Machine Translation (MT) has come a long way in recent years, but it still suffers from data scarcity issue due to lack of parallel corpora for low (or sometimes zero) resource languages. However, Transfer Learning (TL) is one of the directions widely used for low-resource machine translation systems to overcome this issue. Creating parallel corpus for such languages is another way of dealing with data scarcity, yet costly, time-consuming and laborious task. In order to avoid the above listed limitations of parallel corpus formation, we present a TL-based Semi-supervised Pseudo-corpus Generation (TLSPG) approach for zero-shot MT systems. It generates the pseudo corpus by exploiting the relatedness between low resource language pairs and zero-resource language pairs via TL approach. It is further empirically ascertained in our experiments that such relatedness helps improve the performance of zero-shot MT systems. Experiments on zero-resource language pairs show that our approach effectively outperforms the existing state-of-the-art models, yielding improvement of +15.56,+8.13,+3.98 and +2 BLEU points for Bhojpuri→Hindi, Magahi→Hindi, Hindi→Bhojpuri and Hindi→Magahi, respectively.
The healthcare industry has transitioned from traditional healthcare 1.0 to AI-powered healthcare 4.0. However, overall cost for patient treatment remains high and challenging to manage due to the absence of a centralized cost evaluation mechanism before hospital visits. Therefore, in this paper, we devise a cloud-based mechanism to calculate hospitals’ star rating based on questionnaire with the application of Z-score and K* clustering algorithm. To evaluate disease severity at cloud, splitfed technique is utilized in coordination with Wireless Body Area Network (WBAN). Finally, the cloud calculates provisional treatment costs and finds a preferable hospital with a low payable treatment cost and satisfactorily high rating for the patient via utility maximization in a cloud-based environment. Moreover, the effectiveness of the proposed polynomial algorithmic model is shown theoretically, experimentally, and comparing with other state-of-the-art methods on real-world data.
Growing remote health monitoring system allows constant monitoring of the patient's condition and performance of preventive and control check-ups outside medical facilities. However, the real-time smart-healthcare application poses a delay constraint that has to be solved efficiently. Fog computing is emerging as an efficient solution for such real-time applications. Moreover, different medical centers are getting attracted to the growing IoT-based remote healthcare system in order to make a profit by hiring Fog computing resources. However, there is a need for an efficient algorithmic model for allocation of limited fog computing resources in the criticality-aware smart-healthcare system considering the profit of medical centers. Thus, the objective of this work is to maximize the system utility calculated as a linear combination of the profit of the medical center and the loss of patients. To measure profit, we propose a flat-pricing-based model. Further, we propose a swapping-based heuristic to maximize the system utility. The proposed heuristic is tested on various parameters and shown to perform close to the optimal with criticality-awareness in its core. Through extensive simulations, we show that the proposed heuristic achieves an average utility of $96\%$ of the optimal, in polynomial time complexity.
One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) can produce good results with such large amounts of data. However, it is challenging to improve the quality of MT output for low resource languages, especially in NMT and SMT. In order to tackle the challenges faced by MT, we present a novel approach of using a scaled similarity score of sentences, especially for related languages based on a 5-gram KenLM language model with Kneser-ney smoothing technique for filtering in-domain data from out-of-domain corpora that boost the translation quality of MT. Furthermore, we employ other domain adaptation techniques such as multi-domain, fine-tuning and iterative back-translation approach to compare our novel approach on the Hindi-Nepali language pair for NMT and SMT. Our approach succeeds in increasing ~2 BLEU point on multi-domain approach, ~3 BLEU point on fine-tuning for NMT and ~2 BLEU point on iterative back-translation approach.
OBJECTIVETo determine the maternal and fetal risk factors for perinatal asphyxia and to know the mortality in the asphyxiated babies. METHODSAll the consecutive hospital live births were evaluated during the study period of one year.Out of this birth cohort, asphyxiated babies were grouped into cases and non-asphyxiated group as controls.Maternal, intrapartum and neonatal variables were recorded in all births.Data was analysed and various statistical tests of significance applied to find the risk of association of various factors to birth asphyxia. RESULTSAmongst 4714 live births, there were 171 cases of birth asphyxia, providing the incidence of 36 per 1000 live births.Risk factors significantly associated and having most strong association with perinatal asphyxia was observed in Eclampsia (OR 25.5) followed in decreasing frequency by Prematurity (OR 21.3), Meconium staining of amniotic fluid (OR 9.21), Antepartum hemorrhage (OR 8), Gestational diabetes mellitus (OR 4), Breech presentation (OR 3.8), Oligohydramnios (OR 2.8), PROM (OR 2.6), PIH (OR 2.1).Asphyxia related mortality was 10.6 per 1000 live births. CONCLUSIONSThere is a need to strengthen intrapartum management and early identification of mothers with high risk pregnancy to reduce asphyxia mortality and morbidity.
The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the morphologies of the two languages and also the morphosyntax transfer. Even so, their performance for translation in Indian language to Indian language scenario is still not as good as for resource-rich languages. One reason for this is the relative morphological richness of Indian languages, while another is that most of them fall into the extremely low resource or zero-shot categories. Since most major Indian languages use Indic or Brahmi origin scripts, the text written in them is highly phonetic in nature and phonetically similar in terms of abstract letters and their arrangements. We use these characteristics of Indian languages and their scripts to propose an approach based on common multilingual Latin-based encodings (WX notation) that take advantage of language similarity while addressing the morphological complexity issue in NMT. These multilingual Latin-based encodings in NMT, together with Byte Pair Embedding (BPE) allow us to better exploit their phonetic and orthographic as well as lexical similarities to improve the translation quality by projecting different but similar languages on the same orthographic-phonetic character space. We verify the proposed approach by demonstrating experiments on similar language pairs (Gujarati-Hindi, Marathi-Hindi, Nepali-Hindi, Maithili-Hindi, Punjabi-Hindi, and Urdu-Hindi) under low resource conditions. The proposed approach shows an improvement in a majority of cases, in one case as much as ~10 BLEU points compared to baseline techniques for similar language pairs. We also get up to ~1 BLEU points improvement on distant and zero-shot language pairs.
In this article, we first formulate the joint resource allocation, interference minimization, user-level, and cell-level fairness for maximum resource reuse in 5G heterogeneous small cell networks as an NP-hard problem. We then propose three algorithms - centralized, distributed, and randomized distributed algorithms - to efficiently solve the formulated resource allocation problem while minimizing interference, maximizing fairness, and resource reuse. Through extensive real data analysis and network simulations, we show that our proposed solutions outperform state-of-the-art schemes, namely interfering model (INT) and distributed random access (DRA), for both low and high-density 5G networks.
'%3e%3ccircle r='20' fill='%23008'/%3e%3ccircle r='17.5' fill='%23fff'/%3e%3ccircle r='3.5' fill='%23008'/%3e%3cg id='d'%3e%3cg id='c'%3e%3cg id='b'%3e%3cg id='a' fill='%23008'%3e%3ccircle r='.875' transform='rotate(7.5 -8.75 133.5)'/%3e%3cpath d='M0 17.5.6 7 0 2l-.6 5L0 17.5z'/%3e%3c/g%3e%3cuse xlink:href='%23a' transform='rotate(15)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='rotate(30)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='rotate(60)'/%3e%3c/g%3e%3cuse xlink:href='%23d' transform='rotate(120)'/%3e%3cuse xlink:href='%23d' transform='rotate(-120)'/%3e%3c/g%3e%3c/svg%3e)