Explore the vast range of titles available.

Rainfall–runoff modeling is a complex hydrological issue that still has room for improvement. This study developed a coupled bidirectional long short‐term memory (LSTM) with sequence‐to‐sequence (Seq2Seq) learning (BiLSTM‐Seq2seq) model to simulate multi‐step‐ahead runoff for flood events. The bidirectional LSTM with Seq2Seq learning (LSTM‐Seq2Seq) and multilayer perceptron (MLP) was set as benchmarks. The results show that: (1) root mean absolute error is reduced by approximately 19% up to 27%, and the Nash–Sutcliffe coefficient of efficiency is improved by 14% up to 34% for 6‐h‐ahead runoff prediction for BiLSTM‐Seq2Seq compared LSTM‐Seq2Seq and MLP; (2) The BiLSTM‐Seq2Seq model has good performance not only for one‐peak flood events but also for multi‐peak flood events; and (3) BiLSTM‐Seq2Seq can mitigate the time‐delay problem and time lag is shortened by 39% up to 69% in comparison to LSTM‐Seq2Seq and MLP. These results suggest that the time‐delay problem can be mitigated by BiLSTM‐Seq2Seq, which has excellent potential in time series predictions in the hydrological field.

Chatbot for education has great potential to complement human educators and education administrators. For example, it can be around the clock tutor to answer and clarify any questions from students who may have missed class. A chatbot can be implemented either by ruled based or artificial intel-ligence based. However, unlike the ruled-based chatbots, artificial intelli-gence based chatbots can learn and become smarter overtime and is more scalable and has become the popular choice for chatbot researchers recently. Recurrent Neural Network based Sequence-to-sequence (Seq2Seq) model is one of the most commonly researched model to implement artificial intelli-gence chatbot and has shown great progress since its introduction in 2014. However, it is still in infancy and has not been applied widely in educational chatbot development. Introduced originally for neural machine translation, the Seq2Seq model has been adapted for conversation modelling including question-answering chatbots. However, in-depth research and analysis of op-timal settings of the various components of Seq2Seq model for natural an-swer generation problem is very limited. Additionally, there has been no ex-periments and analysis conducted to understand how Seq2Seq model handles variations is questions posed to it to generate correct answers. Our experi-ments add to the empirical evaluations on Seq2Seq literature and provides insights to these questions. Additionally, we provide insights on how a cu-rated dataset can be developed and questions designed to train and test the performance of a Seq2Seq based question-answer model.

Braille, the most popular tactile-based writing system, uses patterns of raised dots arranged in cells to inscribe characters for visually impaired persons. Amharic is Ethiopia’s official working language, spoken by more than 100 million people. To bridge the written communication gap between persons with and without eyesight, multiple Optical braille recognition systems for various language scripts have been developed utilizing both statistical and deep learning approaches. However, the need for half-character identification and character segmentation has complicated these systems, particularly in the Amharic script, where each character is represented by two braille cells. To address these challenges, this study proposed deep learning model that combines a CNN and a BiLSTM network with CTC. The model was trained with 1,800 line images with 32 × 256 and 48 × 256 dimensions, and validated with 200 line images and evaluated using Character Error Rate. The best-trained model had a CER of 7.81% on test data with a 48 × 256 image dimension. These findings demonstrate that the proposed sequence-to-sequence learning method is a viable Optical Braille Recognition (OBR) solution that does not necessitate extensive image pre and post processing. Inaddition, we have made the first Amharic braille line-image data set available for free to researchers via the link: https://github.com/Ne-UoG-git/Am-Br-line-image.github.io .

In this paper, we propose a novel writer-independent global feature extraction framework for the task of automatic signature verification which aims to make robust systems for automatically distinguishing negative and positive samples. Our method consists of an autoencoder for modeling the sample space into a fixed-length latent space and a siamese network for classifying the fixed-length samples obtained from the autoencoder based on the reference samples of a subject as being genuine or forged. During our experiments, usage of attention mechanism and applying downsampling significantly improved the accuracy of the proposed framework. We evaluated our proposed framework using SigWiComp2013 Japanese and GPDSsyntheticOnLineOffLineSignature datasets. On the SigWiComp2013 Japanese dataset, we achieved 8.65% equal error rate (EER) that means 1.2% relative improvement compared to the best-reported result. Furthermore, on the GPDSsyntheticOnLineOffLineSignature dataset, we achieved average EERs of 0.13%, 0.12%, 0.21% and 0.25%, respectively, for 150, 300, 1000 and 2000 test subjects which indicate improvement in relative EER on the best-reported result by 95.67%, 95.26%, 92.9% and 91.52%, respectively. Apart from the accuracy gain, because of the nature of our proposed framework which is based on neural networks and consequently is as simple as some consecutive matrix multiplications, it has less computational cost than conventional methods such as Dynamic Time Warping and could be used concurrently on devices such as Graphics Processing Unit and Tensor Processing Unit.

One of the most crucial problem on training personalized response generation models for conversational robots is the lack of large scale personal conversation data. To address the problem, we propose a two-phase approach, namely initialization then adaptation, to first pre-train an optimized RNN encoder-decoder model (LTS model) in a large scale conversational data for general response generation and then fine-tune the model in a small scale personal conversation data to generate personalized responses. For evaluation, we propose a novel human aided method, which can be seen as a quasi-Turing test, to evaluate the performance of the personalized response generation models. Experimental results show that the proposed personalized response generation model outperforms the state-of-the-art approaches to language model personalization and persona-based neural conversation generation on the automatic evaluation, offline human judgment and the quasi-Turing test.

This paper presents a deep learning-based machine translation (MT) system that translates a sentence of subject-object-verb (SOV) structured language into subject-verb-object (SVO) structured language. This system uses recurrent neural networks (RNNs) and Encodings. Encode embedded RNNs generate a set of numbers from the input sentence, where the second RNNs generate the output from these sets of numbers. Three popular datasets of SOV structured language i.e., EMILLE corpus, Prothom-Alo corpus and Punjabi Monolingual Text Corpus ILCI-II are used as two different case-study to validate. In our experimental case-study 1, for the EMILLE corpus and Prothom-Alo corpus dataset, we have achieved 0.742, 4.11 and 0.18, respectively as Bilingual Evaluation Understudy (BLEU), NIST (metric) and tertiary entrance rank scores. Another case-study for Punjabi Monolingual Text Corpus ILCI-II dataset achieved a BLEU score of 0.75. Our results can be compared with the state-of-the-art results.

Crafting the right keywords and crafting their ad creatives is an arduous task that requires the collaboration of online marketers, creative directors, data scientists, and possibly linguists. Many parts of this craft are still manual and therefore not scalable especially for large e-commerce companies that have big inventories and big search campaigns. Furthermore, the craft is inherently experimental, which means that the marketing team has to experiment with different marketing messages from subtle to strong, with different keywords from broadly relevant (to the product) to exactly/specifically relevant, with different landing pages from informative to transactional, and many other test variants. The failure to experiment quickly for finding what works results in users being dissatisfied and marketing budget being wasted. For rapid experimentation, we set out to generate ad creatives automatically. The process of generating an ad creative from a given landing page is considered as a text summarization problem and we adopted the abstractive text summarization approach. We reported the results of our empirical evaluation on generative adversarial networks and reinforcement learning methods.

Scene text recognition (STR) technology has a rapid development with the rise of deep learning. Recently, the encoder-decoder framework based on attention mechanism is widely used in STR for better recognition. However, the commonly used Long Short Term Memory (LSTM) network in the framework tends to ignore certain position or visual information. To address this problem, we propose a Position Information Enhanced Encoder-Decoder (PIEED) framework for scene text recognition, in which an addition position information enhancement (PIE) module is proposed to compensate the shortage of the LSTM network. Our module tends to retain more position information in the feature sequence, as well as the context information extracted by the LSTM network, which is helpful to improve the recognition accuracy of the text without context. Besides that, our fusion decoder can make full use of the output of the proposed module and the LSTM network, so as to independently learn and preserve useful features, which is helpful to improve the recognition accuracy while not increase the number of arguments. Our overall framework can be trained end-to-end only using images and ground truth. Extensive experiments on several benchmark datasets demonstrate that our proposed framework surpass state-of-the-art ones on both regular and irregular text recognition.

This paper proposed an ensemble methodology comprising neural networks, modified differential evolution algorithm and nonlinear autoregressive network with exogenous inputs (NARX) (called neuro-evolutionary NARX or NE-NARX model) for time series forecasting. In NE-NARX, the structure is designed by connecting the neural model and NARX model, and the weight value connection is optimized by a modified differential evolution algorithm. The effectiveness of the proposed NE-NARX model is tested on two well-known benchmark datasets, including the Canadian lynx and the Wolf sunspot. The proposed model is compared to other models, including the classical backpropagation algorithm, particle swarm optimization, differential evolution (DE) and DE variants. Additionally, an ARIMA model is employed as the benchmark for evaluating the capacity of the proposed model. And then, NE-NARX model is used for hourly energy consumption prediction through comparison with other machine learning models including gated recurrent units, convolutional neural networks (CNN), long short-term memory (LSTM), a hybrid CNN-LSTM and sequence-to-sequence learning. Results show convincingly the superiority of the proposed NE-NARX model over other models.

The analysis of continuous events for any application involves the discretization of an event into sequences with potential historical dependencies. These sequences represent time stamps or samplings of a continuous process collectively forming a time series dataset utilized for training recurrent neural networks (RNNs) such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) for pattern prediction. The challenge is to ensure that the estimates from the trained models are consistent in the same input domain for different discretizations of the same or similar continuous history-dependent events. In other words, if different time stamps are used during the prediction phase after training, the model is still expected to give consistent predictions based on the knowledge it has learned. To address this, we present a novel RNN transition formula intended to produce consistent estimates in a wide range of engineering applications. The approach was validated with synthetically generated datasets in 1D, 2D, and 3D spaces, intentionally designed to exhibit high non-linearity and complexity. Furthermore, we have verified our results with real-world datasets to ensure practical applicability and robustness. These assessments show the ability of the proposed method, which involves restructuring the mathematical structure and extending conventional RNN architectures, to provide reliable and consistent estimates for complex time series data.