Bangla_MER: A unique dataset for Bangla mathematical entity recognition.

Mathematical entity recognition is essential for machines to define and illustrate mathematical substance faultlessly and to facilitate sufficient mathematical operations and reasoning. As mathematical entity recognition in the Bangla language is novel, to our best knowledge, there is no available dataset exists in any repository. In this paper, we present state of the art Bangla mathematical entity dataset containing 13,717 observations. Each record has a mathematical statement, mathematical type and mathematical entity. This dataset can be utilized to conduct research involving the recognition of mathematical operators, renowned mathematical terms (such as complex numbers, real numbers, prime numbers, etc.), and operands as numbers. The findings mentioned above, and their combination are also feasible with a modest tweak to the dataset. Furthermore, we have structured this dataset in raw format and made a CSV file, incorporating three columns: text, math entity, and label. As an outcome, researchers may easily handle the data, facilitating a variety of deep learning and machine learning explorations.

Unhealthy Foods and Sugar-Sweetened Beverages Consumption Among Bangladeshi Adolescents and Their Sociodemographic Determinants: Findings From a Nationally Representative Cross-Sectional Study.

BACKGROUND: Consumption of savory crispy or fried snacks (SCFS), sugary snacks (SS), and sugar-sweetened beverages (SSB) is associated with an increased prevalence of obesity and noncommunicable diseases. We aimed to estimate the consumption of SCFS, SS, and SSB among adolescent males and females in Bangladesh and to report the factors associated with their consumption using data from a nationwide cross-sectional survey. METHODS: We interviewed 4,907 adolescent males and 4,865 females for the seven-day recall on intake of SCFS, SS, and SSB from 82 randomly selected clusters from rural, non-slum urban, and slum areas. Sociodemographic and anthropometry data were also collected. RESULTS: Consumption of SCFS, SS, and SSB for ≥7 times per week was reported by 11.6%, 28.9%, and 25.6% of the males and 4.9%, 24.8%, and 20.7% of the females, respectively. The weekly mean frequency of SCFS, SS, and SSB intake increased after adjustment for potential confounders among females with higher maternal education and for SCFS and SSB among males with the highest level of father's education. Increased intake of SS and SSB for both males and females was associated with dwelling in a female-headed household. SCFS intake was higher among both males and females from the richest households. Nutritional status, both overweight and obesity, and underweight, was not associated with a more frequent intake of SCFS and SS among males and females; however, a lower frequency of intake of SSB was observed among overweight and obese males. Screen time (television viewing: none, up to 1 hour, and more than 1 hour) was not associated with consumption of SCFS and SSB among both males and females. CONCLUSION: Consumption of unhealthy snacks and drinks is high among adolescents in Bangladesh and needs to be addressed through policy and program measures to abate the epidemic of obesity and associated NCD.

Efficient 3D AlexNet Architecture for Object Recognition Using Syntactic Patterns from Medical Images.

In computer vision and medical image processing, object recognition is the primary concern today. Humans require only a few milliseconds for object recognition and visual stimulation. This led to the development of a computer-specific pattern recognition method in this study for identifying objects in medical images such as brain tumors. Initially, an adaptive median filter is used to remove the noise from MRI images. Thereafter, the contrast image enhancement technique is used to improve the quality of the image. To evaluate the wireframe model, the cellular logic array processing (CLAP)-based algorithm is then applied to images. The basic patterns of three-dimensional (3D) images are then identified from the input image by scanning the whole image. The frequency of these patterns is also used for object classification. A deep neural network is then utilized for the classification of brain tumor. In the proposed model, the syntactic pattern recognition technique is used to find the feature vector and 3D AlexNet is used for brain tumor classification. To evaluate the performance of the proposed work, three benchmark brain tumor datasets are used, i.e., Figshare, Brain MRI Kaggle, and Medical MRI datasets and BraTS 2019 dataset. The comparative analyses reveal that the proposed brain tumor classification model achieves significantly better performance than the existing models.

Psychological Analysis for Depression Detection from Social Networking Sites.

Rapid technological advancements are altering people's communication styles. With the growth of the Internet, social networks (Twitter, Facebook, Telegram, and Instagram) have become popular forums for people to share their thoughts, psychological behavior, and emotions. Psychological analysis analyzes text and extracts facts, features, and important information from the opinions of users. Researchers working on psychological analysis rely on social networks for the detection of depression-related behavior and activity. Social networks provide innumerable data on mindsets of a person's onset of depression, such as low sociology and activities such as undergoing medical treatment, a primary emphasis on oneself, and a high rate of activity during the day and night. In this paper, we used five machine learning classifiers-decision trees, K-nearest neighbor, support vector machines, logistic regression, and LSTM-for depression detection in tweets. The dataset is collected in two forms-balanced and imbalanced-where the oversampling of techniques is studied technically. The results show that the LSTM classification model outperforms the other baseline models in the depression detection healthcare approach for both balanced and imbalanced data.

Score-Level Fusion of 3D Face and 3D Ear for Multimodal Biometric Human Recognition.

A novel multimodal biometric system is proposed using three-dimensional (3D) face and ear for human recognition. The proposed model overcomes the drawbacks of unimodal biometric systems and solves the 2D biometric problems such as occlusion and illumination. In the proposed model, initially, the principal component analysis (PCA) is utilized for 3D face recognition. Thereafter, the iterative closest point (ICP) is utilized for 3D ear recognition. Finally, the 3D face is fused with a 3D ear using score-level fusion. The simulations are performed on the Face Recognition Grand Challenge database and the University of Notre Dame Collection F database for 3D face and 3D ear datasets, respectively. Experimental results reveal that the proposed model achieves an accuracy of 99.25% using the proposed score-level fusion. Comparative analyses show that the proposed method performs better than other state-of-the-art biometric algorithms in terms of accuracy.

Prevalence of Infant and Young Child Feeding Practices and Differences in Estimates of Minimum Dietary Diversity Using 2008 and 2021 Definitions: Evidence from Bangladesh.

Background: Infant and young child feeding (IYCF) practices directly impact the health of <2-y-old children. Minimum dietary diversity (MDD) is an IYCF indicator to assess feeding practices of children aged 6-23 mo. The definition of MDD has recently been updated by the WHO and UNICEF, substituting "≥4 out of 7 food groups" (MDD-7FG) with "≥5 out of 8 food groups" (MDD-8FG). Objectives: The goals of this study were to estimate the prevalence of IYCF indicators and identify the implications of the change in the prevalence of MDD at the national and regional levels of Bangladesh. Methods: This study used data from the National Food Security and Nutrition Surveillance 2018-2019 round. A total of 1992 children aged 0-23 mo were included in this analysis. IYCF indicators and MDD were calculated according to the WHO-UNICEF guidelines. The difference between the prevalence of MDD-7FG and MDD-8FG is presented as percentage points. Results: The prevalence of early initiation of breastfeeding was 43.8%, and exclusive breastfeeding was 56.2%. Approximately 55% of children maintained MDD (MDD-7FG), 48% received minimum meal frequency, and 28% received a minimum acceptable diet. Compared with MDD-7FG, the prevalence of MDD-8FG was lower among 6-23-mo-old children. The difference between MDD prevalence (MDD-8FG vs. MDD-7FG) was high for boys (44.0% vs. 53.2%), children aged 12-23 mo (53.4% vs. 63.4%), in urban areas (30.2% vs. 42.4%), in the Dhaka administrative division (42.0% vs. 56.3%), among uneducated mothers (37.1% vs. 47.1%), in households with ≤4 members (44.3% vs. 55%), and for middle-class households (40.3% vs. 57.6%). Conclusions: The new method led to a decrease in the prevalence of MDD in Bangladesh. As the country prepares to implement the new indicator, it is critical to disseminate the new knowledge and its positive implication for improved child feeding and nutrition.

Artificial Intelligence of Things- (AIoT-) Based Patient Activity Tracking System for Remote Patient Monitoring.

Telehealth and remote patient monitoring (RPM) have been critical components that have received substantial attention and gained hold since the pandemic's beginning. Telehealth and RPM allow easy access to patient data and help provide high-quality care to patients at a low cost. This article proposes an Intelligent Remote Patient Activity Tracking System system that can monitor patient activities and vitals during those activities based on the attached sensors. An Internet of Things- (IoT-) enabled health monitoring device is designed using machine learning models to track patient's activities such as running, sleeping, walking, and exercising, the vitals during those activities such as body temperature and heart rate, and the patient's breathing pattern during such activities. Machine learning models are used to identify different activities of the patient and analyze the patient's respiratory health during various activities. Currently, the machine learning models are used to detect cough and healthy breathing only. A web application is also designed to track the data uploaded by the proposed devices.

Medical Image Captioning Using Optimized Deep Learning Model.

Medical image captioning provides the visual information of medical images in the form of natural language. It requires an efficient approach to understand and evaluate the similarity between visual and textual elements and to generate a sequence of output words. A novel show, attend, and tell model (ATM) is implemented, which considers a visual attention approach using an encoder-decoder model. But the show, attend, and tell model is sensitive to its initial parameters. Therefore, a Strength Pareto Evolutionary Algorithm-II (SPEA-II) is utilized to optimize the initial parameters of the ATM. Finally, experiments are considered using the benchmark data sets and competitive medical image captioning techniques. Performance analysis shows that the SPEA-II-based ATM performs significantly better as compared to the existing models.

Evolving Long Short-Term Memory Network-Based Text Classification.

Recently, long short-term memory (LSTM) networks are extensively utilized for text classification. Compared to feed-forward neural networks, it has feedback connections, and thus, it has the ability to learn long-term dependencies. However, the LSTM networks suffer from the parameter tuning problem. Generally, initial and control parameters of LSTM are selected on a trial and error basis. Therefore, in this paper, an evolving LSTM (ELSTM) network is proposed. A multiobjective genetic algorithm (MOGA) is used to optimize the architecture and weights of LSTM. The proposed model is tested on a well-known factory reports dataset. Extensive analyses are performed to evaluate the performance of the proposed ELSTM network. From the comparative analysis, it is found that the LSTM network outperforms the competitive models.

Prevalence of and factors associated with insufficient physical activity among adolescents: evidence from a nationwide survey in Bangladesh.

The World Health Organization set a target of a 15% relative reduction in the prevalence of insufficient physical activity (IPA) by 2025 among adolescents and adults globally. In Bangladesh, there are no national estimates of the prevalence of IPA among adolescents. The aim of this study was to estimate the prevalence of and risk factors associated with IPA among adolescent girls and boys. Data for 4865 adolescent girls and 4907 adolescent boys, collected as a part of a National Nutrition Surveillance in 2018-19, were analysed for this study. A modified version of the Global Physical Activity Questionnaire (GPAQ) was used to collect physical activity data. The World Health Organization recommended cut-off points were used to estimate the prevalence of IPA. Bivariate and multivariable logistic regression was performed to identify factors associated with IPA. Prevalences of IPA among adolescent girls and boys were 50.3% and 29.0%, respectively, and the prevalence was significantly higher among early adolescents (10-14 years) than late adolescents (15-19 years) among both boys and girls. The IPA prevalence was highest among adolescents living in non-slum urban areas (girls: 77.7%; boys: 64.1%). For both boys and girls, younger age, non-slum urban residence, higher paternal education and increased television viewing time were significantly associated with IPA. Additionally, residing in slums was significantly associated with IPA only among the boys. Higher maternal education was associated with IPA only among the girls. This study identified several modifiable risk factors associated with IPA among adolescent boys and girls in Bangladesh. These factors should be addressed through comprehensive public health interventions to promote physical activity among adolescent girls and boys.

Prevalence and associated factors of insufficient physical activity among elderly people in Bangladesh: a nationally representative cross-sectional study.

OBJECTIVES: Insufficient physical activity (IPA) is a crucial risk factor for non-communicable diseases (NCDs). The elderly population has a higher likelihood of suffering from NCDs. We aimed to estimate the prevalence of and factors associated with IPA among the elderly people in Bangladesh. METHODS: We analysed data from the Bangladesh Food Security and Nutrition Surveillance round 2018-2019, collected from 82 rural, non-slum urban and slum clusters selected using multistage cluster sampling. IPA was defined as <150 min of moderate intensity or <75 min of vigorous intensity or equivalent in a typical week. The weighted prevalence of IPA was estimated by gender and across different variables. Crude and adjusted prevalence ratios were calculated using Poisson regression with robust variance. RESULTS: The weighted prevalence of IPA among elderly people was 38.4%, with a slightly higher prevalence in women (39.7% vs 37.3%). Factors associated with higher prevalence of IPA in both sexes were-higher age, living in non-slum urban areas, unemployed or homemaker, not currently married, sedentary behaviour and self-reported hypertension. Further, >10 years of education, inadequate fruits and vegetable consumption, self-reported asthma and higher waist circumference among men; and higher household income and self-reported diabetes among women were associated with a higher prevalence of IPA. CONCLUSIONS: IPA is highly prevalent among Bangladeshi elderly men and women. Sedentary behaviour, inadequate fruits and vegetable consumption and higher waist circumference were the modifiable factors of IPA. Evidence from this study can guide the development of appropriate interventions to promote healthy ageing in Bangladesh.

Ten-years cardiovascular risk among Bangladeshi population using non-laboratory-based risk chart of the World Health Organization: Findings from a nationally representative survey.

The World Health Organization (WHO) has recently developed a non-laboratory based cardiovascular disease (CVD) risk chart considering the parameters age, sex, current smoking status, systolic blood pressure, and body mass index. Using the chart, we estimated the 10-years CVD risk among the Bangladeshi population aged 40-74 years. We analyzed data from a nationally representative survey conducted in 2018-19. The survey enrolled participants from 82 clusters (57 rural, 15 non-slum urban, and 10 slums) selected by multistage cluster sampling. Using the non-laboratory-based CVD risk chart of the World Health Organization (WHO), we categorized the participants into 5 risk groups: very low (<5%), low (5% to <10%), moderate (10% to <20%), high (20% to <30%) and very high (> = 30%) risk. We performed descriptive analyses to report the distribution of CVD risk and carried out univariable and multivariable logistic regression to identify factors associated with elevated CVD risk (> = 10% CVD risk). Of the 7,381 participants, 46.0% were female. The median age (IQR) was 59.0 (48.0-64.7) years. Overall, the prevalence of very low, low, moderate, high, and very high CVD risk was 34.7%, 37.8%, 25.9%, 1.6%, and 0.1%, respectively. Elevated CVD risk (> = 10%) was associated with poor education, currently unmarried, insufficient physical inactivity, smokeless tobacco use, and self-reported diabetes in both sexes, higher household income, and higher sedentary time among males, and slum-dwelling and non-Muslim religions among females. One in every four Bangladeshi adults had elevated levels of CVD risk, and males are at higher risk of occurring CVD events. Non-laboratory-based risk prediction charts can be effectively used in low resource settings. The government of Bangladesh and other developing countries should train the primary health care workers on the use of WHO non-laboratory-based CVD risk charts, especially in settings where laboratory tests are not available.

Prevalence and associated factors of depression among adolescent boys and girls in Bangladesh: findings from a nationwide survey.

OBJECTIVE: To assess the prevalence of and factors associated with depression among adolescent boys and girls. DESIGN: We conducted a nationwide cross-sectional study. SETTING: This study was carried out in 82 randomly selected clusters (57 rural, 15 non-slum urban and 10 slums) from eight divisions of Bangladesh. PARTICIPANTS: We interviewed 4907 adolescent boys and 4949 adolescent girls. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome measure was 'any depression' and the secondary outcome measures were types of depression: no or minimal, mild, moderate, moderately severe and severe. RESULTS: The overall prevalence of no or minimal, mild, moderate, moderately severe and severe depression was 75.5%, 17.9%, 5,4%, 1.1% and 0.1%, respectively. Across most of the sociodemographic, lifestyle and anthropometric strata, the prevalence of any depression was higher among adolescent girls. In both sexes, depression was associated with higher age, higher maternal education, paternal occupation e.g., business, absence of a 6-9-year-old member in the household, food insecurity, household consumption of unfortified oil, household use of non-iodised salt, insufficient physical activity (adjusted odds ratio, AOR: 1.24 for boys, 1.44 for girls) and increased television viewing time e.g., ≥121 minute/day (AOR: 1.95 for boys, 1.99 for girls). Only among boys, depression was also associated with higher paternal education e.g., complete secondary and above (AOR: 1.42), absence of another adolescent member in the household (AOR: 1.34), household use of solid biomass fuel (AOR: 1.39), use of any tobacco products (AOR: 2.17), and consumption of processed food (AOR: 1.24). Only among girls, non-slum urban residence, Muslim religion, and household size ≤4 were also associated with depression. CONCLUSION: The prevalence of depression among adolescent boys and girls is high in Bangladesh. In most sociodemographic, lifestyle and anthropometric strata, the prevalence is higher among girls. In this age group, depression is associated with a number of sociodemographic and lyfestyle factors. The government of Bangladesh should consider these findings while integrating adolescent mental health in the existing and future programmes.

Gender-specific prevalence and associated factors of hypertension among elderly Bangladeshi people: findings from a nationally representative cross-sectional survey.

OBJECTIVE: We aimed to estimate the gender-specific prevalence and associated factors of hypertension among elderly people in Bangladesh. DESIGN AND METHOD: We analysed data from the food security and nutrition surveillance round 2018-2019. The multistage cluster sampling method was used to select the study population. Hypertension was defined as systolic blood pressure ≥140 mm Hg and/or diastolic blood pressure ≥90 mm Hg and/or having a history of hypertension. We carried out the descriptive analysis, bivariate and multivariable logistic regression to report the weighted prevalence of hypertension as well as crude and adjusted ORs with 95% CI. A p value<0.05 was considered statistically significant. SETTING: The study was conducted in 82 clusters (57 rural, 15 non-slum urban and 10 slums) in all eight administrative divisions of Bangladesh. PARTICIPANTS: A total of 2482 males and 2335 females aged ≥60 years were included in this analysis. RESULTS: The weighted prevalence of hypertension was 42% and 56% among males and females, respectively. The prevalence was higher among females across all sociodemographic, behavioural and clinical strata. Factors associated with higher odds of hypertension (adjusted OR (AOR) (95% CI) for males and females, respectively) were age ≥70 years (1.32 (1.09, 1.60) and 1.40 (1.15, 1.71)); insufficient physical activity (1.50 (1.25, 1.81) and 1.38 (1.15, 1.67)); higher waist circumference (2.76 (2.22, 3.43) and 2.20 (1.82, 2.67)); and self-reported diabetes (1.36 (1.02, 1.82) and 1.82 (1.35, 2.45)). Additionally, living in slums decreased (0.71 (0.52, 0.96)) and education >10 years increased odds of hypertension (1.83 (1.38, 2.44)) among males. CONCLUSION: In Bangladesh, half of the elderly persons were hypertensive, with a higher prevalence in females. In both sexes, odds of hypertension was higher among persons with older age (≥70 years), insufficient physical activity, higher waist circumference and self-reported diabetes. The Ministry of Health of Bangladesh should consider these findings while designing and implementing health programmes for elderly population.

Prevalence and socio-economic determinants of inadequate dietary diversity among adolescent girls and boys in Bangladesh: findings from a nationwide cross-sectional survey.

Malnutrition among adolescents is often associated with inadequate dietary diversity (DD). We aimed to explore the prevalence of inadequate DD and its socio-economic determinants among adolescent girls and boys in Bangladesh. A cross-sectional survey was conducted during the 2018-19 round of national nutrition surveillance in Bangladesh. Univariate and multivariable logistic regression was performed to identify the determinants of inadequate DD among adolescent girls and boys separately. This population-based survey covered eighty-two rural, non-slum urban and slum clusters from all divisions of Bangladesh. A total of 4865 adolescent girls and 4907 adolescent boys were interviewed. The overall prevalence of inadequate DD was higher among girls (55⋅4 %) than the boys (50⋅6 %). Moreover, compared to boys, the prevalence of inadequate DD was higher among the girls for almost all socio-economic categories. Poor educational attainment, poor maternal education, female-headed household, household food insecurity and poor household wealth were associated with increased chances of having inadequate DD in both sexes. In conclusion, more than half of the Bangladeshi adolescent girls and boys consumed an inadequately diversified diet. The socio-economic determinants of inadequate DD should be addressed through context-specific multisectoral interventions.

Noncommunicable Disease Risk Factors Among Adolescent Boys and Girls in Bangladesh: Evidence From a National Survey.

OBJECTIVES: To assess the prevalence of noncommunicable disease (NCD) risk factors and the factors associated with the coexistence of multiple risk factors (≥ 2 risk factors) among adolescent boys and girls in Bangladesh. METHODS: Data on selected NCD risk factors collected from face to face interviews of 4,907 boys and 4,865 girls in the national Nutrition Surveillance round 2018-2019, was used. Descriptive analysis and multivariable logistic regression were performed. RESULTS: The prevalence of insufficient fruit and vegetable intake, inadequate physical activity, tobacco use, and being overweight/obese was 90.72%, 29.03%, 4.57%, and 6.04%, respectively among boys; and 94.32%, 50.33%, 0.43%, and 8.03%, respectively among girls. Multiple risk factors were present among 34.87% of boys and 51.74% of girls. Younger age (p < 0.001), non-slum urban (p < 0.001) and slum residence (p < 0.001), higher paternal education (p = 0.001), and depression (p < 0.001) were associated with the coexistence of multiple risk factors in both boys and girls. Additionally, higher maternal education (p < 0.001) and richest wealth quintile (p = 0.023) were associated with the coexistence of multiple risk factors in girls. CONCLUSION: The government should integrate specific services into the existing health and non-health programs which are aimed at reducing the burden of NCD risk factors.