Kumar, Prasanth
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Study on Role of Antenatal Care in Pregnancy Outcome K, Akhila; Kumar, Prasanth; Bhavani, Kenche
Journal of Maternal and Child Health Vol. 7 No. 6 (2022)
Publisher : Masters Program in Public Health, Universitas Sebelas Maret, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (34.634 KB) | DOI: 10.26911/thejmch.2022.07.06.04

Abstract

Background: Antenatal care (ANC) and regular antenatal visits are one of the interventions that have the potential to improve both maternal and child survival. The utilization of antenatal services remains less than 60% in India. The study aimed to find out the association between ANC visits and pregnancy outcome. Subjects and Method: Cross-sectional study was conducted on 200 antenatal women in a tertiary care centre over a period of 3 months. After taking informed consent data was collected by interviewer technique using a pretested semi-structured questionnaire. Questionnaire includes information related to socio-demographic variables, number of ANC visits, delivery outcome (normal/ LSCS) low birth weight, stillbirths, and abortions. Thus, collected data was entered in excel and analyzed using epi info 7.22.6. The bivariate analysis was the chi-square test. Binary logistic regression was used to study the association between delivery outcome and its covariates. Logistic regression was also done to see the association between ANC visits and Low birth weight and stillbirths. Results: Out of 59 women who had less than 4 ANC visits had more number of abortions (18.6%) (OR= 32.08; CI 95%= 4.03 to 255.07; p<0.001), low birth weights (52.5%) (OR= 4.46; CI 95%= 2.31 to 8.62; p= 0.001), still births (8.5%) (OR= -1.00; CI 95%= -1 to -0.001 p=0.001), out of 22 illiterate mothers 16 of them had poor pregnancy outcomes (p= 0.002) and first ANC visit during first trimester had less complications (p <0.001). Binary logistic regression revealed significant association between delivery outcome and Socio-economic status (OR= 2.14; CI 95%= -1.47 to 3.13; p<0.001) as well as frequency of ANC visits (OR= 0.65; CI 95%= 0.55 to 0.77; p<0.001). Significant association was also observed between ANC visits and Low birth weight (OR= 0.52; CI 95%= -0.43 to 0.62; p <0.001). Logistic regression between ANC visits and stillbirths/abortion showed signi­fi­cant association (OR= 0.36 (CI 95%= -0.23 to 0.55; p<0.001). Conclusion: The study shows that less than 4 ANC visits, illiteracy increases the risk of poor preg­nan­cy outcome. Women who had their first ANC visits during first trimester had less comp­li­ca­tions. Keywords: antenatal care, pregnancy outcomes, socio-demographic factors. Correspondence:Bhavani. Department of Community Medicine, Osmania Medical College, Hyderabad, Tela­nga­na. Email: bhavanikenche1969@gmail.com. Mobile: 9502710778.
Pengembangan Model Predictive Maintenance Untuk Kendaraan Menggunakan Algoritma Pembelajaran Mesin Hasugian, Penda Sudarto; Kumar, Prasanth; Aispriyani; Sagala, Jijon Raphita
Jurnal Sistem Informasi dan Teknologi Jaringan Vol 5 No 2 (2024): September
Publisher : CV. ADMITECH SOLUTIONS

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Vehicle maintenance is an important aspect to ensure optimal performance and vehicle life. Conventional maintenance approaches based on time or mileage (Time-Based Maintenance) are often ineffective, because they do not consider the actual condition of the vehicle. Predictive Maintenance supported by machine learning algorithms offers a more accurate solution in detecting potential vehicle damage before failure occurs, so that maintenance can be carried out according to actual needs. This study aims to develop a machine learning-based predictive maintenance model with a case study at the Payung Auto Solution workshop, which leads to the repair of Nissan, Datsun, and other vehicle brands. The methods used in this study include collecting operational data and vehicle maintenance history at Payung Auto Solution. This data is analyzed and processed using machine learning algorithms, such as Random Forest and Neural Network, to build a predictive model that is able to identify damage patterns in vehicle components. This model is tested and evaluated using prediction accuracy metrics, to determine the effectiveness of the model in predicting maintenance needs.