No abstract

Introduction In order to attain Sustainable Development Goal 2 (SDG-II) of eradicating malnutrition among children by 2030, Pakistan has initiated a Community-based Management of Severely Acute Malnutrition (CMAM) program. This program has been established at the public level to detect and treat uncomplicated Severely Acute Malnourished (SAM) children at an early stage. However, during the outbreak of COVID-19, very poor compliance with the CMAM program was observed. Consequently, the nutritional quality of children’s diets has deteriorated, with malnutrition rates expected to rise. Therefore, this study has been set up to evaluate the effect of the COVID-19 lockdown on the health of SAM children and compliance with the CMAM program. Methodology This study used a multicenter cross-sectional design in District Dera Ghazi Khan’s rural areas located in the Southern Province of Punjab. Data were collected from the parents/guardians of SAM children through the researcher-administrated questionnaire. The sample size was 196, and data were analyzed through SPSS version 25. Results The majority of the children enrolled were males (52.5%), had fathers aged between 41 and 50 years (52.0%), mothers aged between 21 and 30 years (52.5%), had illiterate fathers (40.1%), illiterate mothers (73.8%) and had a monthly household income of PKR <15,000 (91.1%). All of the respondents mentioned that COVID-19 affected them in one way or the other (100.0%), with a majority of them did not visit the hospital during COVID-19 for their SAM child (52.5%) as they were afraid of COVID-19 (63.2%) and/or they lacked access to transport for visiting a hospital (93.4%). Bivariate analysis revealed that the father’s age (P = 0.02) and income (P = 0.00) is associated with the perceived effect of COVID-19 on income. In contrast, only the gender of the child (P = 0.00) is related to the visit to the hospital, and the gender of the child (P = 0.01) and mother’s literacy (P = 0.00) is associated with the choice of treatment from any other setup, including Hakeem and Peer. Conclusion This study concludes that health emergencies like the COVID-19 pandemic pose a significant barrier to access to healthcare services and subject a more vulnerable state to already vulnerable groups like SAM children. To lessen their vulnerability, initiatives like mobile health care services should be introduced, especially for socially disadvantaged communities, localities, and groups on regular basis and for future emergencies.

Navigation based task-oriented dialogue systems provide users with a natural way of communicating with maps and navigation software. Natural language understanding (NLU) is the first step for a task-oriented dialogue system. It extracts the important entities (slot tagging) from the user’s utterance and determines the user’s objective (intent determination). Word embeddings are the distributed representations of the input sentence, and encompass the sentence’s semantic and syntactic representations. We created the word embeddings using different methods like FastText, ELMO, BERT and XLNET; and studied their effect on the natural language understanding output. Experiments are performed on the Roman Urdu navigation utterances dataset. The results show that for the intent determination task XLNET based word embeddings outperform other methods; while for the task of slot tagging FastText and XLNET based word embeddings have much better accuracy in comparison to other approaches.