Abstract: Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.
Abstract: The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.
Abstract: Due to the sensor technology, video surveillance has become the main way for security control in every big city in the world. Surveillance is usually used by governments for intelligence gathering, the prevention of crime, the protection of a process, person, group or object, or the investigation of crime. Many surveillance systems based on computer vision technology have been developed in recent years. Moving target tracking is the most common task for Unmanned Aerial Vehicle (UAV) to find and track objects of interest in mobile aerial surveillance for civilian applications. The paper is focused on vision-based collision avoidance for UAVs by recurrent neural networks. First, images from cameras on UAV were fused based on deep convolutional neural network. Then, a recurrent neural network was constructed to obtain high-level image features for object tracking and extracting low-level image features for noise reducing. The system distributed the calculation of the whole system to local and cloud platform to efficiently perform object detection, tracking and collision avoidance based on multiple UAVs. The experiments on several challenging datasets showed that the proposed algorithm outperforms the state-of-the-art methods.
Abstract: Crude oil market is an immensely complex and dynamic environment and thus the task of predicting changes in such an environment becomes challenging with regards to its accuracy. A number of approaches have been adopted to take on that challenge and machine learning has been at the core in many of them. There are plenty of examples of algorithms based on machine learning yielding satisfactory results for such type of prediction. In this paper, we have tried to predict crude oil prices using Long Short-Term Memory (LSTM) based recurrent neural networks. We have tried to experiment with different types of models using different epochs, lookbacks and other tuning methods. The results obtained are promising and presented a reasonably accurate prediction for the price of crude oil in near future.
Abstract: In terms of ITS, information on link characteristic is an essential factor for plan or operation. But in practical cases, not every link has installed sensors on it. The link that does not have data on it is called “Missing Link”. The purpose of this study is to impute data of these missing links. To get these data, this study applies the machine learning method. With the machine learning process, especially for the deep learning process, missing link data can be estimated from present link data. For deep learning process, this study uses “Recurrent Neural Network” to take time-series data of road. As input data, Dedicated Short-range Communications (DSRC) data of Dalgubul-daero of Daegu Metropolitan Area had been fed into the learning process. Neural Network structure has 17 links with present data as input, 2 hidden layers, for 1 missing link data. As a result, forecasted data of target link show about 94% of accuracy compared with actual data.
Abstract: Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.
Abstract: Parallel hybrid storage systems consist of a hierarchy of different storage devices that vary in terms of data reading speed performance. As we ascend in the hierarchy, data reading speed becomes faster. Thus, migrating the application’ important data that will be accessed in the near future to the uppermost level will reduce the application I/O waiting time; hence, reducing its execution elapsed time. In this research, we implement trace-driven two-levels parallel hybrid storage system prototype that consists of HDDs and SSDs. The prototype uses data mining techniques to classify application’ data in order to determine its near future data accesses in parallel with the its on-demand request. The important data (i.e. the data that the application will access in the near future) are continuously migrated to the uppermost level of the hierarchy. Our simulation results show that our data migration approach integrated with data mining techniques reduces the application execution elapsed time when using variety of traces in at least to 22%.
Abstract: In this paper, we present an optimization technique or
a learning algorithm using the hybrid architecture by combining the
most popular sequence recognition models such as Recurrent Neural
Networks (RNNs) and Hidden Markov models (HMMs). In order to
improve the sequence/pattern recognition/classification performance
by applying a hybrid/neural symbolic approach, a gradient descent
learning algorithm is developed using the Real Time Recurrent
Learning of Recurrent Neural Network for processing the knowledge
represented in trained Hidden Markov Models. The developed hybrid
algorithm is implemented on automata theory as a sample test beds
and the performance of the designed algorithm is demonstrated and
evaluated on learning the deterministic finite state automata.
Abstract: Several meteorological parameters were used for the
prediction of monthly average daily global solar radiation on
horizontal using recurrent neural networks (RNNs). Climatological
data and measures, mainly air temperature, humidity, sunshine
duration, and wind speed between 1995 and 2007 were used to design
and validate a feed forward and recurrent neural network based
prediction systems. In this paper we present our reference system
based on a feed-forward multilayer perceptron (MLP) as well as the
proposed approach based on an RNN model. The obtained results
were promising and comparable to those obtained by other existing
empirical and neural models. The experimental results showed the
advantage of RNNs over simple MLPs when we deal with time series
solar radiation predictions based on daily climatological data.
Abstract: This paper studies the problem of exponential stability analysis for recurrent neural networks with time-varying delay.By establishing a suitable augmented LyapunovCKrasovskii function and a novel sufficient condition is obtained to guarantee the exponential stability of the considered system.In order to get a less conservative results of the condition,zero equalities and reciprocally convex approach are employed. The several exponential stability criterion proposed in this paper is simpler and effective. A numerical example is provided to demonstrate the feasibility and effectiveness of our results.
Abstract: By using the theory of exponential dichotomy and Banach fixed point theorem, this paper is concerned with the problem of the existence and uniqueness of positive almost periodic solution in a delayed Lotka-Volterra recurrent neural networks with harvesting terms. To a certain extent, our work in this paper corrects some result in recent years. Finally, an example is given to illustrate the feasibility and effectiveness of the main result.
Abstract: This paper presents the development of recurrent neural network based fuzzy inference system for identification and control of dynamic nonlinear plant. The structure and algorithms of fuzzy system based on recurrent neural network are described. To train unknown parameters of the system the supervised learning algorithm is used. As a result of learning, the rules of neuro-fuzzy system are formed. The neuro-fuzzy system is used for the identification and control of nonlinear dynamic plant. The simulation results of identification and control systems based on recurrent neuro-fuzzy network are compared with the simulation results of other neural systems. It is found that the recurrent neuro-fuzzy based system has better performance than the others.
Abstract: this paper presents an auto-regressive network called the Auto-Regressive Multi-Context Recurrent Neural Network (ARMCRN), which forecasts the daily peak load for two large power plant systems. The auto-regressive network is a combination of both recurrent and non-recurrent networks. Weather component variables are the key elements in forecasting because any change in these variables affects the demand of energy load. So the AR-MCRN is used to learn the relationship between past, previous, and future exogenous and endogenous variables. Experimental results show that using the change in weather components and the change that occurred in past load as inputs to the AR-MCRN, rather than the basic weather parameters and past load itself as inputs to the same network, produce higher accuracy of predicted load. Experimental results also show that using exogenous and endogenous variables as inputs is better than using only the exogenous variables as inputs to the network.
Abstract: The key to the continued success of ANN depends, considerably,
on the use of hybrid structures implemented on cooperative
frame-works. Hybrid architectures provide the ability to the ANN
to validate heterogeneous learning paradigms. This work describes
the implementation of a set of Distributed and Hybrid ANN models
for Character Recognition applied to Anglo-Assamese scripts. The
objective is to describe the effectiveness of Hybrid ANN setups as
innovative means of neural learning for an application like multilingual
handwritten character and numeral recognition.
Abstract: In this paper, the robust exponential stability problem of uncertain discrete-time recurrent neural networks with timevarying delay is investigated. By constructing a new augmented Lyapunov-Krasovskii function, some new improved stability criteria are obtained in forms of linear matrix inequality (LMI). Compared with some recent results in literature, the conservatism of the new criteria is reduced notably. Two numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed results.
Abstract: We present a hybrid architecture of recurrent neural
networks (RNNs) inspired by hidden Markov models (HMMs). We
train the hybrid architecture using genetic algorithms to learn and
represent dynamical systems. We train the hybrid architecture on a
set of deterministic finite-state automata strings and observe the
generalization performance of the hybrid architecture when presented
with a new set of strings which were not present in the training data
set. In this way, we show that the hybrid system of HMM and RNN
can learn and represent deterministic finite-state automata. We ran
experiments with different sets of population sizes in the genetic
algorithm; we also ran experiments to find out which weight
initializations were best for training the hybrid architecture. The
results show that the hybrid architecture of recurrent neural networks
inspired by hidden Markov models can train and represent dynamical
systems. The best training and generalization performance is
achieved when the hybrid architecture is initialized with random real
weight values of range -15 to 15.
Abstract: recurrent neural network (RNN) is an efficient tool for
modeling production control process as well as modeling services. In
this paper one RNN was combined with regression model and were
employed in order to be checked whether the obtained data by the
model in comparison with actual data, are valid for variable process
control chart. Therefore, one maintenance process in workshop of
Esfahan Oil Refining Co. (EORC) was taken for illustration of
models. First, the regression was made for predicting the response
time of process based upon determined factors, and then the error
between actual and predicted response time as output and also the
same factors as input were used in RNN. Finally, according to
predicted data from combined model, it is scrutinized for test values
in statistical process control whether forecasting efficiency is
acceptable. Meanwhile, in training process of RNN, design of
experiments was set so as to optimize the RNN.
Abstract: Cosmic showers, from their places of origin in space,
after entering earth generate secondary particles called Extensive Air
Shower (EAS). Detection and analysis of EAS and similar High
Energy Particle Showers involve a plethora of experimental setups
with certain constraints for which soft-computational tools like
Artificial Neural Network (ANN)s can be adopted. The optimality
of ANN classifiers can be enhanced further by the use of Multiple
Classifier System (MCS) and certain data - dimension reduction
techniques. This work describes the performance of certain data
dimension reduction techniques like Principal Component Analysis
(PCA), Independent Component Analysis (ICA) and Self Organizing
Map (SOM) approximators for application with an MCS formed
using Multi Layer Perceptron (MLP), Recurrent Neural Network
(RNN) and Probabilistic Neural Network (PNN). The data inputs are
obtained from an array of detectors placed in a circular arrangement
resembling a practical detector grid which have a higher dimension
and greater correlation among themselves. The PCA, ICA and SOM
blocks reduce the correlation and generate a form suitable for real
time practical applications for prediction of primary energy and
location of EAS from density values captured using detectors in a
circular grid.
Abstract: This paper describes reactive neural control used to
generate phototaxis and obstacle avoidance behavior of walking
machines. It utilizes discrete-time neurodynamics and consists of
two main neural modules: neural preprocessing and modular neural
control. The neural preprocessing network acts as a sensory fusion
unit. It filters sensory noise and shapes sensory data to drive the
corresponding reactive behavior. On the other hand, modular neural
control based on a central pattern generator is applied for locomotion
of walking machines. It coordinates leg movements and can generate
omnidirectional walking. As a result, through a sensorimotor loop this
reactive neural controller enables the machines to explore a dynamic
environment by avoiding obstacles, turn toward a light source, and
then stop near to it.
Abstract: Accurate demand forecasting is one of the most key
issues in inventory management of spare parts. The problem of
modeling future consumption becomes especially difficult for lumpy
patterns, which characterized by intervals in which there is no
demand and, periods with actual demand occurrences with large
variation in demand levels. However, many of the forecasting
methods may perform poorly when demand for an item is lumpy.
In this study based on the characteristic of lumpy demand patterns
of spare parts a hybrid forecasting approach has been developed,
which use a multi-layered perceptron neural network and a
traditional recursive method for forecasting future demands. In the
described approach the multi-layered perceptron are adapted to
forecast occurrences of non-zero demands, and then a conventional
recursive method is used to estimate the quantity of non-zero
demands. In order to evaluate the performance of the proposed
approach, their forecasts were compared to those obtained by using
Syntetos & Boylan approximation, recently employed multi-layered
perceptron neural network, generalized regression neural network
and elman recurrent neural network in this area. The models were
applied to forecast future demand of spare parts of Arak
Petrochemical Company in Iran, using 30 types of real data sets. The
results indicate that the forecasts obtained by using our proposed
mode are superior to those obtained by using other methods.