Browsing by Author "Nuruzzaman, Md"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Assessment of staffing needs for physicians and nurses at Upazila health complexes in Bangladesh using WHO workload indicators of staffing need (WISN) method
    (BMJ Journals, 2/13/2020) Joarder, Taufique; Bente Kamal Tune, Samiun Nazrin; Nuruzzaman, Md; Alam, Sabina; de Oliveira Cruz, Valeria; Zapata, Tomas
    Objective This study aimed to assess the current workload and staffing need of physicians and nurses for delivering optimum healthcare services at the Upazila Health Complexes (UpHCs) in Bangladesh. Design Mixed-methods, combining qualitative (eg, document reviews, key informant interviews, in-depth interviews, observations) and quantitative methods (timemotion survey). Setting Study was conducted in 24 health facilities of Bangladesh. However, UpHCs being the nucleus of primary healthcare in Bangladesh, this manuscript limits itself to reporting the findings from the providers at four UpHCs under this project. Participants 18 physicians and 51 nurses, males and females. Primary outcome measures Workload components were defined based on inputs from five experts, refined by nine service providers. Using WHO Workload Indicator of Staffing Need (WISN) software, standard workload, category allowance factor, individual allowance factor, total required number of staff, WISN difference and WISN ratio were calculated. Results Physicians have very high (WISN ratio 0.43) and nurse high (WISN ratio 0.69) workload pressure. 50% of nurses’ time are occupied with support activities, instead of nursing care. There are different workloads among the same staff category in different health facilities. If only the vacant posts are filled, the workload is reduced. In fact, sanctioned number of physicians and nurses is more than actual need. Conclusions It is evident that high workload pressures prevail for physicians and nurses at the UpHCs. This reveals high demand for these health workforces in the respective subdistricts. WISN method can aid the policy-makers in optimising utilisation of existing human resources. Therefore, the government should adopt flexible health workforce planning and recruitment policy to manage the patient load and disease burden. WISN should, thus, be incorporated as a planning tool for health managers. There should be a regular review of health workforce management decisions, and these should be amended based on periodic reviews.
  • Thumbnail Image
    Item
    Machine Vision Based Potato Species Recognition
    (Daffodil International University, 2020-07-18) Nuruzzaman, Md; Hossain, MD. Shahadat; Rahman, Md Mostafijur
    One of the bound vegetable elements of our daily life is the potato. There are 4200 kinds of potato species and among them, 82 kinds are found in Bangladesh. It is usually grown for numerous reasons apart from having as a food. Different potatoes are used in different cases. If there’s a curry-making procedure there will a different potato be used and if there’s a French fried making recipe there also a different potato be used. But the problem is many people in our country fail to understand the right kind of potato for the right use. Thus, a big confusion is created in every genre of these potato consuming sectors especially for the people who are unaware of potato species. This is where our project idea born, using a machine vision-based recognition of these potato species which can help people to recognize them. In this paper, we perform an in-depth exploration of a machine vision approach for recognizing different species of potatoes in Bangladesh. A number of potatoes are classified based on the figures analyzed by their images. For our experiment, we collected the data of 4 verities total of 1200 potato images. In this process, we wanted to identify the real image of potatoes. we have applied machine learning algorithms like Random Forest Classifier (RF), Linear Discriminant Analysis (LDA), Logistic Regression, Support Vector Machine (SVM), CART, NB, and KNN on our datasets. Here we apply our developed algorithms to (color, texture, and shape) features. The data obtained from image processing were classified using extraction, resize, and grayscale convert. After applying all algorithms each of them produced different results. Random Forest Classifier (RF) shows the best result and its accuracy rate of 100% and SVM gives the lowest rate. Its accuracy rate 74.074%, which is not only good but also promising for future research.