Neural Machine Translation (NMT) is one step ahead of traditional statistical phrase-based translation systems because of its better translation ability. But it requires a large amount of parallel training data, which can be challenging for languages with limited resources like many Indian languages. In the past, researchers have tried to address the issue using data augmentation. In this paper, we present a data augmentation technique for the Hindi language based on five phrases: noun phrases, verb phrases, prepositional phrases, adjective phrases, and adverb phrases. We augment the training corpus using parser-generated phrasal segments and evaluate the efficiency of the proposed work on the Hindi language. Further, the paper presents training in the NMT model at the character level instead of the word level. This approach can help overcome challenges associated with word-level translations, such as handling rare and out-of-vocabulary words and phrases, dealing with morphological complexity, and addressing languages with ambiguous word boundaries. The proposed work was evaluated on a low-resource language pair, Hindi-English, using the Google Transformer model as the baseline state-of-the-art. The experiments used two distinct datasets: WMT14 Hin-Eng and Samanantar Hin-Eng parallel corpus with character-level encoding for the translation task. The proposed model is able to surpass the cutting-edge baseline and saw an increase in BLEU scores for the WMT14 translation challenge with +2.52 on base paper using three phrase sentences with character-level encoding and +2.68 BLEU Score on base paper using five phrase sentences with character-level encoding. Further, character-level encoding is evaluated on non-augmented Samanantar dataset; it performs better in the baseline approach for translation purposes. It clearly shows that the proposed model outperforms in Hindi language translation.

ABSTRACT Complex websites comprise a variety of diverse web entities, which require constant restructuring resonating with the latest trends, shifting consumer expectations and market driven changes. Therefore, designing suitable models to optimally restructure such websites is of paramount importance and must take into consideration several factors about the web entities such as display size, download time, type, location in the page, sales likelihood, discounts, and the ongoing trend. A recent study has taken all these attributes into consideration and designed a model based on the Access Score, Interface Score, and Purchase Score. However, this model suffers from certain drawbacks such as it did not address the underlying cohesiveness between these attributes. Further, it provided a single optimal solution to the adaptive website structure optimization (AWSO) problem and relied on the a priori knowledge of weights. The basis of the new proposed model is that there can be more than one optimal solution to the AWSO problem in the real world. The novel tri‐objective optimization model uses NSGA‐II algorithm to simultaneously optimize the attributes and finds advantageous trade‐off solutions without requiring a priori knowledge of weights. The proposed MO‐AWSONSGA‐II model is shown to outperform the existing model proving it better suited for the AWSO problem.

Drivers undergo a lot of stress that might cause distraction and might lead to an unfortunate incident. Emotional recognition via facial expressions is one of the most important field in the human–machine interface. The goal of this paper is to analyze the drivers’ facial expressions in order to monitor their stress levels. In this paper, we propose FERNET — a hybrid deep convolutional neural network model for driver stress recognition through facial emotion recognition. FERNET is an integration of two DCNNs, pre-trained ResNet101V2 CNN and a custom CNN, ConvNet4. The experiments were carried out on the widely used public datasets CK[Formula: see text], FER2013 and AffectNet, achieving the accuracies of 99.70%, 74.86% and 70.46%, respectively, for facial emotion recognition. These results outperform the recent state-of-the-art methods. Furthermore, since a few specific isolated emotions lead to higher stress levels, we analyze the results for stress- and nonstress-related emotions for each individual dataset. FERNET achieves stress prediction accuracies of 98.17%, 90.16% and 84.49% for CK[Formula: see text], FER2013 and AffectNet datasets, respectively.

Abstract A development of the Mondex system was undertaken using Event-B and its associated proof tools. An incremental approach was used whereby the refinement between the abstract specification of the system and its detailed design was verified through a series of refinements. The consequence of this incremental approach was that we achieved a very high degree of automatic proof. The essential features of our development are outlined. We also present some modelling and proof guidelines that we found helped us gain a deep understanding of the system and achieve the high degree of automatic proof.