JOURNAL PAPER

Firoj Al-Mamun, Al Mamun Abdullah, Moneerah Mohammad ALmerab, Md. Al Mamun & Mohammed A. Mamun, Prevalence and factors associated with depression and anxiety among the Bangladeshi university entrance test-taking students using GIS technology, Scientific Reports 14, 21590, 2024. doi: 10.1038/s41598-024-72235-z

This study focuses on Bangladeshi university entrance test-taking students' mental health problems and explores the geographical distribution of these problems using the GIS technique. A cross-sectional survey was conducted among 1523 university entrance test-taking students. Data were collected on participants' socio-demographic characteristics, COVID-19-related factors, admission tests, depression, and anxiety. Chi-square tests and logistic regression were performed using SPSS software. GIS mapping was used to visualize the distribution of mental health problems across districts using ArcGIS. The study found that the prevalence rates of depression and anxiety among university entrance examinees were 53.8% and 33.2%, respectively. Males exhibited higher rates of depression and anxiety compared to females, while repeat test-taking students were more susceptible to these mental health issues compared to first-time test-takers. Factors such as urban residence, personal/familial COVID-19 infections, and COVID-19 deaths in close relationships were associated with increased mental health problems. District-based distribution showed no significant variation in depression, but anxiety varied significantly. Post-hoc GIS analysis revealed variations in the distribution of depression and anxiety among males, as well as variations in anxiety distribution based on student status across districts. This study emphasizes the high prevalence of depression and anxiety among university entrance examinees, emphasizing the importance of addressing mental health risks in this population. It also suggests the need for university entrance test-taking system reforms to reduce psychological problems and advocates for a more inclusive approach to student admissions to alleviate mental health burdens.

Abu Bakkar Siddique , Md. Shohag Hosen , Hasna Akter , Syed Mujakkir Hossain and Md. Al Mamun, Assessment of knowledge, attitudes, and practices regarding cardiovascular diseases (CVDs) among older individuals of rural Bangladesh: findings from a face-to-face interview, Frontiers in Public Health, 12, pp.1-14, 2024. doi: ttps://doi.org/10.3389/fpubh.2024.1336531

Cardiovascular diseases (CVDs) stand as the foremost contributor to global mortality, claiming roughly 17.9 million lives each year, constituting 32.1% of total fatalities. Their impact is notably profound in economies such as Bangladesh, exacting a substantial economic burden. Consequently, grasping the landscape of knowledge, attitudes, and practices is essential for timely identification and prevention strategies. This cross-sectional study, carried out between January and May 2023 in the rural regions of Zirani, Savar Upazila, Dhaka, Bangladesh, utilized convenient sampling and conducted face-to-face interviews using a semistructured questionnaire. It encompassed socio-demographic factors, as well as knowledge, attitudes, and practices concerning CVDs. Data analysis employed descriptive statistics, chi-square tests, and regression analyses, utilizing both the R programming language and SPSS

Rifat Nahrin; Firoj Al-Mamun; Mark Mohan Kaggwa; Md. Al Mamun; Mohammed A. Mamun, Prevalence and factors associated with suicidal ideation among students taking university entrance tests: revisited and a study based on Geographic Information System data, BJPsych Open, 9, 4, pp.1-12, 2023. doi: 10.1192/bjo.2023.526

The study revealed a prevalence of 14.4% for past-year suicidal ideation, with 7.4% and 7.2% reporting suicide plans and attempts, respectively. Notably, repeat test-takers exhibited a higher prevalence of suicidal behaviours. Significant risk factors for suicidal ideation included urban residence, smoking, drug use, COVID-19 infection and deaths among close relations, depression, anxiety and burnout. The GIS-based distribution indicated significant variation in the prevalence of suicidal ideation across different districts, with higher rates observed in economically and infrastructurally deprived areas.

Mostafiz AHmed, Md. Al Mamun and Mohammad Shorif Uddin, A machine learning approach for skin disease detection and classification using image segmentation, Healthcare Analytics, 2, pp.100122, 2022. doi: https://doi.org/10.1016/j.health.2022.100122

Skin diseases are common health problems around the world. The perils of the infections are invisible, which cause physical health distress as well as initiate mental depression. In addition, it sometimes leads to skin cancer in severe cases. Subsequently, diagnosing skin diseases from clinical images is one of the foremost challenging tasks in medical image analysis. Moreover, when performed manually by medical experts, diagnosing skin diseases is time-intensive and subjective. As a result, both patients and dermatologists require automatic skin disease prediction, which makes the treatments plan faster. In this work, we introduce a digital hair removal technique based on morphological filtering such as Black-Hat transformation and inpainting algorithm and then apply Gaussian filtering to de-blur or denoise the images. In addition, we apply the automatic Grabcut segmentation technique to segment out the affected lesions. For extracting underlying input patterns from the skin images, we apply the Gray Level Co-occurrence Matrix (GLCM) and statistical features techniques. Three computationally efficient machine learning techniques, Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) classifiers are applied using the extracted features for effectively classifying the skin images as melanoma (MEL), melanocytic nevus (NV), basal cell carcinoma (BCC), actinic keratosis (AK), benign keratosis (BKL), dermatofibroma (DF), vascular lesion (VASC), and  Squamous cell carcinoma (SCC). The models are validated using two standard datasets ISIC 2019 challenge and HAM10000. SVM performs slightly better than the other two classifiers. We have also compared our work with state-of-the-art methods.

Md. Al Mamun, Md. Solaiman Kabir, Morium Akter and Mohammad Shorif Uddin, Recognition of human skin diseases using inception-V3 with transfer learning, International Journal of Information and Technology, 14, pp.3145-3154, 2022. doi: http://dx.doi.org/10.1007/s41870-022-01050-4

Skin disease is an irritable disease and may be the motive of deadly to human life. So, all of us ought to be aware of this alarming health problem. Recognition of skin diseases is a very challenging task because of its various characteristics. To avoid delay in treatment, in this paper, five most common skin diseases: Vascular lesion, Solar lentigo, Actinic keratosis, Squamous cell carcinoma, and Basal cell carcinoma have been investigated through the Inception-V3 with and without transfer learning. An extensive experiment is performed, and the model’s effectiveness is tested through standard metrics such as accuracy, F1 score, and AUC of the Receiver Operating Characteristics (ROC) curve. Inception-V3 with transfer learning has achieved the highest test accuracy of 98.16%. The obtained results are also compared with the state-of-the-art approaches.

Md. Al Mamun and Mohammad Shorif Uddin, Hybrid Methodologies for Segmentation and Classification of Skin Diseases: A Study, Journal of Computer and Communications(JCC), 9, 4, pp.67-84, 2021. doi: 10.4236/jcc.2021.94005

Skin disorders are a serious global health problem for humans. These disorders become dangerous when they grow into the malignant stage. Hence, it is necessary to detect these diseases at their early stage. A mobile-based automated skin disease detection system is vital for detecting skin diseases. This system also offers cure or treatment plans to the affected person through the short message service (SMS) or electronic mail (e-mail). An effective skin disease detection system consists of three processes: segmentation, feature extraction, and classification. Several hybrid methodologies are already developed for the above-mentioned processes for detecting skin diseases at the initial stage. This research gives a standard hybrid framework for detecting skin diseases and highlights some design requirements for achieving high accuracy. Existing state-of-the-art hybrid methods of three processes for detecting skin diseases along with their limitations are also summarized. It also identifies the challenges for developing an effective skin disease detection system and gives future research directions.

Md. Al Mamun and Mohammad Shorif Uddin, A Survey on Matching of Shoeprint with Reference Footwear in Forensic Study, Journal of Computer and Communications(JCC), 7, 9, pp.19-26, 2019. doi: DOI: 10.4236/jcc.2019.79002

Footwear impression marks on the outside surface of shoes are distinctive patterns and an important forensic clue often found at offense scenes. However, in many cases, the footwear mark is treated with improper evidence due to difficulties in visibility and understanding. This paper presents a thorough review of matching algorithms along with enhancement techniques of shoeprint in the forensic study. Finally, it shows some research directions.

Md. Al Mamun and Md. Humayun Kabir, Performance improvement techniques for customized data warehouse, IOSR Journal of Computer Engineering (IOSR-JCE), 9, 3, pp.1-5, 2013. doi: 10.9790/0661-0930105

In this paper, we present performance improvement techniques for data retrieval from customized data warehouses for efficient querying and Online Analytical Processing (OLAP) in relation to efficient database and memory management. Different database management techniques, e.g. indexing, partitioning etc. play vital role in efficient memory management. A comparison of data retrieval time for a particular query from a relational database as well as data warehouse database with and without indexing is performed. We show that the application of different database management techniques result faster query execution by reducing data retrieval time. This improved efficiency may increase the efficiency of OLAP operations, which results better data warehouse performance.

Md. Al Mamun and Mohammad Shorif Uddin, A Survey on a Skin Disease Detection System, International Journal of Healthcare Information Systems and Informatics, 16, 4, pp.17, 2021. doi: https://doi.org/10.4018/IJHISI.20211001.oa35

Skin diseases are frequent and quite perennial in the world, and in some cases, these lead to cancer. These are curable if detected earlier and treated appropriately. An automated image-based detection system consisting of four main modules—image enhancement, region of interest segmentation, feature extraction, and detection—can facilitate early identification of these diseases. Diverse image-based methods incorporating machine learning techniques are developed to diagnose different types of skin diseases. This article focuses on the review of the tools and techniques used in the diagnosis of 28 common skin diseases. Furthermore, it has discussed the available image databases and the evaluation metrics for the performance analysis of various diagnosis systems. This is vital for figuring out the implementation framework as well as the efficacy of the diagnosis methods for the neophyte. Based on the performance accuracy, the state-of-the-art method for the diagnosis of a particular disease is figured out. It also highlights challenges and shows future research directions.

Mohammed A. Mamun , Md. Al Mamun, Ismail Hosen, Tanvir Ahmed, Istihak Rayhan , Firoj al-Mamun and Md. Al Mamun, Trend and gender-based association of the Bangladeshi student suicide during the COVID-19 pandemic: a GIS-based nationwide distribution, International Journal of Social Psychiatry, pp.1-9, 2021. doi: 10.1177/00207640211065670

Background: Students are one of the most vulnerable groups to suicide. Before the COVID-19 pandemic, a Bangladeshi study was conducted assessing their suicide patterns regarding gender-based associations. But how has the pandemic changed the Bangladeshi students’ suicide patterns is not studied yet, which is investigated herein. Besides, for the first time, this study provides GIS-based distribution of suicide cases across the country’s administrative district.

Methods: As Bangladesh has no suicide surveillance system, this study utilized media reporting suicide cases following the prior studies. A total of 127 students’ suicide cases from March 2020 to March 2021 were finally analyzed after eliminating the duplicate ones, and data were synthesized following the prior studies. Arc-GIS was also used to distribute the suicide cases across the administrative district.

Results: Results revealed that female (72.4%; n = 92/127) was more prone to die by suicide than males. About 42.5%

of the cases were aged between 14 and 18 years (mean age 16.44 ± 3.512 years). The most common method of suicide was hanging (79.5%; n = 101), whereas relationship complexities (15.7%), being emotional (12.6%), not getting the desired one (11%), conflict with a family member (9.4%), academic failure (9.4%), mental health problem (8.7%), sexual complexities (6.3%), scolded or forbidden by parents (3.9%) were the prominent suicide causalities. In respect to gender and suicide patterns, only the suicide stressor was significantly distributed, whereas the method of suicide was significantly associated with GIS-based distribution. However, a higher number of suicide cases was documented in the capital (i.e. Dhaka) and the northern region than in its surrounding districts.

Conclusions: The findings reported herein are assumed to be helpful to identify the gender-based suicide patterns and suicide-prone regions in the time of the COVID-19 pandemic to initiate suicide prevention programs of the risky students.

---

CONFERENCE PAPER

Md. Nasirul Haque, MST. Kamrun Nahar Sorna, Md. Al Mamun and Md. Mirazul Islam, A Study on Food Consumption Patterns and Behavior and Related Diseases Among University Students, 5th International Conference on Mechanical Industrial and Materials Engineering, pp.1-6, Rajshahi University of Engineering Technology (RUET), 2022. doi: 978-984-35-3467-5

Health is wealth and a healthy nation can gain development very quickly. To maintain a healthy life, it is essential to take a balanced diet and proper nutritional intake during growing adulthood. Thus, university students are spending very essential time entire their growing period. The aim of the study is to investigate eating behavior, diet pattern and related health issues among university students. This study employed 251 students of Jahangirnagar University. Data of 251 students were collected based on socio-demographic status, knowledge and eating behavior, and pattern of food consumption and related diseases. To analyze the study, the regression and chi-square test was performed using spss. The result suggested that A very good number of participants practice eating meals and nutritional knowledge in a balanced diet. Associated factors of diet portions and eating meals are significantly associated with health problems the students face (p-value= 0.000<0.05). Finding suggests increasing diet and nutritional knowledge and practices among the students to meet healthy manpower in the future.

Md. Al Mamun, A Comparative Study among Segmentation Techniques for Skin Disease Detection System, 2nd International Conference on Trends in Computational and Cognitive Engineering 2020 (TCCE-2020), IIT, Jahangirnagar University, 2020. doi: 10.1007/978-981-33-4673-4_14)

Skin disorders are serious health problems for people. An automatic mobile-oriented skin disease detection system with offline or online is extremely essential for detecting skin diseases and serving patient treatment plans. For any image-based detection as well as recognition task useful features are playing important role. But extraction of essential features is seriously dependent on the segmentation of disease affected region, which ultimately hampers the detection accuracy sensitivity and specificity. In this paper, we have described a comparative study on various segmentation algorithms that are applied to extract the lesion part from the skin images for detecting diseases. The methods are evaluated based on both qualitative and quantitative perspectives. Besides, we have pointed out the challenges and show future directions.

Md. Nasirul Haque, MST. Kamrun Nahar Sorna, Md. Al Mamun and Md. Mirazul Islam, Knowledge and Behavior of Using Tele-health among University Students of Bangladesh: A Cross-sectional Study, 5th International Conference on Mechanical Industrial and Materials Engineering, pp.1-6, Rajshahi University of Engineering Technology (RUET), 2022. doi: 978-984-35-3467-5

Nowadays, students are friendlier with communication technologies. Students are the habitat of socialization and feel comfortable reaching each other through digital media. Telemedicine presents the convenience to amplify students' access to healthcare services easily. This study aims to investigate knowledge about Tele-health and using its behavior of it among university students. This study employed on 248 students from different universities. Data of 248 students were collected based on socio-demographic status, knowledge, and behavior of using Tele-health among them. The related analytical test was performed using spss for the significant relation of associated  factors. Results suggested that 65.7% of participants know the Tele-health word. and 56% of the respondent is a response that they are taking health care through Tele-health. This study finds associated factors of using Tele-health behavior are gender, institutions, educational background, and academic year. The study findings suggest increasing information about Tele-health among the students of the educational sector will raise knowledge about the utilization of telemedicine and help meet health care want easily.

---