Browsing by Author "Akter, Sharmin"

Now showing 1 - 20 of 42

A Comprehensive Review of Predictive Analytics Models for Mental Illness Using Machine Learning Algorithms
(Elsevier, 2024-06-17) Islam, Md. Monirul; Hassan, Shahriar; Hassan, Shahriar; Akter, Sharmin; Jibon, Ferdaus Anam; Sahidullah, Md.
Our emotional, psychological, and social well-being are all parts of our mental health, influencing our thoughts, emotions, and behaviors. Mental health also influences how we respond to stress, interact with others, and make good or bad decisions. There has been growing interest in the use of machine learning for the early detection of mental illness. This study reviews the machine learning models, algorithms, and applications for the early detection of mental disease, particularly emphasizing the data modalities. We further propose a comprehensive methodology for assessing mental health that synergistically combines social media monitoring, data analytics from wearable devices, verbal polls, and individualized support. We provide an overview of the field’s current state, highlight the potential benefits and challenges of using machine learning in mental health care, and a new taxonomy of mental disorders issues based on five domains of data types. We review existing research on using machine learning to detect and treat mental illness and discuss the implications for future research. Finally, the value of this work lies in its potential to provide a fast and accurate method for predicting the mental health status of a person, which may assist in the diagnosis and treatment of mental illness.
A Study of Environmental Degradation in Tahmima Anam’s The Bones of Grace
(Daffodil International University, 23-06-05) Akter, Sharmin
Tahmima Anam’s The Bones of Grace is one of the novels from her Bengali tri-series, including A Golden Age and The Good Muslim. The story gives us a strong image of the developing countries crisis of developing countries like Bangladesh and Pakistan. The protagonist Zubeda is a paleontologist who travels to different countries; not only Zubeda but also most of the characters in this novel keeps traveling, some are searching for work, and others are searching for love. The village that is the birthplace of Zubaida and Anwar is a perfect example of those places that were destroyed during the ecological crisis of environmental degradation. The writer shows how Lobonchora village ecology was damaged, people cannot cultivate the lands, and no crops were growing due to drought. On the other hand, during monsoon, the village area gets flooded. And the same picture we can see in the novel of Chittagong city in Bangladesh. As a result of industrialization, the city area is being polluted, seawater and animals are in danger “a place where people tore ships apart and whales died in swimming pools and tides threw up the trash of the entire world” (Anam 273). Because of flood and drought, Anwar, Ali, and Mohammad, migrate from the village to Chittagong in search of work. Before going to Chittagong, Anwar also tries his luck in Dubai because harvesting is difficult in the village for the lack of water. Therefore, this study also attempts to discover how the ecological crisis is becoming a cause of migration and environmental destruction. Through the lens of ecocriticism, this paper is trying to show how the characters are forced to leave their homeland due to environmental crises and unplanned industrialization and the impact of these on the life of the characters. Keywords: The Bones of Grace, Migration, Industrialization, Ecological Crisis, Environmental Degradation, Anthropocene, Climate Change.
A study on experiences & challenges of mothers of children with autism in Dhaka city
(University of Dhaka, 2014-04-24) Akter, Sharmin
Autism Spectrum Disorders (ASDs), also referred to as Pervasive Developmental Disorders (PDDs), are characterized by deficits in verbal and nonverbal communication, social interaction, and repetitive or restricted interests and behaviors. To date, much of the literature on ASDs has been conducted from a western perspective, although interest in ASDs from a global perspective has dramatically increased in recent years. In Bangladesh just a few years back, people were merely aware about disability with Autism. Although a few researches on ASDs have been conducted in Bangladesh, interest in ASDs from a global perspective has dramatically increased in recent years. However, no research has been conducted in this area. The nature of qualitative methodology makes it best suited for capturing the nuances and complexity of the psychological phenomenon underlying the experiences being studied. These experiences help to capture and reflect the ways in which culture impacts these experiences. The purpose of this study was to examine the lived experiences and challenges of mothers raising children diagnosed with an ASD in Dhaka City using a qualitative research approach. The prevalence is currently rising in many countries around the world. Caring for and educating children and young people with this condition places challenges on health care, education and training programmers. The government is going to count the number of autistic children in Bangladesh. About 10% of Bangladesh's people are challenged of those, 1% is estimated to be autistic, amounting to around 1.5 lakh people. Many children diagnosed with ASDs in our country have very limited access to educational settings, and an abundance of barriers to treatment exist. As such, there is much to be gained from studying mothers’ experiences with their child’s early development and their initial concerns for their child’s development, their experiences with the diagnostic process, the perceived impact of raising a child on the spectrum for themselves and their family, their daily living experiences, their experiences accessing supports and services, their vision for the future, as well as any advice they would give to mothers of children who were recently diagnosed. To this end, the experiences of 20 mothers raising a child diagnosed with an ASD and living in Dhaka City were captured through open-ended interviews in this study.
Advancing Thyroid Care: An Accurate Trustworthy Diagnostics System with Interpretable Ai and Hybrid Machine Learning Techniques
(Elsevier, 2024-08-20) Sutradhar, Ananda; Akter, Sharmin; Shamrat, F M Javed Mehedi; Idris, Mohd Yamani Idna Bin; Ahmed, Kawsar; Moni, Mohammad Ali
The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated potential superiority in mitigating the occurrence of this disease by facilitating early detection and treatment. However, there is a growing demand among stakeholders and patients for reliable and credible explanations of the generated predictions in sensitive medical domains. Hence, we propose an interpretable thyroid classification model to illustrate outcome explanations and investigate the contribution of predictive features by utilizing explainable AI. Two real-time thyroid datasets underwent various preprocessing approaches, addressing data imbalance issues using the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Subsequently, two hybrid classifiers, namely RDKVT and RDKST, were introduced to train the processed and selected features from Univariate and Information Gain feature selection techniques. Following the training phase, the Shapley Additive Explanation (SHAP) was applied to identify the influential characteristics and corresponding values contributing to the outcomes. The conducted experiments ultimately concluded that the presented RDKST classifier achieved the highest performance, demonstrating an accuracy of 98.98 % when trained on Information Gain selected features. Notably, the features T3 (triiodothyronine), TT4 (total thyroxine), TSH (thyroid-stimulating hormone), FTI (free thyroxine index), and T3_measured significantly influenced the generated outcomes. By balancing classification accuracy and outcome explanation ability, this study aims to enhance the clinical decision-making process and improve patient care.
Analysis and Prediction of Air Permeability of 100% Cotton Single Jersey Fabric Using Machine Learning Approaches
(Journal of Textile and Apparel, Technology and Management, 2020) Akter, Sharmin; Ahmed, Md. Sohel; Khan, Dr. Mashiur Rahman
The air permeability property has great significance on the fabric comfort related property. In this study Artificial Neural Network (ANN), Random Forest and Additive Regression Classification Models have been applied for the prediction of the air permeability of single jersey knitted fabrics made of 100% cotton fiber. For this aim, 100 different single jersey knitted fabrics were used and there basic properties such as yarn linear density, tightness factor, fabric loop length, fabric thickness, stitch density, fabric unit weight, and air permeability properties were evaluated. ANN, Random Forest, and Additive Regression Classification Models were developed to predict air permeability properties of single jersey fabrics. It was found that all the models give outputs closer to the experimental results. However, ANN estimation success was found higher than other models.
Analysis of Tort Law’s Right and Liabilities: In the Light of Recent Incident of Sitakunda Fire Blast
(East West University, 2022-09-08) Akter, Sharmin
Tort law is a law where people can get remedy for the civil wrong and damages. Negligence is a main subject matter of tort law. For negligence there are many incidents happened in Bangladesh. In tort law there have remedies for the damages. But this law is not codified law in Bangladesh. As a fundamental right many countries codified the tort law. Although in our country tort law is not codified but the essence is still available in other existing statutory laws. By using tort law many incident can be reduced. In this article I try to find out the loopholes of existing laws and also recommended some remedies which can be prevent future incident as like Sitakunda Fire Blast.
Antidiabetic And Free Radical Scavenging Activities Of Methanolic Extract Of Citrullus Lanatus (Fruit Rind)
(EJPMR, 2015-06-27) Azad, A. K.; Jalil, Abdul; Roy, Debendra Nath; Ahmeda, Nazneen; Nesa, Jeb-Un; Moniruzzaman, M.; Lasker, Shoumen; Rahaman, Irfan-Ur-; Akter, Sharmin
Free radicals are associated with Diabetes and its complications. The present study was designed to investigate DPPH scavenging in-vitro antioxidant activity and antidiabetic activity on alloxan induced diabetic mice. Mice treated with extract dose at 300mg/kg p.o, showed a remarkable decrease ( ***p<0.001) of blood glucose concentration at 90min and 120min compared to diabetic control group and metformin was taken as a reference standard. In this study antioxidant activity of Citrullus lanatus was g/mlg/ml in contrast with ascorbic acid IC50 was 36.34 IC50 was 102.51 g/ml.g/ml in contrast with ascorbic acid IC50 was 36.34 g/ml.
Application & Implementation of Augmented Reality in 3D on Art Gallery
(Daffodil International University, 2019-05) Dipu, Nowshad; Hossain, Khandaker Ishtiaque; Akter, Sharmin
In this advanced world, augmented really has brought a new dimension to view the world where special technology is being used for advancing the visual quality. Museum photo exhibition is one of the visual implementations of AR .we decorated the project in a standard that can be implemented in art galleries to make spectators memorized .we added image detection, animation movements, video contents that creates unique piece of creativity at a time serving individuals with a different view .We It enhances the scenario within viewers & objects that combines the real view with digital scenario .we worked on unity platform here using c# language.
Assessing Rural Women's Satisfaction with Public Services in Bangladesh: Case Study of Provision of Public Services by Civil Society Organization.
(Scopus, 2024) Uddin, Mohammed Nasir; Akter, Sanjida; Mahzabin, ffat Ara; Muchemi, Julius Githinji; Akter, Sharmin
Poverty continues to ravage about 10 percent of the world population. Efforts to eradicate poverty in all its forms remain elusive. The historical decline in global poverty rate experienced from 10.1% in 2015 to 8.6% in 2018 and even further down to 8.3% in 2019 reverses to 9.2% in 2019 due to COVID-19 pandemic. Although the poverty rate is projected to decrease to 8.6% in 2022, efforts to lower it further are confounded by the emerging global uncertainties including the Ukraine-Russia war, the global economic crisis, and catastrophes of earthquakes, and adverse effects of climate change. To address poverty in a country, the government and other development actors, including civil society, must establish national definitions, set targets, and conduct assessments on how the poor access and are satisfied with public services. This necessitates an understanding of the poor's socioeconomic circumstances, as well as the factors that influence service providers' ability to meet their expectations. This study was primarily undertaken to determine the satisfaction level of rural women with public services provided through civil society programs within four villages in the northern parts of Bangladesh. It also explores what factors influence the satisfaction level. Findings indicated that highest proportion of the respondents (53%) had a high level of satisfaction. In addition, the findings show that respondents' knowledge of civil society organization services and duration of involvement in civil society organizations, as well as family size, annual family income, and training, were significantly correlated with women's satisfaction with the services provided by civil society organizations. Furthermore, age, family size, annual income, and farm size are important socioeconomic factors that can influence women's satisfaction with public services provided by civil society organizations. It concludes that the selected civil society organization lacks the necessary personnel to provide public services and assess program success. The implication is that for civil societies to successfully supplement the government's public services, they must examine the existing gaps and barriers that need to be addressed in providing the services.
Attachment at Abanti ColourTex
(Daffodil International University, 2016-10-03) Islam, Md. Khalakul;; Fazle Rabbi, Md.; Akter, Sharmin
Textile and garments sector is the biggest and fastest growing sector in Bangladesh. It is also the highest foreign currency earning sector in Bangladesh. Among this sector, knit dyeing is growing very rapidly due to smaller investment requirement, greater backward linkage facility & higher profit than woven garments. That’s why export of knit dyeing garments has Increasing steadily for last few years. Textile education can’t be completed without industrial training. Because this industrial training minimizes the gap between theoretical and practical knowledge and make us accustomed to industrial environment. I got an opportunity to complete two month (8 Weeks) Long industrial training in “Abanti Colour Tex Ltd which is a 100% export oriented Composite Knit Dyeing Industry. It has well planned & equipped fabric and Knit dyeing finishing units in addition to facilitate Knit and knitting wear manufacturing. The industrial internship is the process, which builds understanding, skills and attitude of the performer, which improves his knowledge in boosting productivity and services. University education provides us vast theoretical knowledge as well as more practical attachment, in despite of all these industrial attachment helps us to be familiar with technical support of modern machinery, skill about various processing stages. It also provides us sufficient practical knowledge about production management, work study, efficiency, industrial management, purchasing, utility and maintenance of machinery and their operation techniques etc. The above mentioned cannot be achieved successfully by means of theoretical knowledge only. This is why it should be accomplished with practical knowledge in which it is based on. Industrial attachment makes us reliable to be accustomed with the industrial atmosphere and improve courage and inspiration to take self responsibility.
Bengali Review Analysis for Predicting Popular Cosmetic Brand Using Machine Learning Classifiers
(Springer Nature Limited, 2022-11-14) Rabeya, Tapasy; Khatun, Eshita; Noori, Sheak Rashed Haider; Akter, Sharmin; Jahan, Israt
Nowadays, online platform has become one of the most popular media to express people’s thought of all ages. That made the online platform a precious source for getting almost every kinds of information. As online shopping is rising in no time in recent years, as a result millions of comments are generating every single day. These users generated opinions on social media and different websites has made it easier for the people choosing the right product for them. Hence, sentimental analysis is a sought-after research topic nowadays. Our research paper has portrayed an experimental study on different cosmetics products review. To do so, we have selected ten popular cosmetic brands for analyzing their product review and chosen to analyze Bengali comments or sentences. The main focus of our work was to get out the most popular cosmetic brands among ten chosen brands. We have applied four classification algorithm such as naive Bayes, random forest, decision tree, and support vector machine for analyzing the final outcome and found vaseline and clear are the most popular brands.
Cancer Registry Importance in Bangladesh: A Review and A Mobile Application Based Solution
(City University, 2020) Akter, Sharmin; Nayeem, Md. Imtiaz
In recent times, cancer becomes the major health issue. Cancer registry is challenging but a part of modern health care that creates awareness globally. Time has come, when Bangladesh has to give supreme priority to make a smart system for cancer registration to collect and manage proper database of the number of cancer patient, survivor rate, death rate and chronic condition for future analysis. . This review has twofold goals, first is propose an effective solution through a mobile app for cancer registry and second is suggest a efficacious method for cancer registration by exploring the cancer registry methods are available in journal articles. The increasing number of smart mobile phone user is immensely helping us in this purpose. In this paper two types of methods are used for cancer registry, one is community clinic based registry approach another is hospital based registry approach. Community clinic is the unique innovation in Bangladesh health care system, and this community clinic based cancer registry is first time going to be implemented through this paper. Base on reviewing the features of apps and surveying on 100 of people including doctors, cancer patients and CHCP, we become able to propose an app of cancer registry. Apps were collected from August 2018 to March 2019 and data was analyzed in April 2019.
Comparative Study on Abstractive Text Summarization
(11th International Conference on Computing, Communication and Networking Technologies, IEEE, 2020-10-15) Talukder, Md Ashraful Islam; Abujar, Sheikh; Masum, Abu Kaisar Mohammad; Akter, Sharmin; Hossain, Syed Akhter
This paper represents a comparative study and gives an overview on some of the great research work done on abstractive text summarization. Getting a gist part from a large text document is known as text summarization. In recent years, text summarization became one of the most interesting and crucial research point in Natural Language Processing(NLP) area. Text summarization is grouped in two subparts and those are Extractive Text Summarization(ETS) and Abstractive Text Summarization(ATS). ETS is more simple than ATS. ETS is based on algorithms and it extracts the salient words or sentences from the given large text document. As opposed to, ATS generates summary by itself. It's a long time process because its includes lots of terms such as content preprocessing, word embedding, fundamental model design, discourse rules, validation of test and training data, attention mechanism, supervised, reinforcement learning and so forth. We are going to give a review on some papers about ATS and will discuss about the pros and cons of their models.
Comparative Study on Abstractive Text Summarization
(11th International Conference on Computing, Communication and Networking Technologies, IEEE, 2020-10-15) Talukder, Md Ashraful Islam; Abujar, Sheikh; Masum, Abu Kaisar Mohammad; Akter, Sharmin; Hossain, Syed Akhter
This paper represents a comparative study and gives an overview on some of the great research work done on abstractive text summarization. Getting a gist part from a large text document is known as text summarization. In recent years, text summarization became one of the most interesting and crucial research point in Natural Language Processing (NLP) area. Text summarization is grouped in two subparts and those are Extractive Text Summarization (ETS) and Abstractive Text Summarization (ATS). ETS is more simple than ATS. ETS is based on algorithms and it extracts the salient words or sentences from the given large text document. As opposed to, ATS generates summary by itself. It's a long time process because its includes lots of terms such as content preprocessing, word embedding, fundamental model design, discourse rules, validation of test and training data, attention mechanism, supervised, reinforcement learning and so forth. We are going to give a review on some papers about ATS and will discuss about the pros and cons of their models.
Corporate sales analysis of Cosmo Tissue LTD
(BRAC University, 4/20/2017) Akter, Sharmin; Tarannum, Iffat
Here is the internship report of me on ‘Corporate Market Analysis of Cosmo Tissue LTD’. Since I have done my internship under sales and marketing my project is about the corporate market analysis. “Cosmo Group” is the trusted name for Garments Accessories & Packaging Sector. Cosmo Group started its Business from 1997 as a trading Business for Garment’s accessories. The Company’s objectives, purpose, vision and mission are also given in this report. Company’s managerial structure and divisions are shown here. Cosmo group has six sister concerns and I joined at one of their sister concerns ‘Cosmo Tissue LTD. My job at Cosmo is described in this report which includes my routine works and other different works at internship. I have done some surveys and analyzed them which were based on customer preference, customer demands, and the results are described in the report. There were some limitations while preparing the report. Finally I had some recommendation to Cosmo which I felt would be beneficial for them to follow. Overall, the experience and learning that I earned will be very beneficial and work as a foundation for me for the upcoming journey. Starting from the way of communication to the discipline, I admire everything that I learned in these three months.
COVID-19 effect on Poultry Farming in the selected area of Chattogram, Bangladesh
(Chattogram Veterinary and Animal Sciences University Chattogram-4225, Bangladesh, 2021-11) Akter, Sharmin
The COVID-19 pandemic had gravely affected innumerable economic sectors across the world, including livestock production in which poultry sector was affected greatly by this pandemic. This study investigated how the pandemic had affected the poultry production and distribution network (PDN), analyzed economic circumstances of the farmer before pandemic and after pandemic in the Rangunia Upazilla, Chittagong. Twenty five poultry farms from Rangunia Upazilla were selected to find out what extent the farm was affected by the COVID-19 crisis besides some retail sellers also included for getting data about price fluctuation in chicken meat and eggs. Per bird average annual gross cost for rearing of broiler and layer were 895.5 BDT and 1557.5 BDT, respectively before pandemic and average annual gross cost/bird for rearing of broiler and layer are 985.5 BDT and1652.5 BDT, respectively throughout pandemic which turns into annual cost/bird for rearing of broiler and layer were 913.5 BDT and 1633.5 BDT, respectively immediate after COVID pandemic. The study showed that the poultry sector was damaged by the COVID-19 pandemic, partly as a result of the lockdown and also by rumors that poultry and their products could transmit the disease. Huge disaster occurred in poultry production due to disrupted production and transportation, falling down consumer demand and volatile markets also brought huge financial struggling, even leading to the permanent closure of many farms.
Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network with Transfer Learning
(International Journal of Ambient Computing and Intelligence, 2021) Haque, Mohammad Reduanul; Hafiz, Rubaiya; Al Azad, Alauddin; Adnan, Yeasir; Akter, Sharmin; Khatun, Amina; Uddin, Mohammad Shorif
Interpersonal violence, such as physical and sexual abuse, eve-teasing, bullying, and taking hostages, is a growing concern in our society. The criminals who directly or indirectly committed the crime often do not go into the trial for the lack of proper evidence as it is very tough to collect photographic proof of the incident. A subject's corneal reflection has the potentiality to reveal the bystander images. Motivated with this clue, a novel approach is proposed in the current paper that uses a convolutional neural network (CNN) along with transfer learning in identifying crime as well as recognizing the criminals from the corneal reflected image of the victim called the Purkinje image. This study found that off-the-shelf CNN can be fine-tuned to extract discriminative features from very low resolution and noisy images. The procedure is validated using the developed datasets comprising six different subjects taken at diverse situations. They confirmed that it has the ability to recognize criminals from corneal reflection images with an accuracy of 95.41%.
Detection of Breast Cancer from Ultrasound Imaging using Deep Learning Model
(Daffodil International University, 23-02-18) Raz, Maruful Islam; Akter, Sharmin
The second most common cause of mortality for women is breast cancer. Female death rates can be decreased if breast cancer is found early. For early cancer detection, an automated system is needed because manual breast cancer diagnosis takes a long time. There is a 30% possibility that the disease can be treated with early identification, but late detection of advanced-stage malignancies makes therapy more challenging [1,2]. Using Deep learning, we created a model that can predict the likelihood of getting breast cancer. In this paper, deep learning models are used to provide a new framework for detecting breast cancer from ultrasound images. Images from the Breast Ultrasound Dataset are divided into three categories: normal, benign, and malignant. In order to increase the amount of the original dataset and improve Convolutional Neural Network (CNN) model learning, data augmentation is carried out. Uses of Model: VGG16, InceptionV3, Exception, DenseNet201. We used these 4 models in deep learning, among which the accuracy of inception is the best and the accuracy value is 88%.
EFFECT OF SAW DUST ON WEIGHT OF GIZZARD & LIVER, PH & MICROBIAL LOAD IN CAECAL FLUID OF BROILER
(Chattogram Veterinary & Animal Sciences University, Khulshi,Chattogram, 2014-01) Akter, Sharmin
The experiment was conducted to know the effect of saw dust as unconventional feed ingredients in broiler ration. The diets purchased from local market contained 3100 ME (kcl/kg feed),Cp 22(g/100g).Diet was replaced by 6% of sawdust collected from nearest sawmill. After 5 days of feeding trial broiler finishers were slaughtered for measurement of variables. Average Liver weight in sawdust diet was 33.0 gm, Gizzard weight was 39.0 gm, ph of caecum and colon fluid was 6.67,7.3 respectively. Microbial load by 30 focus was examined & counted as 359 colonies in caecal fluid. No Mortality was found among the treatments. It may be concluded that there may be differences in above parameters in different breeds, age, sex. However, sawdust are abundant in the country, it can be used as unconventional feed in the diet of poultry ration to make it cheaper
Effect of Shade Depth on Lea Strength, Weight Loss and Wash Fastness Properties of Reactive Dyed Cotton Yarn
(Daffodil International University, 2020-01) Disha, Fatima Binta Satter; Akter, Sharmin; Hossain, Md Arafat; Khatun, Murshida; Islam, Md. Kamrul; Farzana, Nawshin; Khatun, Mahmuda
Analysis of the change in lea strength, weight loss percentage and wash fastness properties of 100 percent cotton reactive dyed yarn with various shade depth (1% to 4%) is carried out to represent correlation between the specified yarn properties with shade depth change in two different yarn counts. It is observed that increase in shade depth increases the yarn lea strength but shows a decreasing rate in wash fastness and weight loss (%). Finer yarn shows wash fastness rating of 4/5 whereas coarser yarn shows higher value in weight loss (%) and yarn lea strength.