Browsing by Author "Hossain, MD. Belal"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Change in Prevalence Over Time and Factors Associated with Depression Among Bangladeshi Older Adults During the COVID-19 Pandemic
    (Daffodil International University, 2022-12-15) Mistry, Sabuj K.; Ali, Arm Mehrab; Yadav, Uday N.; Huda, MD. Nazmul; Khanam, Fouzia; Kundu, Satyajit; Khan, Jahidur R.; Khan, Jahidur R.; Hossain, MD. Belal; Anwar, Afsana; Ghimire, Saruna
    Background: Globally, the COVID-19 pandemic seriously affected both physical and mental health conditions. This study aims to assess changes in the prevalence of depression among older adults during the COVID-19 pandemic in Bangladesh and explore the correlates of depression in pooled data. Methods: This study followed a repeated cross-sectional design and was conducted through telephone interviews on two successive occasions during the COVID-19 pandemic (October 2020 and September 2021) among 2077 (1032 in 2020-survey and 1045 in 2021-survey) older Bangladeshi adults aged 60 years and above. Depression was measured using the 15-item Geriatric Depression Scale (GDS-15). The binary logistic regression model was used to identify the factors associated with depression in pooled data. Results: A significant increase in the prevalence of depression was noted in the 2021 survey compared to the 2020 survey (47.2% versus 40.3%; adjusted odds ratio (aOR): 1.40, 95% confidence interval (CI): 1.11-1.75). Depression was significantly higher among participants without a partner (aOR 1.92, 95% CI 1.45-2.53), with a monthly family income of <5000 BDT (aOR: 2.65, 95% CI 1.82-3.86) or 5000-10 000 BDT (aOR: 1.30, 95% CI 1.03-1.65), living alone (aOR 2.24, 95% CI 1.40-3.61), feeling isolated (aOR 3.15, 95% CI 2.49-3.98), with poor memory/concentration (aOR 2.02, 95% CI 1.58-2.57), with non-communicable chronic conditions (aOR 1.34, 95% CI 1.06-1.69), overwhelmed by COVID-19 (aOR 1.54, 95% CI 1.18-2.00), having difficulty earning (aOR 1.49, 95% CI 1.15-1.92) or obtaining food (aOR 1.56, 95% CI 1.17-2.09) during COVID-19 pandemic, communicating less frequently (aOR 1.35, 95% CI 1.07-1.70) and needing extra care (aOR 2.28, 95% CI 1.75-2.96) during the pandemic. Conclusions: Policymakers and public health practitioners should provide immediate mental health support initiatives for this vulnerable population during the COVID-19 pandemic and beyond. Policymakers should also invest in creating safe places to practise mindful eating, exercise, or other refuelling activities as a means of preventing and managing depression.
  • Thumbnail Image
    Item
    Human Face Recognition Using HAAR Cascade Classifier and Gender Recognition Using Caffemodel with SMTP
    (Daffodil International University, 2022-01-04) Hossain, MD. Belal; Nahar, Nurun
    Due to the non-modeling nature and wide range of applications, facial recognition has always been a persistent study field. Computer vision is now a broad subject that uses high-level programming to automatically execute tasks such as detection, identification, and classification using input images/videos. They are superior than the regular human visual system, even using deep learning approaches. A computer system that detects or confirms a person based on their facial characteristics from a digital picture or video source is known as face recognition. This technology enables us to influence security systems, biometric identification, gait analysis, social networking, and other areas. Because of its non-intrusiveness, accuracy, and speed, live face recognition has gained a lot of traction in security systems. In our project, we created a facial recognition system that uses the Local Binary Pattern Histogram (LBPH) approach to treat real-time human face recognition in low and high-level images. Our research was specifically focused on developing a system that is based on a human gesture known as Face. This is a four-step process. Face detection using the Haar cascade classifier is the first. Face recognition using LHBP classifiers, which are produced from learned faces, is the second option. The third step is to identify the person's gender, and the last step is to record the attendance with the date and time, save it in a database, and email it to the owner by using SMTP. A graphical user interface (GUI) was also employed to make it more user-friendly.