Search

This paper plans to examine the effects of board extent on non-performing assets (NPA) and firm value measured as comprehensive financial performance (CFP) of banks in Bangladesh using data from 2016 to 2022. Using a sample of 210 firm-year observations, this paper reveals that NPA is significantly related to board size, which signals that a big board of directors (BODs) is linked with lowering the extent of NPA in the context of developing economies like Bangladesh. Besides, the affinity between board extent and firm value proxies as CFP is positive, but the result is not consequential. This research would be value additive to the literature because it examines the effects of board size on NPA and CFP, which is scanty in the corporate finance literature. Furthermore, this research finds no literature that applies CFP as the performance measure of banks, especially in Bangladesh.

The classification of gender from handwriting is a challenging issue that have great attention recently. Most of the exiting works were conducted on gender classification using face image and offline handwritten texts. This study explored an automated system for gender classification from online handwritten patterns. The handwritten samples were collected from 79 (Male: 32 and Female: 47) using pen tablet device. Each subject was asked to perform four tasks such as Zigzag trace (ZigZ-T), Zigzag predict (ZigZ-P), periodic line trace (PL-T), and periodic line predict (PL-P) and repeated its into three times. Thirty-six statistical features were derived from the six raw features, obtained from the Pen tablet device. Following that, we selected the best subset of features by employing Sequential Forward Floating Selection (SFFS)-based algorithm. At the same time, four machine learning (ML)-based algorithms like support vector machine (SVM), random forest, AdaBoost, and Gradient Boosting (GB) were employed for gender classification. We trained these four ML-based algorithms with leave-one-out method and optimized their hyperparameters using Optuna. The experimental results showed that SVM achieved a recognition accuracy of 88.10% for adult ZigZ-T tasks and 90.09% recognition accuracy was obtained by GB-based algorithm for children whose drawing ZigZ-P tasks. our proposed system demonstrates promise in automating gender classification based on handwriting patterns, offering insights into the significant differences between adult and child handwriting. The ability to identify gender accurately from handwriting has broad applications, including security enhancements and personalized service provision.

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by the symptoms of inattention, hyperactivity, and impulsivity that significantly affect daily functioning. It is usually 1st diagnosed in childhood and often lasts into adulthood. Various researchers introduced different statistical tools to identify children with ADHD based on phonotype, vision, and image-based data. The main causes of children with ADHD are still unknown and its diagnostic accuracy rate remains low. There is still some scopes to establish valid biomarkers for ADHD and improve the classification accuracy, which will help for children enhance their quality of life. This study aimed to establish and determine potential biomarkers for children with ADHD and then proposed a machine learning (ML)-based ADHD detection system. A multicenter approach was employed to collect Reverse Stroop Task (RST) data, including age, behavioral, and physiological indicators from 72 children with ADHD (aged 6–13 years) and 171 typically developing (TD) children. Moreover, we also collected the signal information from each subject using functional near-infrared spectroscopy (fNIRs) and quantified the change in prefrontal cortex oxygenated hemoglobin during RST. At the same time, we also computed the mean signal for every channel during the last 20 seconds of RST. We selected 70% of the dataset as a training set (ADHD: 51 and TD: 120) and the remaining dataset was used as a testing set (ADHD: 21 and TD: 51). To determine the potential biomarkers for ADHD, we employed independent t-test (p

Parkinson’s disease (PD) is a neurological disorder caused by degeneration of dopaminergic neurons in the midbrain. PD patients mainly suffer from motor symptoms, which significantly impact their daily lives. The diagnostic criteria for PD include the presence of muscle rigidity, tremor, and postural reflex disturbances. The Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) is the standard tool for evaluating PD symptoms, part III of which is dedicated to motor symptoms. That part involves a comprehensive set of specific physical examinations, and physicians assign semi quantitative scores from 0 to 4. However, this approach faces notable challenges, including the requirement for movement-disorder experts proficient in using MDS-UPDRS and the presence of substantial inter rater variability even among experts. Overcoming these challenges requires a quantitative and objective assessment method. Given that the rating of motor symptoms predominantly involves assessing kinematic characteristics, the integration of sensor-based devices and machine learning techniques holds the potential to outperform human experts in symptom evaluations. This study used the Leap Motion optical motion-capture device to quantitatively measure and analyze hand movements while 45 PD patients performed the following 3 tasks from the MDS-UPDRS part III: finger tapping (FT), hand opening and closing (OC), and forearm pronation and supination (PS). Data from these tasks were collected and processed, resulting in the extraction of 31 movement patterns for each task. Additionally, 69 statistical features were extracted from each movement pattern, yielding 2139 features for each task. We subsequently employed a random forest algorithm to select the top 15% of features based on the reduction of Gini impurity. These selected features were subsequently fed into a sequential-forward-floating-selection algorithm, combined with a support vector machine, to identify relevant feature combinations and predict the severity of the motor symptoms. The classification accuracy was 87.0% for FT, 93.2% for OC, and 92.2% for PS. One-way analysis of variance identified 13 features of the OC task that were significantly more discriminative for classifying the movement disability of PD patients ( ${p}$

Abstract Hepatocellular carcinoma (HCC) is the most common lethal malignancy of the liver worldwide. Thus, it is important to dig the key genes for uncovering the molecular mechanisms and to improve diagnostic and therapeutic options for HCC. This study aimed to encompass a set of statistical and machine learning computational approaches for identifying the key candidate genes for HCC. Three microarray datasets were used in this work, which were downloaded from the Gene Expression Omnibus Database. At first, normalization and differentially expressed genes (DEGs) identification were performed using limma for each dataset. Then, support vector machine (SVM) was implemented to determine the differentially expressed discriminative genes (DEDGs) from DEGs of each dataset and select overlapping DEDGs genes among identified three sets of DEDGs. Enrichment analysis was performed on common DEDGs using DAVID. A protein-protein interaction (PPI) network was constructed using STRING and the central hub genes were identified depending on the degree, maximum neighborhood component (MNC), maximal clique centrality (MCC), centralities of closeness, and betweenness criteria using CytoHubba. Simultaneously, significant modules were selected using MCODE scores and identified their associated genes from the PPI networks. Moreover, metadata were created by listing all hub genes from previous studies and identified significant meta-hub genes whose occurrence frequency was greater than 3 among previous studies. Finally, six key candidate genes (TOP2A, CDC20, ASPM, PRC1, NUSAP1, and UBE2C) were determined by intersecting shared genes among central hub genes, hub module genes, and significant meta-hub genes. Two independent test datasets (GSE76427 and TCGA-LIHC) were utilized to validate these key candidate genes using the area under the curve. Moreover, the prognostic potential of these six key candidate genes was also evaluated on the TCGA-LIHC cohort using survival analysis.

Hybrid development is basically dependent on the variability among available genetic resources. Polymorphism among the maize inbreds is essentially needed for maize hybridization. This study aimed at the assessment of diversity among 22 maize inbreds by 18 microsatellite markers. The study identified 187 alleles at 18 SSR loci. The amplified allele frequency per microsatellite locus was 10.4 and the highest allele per locus was 17 in SSR primer pair phi026. SSR primer set p-umc1292, phi074 and phi090 showed the lowest 6 alleles per genotype per locus. The locus phi026 showed the highest degree of gene diversity (0.92), and the locus p-umc1292 had the lowest of gene diversity (0.77) with a mean value of 0.862 among the microsatellites. At each site, the most prevalent allele varied between 0.14 (bnlg371) and 0.36. (p-umc1292). At any given locus, an average of 0.22 out of the 22 selected maize inbred lines had a common major allele. The average value of the polymorphic information content (PIC) was 0.85, within the range of 0.74 at the lowest to 0.92 at the highest. The higher PIC values of phi026 and nc013 established them to be the best markers for maize inbred lines. The UPGMA clustering generated seven distinct groups having 12.5% of similarity coefficient. The results revealed that inbred lines E10, E27, E19, E34, E35, E4, E43, E28, E11, E21, E17, E38, E25, E34, E14, E16, E39 and E3 were more diversified. These lines are promising to be used as parent materials for hybrid maize development in the future.

Attention deficit hyperactivity disorder (ADHD) for children is one of the behavioral disorders that affect the brain’s ability to control attention, impulsivity, and hyperactivity and its prevalence has increased over time. The cure for ADHD is still unknown and only early detection can improve the quality of life for children with ADHD. At the same time, children with ADHD often suffer from various comorbidities like autism spectrum disorder (ASD), major depressive disorder (MDD), etc. Various researchers developed computational tools to detect children with ADHD depending on handwriting text. Handwriting text-based systems are depending on a specific language that causes problems for non-native speakers of that language. Moreover, very few researchers considered other comorbidities such as ASD, MDD, etc., in their studies to detect ADHD for children. In this study, handwriting patterns or drawing is assumed as an aspect to identify/detect ADHD children who have ASD using machine learning (ML)-based approaches. We collected handwriting samples from 29 Japanese children (14 ADHD with coexisting ASD children and 15 healthy children) using a pen tablet. We asked each child to draw two patterns, namely zigzag lines (ZL) and periodic lines (PL) on a pen tablet and repeated them three times. We extracted 30 statistical features from raw datasets and these features were analyzed using sequential forward floating search (SFFS) and selected the best combinations or subsets of features. Finally, these selected features were fed into seven ML-based algorithms for detecting ADHD with coexisting ASD children. These classifiers were trained with leave-one-out cross-validation and evaluated their performances using accuracy, recall, precision, f1-score, and area under the curve (AUC). The experimental results showed that the highest performance scores (accuracy: 93.10%; recall: 90.48%; precision: 95.00%; f1-score: 92.68%; and AUC: 0.930) were achieved by the RF-based classifier for the PL predict task. This study will be helpful and provide evidence of the possibility of classifying ADHD children having ASD and healthy children based on their handwriting patterns.

Osteoporosis, a common skeletal disorder, necessitates the identification of its risk factors to develop effective preventive measures. It is crucial to identify the underlying risk factors and their relationships with the response class attribute. Different machine learning (ML) algorithms and feature selection approaches are used to estimate the risk of osteoporosis. However, ML-based algorithms may struggle to detect risk factors as well as grading of osteoporosis due to different measurement scale of data and their probability distributional assumptions. Violation of these assumptions and results interpretation may be improper in the presence of heteroscedasticity, or unequal variance in data. In this study, we seek to overcome distribution assumption constraints and improve the interpretability of our results by using rigorous statistical approaches, ensuring a robust and trustworthy study of osteoporosis risk variables. The study dataset consists of 40 clinical, lifestyle, and genetic attributes, allowing for a comprehensive analysis of potential risk factors associated with osteoporosis. In the analysis, after confirming the normality assumption using Kolmogorov-Smirnov and Shapiro-Wilk tests, independent t-test assess the factor ALT, FBG, HDL-C, LDL-C, FNT, TL, TLT, and URIC has a substantial impact on the risk of developing osteoporosis. The Mann-Whitney U test for the non-normal FN variable likewise showed a p-value of less than 0.05, indicating that this variable has a significant effect on the likelihood of developing osteoporosis. Based on the chi-square test p-values for the categorical factors, gender, calcium, calcitriol, bisphosphonate, calcitonin, COPD, CAD, and drinking have a severe significant risk of osteoporosis. For developing the predictive Gaussian Process (GPs) model, we proposed two customized integrated GP kernels into the analysis to enhance the modeling of complex relationships within the data. The proposed GP kernel model (modified kernel 2) outperforms the other individual kernels in this experiment and has the best accuracy score of 86.64% and AUC score of 86.63% on osteoporosis data. Moreover, a simulation study is also conducted to robustify the proposed model, the results are improved by different evaluation matrices ranging in accuracy from 0.60-11.41% and AUC from 0.50-11.60%.

Attention deficit hyperactivity disorder (ADHD) for children is one of the most common neurodevelopmental disorders and its prevalence has increased globally. Children with ADHD are faced with various difficulties, including inattention, impulsivity, and hyperactivity. Therefore, it is important to use an early detection system that is simple, non-invasive, and automated. Children with ADHD also suffer from other coexisting one or more disorders, including major depressive disorder (MDD), autism spectrum disorder (ASD), etc and it creates more challenges to detect ADHD children. Very few researchers considered such kinds of these comorbidities in their studies to detect ADHD for children. In this work, we proposed a deep learning (DL)-based algorithm to identify ADHD children with coexisting ASD. Functional near-infrared spectroscopy (fNIRs) signals from thirteen ADHD children who have coexisting ASD and fifteen typically developing (TD) children were recorded during the drawing of handwriting patterns. We asked each child to draw periodic lines (PL) and zigzag lines (ZL) under the predict and trace condition and repeated them three times. Finally, a hybrid approach was designed by combining convolutional neural networks (CNN) and bidirectional long short-time memory (Bi-LSTM) to determine children with ADHD who have ASD. The experimental results showed that our proposed hybrid approach could determine ADHD children with coexisting ASD with a classification accuracy of 94.0%, a sensitivity of 89.7%, specificity of 97.8%, f1-score of 93.3%, and AUC of 0.938, respectively, for the PL predict task.

Attention deficit hyperactivity disorder (ADHD) is one of the major psychiatric and neurodevelopment disorders worldwide. Electroencephalography (EEG) signal-based approach is very important for the early detection and classification of children with ADHD. However, diagnosing children with ADHD using full EEG channels with all features may lead to computational complexity and overfitting problems. To solve these problems, machine learning (ML)-based ADHD detection was designed by identifying optimal channels and its significant features. In this work, support vector machine and t-test based, two separate approaches were devised to select optimal channels individually and then proposed a hybrid channel selection approach by combining these two channel selection methods in order to select the optimal channels. After that, LASSO logistic regression-based model was used to select the important features from the selected channels. Finally, six ML-based classifiers, like Gaussian process classification (GPC), random forest, k-nearest neighbors, multilayer perceptron, decision tree, and logistic regression were applied for the detection of children with ADHD and evaluated their performances using accuracy and area under the curve (AUC). This study utilized a total of one hundred twenty-one children, with sixty-one children with ADHD, aged 7-12 years, and had nineteen channels. Ten different channels were selected by SVM based and an independent t-test-based approach separately and six overlapping channels were identified from both channel selection methods. Then, we selected twenty-eight features from selected six channels using LASSO. Using only six channels and twenty-eight features, GP-based classifier achieved an accuracy rate of 97.53% and AUC of 0.999. This is an improvement of 3% over previously developed techniques published in the literature. This study illustrated that LASSO with GP-based system performed outstanding performance in distinguishing children with ADHD from healthy children. This proposed system will be helpful to doctors and physicians in order to detect children with ADHD at an early stage and take the necessary steps for the patients to access appropriate healthcare services, receive effective treatment, and be more conscious of maintaining their lives.

Cumilla Sadar Dakshin region is highly diverse in respect to land types, topography, agro-ecology, land-use pattern, cropping systems and crop variability & variety. Agricultural development of the region largely depends on the reliable and comprehensive statistics of the existing cropping cultivation and its related system adopted by the farmers. To investigate the homestead vegetable production and its impact on family nutrition, food security, income generation as well as involvement of female members a survey study was conducted at Cumilla Sadar Dakshin during 2019. A total of 150 selected homesteads were surveyed for this purpose through developed questionnaire and focus group discussion. Both primary and secondary data has been collected from different sources to fulfill the objectives of the study. The results of this study indicated that the farmer’s age, marital status, education level, farm size, source of income, women participation etc. Farmer’s knowledge and farming experiences, perception and attitude differs on different demographic conditions like: age, sex, education, farm size, training which significantly influence the adoption of modern technologies provided by different organizations. The results also showed that women contribution in homestead vegetable production is high in medium farmer’s category 41.67% and low in small farmers 36.36% respectively. The highest number of total vegetables was produced by the medium farmer (63,732 kg/year) followed by small (39,445 kg/year) and marginal farmer (25,514 kg/year). This study provides some recommendation which might impacts on betterment of farmers’ occupational and socio-economic condition by establishing proper policy and legislation both in local and national level administration as well as agricultural extension.

Abstract Immunoglobulin-A-nephropathy (IgAN) is a kidney disease caused by the accumulation of IgAN deposits in the kidneys, which causes inflammation and damage to the kidney tissues. Various bioinformatics analysis-based approaches are widely used to predict novel candidate genes and pathways associated with IgAN. However, there is still some scope to clearly explore the molecular mechanisms and causes of IgAN development and progression. Therefore, the present study aimed to identify key candidate genes for IgAN using machine learning (ML) and statistics-based bioinformatics models. First, differentially expressed genes (DEGs) were identified using limma, and then enrichment analysis was performed on DEGs using DAVID. Protein-protein interaction (PPI) was constructed using STRING and Cytoscape was used to determine hub genes based on connectivity and hub modules based on MCODE scores and their associated genes from DEGs. Furthermore, ML-based algorithms, namely support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), and partial least square discriminant analysis (PLS-DA) were applied to identify the discriminative genes of IgAN from DEGs. Finally, the key candidate genes (FOS, JUN, EGR1, FOSB, and DUSP1) were identified as overlapping genes among the selected hub genes, hub module genes, and discriminative genes from SVM, LASSO, and PLS-DA, respectively which can be used for the diagnosis and treatment of IgAN.

Background and Objectives: Malnutrition among women is a major public health problem that has been linked to stunted growth, diabetes, and has adverse consequences for children, including low birth weight, less resistance to infections, and a higher risk of death. This current study presents an exhaustive comprehensive study of machine learning (ML) system which has two major objectives: (i) identification of the potential risk factors of malnourished women; and (ii) propose a better ML-based model for predicting malnourished women. Methods: About 15,464 respondents were taken from the Bangladesh Demographic and Health Survey. The potential risk factors for malnutrition were extracted using multinomial logistic regression (MLR). Five ML-based algorithms such as Naïve Bayes, support vector machine, decision tree, artificial neural network, and random forest (RF) were implemented for predicting malnourished women and evaluating their performances using accuracy and area under the curve (AUC). Results: MLR illustrates that age, region, wealth index, respondent's education, currently breastfeeding and pregnant women, marital status, toilet facility, and cooking fuel are the potential risk factors for underweight, while age, region, residence, wealth index, respondent's and husband's education, currently breastfeeding and working, children's ever-born, drinking water source, and cooking fuel for overweight/obese. Our findings show that RF-based classifier provides 81.4% accuracy and 0.837 AUC for underweight and 82.4% accuracy and 0.853 AUC for overweight/obese. Conclusion: The combination of MLR-RF-based system could accurately classify malnourished women with higher accuracy. The proposed system will be helpful in predicting which women are at high risk of malnutrition and reducing the burden of the health system.

Aims This study aimed to determine the impact of correlates on tobacco control/smoke-free status of homes and workplace among Indian people. To assess the magnitude of the problem, the relationship between smoke-free status and secondhand smoke (SHS) exposure was also explored. Methods Data was extracted from the Global Adult Tobacco Survey Data (GATS)-2017. It was a household survey that included people aged 15 years or older and covered all 30 states and 2 Union Territories (UTs) of India. A logistic regression model was used to determine the correlates of smoke-free status of homes and workplaces. Additionally, the Pearson correlation was used to explore the relationship between smoke-free status and the proportion of participants exposed to SHS both at homes and in the workplaces. Results The overall prevalence of smoke-free status in the home and workplace was 62.8% and 51.7%, respectively. Results of multivariate analysis (Logistic regression) illustrated that indicators like tobacco smoking status, place of residence, region, education, occupation, wealth quintile, and knowledge status about children’s illness were significantly associated with the respondent’s intention to live in a completely smoke-free environment both at home and in the workplace in India. This study revealed that SHS exposure was significantly negatively associated with a smoke-free status. Conclusion This study will help the policymakers to promote efficient policies for improving smoke-free status and to ensure a better environment both at home and in the workplace in India.

Water deficit is a major limiting condition for adaptation of maize in tropical environments. The aims of the current observations were to evaluate the kernel water relations for determining kernel developmental progress, rate, and duration of kernel filling, stem reserve mobilization in maize. In addition, canopy temperature, cell membrane stability, and anatomical adaptation under prolonged periods of pre- and post-anthesis water deficit in different hybrids was quantified to support observations related to kernel filling dynamics. In this context, two field experiments in two consecutive years were conducted with five levels of water regimes: control (D1), and four water deficit treatments [V10 to V13 (D2); V13 to V17 (D3); V17 to blister stage (D4); blisters to physiological maturity (D5)], on three maize hybrids (Pioneer 30B80, NK 40, and Suwan 4452) in Expt. 1. Expt. 2 had four water regimes: control (D1), three water deficit treatments [V10 to anthesis (D2); anthesis to milk stage (D3); milk to physiological maturity (D4)], and two maize hybrids (NK 40 and Suwan 4452). Water deficit imposed at different stages significantly reduced maximum kernel water content (MKWC), kernel filling duration (KFD), final kernel weight (FKW), and kernel weight ear–1 while it increased kernel water loss rate (KWLR), kernel filling rate (KFR), and stem weight depletion (SWD) across maize hybrids in both experiments. The lowest MKWC under water deficit was at D3 in both experiments, indicating that lower KFR results in lowest FKW in maize. Findings indicate that the MKWC (R2 = 0.85 and 0.41) and KFR (R2 = 0.62 and 0.37) were positively related to FKW in Expt. 1 and 2, respectively. The KFD was reduced by 5, 7, 7, and 11 days under water deficit at D3, D4 in Expt. 2 and D4, D5 in Expt. 1 as compared to control, respectively. Water deficit at D5 in Expt. 1 and D4 in Expt. 2 increased KWLR, KFR, and SWD. In Expt. 2, lower canopy temperature and electrical conductivity indicated cell membrane stability across water regimes in NK 40. Hybrid NK 40 under water deficit had significantly higher cellular adaptation by increasing the number of xylem vessel while reducing vessel diameter in leaf mid-rib and attached leaf blade. These physiological adjustments improved efficient transport of water from root to the shoot, which in addition to higher kernel water content, MKWC, KFD, KFR, and stem reserve mobilization capacity, rendered NK 40 to be better adapted to water-deficit conditions under tropical environments.

The aim of this study was to investigate and compare the effect of process variables on the color and physical characteristics of viscose and cotton knitted fabrics. The effect of dye concentration, salt concentration, soda ash, dyeing time, dyeing temperature, material to liquor ratio, different dye class, fabric GSM, washing time, washing temperature, and enzyme concentration were investigated in terms of color strength (K/S value), color fastness, and pilling resistance. The K/S value of the colored fabric was calculated using UV visible spectrophotometer SF 650 TM and the pilling resistance of the enzyme-treated fabrics was tested by an ICI pilling tester. The results show that dye concentration has the greatest and key effect on the K/S value of viscose and cotton fabric. However, viscose fabric shows a higher K/S value than that of cotton fabric in similar dyeing conditions. Furthermore, the multi-functional dyes demonstrate the upmost K/S value than the vinyl sulphone dyes. Moreover, it was found that enzymatic treatment improved the pilling grade of cotton fabric, whereas no enzymatic effect on viscose fabric was observed.

Writer identification has become a hot research topic in the fields of pattern recognition, forensic document analysis, the criminal justice system, etc. The goal of this research is to propose an efficient approach for writer identification based on online handwritten Kanji characters. We collected 47,520 samples from 33 people who wrote 72 online handwritten-based Kanji characters 20 times. We extracted features from the handwriting data and proposed a support vector machine (SVM)-based classifier for writer identification. We also conducted experiments to see how the accuracy changes with feature selection and parameter tuning. Both text-dependent and text-independent writer identification were studied in this work. In the case of text-dependent writer identification, we obtained the accuracy of each Kanji character separately. We then studied the text-independent case by considering some of the top discriminative characters from the text-dependent case. Finally, another text-dependent experiment was performed by taking two, three, and four Kanji characters instead of using only one character. The experimental results illustrated that SVM provided the highest identification accuracy of 99.0% for the text-independent case and 99.6% for text-dependent writer identification. We hope that this study will be helpful for writer identification using online handwritten Kanji characters.

Effective coverage of antenatal iron and folic acid (IFA) supplementation is important to prevent adverse maternal and newborn health outcomes. We interviewed 2572 women from two rural districts in Bangladesh who had a live birth in the preceding six months. We analysed the number of IFA tablets received and consumed during pregnancy and examined the factors influencing IFA consumption by multiple linear regression and user adherence-adjusted effective coverage of IFA (consuming ≥180 IFA tablets) by Poisson regression. Overall, about 80% of women consumed IFA supplements in any quantity. About 76% of women received antenatal care at least once, only 8% received ≥180 IFA tablets, and 6% had user adherence-adjusted coverage of antenatal IFA supplementation. Multivariable analysis showed a linear relationship between the number of antenatal care (ANC) visits and the number of IFA supplements consumed, which was modified by the timing of the first ANC visit. Women’s education, free IFA, and advice on IFA were also associated with higher IFA consumption. Interventions targeting at least eight ANC contacts, starting early in pregnancy, providing advice on the importance of IFA, and providing IFA supplements in higher quantity at ANC contacts are likely to increase effective coverage of antenatal IFA supplementation.

The classification of different age groups, such as adult and child, based on handwriting is very important due to its various applications in many different fields. In forensics, handwriting classification helps investigators focus on a certain category of writers. This paper aimed to propose a machine-learning (ML)-based approach for automatically classifying people as adults or children based on their handwritten data. This study utilized two types of handwritten databases: handwritten text and handwritten pattern, which were collected using a pen tablet. The handwritten text database had 57 subjects (adult: 26 vs. child: 31). Each subject (adult or child) wrote the same 30 words using Japanese hiragana characters. The handwritten pattern database had 81 subjects (adult: 42 and child: 39). Each subject (adult or child) drew four different lines as zigzag lines (trace condition and predict condition), and periodic lines (trace condition and predict condition) and repeated these line tasks three times. Handwriting classification of adult and child is performed in three steps: (i) feature extraction; (ii) feature selection; and (iii) classification. We extracted 30 features from both handwritten text and handwritten pattern datasets. The most efficient features were selected using sequential forward floating selection (SFFS) method and the optimal parameters were selected. Then two ML-based approaches, namely, support vector machine (SVM) and random forest (RF) were applied to classify adult and child. Our findings showed that RF produced up to 93.5% accuracy for handwritten text and 89.8% accuracy for handwritten pattern databases. We hope that this study will provide the evidence of the possibility of classifying adult and child based on handwriting text and handwriting pattern data.

Decomposed organic materials, in combination with plant growth-promoting bacteria (PGPB), are environmentally friendly and reduce synthetic fertilizer use in rice production. A bio-organic fertilizer (BoF) was prepared using kitchen waste (79%), chita-dhan (unfilled rice grain) biochar (15%), rock phosphate (5%), and a consortium of 10 PGPB (1%) to supplement 30% nitrogen and to replace triple superphosphate (TSP) fertilizer in rice production with an improvement of soil health. PGPB were local isolates and identified using 16S ribosomal RNA partial gene sequences as Bacillus mycoides, Proteus sp., Bacillus cereus, Bacillus subtilis, Bacillus pumilus, Paenibacillus polymyxa, and Paenibacillus spp. Isolates could fix N2 by 0.7–1.4 g kg–1, solubilize 0.1–1.2 g kg–1 phosphate, and produce 0.1–40 g kg–1 indoleacetic acid. The performance of BoF was evaluated by 16 field experiments and 18 farmers’ field demonstration trials during the year 2017–2020 in different parts of Bangladesh. Performances of BoF were evaluated based on control (T1), full synthetic fertilizer dose of N, P, and K (T2), BoF (2 t ha–1) + 70% N as urea + 100% K as muriate of potash (T3), 70% N as urea + 100% P as TSP + 100% K as muriate of potash (T4), and 2 t ha–1 BoF (T5) treatments. At the research station, average grain yield improved by 10–13% in T3 compared with T2 treatment. Depending on seasons, higher agronomic N use efficiency (19–30%), physiological N use efficiency (8–18%), partial factor productivity (PFP)N (114–150%), recovery efficiency (RE)N (3–31%), N harvest index (HIN) (14–24%), agronomic P use efficiency (22–25%), partial factor productivity of P (9–12%), AREP (15–23%), and HIP (3–6%) were obtained in T3 compared with T2 treatment. Research results were reflected in farmers’ field, and significant (P < 0.05) higher plant height, tiller, panicle, grain yield, partial factor productivity of N and P were obtained in the same treatment. Application of BoF improved soil organic carbon by 6–13%, along with an increased number of PGPB as compared with full synthetic fertilizer dose. In conclusion, tested BoF can be considered as a green technology to reduce 30% synthetic N and 100% TSP requirements in rice production with improved soil health.

Social scientists around the world commonly use the Likert scale. The scale has some limitations; in many cases, researchers are ignoring those limitations. Many social scientists have been trying to find out an alternative, but all initiatives do not correctly solve the problems. Among all limitations, the most critical issue is that Likert scale adopts a similar variance between two successive scale points. Fuzzy-Likert scale is a useful alternative for solving the existing limitation of the traditional Likert scale. Therefore, the current article describes the limitations of existing Likert scale and application of Fuzzy-Likert scale in perceived risk assessment. Naturally, risks are interrelated with different factors. Assessing risks with simple existing Likert scale is not entirely appropriate. A well-structured Fuzzy-Likert scale can be used to mitigate the existing problems. This article clarifies how efficiently researchers can use a Fuzzy-Likert scale for assessing the perceived risk in agriculture using a simple structured questionnaire with the help of an example. To reach the conclusions and recommendations, the researchers used different published articles, online repositories, report etc. through content analysis.

In the changing climatic condition, temperature is the most vulnerable parameter and is projecting a trend of increase in the future. Crop growth and development process depend largely on air temperature. This study aims to determine the role of increasing air temperature in yield, crop water requirement (CWR), and other agronomic parameters of irrigated rice. Ceres-rice model associated in the Decision Support System for Agrotechnology Transfer (DSSAT) was used in 15 different locations of Bangladesh. Grain yield, growth duration, and crop water requirement of widely cultivated irrigated rice (Boro rice) variety BRRI dhan28 were analysed in normal temperature and elevated air temperature by 1°C, 2°C, 3°C, and 4°C. The result revealed detrimental effect of elevated temperature on growth duration and grain yield. The estimated highest growth duration reduction of 30 days was found in Moulvibazar for 4°C temperature rise. The grain yield reduction was projected by 0–17%, 16–35%, 31–49%, and 39–61% from the normal condition if the seasonal mean temperature increased by 1°C, 2°C, 3°C, and 4°C, respectively. The country average crop water requirement was found to be 405 mm of which the highest 445 mm and the lowest 358 mm were recorded in Moulvibazar and Chandpur, respectively. The study revealed that the country average rice CWR reduced by 5%, 8%, 12%, and 17% over the normal condition for 1°C, 2°C, 3°C, and 4°C rising temperature, respectively. For 1°C temperature rise, BRRI dhan28 life span shortened by 6.4 days, grain yield reduced by 695 kg, and estimated CWR decreased by 14 mm. The projected declining CWR indicated that irrigated rice will require less irrigation water, but it will cause considerable yield loss under elevated temperature. Though elevated temperature will save huge irrigation water used in country-wide Boro rice cultivation, the crop developers need to introduce new heat-tolerant cultivar to minimize yield loss.

Attention deficit hyperactivity disorder (ADHD) is one of childhood’s most frequent neurobehavioral disorders. The purpose of this study is to: (i) extract the most prominent risk factors for children with ADHD; and (ii) propose a machine learning (ML)-based approach to classify children as either having ADHD or healthy. We extracted the data of 45,779 children aged 3–17 years from the 2018–2019 National Survey of Children’s Health (NSCH, 2018–2019). About 5218 (11.4%) of children were ADHD, and the rest of the children were healthy. Since the class label is highly imbalanced, we adopted a combination of oversampling and undersampling approaches to make a balanced class label. We adopted logistic regression (LR) to extract the significant factors for children with ADHD based on p-values (

Potassium (K) is an essential plant nutrient affecting most of the biochemical and physiological processes. It is classified as a macronutrient due to large quantities being taken up by plants during their life cycle. With the aim of establishing a scientific basis of K fertilization on the growth, leaf production, minimum K requirement and critical leaf K concentration of stevia, a pot experiment was carried out in the net house of the Department of Agricultural Chemistry, Bangladesh Agricultural University. Six levels of K viz. 0 (K0), 50 (K50), 100 (K100), 150 (K150), 200 (K200) and 250 (K250) kg ha-1 were used in acid and non-calcareous soils. Plants were harvested at 60 days after planting (DAP). Results showed that K application significantly influenced the growth attributes, leaf yield and other parameters. Highest values of all the parameters except K content were obtained when K was applied @ 200 kg ha-1 which was significantly different from other levels of K including control. Dry weight of stevia leaves at harvest was increased from 0.77-7.41g and 0.99-7.74g Pot-1 in acid and non-calcareous soils, respectively over control. Potassium content was directly proportional with the increased levels of K though uptake did not follow the same trend. Leaf critical K content was estimated to be ca 1.75 and 1.71% in the plants grown in acid and non-calcareous soils, respectively. The minimum K requirement for maximum leaf biomass production (80%) of stevia was estimated to be ca 220 and 199 kg ha-1 grown in acid and non-calcareous soils, respectively. This study would contribute to improve K fertilization of stevia in various types of soil. [Fundam Appl Agric 2017; 2(3.000): 297-302]

Abstract Purpose Information on carbon dioxide (CO2) emission from different organic sources and their temperature sensitivity to decomposition is scarce in Bangladesh. Therefore, this study quantified the rates of CO2 emission and carbon (C) degradation constants from different organic material mixed soils at variable temperatures in two laboratory experiments. Methods The first experiment was conducted at room temperature for 26 weeks to study CO2 emission and C mineralization using vermicompost, chicken manure, cow dung, rice straw, and rice husk biochar. Weekly CO2 emission was measured by alkali absorption followed by acid titration. The second experiment comprised two factors, viz. four organic materials (vermicompost, chicken manure, cow dung, and rice straw) and six temperature regimes (25, 30, 35, 40, 45, and 50 °C). Organic materials at 2.5 g C kg−1 soil were mixed in both experiments. Results CO2 emission reached the peak at 5th weeks of incubation and then decreased with irregular fashion until 21st week. The C emission loss followed in the order of chicken manure > rice straw > vermicompost > cow dung > rice husk biochar, and C degradation constants indicated the slower decomposition of rice husk biochar compared to cow dung, vermicompost, chicken manure, and rice straw. Temperature positively enhanced the mineralization of organic materials in the order of 50 > 45 > 40 > 35 > 30 > 25 °C, which contributed to higher availability of soil phosphorus. Conclusions High temperature increased mineralization of tested organic materials. Because of slower decomposition rice husk biochar, cow dung and vermicompost application can be considered as climate-smart soil management practices that might help in reducing CO2 emission from soil.

Brown planthopper (BPH; Nilaparvata lugens Stål) is one of the most serious insect pests, which reduce rice yield remarkably in many rice-growing areas. A few plant growth-promoting rhizobacteria induce systemic resistance against herbivorous insects. Here we show that root drenching of rice seedlings with an endophytic strain Bacillus velezensis YC7010 enhanced defenses against BPH. Based on high-throughput transcriptome analysis, systemic resistance against BPH was induced by B. velezensis YC7010 via salicylic acid (SA)- and jasmonic acid (JA)-dependent pathways. Increased leaf contents of secondary metabolites, tricin and C-glycosyl flavone and cell-wall contents of lignin and cellulose were the key defense mechanisms inducing resistance against BPH during the three-way interaction. This study shows for the first time that chemical changes and strengthening of physical barriers play important roles simultaneously in plant defense against BPH in rice by the endophytic bacteria. This defense was induced by lipopeptides including a novel bacillopeptin X.

While recent advances in next-generation sequencing technologies have accelerated research in microbial ecology, the application of high throughput approaches to study the ecology of nematodes remains unresolved due to several issues, e.g., whether to include an initial nematode extraction step or not, the lack of consensus on the best performing primer combination, and the absence of a curated nematode reference database. The objective of this method development study was to compare different primer sets to identify the most suitable primer set for the metabarcoding of nematodes without initial nematode extraction. We tested four primer sets for amplicon sequencing: JB3/JB5 (mitochondrial, I3-M11 partition of COI gene), SSU_04F/SSU_22R (18S rRNA, V1-V2 regions), and Nemf/18Sr2b (18S rRNA, V6-V8 regions) from earlier studies, as well as MMSF/MMSR (18S rRNA, V4-V5 regions), a newly developed primer set. We used DNA from 22 nematode taxa, 10 mock communities, 20 soil samples, 4 root samples, and one bulk soil. We amplified the target regions from the DNA samples with the four different primer combinations and sequenced the amplicons on an Illumina MiSeq sequencing platform. We found that the Nemf/18Sr2b primer set was superior for detecting soil nematodes compared to the other primer sets based on our sequencing results and on the annotation of our sequence reads at the genus and species ranks. This primer set generated 74% reads of Nematoda origin in the soil samples. Additionally, this primer set did well with the mock communities, detecting all the included specimens. It also worked better in the root samples than the other primer set that was tested. Therefore, we suggest that the Nemf/18Sr2b primer set could be used to study rhizosphere soil and root associated nematodes, and this can be done without an initial nematode extraction step.

About 1.0 million ha coastal lands in Bangladesh are mono-cropped suffer from varying degree of soil salinity, waterlogging and climate vulnerability. Low yielding, traditional T. Aman rice is grown only in wet season. Growing non-rice crop after late harvested T. Aman rice is not profitable. This study was aimed to introduce high yielding, short duration T. Aman rice varieties for advancing its harvesting time and to make the avenue for timely establishment of dry season crops. Varietal trials were made at Dacope and Amtali under ACIAR funded project during 2016-2018 and compared with local cultivars. Among tested varieties BRRI dhan76 followed by BRRI dhan77 and BRRI dhan54 in Dacope and BRRI dhan77 followed by BRRI dhan76 and BRRI dhan54 in Amtali were preferred for 0.5−1.0 tha−1 yield advantage and 15−25 days earliness compared to traditional varieties. Early harvesting of T. Aman created the avenue of timely establishment of rice and non-rice crops depending on availability of fresh water and thus crop intensification and land productivity was improved. The new cropping system increased annual rice yield and farmers’ profits by 1.5- to 2-folds compared with traditional system without environmental degradation. This technique can be replicated in similar coastal zones of Bangladesh.

Rice production takes a leading role in the agricultural sector of Bangladesh contributing to 35% of the gross value added of total agricultural production (December 2011), employing 48% of the rural workforce. While the country achieved self-sufficiency in rice, continuous population growth requires Bangladesh to further increase the production of this staple cereal. However, considering the steady decline of the cropped area and available rural workforce, such increase could be reached by increasing the efficiency in rice production. This study aims to examine the resource use efficiency and its drivers in the performance of rice farms in the Northwest region of Bangladesh, which is considered as the food bowl of the country. The study applied a two-stage approach of Data Envelopment Analysis followed by Ordinary Least Squares to estimate the impact of contextual variables on rice production. The empirical research results show that 83% of rice farms among the sample of 184 farms are efficient being located on efficiency frontier, while the 2% farms are inefficient and could improve their efficiency. The remaining 15% of farms are at level that is close to the efficiency frontier. Such factors as the cost of irrigation, pest control, and crop harvesting and carrying are the main drivers of efficiency amongst the considered rice farms.

Background and objectiveLow birth weight is one of the primary causes of child mortality and several diseases of future life in developing countries, especially in Southern Asia. The main objective of this study is to determine the risk factors of low birth weight and predict low birth weight babies based on machine learning algorithms.Materials and methodsLow birth weight data has been taken from the Bangladesh Demographic and Health Survey, 2017-18, which had 2351 respondents. The risk factors associated with low birth weight were investigated using binary logistic regression. Two machine learning-based classifiers (logistic regression and decision tree) were adopted to characterize and predict low birth weight. The model performances were evaluated by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve.ResultsThe average percentage of low birth weight in Bangladesh was 16.2%. The respondent's region, education, wealth index, height, twin child, and alive child were statistically significant risk factors for low birth weight babies. The logistic regression-based classifier performed 87.6% accuracy and 0.59 area under the curve for holdout (90:10) cross-validation, whereas the decision tree performed 85.4% accuracy and 0.55 area under the curve.ConclusionsLogistic regression-based classifier provided the most accurate classification of low birth weight babies and has the highest accuracy. This study's findings indicate the necessity for an efficient, cost-effective, and integrated complementary approach to reduce and correctly predict low birth weight babies in Bangladesh.