Browsing by Author "Islam, Ashraful"

Now showing 1 - 20 of 36

A Comparative Overview of Local Mobile Financial Services Smartphone Apps Available in Bangladesh
(International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS), 2023, IEEE, 2023-10) Smaron, J,M, Sadik-Ul Islam; Tabassum, Yousra; Simoon, M.M.; Rahman, Zara; Rafid, Lishan; Islam, Ashraful
The rapid growth of mobile financial services (MFS) contributes toward the revolution of the financial landscape in developing economies, particularly Bangladesh. As a key player in promoting financial inclusion and the rising numbers of smartphone users, MFS smartphone apps have become increasingly popular in the country, catering to the needs of millions of unbanked and underbanked individuals. This paper aims to conduct a comprehensive comparative analysis of the various official MFS apps (n=13) available in Bangladesh, evaluating their features, functionalities, operational aspects, security measures, and overall facilities. The comprehensive exploration identified 18 distinct elements spanning four primary themes that stand out in the functionality of these apps: (1) Money Transfers and Transactions, (2) Financial Services and Bill Payments, (3) Service-related Charges, and (4) Consumer Finance. Each theme brings forth critical insights into the capabilities of these MFS apps, their user-friendliness, and their potential to effectively serve the unbanked and underbanked populations of Bangladesh. This comparative analysis is anticipated to provide valuable insights that can serve as a foundation for future advancements in MFS, fostering financial inclusion and promoting a more efficient and secure digital financial ecosystem in Bangladesh.
A Federated Learning Approach for Type-2 Diabetes Detection Using a Naive Bayes Classifier
(, The International Diabetes Federation (IDF), 2023, 2023-10) Rahman, M. M.; Islam, Ashraful; Pasha, Syed Tangim; Islam, M. Usama; Alam, Md Zahangir
Federated learning (FL) is a new way of training machine learning models across decentralized devices without exchanging the raw data. This approach preserves privacy and promotes the development of more personalized models by exploiting the heterogeneity of data. Common phenomena of FL is to employ deep learning models. Nonetheless, simple machine learning models such as Naive Bayes have promising potentials for detecting diabetes mellitus in a FL environment. To explore the practical prospects of building a privacy-preserving model for identifying patients with diabetes mellitus, utilizing their individual data. A cohort of 103 persons are enrolled in this study. Each participant was sent a questionnaire to answer with their own personal data about their age, Body Mass Index (BMI), insulin level, glucose concentration, skin thickness of an individual. Subsequently, an initial model, built using the Pima Indian Diabetes dataset, was sent to their mobile devices [1]. The participants utilized the initial model to train with their own data. Following this, the model parameters are updated and sent to the server. The server aggregated the parameters and averaged them to make a global model. This completes a single iteration of federated learning life cycle. Participants are diversed in gender: male (60.2%) and female (39.8%); in age groups: 20-35 (14.6%), 36-50 (46.6%), 51-65 (38.8%). The work shows an accuracy of 89.32% and a precision of 88.89% for those having diabetes while 90.32% precision in detecting patients not having a diabetes mellitus. The number of communication rounds was 50 where in each round at least two participants participants in building federated model updates. Since one of the key reasons for using FL is to improve data privacy, quantifying the level of privacy is critical. An network intruder could decoded the model updates by examining the changes in the global model over time. However, a membership inference attack (MIA) is measured in various differential privacy (DP) budgets. DP aims to prevent this kind of inference by adding noise to the data (model updates). For instance, if the model update would normally be a weight change of +0.5, a noise from a Laplacian distribution with mean 0 is added. Hence, the resulting noisy update might then be +0.52. A naive bayes based federated learning system is built to detect diabetes mellitus (Type-2) preserving the privacy of user data at the first place.
A Framework to Address Security Concerns in Three Layers of IoT
(IEEE, 2020-11) Jose, Alwyn; Azam, Sami; Karim, Asif; Shanmugam, Bharanidharan; Faisal, Fahad; Islam, Ashraful; De Boer, Friso; Jonkma, Mirjam
The Internet of Things (IoT) is becoming part of many aspects of our life, including healthcare, home utilities, retail, energy, logistics, etc. This prolific and ubiquitous nature of IoT based systems brings with it the threats of cyber-attacks in a variety of forms. An IoT framework is a set of controlling rules, standards and protocols which makes implementation of IoT applications somewhat streamlined. However, due to the existence of a plethora of IoT devices, applications and technologies, standardization of IoT protocols is a complex undertaking. Several well-known IT organizations have their own customized standards for the IoT platform. However, the lack of stable standardization has been a prime concern for quite some time. This research outlines the overall technologies used in IoT security implementation and an overview of different threats faced by IoT devices. The work also recommends a security framework that can effectively be implemented with various IoT based systems.
A Framework to Address Security Concerns in Three Layers of IoT
(IEEE, 2020-11-20) Jose, Alwyn; Azam, Sami; Karim, Asif; Shanmugam, Bharanidharan; Faisal, Fahad; Islam, Ashraful; De Boer, Friso; Jonkman, Mirjam
The Internet of Things (IoT) is becoming part of many aspects of our life, including healthcare, home utilities, retail, energy, logistics, etc. This prolific and ubiquitous nature of IoT based systems brings with it the threats of cyber-attacks in a variety of forms. An IoT framework is a set of controlling rules, standards and protocols which makes implementation of IoT applications somewhat streamlined. However, due to the existence of a plethora of IoT devices, applications and technologies, standardization of IoT protocols is a complex undertaking. Several well-known IT organizations have their own customized standards for the IoT platform. However, the lack of stable standardization has been a prime concern for quite some time. This research outlines the overall technologies used in IoT security implementation and an overview of different threats faced by IoT devices. The work also recommends a security framework that can effectively be implemented with various IoT based systems.
Adaptive Feature Selection and Classification of Colon Cancer from Gene Expression Data
(ACM International Conference Proceeding Series, 2020-01) Islam, Ashraful; Rahman, Mohammad Masudur; Ahmed, Eshtiak; Arafat, Faisal; Rabby, Md Fazle
Cancer research is one of the major and significant areas in medical research. A substantial number of research has been performed in this area and several methods have been employed. However, accuracy of cancer prediction is yet to reach near perfection as the conventional classification methods have several limitations. In recent times, microarray processed gene expression data has been used to predict cancer with significant accuracy. The gene expression data are usually high dimensional and comprises of relatively small number of samples which makes them difficult to classify. In order to achieve higher accuracy, ensembles method can be deployed which combines multiple classification methods. In this study, we have used the public colon cancer gene expression data set that consists of 62 instances having 2,000 attributes. An adaptive pre-processing procedure has been conducted including Linear Discriminant Analysis (LDA) and Principle Component Analysis (PCA) to cope up with the high dimensionality of the data. This was followed by building an ensemble learning model with k-Nearest Neighbors (kNN), Random Forest (RF), Kernel Support Vector Machines (KSVM), eXtreme Gradient Boosting (XGBoost), and Bayes Generalized Linear Model (GLM). Comparing with other classifiers, this study offers a significant improvement as our ensemble learning model gives higher accuracy than previously employed classification techniques. Thus the obtained accuracy is 91.67% with the scores 0.75, 1.00 and 0.85 of precision, recall and Matthews correlation coefficient (MCC) values respectively.
An Automated System in ATM Booth Using Face Encoding and Emotion Recognition Process
(ACM International Conference Proceeding Series, 2020) Chowdhury, Atiqul Islam; Shahriar, Mohammad Munem; Islam, Ashraful; Ahmed, Eshtiak; Karim, Asif; Islam, Mohammad Rezwanul
Nowadays, the banking transaction system is more flexible than the previous one. When the banking sector introduces the ATM booth to us, it was a step ahead to ease the human effort. Here, ATM booth is an automated teller machine that gives out money to the consumer by inserting a card in it. All ATM booths support both credit and debit cards for the transaction, and this has saved everyone's time. But still, there are some certain situations, i.e., forgetting the card authentication details for a transaction can ruin a consumer's day. For this reason, this paper has tried to propose a system that will help everyone regarding this situation. This proposed system is about face encoding process with an emotion recognition test for making transactions faster and accurate, based on Convolutional Neural Network (CNN). However, normal card transactions can still be possible besides using the proposed system. FER2013 dataset was used for training and then tested the model using our own sample images. The result shows that the proposed system can correctly separate ‘Happy’ faces from other emotional faces and allow the transaction to proceed.
An Investigation into the Level of Valence Offered By Different Pointing Devices against Challenging Tasks
(International Conference on Advanced Computer Science and Information Systems (ICACSIS), 2020) Ahmed, Eshtiak; Islam, Ashraful; Ashraf, Mohsena; Khan, Md. Ibrahim; Chowdhury, Atiqul Islam; Karim, Asif
Pointing devices are the primary media of interac-tion between humans and computers. The three most popular pointing devices used in computers (both portable and non-portable) are mouse, touchpad and nubs (joystick). They have their different advantages and use cases while being targeted to different user groups. The aim of this study was to investigate whether the aforementioned pointing devices have different effects on human valence. A total of 12 participants were recruited for the experiment. Each participant completed a pointing reaction test with every pointing device aforementioned, where they selected as many randomly appearing circles as possible in a given amount of time. Then, subjective ratings of emotional valence and arousal were collected, and the effects of the pointing device used on these ratings were investigated. Our study shows that the valence rating of using the mouse were significantly higher in challenging scenarios, compared to the likes of touchpad and nub.
An Optimization Approach to Improve Classification Performance in Cancer and Diabetes Prediction
(IEEE, 2019-04-04) Islam, Ashraful; Ahmed, Eshtiak; Mahmud, Md. Swakshar; Hossain, Sabrina
There are many destructive diseases in the world which cause rapid death by taking time to affect such as cancer and diabetes. They take a lot of time to spread, thus they are curable or somewhat scalable to a great extent if they are diagnosed soon after introduced into the human body. Research shows that almost all type of cancer can be cured if they are detected in the early stage. It is also true for diabetes as they can be controlled if they are detected at the right time. So, a prediction technique that takes help from the computer and processes data from affected user to detect possible contamination can be a great tool for assisting both the doctors and patients with these diseases. A challenge in the process is that the detection accuracy has to be acceptable in order to make the system a reliable one. In this study, we have analyzed medical data using several classification algorithms in order to optimize classifier performance for cancer and diabetes prediction.
Analyzing Performance of Different Machine Learning Approaches with Doc2vec for Classifying Sentiment of Bengali Natural Language
(2nd International Conference on Electrical, Computer and Communication Engineering, IEEE, 2019-04-04) Hoque, Md. Tazimul; Islam, Ashraful; Ahmed, Eshtiak; Mamun, Khondaker A.; Huda, Mohammad Nurul
Vector or numeric representation of text documents has been a revolution in natural language processing as it represents similar parts of text in such a way that they are very close to each other, making it very easy to classify or find similarities among them. These vectors also represent the way we use the words or parts of documents as well which helps finding similarity even between pair of words. While word2vec is such a technique that represents each word as a vector, doc2vec takes it to another level by representing a whole sentence or document as a vector. Being able to represent an entire document as a vector allows comparing a substantial number of words or sentences at a time which can save computational power as well as bandwidth. This relatively newer doc2vec technology has not yet been implemented for Bengali sentiment analysis and its feasibility is also unknown. In this study, we have trained a doc2vec model using a corpus constructed with 7,000 Bengali sentences. The model consists of two types of data differentiated by their polarity i.e. positive and negative. Later, we have employed several machine learning algorithms for comparing the accuracy of classification among which Bi-Directional Long Short-Term Memory (BLSTM) has obtained the highest accuracy of 77.85% along with precision, recall and F-1 score of 78.06%,77.39% and 77.72% respectively.
Assessing Early Stage Design of a mHealth App for Gestational Diabetes Mellitus Management in Bangladeshi Women
(The International Diabetes Federation (IDF), 2023, 2023-10) Islam, Ashraful; AHMED, ESHTIAK; Zaman, Marzia; Rangon, Fairy Hasan; Amin, M Ashraful; Islam, Rakibul
There is significant concern over the rising incidence of Gestational Diabetes Mellitus (GDM) among expectant mothers in Bangladesh [1]. Limited healthcare facilities in rural areas hinder prompt diagnosis and efficient management of GDM in Bangladesh. Despite mHealth's benefits, there is a lack of GDM management apps in Bangla, the native language of Bangladeshi citizens. To assess the viability of the first GDM management mHealth app in Bangla, users were asked about its early designs and functionalities. The app features a blood glucose tracker, food diary, medication reminder, educational resources, activity tracker, and personalized recommendations. 30 women with pre-existing GDM who were visiting a clinic in Dhaka, Bangladesh, were freely recruited during July 2023, and participation was anonymized. Participants ranged in age from 24 to 43 years (mean 33.43, SD 5.4). Following a briefing on the app's features and functionalities, participants were shown early sketches of the app. Later, they were prompted with a series of questions to provide feedback on the initial design and features. The majority (n=24) participants exhibited a positive response towards the app, expressing a wish that they had such a tool during their experience with GDM. However, 2 participants viewed the app as an impractical tool, while 3 were uncertain, expressing concerns about the accuracy of the information and guidance provided by the app. Beyond a textual interface, 1 participant suggested the inclusion of voice-based interaction to accommodate users who are illiterate, unfamiliar with using apps or having visual impairments. All participants appreciated the interface's use of the Bangla language and its cultural tailoring. 9 participants specifically highlighted the culturally tailored dietary recommendation feature as particularly praiseworthy. The app can play a crucial role in managing GDM in Bangladesh based on the early-stage evaluation feedback. However, further research is warranted to evaluate the real-world effectiveness and feasibility of it with a high-fidelity prototype for in-situ evaluation with the target users.
Client servicing and public engagement of Mirai International Event Management
(BRAC University, 12/21/2017) Islam, Ashraful; Shaown, Jubairul Islam
Mirai International Event Management (MIEM) BD Ltd. is a reputed Bangladesh-Japan joint venture Event Organizing Company. It has successfully organized national and international expos in several countries. Mirai International Event Management (MIEM) is a fully integrated event management, creative and experiential marketing company which is specialized in organizing and managing global event and expo solutions through a power team of innovative, energetic and dynamic souls. Mirai International Event Management (MIEM) is an event management company which is committed to achieve success by organizing international events with participations of young, dynamic and talented group. The purpose is to deliver insightful, simple and creative solutions via events, experiential marketing and corporate hospitality. They also deliver corporate events, conference, exhibitions, concerts and brand experience locally and globally. The Mirai International Event Management (MIEM) team is expert in organizing and managing corporate events, delivering the very best value of money and creating something special behind the scenes. Their aim is to take Bangladesh to the next level in near future by showcasing their products as we all know how rich our country is in garments, textiles, leather, handicrafts and other sectors. Our products and services quality is doing better recent days than many countries but we never have got the chance to explore much. MIEM is working on it to get more exposure of our own products and services worldwide.
Cloud-POA: A cloud-based map only implementation of PO-MSA on Amazon multi-node EC2 Hadoop Cluster
(IEEE, 2018-02-08) Neehal, Nafis; Karim, Dewan Ziaul; Islam, Ashraful
Sequence alignment in bioinformatics and computational biology has always been a challenging task. With Next Generation Sequencing (NGS) techniques in hand, researchers are now capable of studying biological systems at a level never been possible before. Scientists now have billions of bytes of biological data to work with, trillions of sequences to align. But this comes at a cost of requiring computing machines having a tremendous amount of computational and analytical power. Purchasing this huge amount of hardware and setting up a standalone infrastructure would not only cost an unnecessarily massive amount of money and labor but also would become troublesome to maintain. Moreover, for aligning a huge number of DNA or Protein sequences a scalable multiple sequence alignment (MSA) algorithms is needed with decent accuracy. In such context, this paper presents a novel implementation of Partial Order Alignment (POA) algorithm on a multi-node Hadoop Cluster running on MapReduce framework. The implementation was done in Amazon AWS platform with multiple EC2 instances. It is a map-only implementation with Hadoop Streaming. The result of this implementation shows a drastic reduction in runtime with no accuracy degradation.
Designing Healthcare Relational Agents: A Conceptual Framework with User-Centered Design Guidelines
(Independent University, Bangladesh, 2023-06) Islam, Ashraful; Chaudhry, Beenish M.; Islam, Aminul
This paper presents a conceptual framework for designing relational agents (RAs) in healthcare contexts, developed through the findings from multiple user studies on RAs about their acceptance, efficacy, and usability. The framework emphasizes a user-centered design (UCD) approach that takes into account the unique needs and preferences of patients, nonpatient users, and healthcare professionals (HCPs). Based on the results of these studies, we analyzed and refined the RA designs and proposed a UCD-based conceptual framework for designing effective and user-friendly healthcare RAs. The paper aims to provide an initial resource for researchers, designers, and developers interested in developing RAs for healthcare contexts by thinking of UCD techniques.
Efficacy and Acceptance of Virtual Classrooms During COVID-19
(Daffodil International University, 2021-06-13) Halder, Nabarun; Islam, S. M. Rakibul; Hosain, Md. Sarwar; Ahmed, Eshtiak; Islam, Ashraful; Noori, Sheak Rashed Haider
The sudden spread of COVID-19 shut down educational institutions worldwide, and Bangladesh was no exception. Educational institutions were forced to start their activities online; there was no alternative to keep the students in the study. Although online education has been seen as part of a futuristic approach, its effectiveness and acceptability still remains questionable when it comes to institutional education. It's yet to be investigated if online education can be as effective as contact teaching. We conducted an online survey to determine what students feel about online classes, how they accepted online classes, and how useful it was for them depending on their current situation. Our survey was open to everyone who has taken online classes during COVID-19, and the number of participants in our survey was 210. The survey provided with both qualitative and quantitative data which were then categorized into themes for analysis. Findings suggest, that most students feel that by rethinking the class style, if teachers can provide well-structured lecture content and have an equal focus on all students, it can be an alternative for them during emergency days.
Efficacy and Acceptance of Virtual Classrooms during Covid-19
(2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), IEEE, 2021-08-25) Halder, Nabarun; Islam, S. M. Rakibul; Hosain, Md. Sarwar; Ahmed, Eshtiak; Islam, Ashraful; Noori, Sheak Rashed Haider
The sudden spread of COVID-19 shut down educational institutions worldwide, and Bangladesh was no exception. Educational institutions were forced to start their activities online; there was no alternative to keep the students in the study. Although online education has been seen as part of a futuristic approach, its effectiveness and acceptability still remains questionable when it comes to institutional education. It's yet to be investigated if online education can be as effective as contact teaching. We conducted an online survey to determine what students feel about online classes, how they accepted online classes, and how useful it was for them depending on their current situation. Our survey was open to everyone who has taken online classes during COVID-19, and the number of participants in our survey was 210. The survey provided with both qualitative and quantitative data which were then categorized into themes for analysis. Findings suggest, that most students feel that by rethinking the class style, if teachers can provide well-structured lecture content and have an equal focus on all students, it can be an alternative for them during emergency days.
Financial Performance Analysis of Grameen Bank
(©Daffodil International University, 2021-02-17) Islam, Ashraful
The report is based on an analysis of Grameen Bank financial statements. In this report, the results are based on the criteria in the analysis in which we have identified the simple measurements, the sample values, the cost comparison, the results obtained benefit etc. In this report, we analyze the revenue from Grameen Bank from 2016 to 2020. The main activities of the bank are divided into two sections called deposits and loans. The main purpose of the bank is collecting the remaining funds and submits the funds to the grievance committee. So, from fundraising, I find that they work very well Compare all the private and government funds in Bangladesh with the existing ones. They have raised 208,022 million taka as investment by 2020 and it is still growing day by day. But, unfortunately, saving is a change in financial education. They also have to run other changes and have to use the money they save and lend to customers so that they can make money, which is the goal or end of any organization. business. So in order to generate income and engage with more rich people, they need to borrow money and get more income. Moreover, their performance in some areas we have mentioned before and we have discussed them in detail in this report, and in some areas their performance is not good. , as stated in this report. In the end, I hope they do well next year.
Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques
(IEEE, 2023-07-13) Pasha, Syed Tangim; Islam, Ashraful; Rahman, Mohammed Masudur; Ahmed, Eshtiak; Foysal, Md. Ferdouse Ahmed; Alam, Md Zahangir
The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%.
Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques
(Independent University, Bangladesh, 2023-05) Pasha, Syed Tangim; Islam, Ashraful; Rahman, Mohammed Masudur; Ahmed, Eshtiak; Foysal, Md. Ferdouse Ahmed; Alam, Md Zahangir
The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%.
hActNET
(Scopus, 2020) Chowdhury, Atiqul Islam; Ashraf, Mohsena; Islam, Ashraful; Ahmed, Eshtiak; Jaman, Md. Saroar; Rahman, Mohammad Masudur
Human activity recognition (HAR) is considered as one of the most difficult and challenging issues now a days. Many experiments are now in progress regarding this problem. Among many human activities, mostly six are considered for research in this area. This activity recognition issue can be measured with the help of smartphones and smartphone sensors, along with the connection of Internet of Things (IoT) devices. In this research, an improved deep learning scheme is proposed for the recognition of human activities. A customized Neural Network (NN) model was designed and tested for the research. The proposed model obtained 96.47% accuracy on the HAR with smartphones dataset that is better than most other analyzed models. Sensors such as accelerometer, gyroscope are focused on the data analysis portion of this research work. This article will give a clear idea of the dataset, Machine Learning algorithms, and the effect of the proposed algorithm.
Icons for the Mass
(1st International Conference on Advances in Science, Engineering and Robotics Technology 2019, IEEE, 2019-05-05) Ahmed, Eshtiak; Hasan, Md. Mahade; Faruk, Mirza Omar; Hossain, Muhammad Farhad; Rahman, Md. Arifur; Islam, Ashraful
A major population of 3 rd world countries have problems reading out texts because of the low literacy rate. While smartphones have given them a hope to lead a better life, interacting with them needs a certain level of literacy which a majority of them lack. Given the rapid growth of variation in this user base, it is evident that interactive graphical representations can give a better understanding of contents especially to the children and to the illiterate people. This work emphasizes on making the Google Play App Store more usable as this is the most used app for smartphone users. In this study, new icons have been designed and then compared side by side with 16 existing Google Play Store app category icons to initially find out the legitimacy of the new icons. Further, a survey between smartphone users has been conducted and the results show that the new icons fare better while representing app categories. Based on the survey results and more widely accepted icons, some key factors to design icons have been identified.