An End-to-End Model Based on Multiple Neural Networks with Data Augmentation for Keyword Spotting

2020 ◽  
pp. 2050006
Author(s):  
Shuzhou Chai ◽  
Wei-Qiang Zhang ◽  
Changsheng Lv ◽  
Zhenye Yang
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Attention Mechanism ◽  
Keyword Spotting ◽  
Data Set ◽  
Positive Rate ◽  
Memory Network ◽  
Hidden Layer ◽  
High Level

In this paper, we propose a network for small footprint keyword spotting. It includes four parts, data augmentation, Time-Delay Neural Network (TDNN) and Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and attention mechanism. Data augmentation is Google SpecAugment with time warping and frequency mask and time mask to the spectrum on clean data set and noisy data set. TDNN and CNN model the spectrogram features from the time and space dimensions. RNN-type networks include RNN, Long Short-Term Memory network (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory network (BiLSTM), and Bidirectional Gated Recurrent Unit (BiGRU). The RNN extracts hidden layer features and transforms them into high-level representations. The attention mechanism is selected to generate different weights and multiplied by the high-level representation generated by the RNN to obtain a fixed-length vector. Finally, we use a linear transformation and softmax function to generate scores. We also explored the size of attention mechanism, two attention mechanisms, rectified linear unit and hidden layer of RNN. Our model has achieved a true positive rate of 99.81% at a 5% false positive rate.

scholarly journals Daily runoff forecasting based on data-augmented neural network model

2020 ◽  
Vol 22 (4) ◽  
pp. 900-915 ◽  
Author(s):  
Xiao-ying Bi ◽  
Bo Li ◽  
Wen-long Lu ◽  
Xin-zhi Zhou
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Interpolation Method ◽  
Linear Interpolation ◽  
Attention Mechanism ◽  
Ar Model ◽  
Support Vector ◽  
Runoff Forecasting ◽  
Comparison Results

Abstract Accurate daily runoff prediction plays an important role in the management and utilization of water resources. In order to improve the accuracy of prediction, this paper proposes a deep neural network (CAGANet) composed of a convolutional layer, an attention mechanism, a gated recurrent unit (GRU) neural network, and an autoregressive (AR) model. Given that the daily runoff sequence is abrupt and unstable, it is difficult for a single model and combined model to obtain high-precision daily runoff predictions directly. Therefore, this paper uses a linear interpolation method to enhance the stability of hydrological data and apply the augmented data to the CAGANet model, the support vector machine (SVM) model, the long short-term memory (LSTM) neural network and the attention-mechanism-based LSTM model (AM-LSTM). The comparison results show that among the four models based on data augmentation, the CAGANet model proposed in this paper has the best prediction accuracy. Its Nash–Sutcliffe efficiency can reach 0.993. Therefore, the CAGANet model based on data augmentation is a feasible daily runoff forecasting scheme.

scholarly journals Generating Scenery Images with Larger Variety According to User Descriptions

2021 ◽  
Vol 11 (21) ◽  
pp. 10224
Author(s):  
Hsu-Yung Cheng ◽  
Chih-Chang Yu
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Memory Cell ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Hidden Layer

In this paper, a framework based on generative adversarial networks is proposed to perform nature-scenery generation according to descriptions from the users. The desired place, time and seasons of the generated scenes can be specified with the help of text-to-image generation techniques. The framework improves and modifies the architecture of a generative adversarial network with attention models by adding the imagination models. The proposed attentional and imaginative generative network uses the hidden layer information to initialize the memory cell of the recurrent neural network to produce the desired photos. A data set containing different categories of scenery images is established to train the proposed system. The experiments validate that the proposed method is able to increase the quality and diversity of the generated images compared to the existing method. A possible application of road image generation for data augmentation is also demonstrated in the experimental results.

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

scholarly journals Automatic Labeled Dialogue Generation for Nursing Record Systems

2020 ◽  
Vol 10 (3) ◽  
pp. 62
Author(s):  
Tittaya Mairittha ◽  
Nattaya Mairittha ◽  
Sozo Inoue
Keyword(s):  
Data Augmentation ◽  
Short Term Memory ◽  
Generative Models ◽  
Abstract Knowledge ◽  
Augmentation Techniques ◽  
Nursing Record ◽  
Long Short Term Memory ◽  
The Individual ◽  
High Level ◽  
Embedding Methods

The integration of digital voice assistants in nursing residences is becoming increasingly important to facilitate nursing productivity with documentation. A key idea behind this system is training natural language understanding (NLU) modules that enable the machine to classify the purpose of the user utterance (intent) and extract pieces of valuable information present in the utterance (entity). One of the main obstacles when creating robust NLU is the lack of sufficient labeled data, which generally relies on human labeling. This process is cost-intensive and time-consuming, particularly in the high-level nursing care domain, which requires abstract knowledge. In this paper, we propose an automatic dialogue labeling framework of NLU tasks, specifically for nursing record systems. First, we apply data augmentation techniques to create a collection of variant sample utterances. The individual evaluation result strongly shows a stratification rate, with regard to both fluency and accuracy in utterances. We also investigate the possibility of applying deep generative models for our augmented dataset. The preliminary character-based model based on long short-term memory (LSTM) obtains an accuracy of 90% and generates various reasonable texts with BLEU scores of 0.76. Secondly, we introduce an idea for intent and entity labeling by using feature embeddings and semantic similarity-based clustering. We also empirically evaluate different embedding methods for learning good representations that are most suitable to use with our data and clustering tasks. Experimental results show that fastText embeddings produce strong performances both for intent labeling and on entity labeling, which achieves an accuracy level of 0.79 and 0.78 f1-scores and 0.67 and 0.61 silhouette scores, respectively.

scholarly journals An efficient technique for CT scan images classification of COVID-19

2020 ◽  
pp. 1-14
Author(s):  
Esraa Hassan ◽  
Noha A. Hikal ◽  
Samir Elmuogy
Keyword(s):  
Neural Network ◽  
Diagnostic Tool ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Performance Metrics ◽  
Classification Model ◽  
Data Set ◽  
Training Models ◽  
The Earth ◽  
Diagnostic Time

Nowadays, Coronavirus (COVID-19) considered one of the most critical pandemics in the earth. This is due its ability to spread rapidly between humans as well as animals. COVID_19 expected to outbreak around the world, around 70 % of the earth population might infected with COVID-19 in the incoming years. Therefore, an accurate and efficient diagnostic tool is highly required, which the main objective of our study. Manual classification was mainly used to detect different diseases, but it took too much time in addition to the probability of human errors. Automatic image classification reduces doctors diagnostic time, which could save human’s life. We propose an automatic classification architecture based on deep neural network called Worried Deep Neural Network (WDNN) model with transfer learning. Comparative analysis reveals that the proposed WDNN model outperforms by using three pre-training models: InceptionV3, ResNet50, and VGG19 in terms of various performance metrics. Due to the shortage of COVID-19 data set, data augmentation was used to increase the number of images in the positive class, then normalization used to make all images have the same size. Experimentation is done on COVID-19 dataset collected from different cases with total 2623 where (1573 training,524 validation,524 test). Our proposed model achieved 99,046, 98,684, 99,119, 98,90 In terms of Accuracy, precision, Recall, F-score, respectively. The results are compared with both the traditional machine learning methods and those using Convolutional Neural Networks (CNNs). The results demonstrate the ability of our classification model to use as an alternative of the current diagnostic tool.

scholarly journals Pemanfaatan Asynchronous Advantage Actor-Critic Dalam Pembuatan AI Game Bot Pada Game Arcade

2019 ◽  
Vol 1 (2) ◽  
pp. 74-84
Author(s):  
Evan Kusuma Susanto ◽  
Yosi Kristian
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Reinforcement Learning ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Trial And Error ◽  
Short Term ◽  
Term Memory ◽  
Memory Network ◽  
Long Short Term Memory

Asynchronous Advantage Actor-Critic (A3C) adalah sebuah algoritma deep reinforcement learning yang dikembangkan oleh Google DeepMind. Algoritma ini dapat digunakan untuk menciptakan sebuah arsitektur artificial intelligence yang dapat menguasai berbagai jenis game yang berbeda melalui trial and error dengan mempelajari tempilan layar game dan skor yang diperoleh dari hasil tindakannya tanpa campur tangan manusia. Sebuah network A3C terdiri dari Convolutional Neural Network (CNN) di bagian depan, Long Short-Term Memory Network (LSTM) di tengah, dan sebuah Actor-Critic network di bagian belakang. CNN berguna sebagai perangkum dari citra output layar dengan mengekstrak fitur-fitur yang penting yang terdapat pada layar. LSTM berguna sebagai pengingat keadaan game sebelumnya. Actor-Critic Network berguna untuk menentukan tindakan terbaik untuk dilakukan ketika dihadapkan dengan suatu kondisi tertentu. Dari hasil percobaan yang dilakukan, metode ini cukup efektif dan dapat mengalahkan pemain pemula dalam memainkan 5 game yang digunakan sebagai bahan uji coba.

scholarly journals A hybrid of convolutional neural network and long short-term memory network approach to predictive maintenance

2022 ◽  
Vol 12 (1) ◽  
pp. 721
Author(s):  
Ahmed Nasser ◽  
Huthaifa AL-Khazraji
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Predictive Maintenance ◽  
Fault Prediction ◽  
Gradient Boosting ◽  
Short Term ◽  
Term Memory ◽  
Memory Network ◽  
Long Short Term Memory

<p>Predictive maintenance (PdM) is a successful strategy used to reduce cost by minimizing the breakdown stoppages and production loss. The massive amount of data that results from the integration between the physical and digital systems of the production process makes it possible for deep learning (DL) algorithms to be applied and utilized for fault prediction and diagnosis. This paper presents a hybrid convolutional neural network based and long short-term memory network (CNN-LSTM) approach to a predictive maintenance problem. The proposed CNN-LSTM approach enhances the predictive accuracy and also reduces the complexity of the model. To evaluate the proposed model, two comparisons with regular LSTM and gradient boosting decision tree (GBDT) methods using a freely available dataset have been made. The PdM model based on CNN-LSTM method demonstrates better prediction accuracy compared to the regular LSTM, where the average F-Score increases form 93.34% in the case of regular LSTM to 97.48% for the proposed CNN-LSTM. Compared to the related works the proposed hybrid CNN-LSTM PdM approach achieved better results in term of accuracy.</p>

scholarly journals Robot Communication: Network Traffic Classification Based on Deep Neural Network

2021 ◽  
Vol 15 ◽  
Author(s):  
Mengmeng Ge ◽  
Xiangzhan Yu ◽  
Likun Liu
Keyword(s):  
Neural Network ◽  
Network Traffic ◽  
Short Term Memory ◽  
Traffic Classification ◽  
Classification Framework ◽  
Network Traffic Classification ◽  
Scalar Input ◽  
Memory Network ◽  
Encrypted Traffic ◽  
Robot Communication

With the rapid popularization of robots, the risks brought by robot communication have also attracted the attention of researchers. Because current traffic classification methods based on plaintext cannot classify encrypted traffic, other methods based on statistical analysis require manual extraction of features. This paper proposes (i) a traffic classification framework based on a capsule neural network. This method has a multilayer neural network that can automatically learn the characteristics of the data stream. It uses capsule vectors instead of a single scalar input to effectively classify encrypted network traffic. (ii) For different network structures, a classification network structure combining convolution neural network and long short-term memory network is proposed. This structure has the characteristics of learning network traffic time and space characteristics. Experimental results show that the network model can classify encrypted traffic and does not require manual feature extraction. And on the basis of the previous tool, the recognition accuracy rate has increased by 8%

Predicting Outcomes of Business Process Executions Based on LSTM Neural Networks and Attention Mechanism

2021 ◽  
Author(s):  
Jiaojiao Wang ◽  
Dongjin Yu ◽  
Chengfei Liu ◽  
Xiaoxiao Sun
Keyword(s):  
Short Term Memory ◽  
Attention Mechanism ◽  
Sequential Data ◽  
Time Prediction ◽  
Prediction Time ◽  
Highly Sensitive ◽  
Long Short Term Memory ◽  
Early Decision ◽  
Lstm Network ◽  
Hidden Layer

Abstract To effectively predict the outcome of an on-going process instance helps make an early decision, which plays an important role in so-called predictive process monitoring. Existing methods in this field are tailor-made for some empirical operations such as the prefix extraction, clustering, and encoding, leading that their relative accuracy is highly sensitive to the dataset. Moreover, they have limitations in real-time prediction applications due to the lengthy prediction time. Since Long Short-term Memory (LSTM) neural network provides a high precision in the prediction of sequential data in several areas, this paper investigates LSTM and its enhancements and proposes three different approaches to build more effective and efficient models for outcome prediction. The first move on enhancement is that we combine the original LSTM network from two directions, forward and backward, to capture more features from the completed cases. The second move on enhancement is that we add attention mechanism after extracting features in the hidden layer of LSTM network to distinct them from their attention weight. A series of extensive experiments are evaluated on twelve real datasets when comparing with other approaches. The results show that our approaches outperform the state-of-the-art ones in terms of prediction effectiveness and time performance.

Sign in / Sign up

Export Citation Format

Share Document