Browsing by Author "Islam, Md Shariful"

Now showing 1 - 5 of 5

Analysis of Feature Tree using Miranda
(East West University, 12/31/2017) Badhan, Ferdous Hussain; Islam, Md Shariful
Feature models are used to specify the variability of software product lines. We study a special subset of trees, called generalised feature trees, and show how they can be used to compute properties of the corresponding software product lines. We introduce our paper the concept of generalised feature trees, which are feature trees where features can have multiple occurrences. It is shown how an important class of feature models can be transformed into generalised feature trees. We present algorithms which, after transforming a feature model to a generalised feature tree, compute properties of the corresponding software product line. We discuss the computational complexity of these algorithms and provide executable specifications in the functional programming language Miranda.
Aspect Based Sentiment Analysis in Bangla Dataset Based on Aspect Term Extraction
(Springer, 2020-07-30) Haque, Sabrina; Rahman, Tasnim; Shakir, Asif Khan; Arman, Md. Shohel; Biplob, Khalid Been Badruzzaman; Himu, Farhan Anan; Das, Dipta; Islam, Md Shariful
Recent years have seen rapid growth of research on sentiment analysis. In aspect-based sentiment analysis, the idea is to take sentiment analysis a step further and find out what exactly someone is talking about, and then measuring the sentiment if she or he likes or dislikes it. Sentiment analysis in Bengali language is progressing and is considered as an important research interest. Due to scarcity of resources like proper annotated dataset, corpora, lexicon such as part of speech tagger etc. aspect-based sentiment analysis hardly has been done in Bengali language. In this paper, we have conducted our experiments based on a recent work from 2018 using conventional supervised machine learning algorithms (RF, SVM, KNN) to perform one of the ABSA’s tasks - aspect category extraction. The work is done on two datasets named – Cricket and Restaurant. We then compared our results with the existing work. We used two traditional steps to clean data and found that less preprocessing leads to better F1 Score. For Cricket dataset, SVM and KNN performed better, resulting F1 score of 37% and 27%. For Restaurant dataset, RF and SVM achieved improved score of 35% and 39% respectively. Additionally, we selected two more algorithms LR and NB, LR achieved best F1 score (43%) for Restaurant dataset among all.
Early Prevention and Detection of Cancer Risk for Low Income Country using Data Mining Technology: Bangladesh Perspective
(Semantic Scholar, 2016) Islam, Md Shariful; Akhter, Sharmin; Salahuddin, Md.; Sah, Jay Prakash; Rahman, Md Ramim Tanver; Asaduzzaman, Sayed; Ahmed, Kawsar; Mohiuddin, AKM; Shibly, Abu Zaffar
Dominant population of the world including Bangladesh is suffering from skin, lung, cervical and ovarian cancer because of being unconsciousness about cancer as well as their risk factors. Many of them are illiterate and poor. They cannot go to doctor and do must outdoor activities due to lack of money. Most of them do not even know they have skin cancer. So the ability to predict such cancer with minimum cost plays a pivotal role in the diagnosis process. Therefore use of new information technology data mining and risk prediction systems for cancer research can be more effective for early detection and awareness for future possible chemotherapeutic treatment. Full Text Link: http://doi.org/10.4172/2168-9652.1000e150
Prevalence of and Factors Associated With Tobacco Smoking in the Gambia
(Daffodil International University, 2022-05-18) Islam, Md Shariful; Al-Wajeah, Haifaa; Rabbani, Md Golam; Ferdous, Md; Mahfuza, Nusrat Sharmin; Konka, Daniel; Silenga, Eva; Ullah, Abu Naser Zafar
Objectives To examine the prevalence of and risk factors associated with tobacco smoking in the Gambia. Design A nationwide cross-sectional study. Setting The Gambia. Participants The study participants were both women and men aged between 15 and 49 years old. We included 16,066 men and women in our final analysis. Data analysis We analysed data from the Gambia Demographic and Health Survey (DHS), 2019–2020. DHS collected nationally stratified data from local government areas and rural–urban areas. The outcome variable was the prevalence of tobacco smoking. Descriptive analysis, prevalence and logistic regression methods were used to analyse data to identify the potential determinants of tobacco smoking. Results The response rate was 93%. The prevalence of current tobacco smoking was 9.92% in the Gambia in 2019–2020, of which, 81% of the consumers smoked tobacco daily. Men (19.3%) smoked tobacco much higher than women (0.65%) (p<0.001). People aged 40–49 years, with lower education, and manual workers were the most prevalent group of smoking in the Gambia (p<0.001). Men were 33 times more likely to smoke tobacco than women. The chance of consuming smoked tobacco increased with the increase of age (adjusted OR (AOR) 9.08, 95% CI 5.08 to 16.22 among adults aged 40–49 years, p<0.001). The strength of association was the highest among primary educated individuals (AOR 5.35, 95% CI 3.35 to 8.54). Manual workers (AOR 2.73) and people from the poorest households (AOR 1.86) were the risk groups for smoking. However, place of residency and region were insignificantly associated with smoking in the Gambia. Conclusions Men, older people, manual workers, individuals with lower education and lower wealth status were the vulnerable groups to tobacco smoking in the Gambia. Government should intensify awareness programmes on the harmful effects of smoking, and introduce proper cessation support services among tobacco smoking users prioritising these risk groups.
Work-Related Stress and Its Effects on Personal Life of Pharmaceutical Sales Representatives: Bangladesh Aspect
(Daffodil International University, 22-11-22) Islam, Md Shariful
Introduction: Pharmaceutical Sales Representatives (PSRs) are becoming more and more necessary as the pharmaceutical business expands daily. Target-related pressure is changing the character of work, which finally causes Job Induced Stress (JIS) within PSRs. Objective: This research attempts to evaluate JIS and the different contributing elements, while also taking into account some of the health effects. Method: The data was collected utilizing a self-administered questionnaire sent to the PSRs (n=100). Data was imported into MS Excel (version 2016) and descriptive statistics were used to examine it. Result: One hundred Pharmaceutical Sales Representatives completed the questionnaire. 88% percent respondents are male and 12% are female. 45% start their daily work at 7 am, 37% start at 8 am, and the rest 18% start at 9 am. 32% of Respondents close their work at 6 pm, 20% close at 7 pm, 22% close at 8 pm, 13% close at 9 pm, and the rest 13% close at 10 pm. Among all respondents, 84% of respondents enjoy their job, and 82% can meet their Target sales quantity. On the other hand, 54% of PSRs feel stress in their personal life, and 70% Feel distance from family. As a result of stress, 62% of respondents' PSRs experienced Headache, 20% experienced Fatigue, 33% experienced Irritability, 29% experienced Loss of Appetite, 27% experienced Over Sensitivity, 21% Suffering Insomnia, 29% experienced Anxiety and 29% are in depression. Conclusion: Any improvement in the way a work is performed professionally must be viewed in light of how it will effect and be implemented by PSRs. If JIS for the PSRs is not acknowledged and lessened, they will continue to be at high risk of experiencing several negative health effects. Keywords: Job Induced Stress (JIS), Pharmaceutical Sales Representatives (PSRs), Stress