The method of translation from one language to another without human intervention is known as Machine Translation (MT). Multilingual neural machine translation (MNMT) is a technique for MT that builds a single model for multiple languages. It is preferred over other approaches, since it decreases training time and improves translation in low-resource contexts, i.e., for languages that have insufficient corpus. However, good-quality MT models are yet to be built for many scenarios such as for Indic-to-Indic Languages (IL-IL). Hence, this article is an attempt to address and develop the baseline models for low-resource languages i.e., IL-IL (for 11 Indic Languages (ILs)) in a multilingual environment. The models are built on the Samanantar corpus and analyzed on the Flores-200 corpus. All the models are evaluated using standard evaluation metrics i.e., Bilingual Evaluation Understudy (BLEU) score (with the range of 0 to 100). This article examines the effect of the grouping of related languages, namely, East Indo-Aryan (EI), Dravidian (DR), and West Indo-Aryan (WI) on the MNMT model. From the experiments, the results reveal that related language grouping is beneficial for the WI group only while it is detrimental for the EI group and it shows an inconclusive effect on the DR group. The role of pivot-based MNMT models in enhancing translation quality is also investigated in this article. Owing to the presence of large good-quality corpora from English (EN) to ILs, MNMT IL-IL models using EN as a pivot are built and examined. To achieve this, English-Indic Language (EN-IL) models are developed with and without the usage of related languages. Results show that the use of related language grouping is advantageous specifically for EN to ILs. Thus, related language groups are used for the development of pivot MNMT models. It is also observed that the usage of pivot models greatly improves MNMT baselines. Furthermore, the effect of transliteration on ILs is also analyzed in this article. To explore transliteration, the best MNMT models from the previous approaches (in most of cases pivot model using related groups) are determined and built on corpus transliterated from the corresponding scripts to a modified Indian language Transliteration script (ITRANS). The outcome of the experiments indicates that transliteration helps the models built for lexically rich languages, with the best increment of BLEU scores observed in Malayalam (ML) and Tamil (TA), i.e., 6.74 and 4.72, respectively. The BLEU score using transliteration models ranges from 7.03 to 24.29. The best model obtained is the Punjabi (PA)-Hindi (HI) language pair trained on PA-WI transliterated corpus.

Flipped learning (FL) utilizes blended learning approaches, where students first learn the lesson from preloaded lecture videos (i.e., online lectures). They complete their activities such as assignments, doubt clearing, practical work, real-life problemsolving inside classroom. Learning is directly connected to brain activities, and it becomes crucial to analyze the brain signals to identify the attention level of the learner. In order to analyze students' activity during the lesson, we capture the brain signals of the students and propose a framework for the feature extraction of brain wave (Electroencephalogram (EEG)) signals using variational autoencoder (VAE) in this article. The classification techniques are exploited to identify the weak students in the flipped learning scenario based on their cognitive state; subsequently, cognitive-aware lecture video recommendation system is developed to recommend the non-attentive lecture video/videos to the weak students. This study can be useful for instructors to identify learners who require special care to enhance their learning ability.

The Machine Translation System (MTS) serves as effective tool for communication by translating text or speech from one language to another language. Recently, neural machine translation (NMT) has become popular for its performance and cost-effectiveness. However, NMT systems are restricted in translating low-resource languages as a huge quantity of data is required to learn useful mappings across languages. The need for an efficient translation system becomes obvious in a large multilingual environment like India. Indian languages (ILs) are still treated as low-resource languages due to unavailability of corpora. In order to address such an asymmetric nature, the multilingual neural machine translation (MNMT) system evolves as an ideal approach in this direction. The MNMT converts many languages using a single model, which is extremely useful in terms of training process and lowering online maintenance costs. It is also helpful for improving low-resource translation. In this article, we propose an MNMT system to address the issues related to low-resource language translation. Our model comprises two MNMT systems, i.e., for English-Indic (one-to-many) and for Indic-English (many-to-one) with a shared encoder-decoder containing 15 language pairs (30 translation directions). Since most of IL pairs have a scanty amount of parallel corpora, not sufficient for training any machine translation model, we explore various augmentation strategies to improve overall translation quality through the proposed model. A state-of-the-art transformer architecture is used to realize the proposed model. In addition, the article addresses the use of language relationships (in terms of dialect, script, etc.), particularly about the role of high-resource languages of the same family in boosting the performance of low-resource languages. Moreover, the experimental results also show the advantage of back-translation and domain adaptation for ILs to enhance the translation quality of both source and target languages. Using all these key approaches, our proposed model emerges to be more efficient than the baseline model in terms of evaluation metrics, i.e., BLEU (BiLingual Evaluation Understudy) score for a set of ILs.

Flipped Classroom is an innovative learning pedagogy based on students’ academic engagement inside and outside the classroom. Students take lessons from pre-loaded lecture videos through desktop, tablets and mobiles before coming to the classroom. Inside the classroom, the sole focus is on doubt clearing and problem solving. However, it is very difficult to ensure that students really pay attention while watching lecture videos. This is a concern, given the levels of distraction the students are exposed to in this age of internet. Electroencephalogram (EEG) signals can be captured from brain of students and used to monitor their attention.In this study, we develop an efficient approach of feature engineering to analyze the attention level of students in Flipped Classroom from captured brain wave signals. We process the EEG signals using Fast Fourier Transform (FFT). Subsequently, we apply our proposed novel handcrafted features method to obtain the features. Standard classification methods are employed to test the effectiveness of our designed features. Experimental results demonstrate that our proposed handcrafted features perform better than standard FFT-derived-frequency bands.

In traditional teacher-directed learning pedagogy (direct instruction), an instructor devotes a significant amount of time in delivering the instruction or lesson. As a result, class hours have not been used effectively for critical problem solving, collaborative activities, etc. Flipped learning is an innovative learning pedagogy in which students are allowed to take lesson from pre-recorded lecture videos outside class hours and be active and accountable for their development. Organization of pre-recorded lecture videos play an important role for effective learning. So, attentiveness of the students also depends on the arrangements and organization of the contents of lecture video. Research in this direction of educational technology is unexplored.In this paper, we propose a method to verify whether the organization of lecture videos is effective for the learner to learn the concept. In this proposed method, we suggest the instructors modify the learning materials (lecture video) based on the attention and feedback of the student. Dataset collected at National Institute of Technology Rourkela for the purpose of research in flipped learning is used. Results show the effectiveness of our proposed method.

Various learning pedagogies have been developed, and they are adapted in a large number of institutes in various forms for improving learning ability of individual students. Flipped Learning (FL) model is one popular approach adopted in many higher learning institutions across the globe. In the flipped learning model, students take lesson from pre-loaded lecture videos before they solve critical problems in live classroom unlike other learning modes such as MOOCs (Massive Open Online Courses), Distance Learning, etc. However, student may not remain attentive throughout the video duration before solving critical problems in the live classroom. This may lead to serious learning incompetence over time in this learning pedagogy. In this paper, we analyze cognitive states of an individual student using brain waves signals while taking instructions in the absence of an instructor. The brain waves (Electroencephalogram (EEG)) signal is analyzed using unsupervised learning (clusters) techniques to group similar behaviors exhibited by student over video duration. Based on this analysis, we propose a recommendation technique which detects non-attentive video and suggests for retaking the lesson. This is termed as L ecture Video R ecommendation in F lipped L earning (LRFL) . We validate our approach with the data collected at our laboratory for the research purpose on flipped learning. Results demonstrate the effectiveness of our recommender technique.

Flipped Classroom is a mode of learning which is developed based on students' academic engagement inside and outside the classroom. In this learning pedagogy, students take lessons from pre-loaded lecture videos before coming to the classroom for doubt clearing, discussion, problem solving, etc. However, it is very difficult to ensure that students really pay attention while watching lecture videos. In this paper, we adopt a feature selection technique called 1D local binary pattern (1D-LBP) to analyze captured brain signals of the students. The proposed feature selection technique is termed as 1D Multi-Point Local Ternary Pattern (MP-LTP), which extracts unique statistical features from EEG signals. Subsequently, standard classification techniques are exploited to analyze the attention level of students. Experimental results show that the proposed method outperforms state-of-the-art classification techniques using LBP.

Recommender system is a popular tool that aims to provide personalized suggestions to user about items, products, services, and so on. Recommender system has effectively been used in online social networks, especially the location-based social networks for providing suggestions for interesting places known as POIs (points-of-interest). Popular recommender systems explore historical data to learn users’ preferences and, subsequently, they recommend locations to an active user. This strategy faces a major problem when a new POI or business evolves in a city. New business has no historical user experience data. Thus, a recommender system fails to gather enough knowledge about the new businesses, resulting in ignoring them during recommendations. This scenario is popularly known as a cold-start POI problem. Users never get recommendations of the new businesses in a city even though they can be relevant to a user. Also, from a business owner’s perspective, such a recommendation strategy does not help its reachability among users. Therefore, it is important for a recommender system to remain updated with new businesses in a city and ensure that all relevant POIs are recommended to a user irrespective of their lifetime. A POI recommendation approach is proposed in this work that can effectively handle the new businesses, or the cold-start POI problem, in a city. We crowdsource descriptions of cold-start POIs from various online social networks. The reviews of users are exploited here to learn the inherent features at the existing POIs and the new crowdsourced POIs. Finally, the proposed approach recommends top- K POIs consisting of the existing and new POIs. We perform experiments on the real-world Yelp dataset, which is one of the largest available data resources containing details on a wide range of businesses, users, and reviews. The proposed approach is compared with four existing POI recommendation approaches. The obtained results show that our approach outperforms others in handling cold-start POIs.

Recommender System (RS) is an essential component of many businesses, especially in e-commerce domain. RS exploits the preference history (rating, purchase, review, etc.) of users in order to provide the recommendations. A user in traditional RS can provide only one rating value about an item. Deep Neural Networks have been used in this single rating system to improve recommendation accuracy in the recent times. However, the single rating systems are inadequate to understand the usersfi preferences about an item. On the other hand, business enterprises such as tourism, e-learning, etc. facilitate users to provide multiple criteria ratings about an item, thus it becomes easier to understand users' preference over single rating system. In this paper, we propose an extended Stacked Autoencoders (a Deep Neural Network technique) to utilize the multi-criteria ratings. The proposed network is designed to learn the relationship between each user's criteria and overall rating efficiently. Experimental results on real world datasets (Yahoo! Movies and TripAdvisor) demonstrate that the proposed approach outperforms state-of-the-art single rating systems and multi-criteria approaches on various performance metrics.