There is increasing interest in how the pupil dynamics of the eye reflect underlying cognitive processes and brain states. Problematic, however, is that pupil changes can be due to non-cognitive factors, for example luminance changes in the environment, accommodation and movement. In this paper we consider how by modeling the response of the pupil in real-world environments we can capture the non-cognitive related changes and remove these to extract a residual signal which is a better index of cognition and performance. (...) Specifically, we utilize sequence measures such as fixation position, duration, saccades, and blink-related information as inputs to a deep recurrent neural network (RNN) model for predicting subsequent pupil diameter. We build and evaluate the model for a task where subjects are watching educational videos and subsequently asked questions based on the content. Compared to commonly-used models for this task, the RNN had the lowest errors rates in predicting subsequent pupil dilation given sequence data. Most importantly was how the model output related to subjects' cognitive performance as assessed by a post-viewing test. Consistent with our hypothesis that the model captures non-cognitive pupil dynamics, we found (1) the model's root-mean square error was less for lower performing subjects than for those having better performance on the post-viewing test, (2) the residuals of the RNN (LSTM) model had the highest correlation with subject post-viewing test scores and (3) the residuals had the highest discriminability (assessed via area under the ROC curve, AUC) for classifying high and low test performers, compared to the true pupil size or the RNN model predictions. This suggests that deep learning sequence models may be good for separating components of pupil responses that are linked to luminance and accommodation from those that are linked to cognition and arousal. (shrink)

Timely detection and efficient recognition of fault are challenging for the bogie of high-speed train, owing to the fact that different types of fault signals have similar characteristics in the same frequency range. Notice that convolutional neural networks are powerful in extracting high-level local features and that recurrent neural networks are capable of learning long-term context dependencies in vibration signals. In this paper, by combining CNN and RNN, a so-called convolutional recurrent neural network is (...) proposed to diagnose various faults of the HST bogie, where the capabilities of CNN and RNN are inherited simultaneously. Within the novel architecture, the proposed CRNN first filters out the features from the original data through convolutional layers. Then, four recurrent layers with simple recurrent cell are used to model the context information in the extracted features. By comparing the performance of the presented CRNN with CNN, RNN, and ensemble learning, experimental results show that CRNN achieves not only the best performance with accuracy of 97.8% but also the least time spent in training model. (shrink)

This paper implements the continuous Hindi Automatic Speech Recognition (ASR) system using the proposed integrated features vector with Recurrent Neural Network (RNN) based Language Modeling (LM). The proposed system also implements the speaker adaptation using Maximum-Likelihood Linear Regression (MLLR) and Constrained Maximum likelihood Linear Regression (C-MLLR). This system is discriminatively trained by Maximum Mutual Information (MMI) and Minimum Phone Error (MPE) techniques with 256 Gaussian mixture per Hidden Markov Model(HMM) state. The training of the baseline system has (...) been done using a phonetically rich Hindi dataset. The results show that discriminative training enhances the baseline system performance by up to 3%. Further improvement of ~7% has been recorded by applying RNN LM. The proposed Hindi ASR system shows significant performance improvement over other current state-of-the-art techniques. (shrink)

In today’s era of rapid development in science and technology, the development of digital technology has increasingly higher requirements for data processing functions. The matrix signal commonly used in engineering applications also puts forward higher requirements for processing speed. The eigenvalues of the matrix represent many characteristics of the matrix. Its mathematical meaning represents the expansion of the inherent vector, and its physical meaning represents the spectrum of vibration. The eigenvalue of a matrix is the focus of matrix theory. The (...) problem of matrix eigenvalues is widely used in many research fields such as physics, chemistry, and biology. A neural network is a neuron model constructed by imitating biological neural networks. Since it was proposed, the application research of its typical models, such as recurrent neural networks and cellular neural networks, has become a new hot spot. With the emergence of deep neural network theory, scholars continue to combine deep neural networks to calculate matrix eigenvalues. This article aims to study the estimation and application of matrix eigenvalues based on deep neural networks. This article introduces the related methods of matrix eigenvalue estimation based on deep neural networks, and also designs experiments to compare the time of matrix eigenvalue estimation methods based on deep neural networks and traditional algorithms. It was found that under the serial algorithm, the algorithm based on the deep neural network reduced the calculation time by about 7% compared with the traditional algorithm, and under the parallel algorithm, the calculation time was reduced by about 17%. Experiments are also designed to calculate matrix eigenvalues with Obj and recurrent neural networks (RNNS) models, which proves that the Oja algorithm is only suitable for calculating the maximum eigenvalues of non-negative matrices, while RNNS is commonly used in general models. (shrink)

Recurrent neural network has been widely applied to many sequential tagging tasks such as natural language process and time series analysis, and it has been proved that RNN works well in those areas. In this paper, we propose using RNN with long short-term memory units for server load and performance prediction. Classical methods for performance prediction focus on building relation between performance and time domain, which makes a lot of unrealistic hypotheses. Our model is built based on (...) events, which is the root cause of server performance. We predict the performance of the servers using RNN-LSTM by analyzing the log of servers in data center which contains user’s access sequence. Previous work for workload prediction could not generate detailed simulated workload, which is useful in testing the working condition of servers. Our method provides a new way to reproduce user request sequence to solve this problem by using RNN-LSTM. Experiment result shows that our models get a good performance in generating load and predicting performance on the data set which has been logged in online service. We did experiments with nginx web server and mysql database server, and our methods can been easily applied to other servers in data center. (shrink)

Introduction of deep neural networks to the machine translation research ameliorated conventional machine translation systems in multiple ways, specifically in terms of translation quality. The ability of deep neural networks to learn a sensible representation of words is one of the major reasons for this improvement. Despite machine translation using deep neural architecture is showing state-of-the-art results in translating European languages, we cannot directly apply these algorithms in Indian languages mainly because of two reasons: unavailability of the (...) good corpus and Indian languages are morphologically rich. In this paper, we propose a neural machine translation (NMT) system for four language pairs: English–Malayalam, English–Hindi, English–Tamil, and English–Punjabi. We also collected sentences from different sources and cleaned them to make four parallel corpora for each of the language pairs, and then used them to model the translation system. The encoder network in the NMT architecture was designed with long short-term memory (LSTM) networks and bi-directional recurrent neural networks (Bi-RNN). Evaluation of the obtained models was performed both automatically and manually. For automatic evaluation, the bilingual evaluation understudy (BLEU) score was used, and for manual evaluation, three metrics such as adequacy, fluency, and overall ranking were used. Analysis of the results showed the presence of lengthy sentences in English–Malayalam, and the English–Hindi corpus affected the translation. Attention mechanism was employed with a view to addressing the problem of translating lengthy sentences (sentences contain more than 50 words), and the system was able to perceive long-term contexts in the sentences. (shrink)

Recommender system depends on the thoughts of numerous users to predict the favourites of potential consumers. RS is vulnerable to malicious information. Unsuitable products can be offered to the user by injecting a few unscrupulous “shilling” profiles like push and nuke attacks into the RS. Injection of these attacks results in the wrong recommendation for a product. The aim of this research is to develop a framework that can be widely utilized to make excellent recommendations for sales growth. This study (...) uses the methodology that presents an enhanced clustering algorithm named as modified density peak clustering algorithm on the consumer review dataset to ensure a well-formed cluster. An improved recurrent neural network algorithm is proposed to detect these attacks in hybrid RS, which uses the content-based RS and collaborative filtering RS. The results are compared with other state of the art algorithms. The proposed method is more suitable for E-commerce applications where the number of customers and products grows rapidly. (shrink)

With the rapid growth of informatics systems’ technology in this modern age, the Internet of Things (IoT) has become more valuable and vital to everyday life in many ways. IoT applications are now more popular than they used to be due to the availability of many gadgets that work as IoT enablers, including smartwatches, smartphones, security cameras, and smart sensors. However, the insecure nature of IoT devices has led to several difficulties, one of which is distributed denial-of-service (DDoS) attacks. IoT (...) systems have several security limitations due to their disreputability characteristics, like dynamic communication between IoT devices. The dynamic communications resulted from the limited resources of these devices, such as their data storage and processing units. Recently, many attempts have been made to develop intelligent models to protect IoT networks against DDoS attacks. The main ongoing research issue is developing a model capable of protecting the network from DDoS attacks that is sensitive to various classes of DDoS and can recognize legitimate traffic to avoid false alarms. Subsequently, this study proposes combining three deep learning algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM)-RNN, and convolutional neural network (CNN), to build a bidirectional CNN-BiLSTM DDoS detection model. The RNN, CNN, LSTM, and CNN-BiLSTM are implemented and tested to determine the most effective model against DDoS attacks that can accurately detect and distinguish DDoS from legitimate traffic. The intrusion detection evaluation dataset (CICIDS2017) is used to provide more realistic detection. The CICIDS2017 dataset includes benign and up-to-date examples of typical attacks, closely matching real-world data of Packet Capture. The four models are tested and assessed using Confusion Metrix against four commonly used criteria: accuracy, precision, recall, and F-measure. The performance of the models is quite effective as they obtain an accuracy rate of around 99.00%, except for the CNN model, which achieves an accuracy of 98.82%. The CNN-BiLSTM achieves the best accuracy of 99.76% and precision of 98.90%. (shrink)

The approach used by physics is based on the identification and study of ideal objects, which is also the basis of biophysics, in combination with von Neumann heuristic modeling and functional fractionation according to R.Rosen is discussed as a tool for studying the properties of consciousness. The object of the study is a kind of line of analog systems: the human brain, the vertebrate brain, the invertebrate brain and artificial neural networks capable of reflection, which is a key property (...) characteristic of consciousness. Reflection in the broad sense of the word, understood as an internal representation of the external world, is characteristic of a wide range of animals, and some of them (bumblebees, fish) even demonstrate reflection in the narrow sense of the word, understood as an inner self-representation. This complex behavior is realized by miniature brains of ~1 million neurons. The use of simple recurrent neural networks (RNNs) to obtain answers to general questions is illustrated. For example, it has been shown a small RNS is able to pass delayed matching to sample (DMTS) test, forming an individual dynamic representation of the received stimulus, allowing decoding by a special external neural detector.. It has been demonstrated in the reflexive game “even-odd”, the RNS has a huge advantage over a multi-layered neural network, with the same and a larger number of neurons – reflection defeats regression. It was found that the asymmetry of outcomes in the odd-even game, which was explained by various causes, including psychological ones – “it’s easier to catch up than to run away”, is reproduced in the game of two RNNs. Obviously, there are no psychological causes here and the advantage of the player playing for “even” is explained by the more complex strategy of the “odd” player – he needs to predict the opponent’s move and choose the opposite one. (shrink)

The approach used by physics is based on the identification and study of ideal objects, which is also the basis of biophysics, in combination with von Neumann heuristic modeling and functional fractionation according to R.Rosen is discussed as a tool for studying the properties of consciousness. The object of the study is a kind of line of analog systems: the human brain, the vertebrate brain, the invertebrate brain and artificial neural networks capable of reflection, which is a key property (...) characteristic of consciousness. Reflection in the broad sense of the word, understood as an internal representation of the external world, is characteristic of a wide range of animals, and some of them (bumblebees, fish) even demonstrate reflection in the narrow sense of the word, understood as an inner self-representation. This complex behavior is realized by miniature brains of ~1 million neurons. The use of simple recurrent neural networks (RNNs) to obtain answers to general questions is illustrated. For example, it has been shown a small RNS is able to pass delayed matching to sample (DMTS) test, forming an individual dynamic representation of the received stimulus, allowing decoding by a special external neural detector.. It has been demonstrated in the reflexive game “even-odd”, the RNS has a huge advantage over a multi-layered neural network, with the same and a larger number of neurons – reflection defeats regression. It was found that the asymmetry of outcomes in the odd-even game, which was explained by various causes, including psychological ones – “it’s easier to catch up than to run away”, is reproduced in the game of two RNNs. Obviously, there are no psychological causes here and the advantage of the player playing for “even” is explained by the more complex strategy of the “odd” player – he needs to predict the opponent’s move and choose the opposite one. (shrink)

In order to improve the efficiency of the English translation, machine translation is gradually and widely used. This study briefly introduces the neural network algorithm for speech recognition. Long short-term memory (LSTM), instead of traditional recurrent neural network (RNN), was used as the encoding algorithm for the encoder, and RNN as the decoding algorithm for the decoder. Then, simulation experiments were carried out on the machine translation algorithm, and it was compared with two other machine (...) translation algorithms. The results showed that the back-propagation (BP) neural network had a lower word error rate and spent less recognition time than artificial recognition in recognizing the speech; the LSTM–RNN algorithm had a lower word error rate than BP–RNN and RNN–RNN algorithms in recognizing the test samples. In the actual speech translation test, as the length of speech increased, the LSTM–RNN algorithm had the least changes in the translation score and word error rate, and it had the highest translation score and the lowest word error rate under the same speech length. (shrink)

The accurate recognition of speech is beneficial to the fields of machine translation and intelligent human–computer interaction. After briefly introducing speech recognition algorithms, this study proposed to recognize speech with a recurrent neural network (RNN) and adopted the connectionist temporal classification (CTC) algorithm to align input speech sequences and output text sequences forcibly. Simulation experiments compared the RNN-CTC algorithm with the Gaussian mixture model–hidden Markov model and convolutional neural network-CTC algorithms. The results demonstrated that the (...) more training samples the speech recognition algorithm had, the higher the recognition accuracy of the trained algorithm was, but the training time consumption increased gradually; the more samples a trained speech recognition algorithm had to test, the lower the recognition accuracy and the longer the testing time. The proposed RNN-CTC speech recognition algorithm always had the highest accuracy and the lowest training and testing time among the three algorithms when the number of training and testing samples was the same. (shrink)

Seepage analysis is always a concern in dam safety and stability research. The prediction and analysis of seepage pressure monitoring data is an effective way to ensure the safety and stability of dam seepage. With the timeliness of a change in a monitoring value and lag due to external influences, a RS-LSTM model written in Python is developed in this paper which combines rough set theory and the long- and short-term memory network model. The model proposed calculates the prediction (...) score of the seepage pressure of a dam experiencing multiple effects by preordering factor importance values to eliminate the interference of redundant factors. A case study shows that the water level, rainfall, temperature, and duration are all factors that affect the seepage pressure, and their importance values decrease successively. Thus, the seepage pressure of a dam can be predicted with a determination coefficient R2 of 0.96. Compared with the recurrent neural network model and BP neural network model, the training time of the RS-LSTM model proposed is 6.37 s, and the operation efficiency is 41% and 59% higher than that of the RNN and BP models, respectively. The mean relative error is also 3.00%, which is 50% lower than that of the RNN model and 31% lower than that of the BP model. Based on these results, this model has the advantages of fast computation speed and high accuracy in prediction. (shrink)

Metaverse is to build a virtual world that is both mapped and independent of the real world in cyberspace by using the improvement in the maturity of various digital technologies, such as virtual reality, augmented reality, big data, and 5G, which is important for the future development of a wide variety of professions, including education. The metaverse represents the latest stage of the development of visual immersion technology. Its essence is an online digital space parallel to the real world, which (...) is becoming a practical field for the innovation and development of human society. The most prominent advantage of the English-teaching metaverse is that it can provide an immersive and interactive teaching field for teachers and students, simultaneously meeting the teaching and learning needs of teachers and students in both the physical world and virtual world. This study constructs experiential situational English-teaching scenario and convolutional neural networks –recurrent neural networks fusion models are proposed to recognize students’ emotion electroencephalogram in experiential English teaching during the feature space of time domain, frequency domain, and spatial domain. Analyzing EEG data collected by OpenBCI EEG Electrode Cap Kit from students, experiential English-teaching scenario is designed into three types: sequential guidance, comprehensive exploration, and crowd-creation construction. Experimental data analysis of the three kinds of learning activities shows that metaverse-powered experiential situational English teaching can promote the improvement of students’ sense of interactivity, immersion, and cognition, and the accuracy and analysis time of CNN–RNN fusion model is much higher than that of baselines. This study can provide a nice reference for the emotion recognition of students under COVID-19. (shrink)

The foremost aim of this research was to forecast the performance of three stock market indices using the multilayer perceptron, recurrent neural network, and autoregressive integrated moving average on historical data. Moreover, we compared the extrapolative abilities of a hybrid of ARIMA with MLP and RNN models, which are called ARIMA-MLP and ARIMA-RNN. Because of the complicated and noisy nature of financial data, we combine novel machine-learning techniques such as MLP and RNN with ARIMA model to predict (...) the three stock market data. The data used in this study are taken from the Pakistan Stock Exchange, National Stock Exchange India, and Sri Lanka Stock Exchange. In the case of Pakistan, the findings show that the ARIMA-MLP and ARIMA-RNN beat the individual ARIMA, MLP, and RNN models in terms of accuracy. Similarly, in the case of Sri Lanka and India, the hybrid models show more robustness in terms of forecasting than individual ARIMA, MLP, and RNN models based on root-mean-square error and mean absolute error. Apart from this, ARIMA-MLP outperformed the ARIMA-RNN in the case of Pakistan and India, while in the context of Sri Lanka, ARIMA-RNN beat the ARIMA-MLP in forecasting. Our findings reveal that the hybrid models can be regarded as a suitable option for financial time-series forecasting. (shrink)

The purpose of this study was to apply deep learning to music perception education. Music perception therapy for autistic children using gesture interactive robots based on the concept of educational psychology and deep learning technology is proposed. First, the experimental problems are defined and explained based on the relevant theories of pedagogy. Next, gesture interactive robots and music perception education classrooms are studied based on recurrent neural networks. Then, autistic children are treated by music perception, and an electroencephalogram (...) is used to collect the music perception effect and disease diagnosis results of children. Due to significant advantages of signal feature extraction and classification, RNN is used to analyze the EEG of autistic children receiving different music perception treatments to improve classification accuracy. The experimental results are as follows. The analysis of EEG signals proves that different people have different perceptions of music, but this difference fluctuates in a certain range. The classification accuracy of the designed model is about 72–94%, and the average classification accuracy is about 85%. The average accuracy of the model for EEG classification of autistic children is 85%, and that of healthy children is 84%. The test results with similar models also prove the excellent performance of the design model. This exploration provides a reference for applying the artificial intelligence technology in music perception education to diagnose and treat autistic children. (shrink)

Forecasting blood glucose values for patients can help prevent hypoglycemia and hyperglycemia events in advance. To this end, this study proposes an intelligent ensemble deep learning system to predict BG values in 15, 30, and 60 min prediction horizons based on historical BG values collected via continuous glucose monitoring devices as an endogenous factor and carbohydrate intake and insulin administration information as exogenous factors. Although there are numerous deep learning algorithms available, this study applied five algorithms, namely, recurrent (...) class='Hi'>neural network, which is optimized for sequence data, and RNN-based algorithms, stacked LSTM, bidirectional LSTM, and gated recurrent unit). Then, a genetic algorithm was applied to the five prediction models to optimize their weights through ensemble techniques and to yield the final predicted BG values. The performance of the proposed model was compared to that of the autoregressive integrated moving average model as a baseline. The results show that the proposed model significantly outperforms the baseline in terms of the root mean square error and continuous glucose error grid analysis. For the valid 29 diabetic patients for the multivariate models, the RMSE was 11.08, 19.25, and 31.30 mg/DL for 15, 30, and 60 min PH, respectively. When the same data were applied to univariate models, the RMSE was 11.28, 19.99, and 33.13 mg/DL for 15, 30, and 60 min PH, respectively. Both the univariate and multivariate models showed a statistically significant difference compared with the baseline at a 5% statistical significance level. Instead of using a model with a single algorithm, applying a GA based on each output of a model with multiple algorithms was found to play a significant role in improving model performance. (shrink)