types of microengines. The data are partitioned into training data (the majority) and validation data (the remainder). A neural network is applied to the training data (both attribute and reliability); the attributes become the system inputs and reliability data (cycles to failure), the system output. After the neural network is trained with sufficient data. the validation data are used to verify the neural networks provided accurate reliability estimates. Now, the reliability of a new proposed MEMS device can be estimated by using the appropriate trained neural networks developed in this work.

A Volterra series approach was applied to the identification of nonlinear systems which are described by a neural network model. A procedure is outlined by which a mathematical model can be developed from experimental data obtained from the network structure. Applications of the results to the control of robotic systems are discussed.

Deep Convolutional Neural Networks (CNNs) are playing important roles in state-of-the-art visual recognition. This paper focuses on modeling the spatial co-occurrence of neuron responses, which is less studied in the previous work. For this, we consider the neurons in the hidden layer as neural words, and construct a set of geometric neural phrases on top of them. The idea that grouping neural words into neural phrases is borrowed from the Bag-of-Visual-Words (BoVW) model. Next, the Geometric Neural Phrase Pooling (GNPP) algorithm is proposed to efficiently encode these neural phrases. GNPP acts as a new type of hidden layer, which punishes the isolated neuron responses after convolution, and can be inserted into a CNN model with little extra computational overhead. Experimental results show that GNPP produces significant and consistent accuracy gain in image classification.

A simple model that replicates the dynamics of spiking and spiking-bursting activity of real biological neurons is proposed. The model is a two-dimensional map which contains one fast and one slow variable. The mechanisms behind generation of spikes, bursts of spikes, and restructuring of the map behavior are explained using phase portrait analysis. The dynamics of two coupled maps which model the behavior of two electrically coupled neurons is discussed. Synchronization regimes for spiking and bursting activity of these maps are studied as a function of coupling strength. It is demonstrated that the results of this model are in agreement with the synchronization of chaotic spiking-bursting behavior experimentally found in real biological neurons.

In this paper, we study neural cognition in social network. A stochastic model is introduced and shown to incorporate two well-known models in Pavlovian conditioning and social networks as special case, namely Rescorla-Wagner model and Friedkin-Johnsen model. The interpretation and comparison of these model are discussed. We consider two cases when the disturbance is independent identical distributed for all time and when the distribution of the random variable evolves according to a markov chain. We show that the systems for both cases are mean square stable and the expectation of the states converges to consensus.