Browsing by Author "Sattar, Abdus"

Now showing 1 - 20 of 44

A Case Study and Fraud Rate Prediction in e-Banking Systems Using Machine Learning and Data Mining
(Scopus, 2021) Nuha, Musfika; Mahmud, Sakib; Sattar, Abdus
Recently banking sector of Bangladesh is undergoing in a revolutionizing change. Over the last few years, Bangladesh’s banking industry has achieved remarkable momentum. Especially radical change has come in e-banking and mobile banking sectors. Because of convenience, easy to use, time saving and less complexity, both educated and uneducated people are using those facilities. At the same time, fraudulent activity is also rising rapidly. It is noticed that fraudsters use scary tactics and emotional manipulation to obtain sensitive or confidential customer information instead of coding-based hacking process. As a result, cyber security is the main challenge for the banking sector in Bangladesh. The purpose of the research is to determine the key factors behind increasing fraudulent activities. Concurrently, this study focuses on the relationship between lack of awareness and likeliness to be affected by fraud. In order to acquire the specified purpose of this study, several investigations were conducted on primary and secondary data. Results show that there is a strong correlation between lack of awareness and likeliness to be affected by fraud. 76% people have no idea about e-banking and mobile banking fraud. Furthermore, our findings show that 86.3% of victims of e-banking or mobile banking fraud had no prior knowledge of this type of fraud. Simultaneously, 13.7% of victims in those sectors had prior knowledge of fraud. It is obvious that, behind this type of fraud, lack of knowledge and awareness can be a major fact.
A Case Study and Fraud Rate Prediction in e-Banking Systems Using Machine Learning and Data Mining
(Springer, 2021) Nuha, Musfika; Mahmud, Sakib; Sattar, Abdus
Recently banking sector of Bangladesh is undergoing in a revolutionizing change. Over the last few years, Bangladesh’s banking industry has achieved remarkable momentum. Especially radical change has come in e-banking and mobile banking sectors. Because of convenience, easy to use, time saving and less complexity, both educated and uneducated people are using those facilities. At the same time, fraudulent activity is also rising rapidly. It is noticed that fraudsters use scary tactics and emotional manipulation to obtain sensitive or confidential customer information instead of coding-based hacking process. As a result, cyber security is the main challenge for the banking sector in Bangladesh. The purpose of the research is to determine the key factors behind increasing fraudulent activities. Concurrently, this study focuses on the relationship between lack of awareness and likeliness to be affected by fraud. In order to acquire the specified purpose of this study, several investigations were conducted on primary and secondary data. Results show that there is a strong correlation between lack of awareness and likeliness to be affected by fraud. 76% people have no idea about e-banking and mobile banking fraud. Furthermore, our findings show that 86.3% of victims of e-banking or mobile banking fraud had no prior knowledge of this type of fraud. Simultaneously, 13.7% of victims in those sectors had prior knowledge of fraud. It is obvious that, behind this type of fraud, lack of knowledge and awareness can be a major fact.
A Comprehensive Approach to Detecting Chemical Adulteration in Fruits Using Computer Vision, Deep Learning, and Chemical Sensors
(Elsevier, 2024-06-19) Sattar, Abdus; Ridoy, Md. Asif Mahmud; Saha, Aloke Kumar; Babu, Hafiz Md. Hasan; Huda, Mohammad Nurul
Contamination of harmful additives in fruits has become a concerning norm these days. Owing to the great popularity of fruits, dishonest vendors frequently use harmful chemicals to contaminate fruits to extend their shelf life, which is extremely dangerous for the general public's health. To mitigate this issue, machine-learning algorithms like Decision Tree Classifier, Naïve Bayes and a deep learning model named “DurbeenNet” are evaluated separately. Alongside, a computer vision-based detection method coupled with a hybrid model is proposed that combines deep learning and chemical sensor. Formaldehyde Detection Sensor is used in this experiment to take reading of the sensor data. Mango, Apple, Banana, and Malta are taken as sample fruits in this study. Sensor data for both fresh and chemical-mixed fruit is newly collected using Formaldehyde Detection Sensor. The above mentioned sensor data along with the previously captures images of both fresh and chemical-mixed state are being integrated to a hybrid model. Among two machine learning algorithms naïve bayes come up with 82 % accuracy. Using both sensor data and captured image data, the proposed model “SensorNet” provides highest accuracy of 97.03 % which is substantial than “DurbeenNet” model's accuracy. Through the utilization of these fruit samples, formaldehyde detection sensor provides instantaneous detection, identifying the specific toxic substances present in the contaminated fruits.
A Conceptual Design to Encourage Sustainable Grocery Shopping
(IEEE, 2020-06-16) Sattar, Abdus; Shohel, Md. Jamal Hosen; Banni, Fahima Sultana; Antu, Amit Kumar Bala
Grocery shopping is a frequent event on our life that has a great impact on climate change and direct connection with health issues. The purchases of organic and healthy foods are increasing but still, we could not make any breach between our customer's awareness and feasting of environment-friendly healthy foods. This paper aims at providing information about products and helps consumers understand their food for making a better choice for their health and environment. We designed a system that provides information on nutritional values and the environmental impact of foods and advice users to make a food choice. It also keeps track of monthly grocery expenditure and shows how much of it is healthy and eco-friendly. The system works by scanning QR codes and AR markers that are embedded with the products. It will be a perfect assistant for grocery shopping for consumers of any age.
A Convolutional Neural Network Approach to Recognize the Insect
(IEEE, 2020-06-16) Hossain, Md. Imran; Paul, Bidhan; Sattar, Abdus; Islam, Md. Mushfiqul
In Bangladesh huge amount of agricultural products are destroying by the pests every year due to lack of poor knowledge about pest detection. As we know that manually identification is difficult for a farmer. So, classic pest detection and identification can ensure excellent productivity. This would be a fulfil research in the technical area of computer vision. The dataset is typically random cropping of square size images together with grayscale color and brightness shifts are used here. Here Convolutional Neural Network (CNN) will be used to do the image recognition and the algorithm will provide an optimal architecture for image recognition. The big idea behind CNNs is that a local understanding of an image is good enough. The research contains the proportions of validation accuracy of 93.46%. This approach resulted in the agriculture sector that will help a farmer to recognize the insect from harvest. The computer vision and object recognition can be used with image processing to create an interactive and enlarge user experience of the real world. This research aims to demonstrate the possibility and test the performance of the project which only focuses on insect detection in crop plants that recognize the pest which can help a farmer to get immediate solution of harvest problem.
A Convolutional Neural Network Based Potato Leaf Diseases Detection Using Sequential Model
(IEEE, 2023-04-03) Bonik, Choyon Chandra; Akter, Flora; Rashid, Md. Harunur; Sattar, Abdus
One of Bangladesh’s primary agricultural products is the potato. In recent decades, Bangladesh has seen a surge in the popularity of potato farms. Nonetheless, farmer’s expenses in potato production are rising as a result of a number of illnesses. Nonetheless, the high cost of potato production is mostly attributable to a number of illnesses that are affecting the crop. Which is wreaking havoc on the farmer’s schedule. In order to modernize the potato industry and speed up disease diagnosis, automation has been implemented. In spite of the claims to the contrary, potato leaf disease is a serious problem that can severely reduce crop yields. The leaves of diseased potato plants will show symptoms of early blight, Septoria blight, late blight, and other diseases. If such outbreaks are discovered at the initial level and enough intervention is done, the farmer will not be at risk of incurring significant economic losses. Based on the results of this study, a new model is presented for accurately identifying and detecting illnesses in potato leaf stands using image processing. While there are several methods that may be utilized in machine learning, the Convolutional Neural Network (CNN) model is what’s being employed here to identify the disease in potato leaf photos. This work implements a CNN based sequential model to predict the disease of potato leaves. This research achieved 94.2% model accuracy on this model. The presented model was tested on both typical and disordered potato leaves in an effort to distinguish between the two. Next, the algorithm is applied to the images, and the potato tree’s leaf is classified as either healthy or unhealthy.
A Multifactor Authentication Model to Mitigate the Phishing Attack of E-Service Systems from Bangladesh Perspective
(Scopus, 2020) Hasan, Md. Zahid; Sattar, Abdus; Mahmud, Arif; Talukder, Khalid Hasan
A new multifactor authentication model has been proposed for Bangladesh taking cost-effectiveness in primary concern. We considered two-factor authentications in our previous e-service models which were proven to be insufficient in terms of phishing attack. Users often fail to identify phishing site and provide confidential information unintentionally, resulting in a successful phishing attempt. As a result, phishing can be considered as one of the most serious issues and required to be addressed and mitigated. Three factors were included to form multifactor authentication, namely, user ID, secured image with caption, and one-time password. Through the survey, the proposed multifactor model is proven to be better by 59% points for total users which comprises 55% points for technical users and 64% points for nontechnical users in comparison to traditional two-factor authentication model. Since the results and recommendations from the user were reflected in the model, user satisfaction was achieved.
A Neural Network Based Software Defect Prediction Approach Using SMOTE and Noise Filtering-CLNI
(Research and Development Wing, MIST, 2025-12-30) Ashfaque, Ahmmed Bin; Sattar, Abdus; Jahan, Hosney; Akhtaruzzaman, M.; Nur, Fernaz Narin
Software defects can cause significant loss and system failures in software development life cycle. Software Defect Prediction (SDP) is a vital step for ensuring the quality of software. Till now, a number of machine learning models have been proposed to predict potential defects and make the software more reliable. However, SDP models suffer from the problem of imbalanced dataset, resulting in poor prediction accuracy. To mitigate this, issue several data balancing techniques, i.e., over sampling, under sampling etc. have been proposed to balance the dataset. In some cases, the data balancing methods may further introduce noisy and mislabeled samples in the dataset. To deal with these issues, in this paper, we propose a neural network based approach that combines the oversampling technique Synthetic Minority Oversampling Technique (SMOTE) with the noise filtering technique Class Level Noise Identification (CLNI). Here, we applied three different CLNI methods which are Edited Nearest Neighbor (ENN), Repeated ENN (RENN) and All-KNN. Our aim is to make the dataset clean, balanced and efficient by combining SMOTE with CLNI. In addition, we applied a number of feature selection methods to identify the most important features, further contributing towards achieving better prediction accuracy. To evaluate the effectiveness of the proposed model, we conduct experiments on several benchmark datasets (MC1, PC1, PC2, PC3 and PC4) obtained from NASA MDP and (ML, LC and JDT) AEEEM repository. The experimental results have been evaluated and compared in terms of accuracy, precision, recall and AUC-ROC curve. The experimental results demonstrated that our proposed approach has achieved up to 98% accuracy and outperformed state-of- the-art approaches.
Arabian Date Classification Using CNN Algorithm with Various Pre-trained Models
(2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), IEEE, 2021-03-31) khayer, Md.Abu; Hasan, Md.Sakibul; Sattar, Abdus
The people of Bangladesh have a lack of knowledge to detect fruit so many consumers suffer when they go to buy fruit every day. We know it is very difficult for consumers to detect the class of date on their naked eyes. It is necessary to build a model that can predict the class of a date. We have been select computer vision terminology for properly classifying the data images. Here the random typical fruiting of images in our dataset is used. We used CNN for image classification here and the algorithm provides an optimal architecture through image classification. The CNN's algorithm works well for any image This method will help consumers to identify the dates. We use computer vision and object recognition image processing to create interactive real-world and thereby enhancing the user experience. The main goal of our research is to demonstrate the feasibility and test the effectiveness of the project and the focus of our project is to identify different types of dates and this can help a consumer to get an instant solution to the date fruit identification problem very easily. The validation accuracy proportions of our research contain 82.67%.
Brain Sensing with Wearable Headband (ACP2)
(Scopus, 2021) Akter, Nasrin; Hossain, Nijar; Sattar, Abdus
This paper demonstrates an implementation of a mobile application capable of visualizing EEG data in a meaningful way. The project revolves around the Muse Wearable headband, a commercial device capable of reading EEG brainwaves of the user. With its compatible and downloadable application, Muse is designed to help the user with a meditation, providing aural feedback depending on the EEG measurements of the user during a meditation session. The paper also explores previously conducted research regarding EEG measurement studies. The observed studies include research work from the medical field, practical usability tests, and studies regarding meditation and human state of mind. All of the introduced research gives more insight in the usage of Muse Wearable Headband, EEG signal processing, or meditation research. The implementation is tested and evaluated. The evaluation phase includes separate test setups with different tasks. The aim of the evaluation is to test the performance of the implemented system, and also observe and analyze the EEG measurements while the user is performing different activities during the usage of the application.
Brain Tumor Analysis Using Deep Neural Network
(Proceedings - 5th International Conference on Intelligent Computing and Control Systems, IEEE, 2021-05-26) Khan, Iftekhar; Ahsan, Kuheli; Hasan, Md. Arid; Sattar, Abdus
The identification of tumors is one of the most tenacious and emerging fields in medical image processing. A tumor means the unrestricted existence of a bunch of cells in a precise area of the human body which destroys the normal body cells and keeps increasing. In human body, brain tumor is measured as the most common tumor which affects the nervous system, memory functional cells, glands, and membranes that surround the brain and can conduct to a high mortality rate if the affected one is unsuccessful to reach proper medical treatment. For effective treatment, precise and early recognition of the tumors is critical work and also a vital step in diagnosis and treatment preparation for affected one which not only benefits to arise with improved medications but also saves the affected life in due time. This research work uses Magnetic Resonance Imaging (MRI), which is a prominent imaging procedure in terms of brain tumor recognition. For features extraction, segmentation and classification, the proposed research work includes the deep neural network integrated method and Convolutional Neural Network (CNN) to classify the MRI images and an accuracy of about 97.92% has been achieved.
Breast Cancer Detection using Machine Learning Approach
(Daffodil International University, 2023-04-05) Sattar, Abdus
We have gathered the features of breast cancer and normal persons’ cells both. To classify malignant and benign tumors, we used a supervised machine learning classifier algorithm. This paper shows the last update in this machine learning field on breast cancer in Bangladesh. We have used many classifiers of ML in this review. Most of cases it is difficult to identify the malignant tumors. For this, we hoped that with the help of math and the computational power of ML we can resolve this issue at a significant scale. Yet, there were a few difficulties with the process. Starting with featuring the dataset and creating a data frame we proceed to apply different types of machine learning classifiers. This paper presents an overview of the opinion examination challenges applicable to their methodologies and strategies.
Bridging the Gap in HCI between Industry and Academia
(10th International Conference on Computing, Communication and Networking Technologies, IEEE, 2019-07-08) Sattar, Abdus; Khan, Nafim; Moheeuddin, Md.; Shaon, Nasir Uddin Khan
HCI currently a sonorous regulation which is wholly committed to the design of interactive systems that allow information flow between human and computer. Implementation and judgment are the other two major concern of HCI. Now a day's interest in improving communication between human and computer is an undisputed concern. Nevertheless, natural or flow less communication between the computer and human using artificial intelligence is also a concern, analogous to human-computer interaction. Notwithstanding there are still some gaps exists between theory and practice. But the castle in the air is there is some country who tries to improve the visibility of the HCI community. As opposed to the community of the software industry, still doesn't have much knowledge about HCI. Because there is no linking between the industry of software, and what they taught in undergraduate and postgraduate level. In this research, discover these phenomena is somewhat true for Bangladesh where we want to analyze what student taught and what software companies requirement when it comes to human-computer interaction. In this paper present some key activities of which are proposed to some directions in HCI for the bridging between industry and academia in Bangladesh.
Burst Header Packet Flood Detection in Optical Burst Switching Network Using Deep Learning Model
(Elsevier B.V., 2018-11-19) Hasan, Md. Zahid; Hasan, K.M. Zubair; Sattar, Abdus
The Optical Burst Switching (OBS) network is mostly victimized to the Denial of Service (DOS) attack, referred as Burst Header Packet (BHP) flooding attack can prevent reasonable traffics from keeping the necessary resources at transitional core nodes. The attack scenario is to flood the malicious BHP without acknowledging Data Bursts (DB) which can affect low bandwidth utilization, degrade network performance, high data loss rate and ultimately DOS. Therefore, machine predicted analysis has become very promising in recent decades that can effectually identify the attack in the optical switching network. However, due to a very small number of samples of the datasets, traditional machine learning approaches such as Naïve Bayes, K-Nearest Neighbor’s (KNN) and Support Vector Machine (SVM) cannot analyse the data efficiently. In this regard, we intend a Deep Convolution Neural Network (DCNN) model to automatically detect the edge nodes at an early stage. Finally, presented that proposed deep model is working enhanced rather than any other traditional model (e.g. Naïve Bayes, SVM and KNN).
CNN and Transfer Learning Modeling for Jujube Spices Recognition
(IEEE, 2023-11-23) Sakib, Md. Mamun; Hasan, Md. Mehedi; Bibi, Rabeya; Rahman, Md. Hamidur; Sattar, Abdus
Jujube make up a major portion of Bangladesh's total fruit production. It might be challenging to tell the differences between the many different species of jujube. The manual examination of jujube' physical qualities, which is time-consuming and prone to human mistakes, is the method of identification most commonly used in traditional methods. In this investigation, we make use of computer vision methods to zero in on particular jujube types that are native to the Bangladeshi region. In our approach, the question is solved with the assistance of a deep convolutional neural network (CNN) and Transfer Learning. Our method obtains an outstanding 98.0% accuracy on a test dataset after being trained on photographs of jujube taken in and around Bangladesh. Our work contributes to the growing body of research on applying computer vision and deep learning techniques to agricultural problems. Further research can be conducted to improve the accuracy of our system by collecting a larger dataset of jujube images, exploring the generalizability of our system to other regions and countries, and investigating the potential for using our system to recognize other fruit crops in Bangladesh or other countries.
Computer vision based deep learning approach for toxic and harmful substances detection in fruits
(Scopus, 2024-02-15) Sattar, Abdus; Ridoy, Md. Asif Mahmud; Saha, Aloke Kumar; Babu, Hafiz Md. Hasan; Huda, Mohammad Nurul
Formaldehyde (CH₂O) is one of the significant chemicals mixed with different perishable fruits in Bangladesh. The fruits are artificially preserved for extended periods by dishonest vendors using this dangerous chemical. Such substances are complicated to detect in appearance. Hence, a reliable and robust detection technique is required. To overcome this challenge and address the issue, we introduce comprehensive deep learning-based techniques for detecting toxic substances. Four different types of fruits, both in fresh and chemically mixed conditions, are used in this experiment. We have applied diverse data augmentation techniques to enlarge the dataset. The performance of four different pre-trained deep learning models was then assessed, and a brand-new model named “DurbeenNet,” created especially for this task, was presented. The primary objective was to gauge the efficacy of our proposed model compared to well-established deep learning architectures. Our assessment centered on the models' accuracy in detecting toxic substances. According to our research, GoogleNet detected toxic substances with an accuracy rate of 85.53 %, VGG-16 with an accuracy rate of 87.44 %, DenseNet with an impressive accuracy rate of 90.37 %, and ResNet50 with an accuracy rate of 91.66 %. Notably, the proposed model, DurbeenNet, outshone all other models, boasting an impressive accuracy rate of 96.71 % in detecting toxic substances among the sample fruits.
Crime Rate Prediction Using Machine Learning and Data Mining
(Soft Computing Techniques and Applications. Advances in Intelligent Systems and Computing, Springer, 2020-11-28) Mahmud, Sakib; Nuha, Musfika; Sattar, Abdus
Analysis of crime is a methodological approach to the identification and assessment of criminal patterns and trends. In a number of respects cost our community profoundly. We have to go many places regularly for our daily purposes, and many times in our everyday lives we face numerous safety problems such as hijack, kidnapping, and harassment. In general, we see that when we need to go anywhere at first, we are searching for Google Maps; Google Maps show one, two, or more ways to get to the destination, but we always choose the shortcut route, but we do not understand the path situation correctly. Is it really secure or not that’s why we face many unpleasant circumstances; in this job, we use different clustering approaches of data mining to analyze the crime rate of Bangladesh and we also use K-nearest neighbor (KNN) algorithm to train our dataset. For our job, we are using main and secondary data. By analyzing the data, we find out for many places the prediction rate of different crimes and use the algorithm to determine the prediction rate of the path. Finally, to find out our safe route, we use the forecast rate. This job will assist individuals to become aware of the crime area and discover their secure way to the destination.
Crime Rate Prediction Using Machine Learning and Data Mining
(Scopus, 2021) Mahmud, Sakib; Nuha, Musfika; Sattar, Abdus
Analysis of crime is a methodological approach to the identification and assessment of criminal patterns and trends. In a number of respects cost our community profoundly. We have to go many places regularly for our daily purposes, and many times in our everyday lives we face numerous safety problems such as hijack, kidnapping, and harassment. In general, we see that when we need to go anywhere at first, we are searching for Google Maps; Google Maps show one, two, or more ways to get to the destination, but we always choose the shortcut route, but we do not understand the path situation correctly. Is it really secure or not that’s why we face many unpleasant circumstances; in this job, we use different clustering approaches of data mining to analyze the crime rate of Bangladesh and we also use K-nearest neighbor (KNN) algorithm to train our dataset. For our job, we are using main and secondary data. By analyzing the data, we find out for many places the prediction rate of different crimes and use the algorithm to determine the prediction rate of the path. Finally, to find out our safe route, we use the forecast rate. This job will assist individuals to become aware of the crime area and discover their secure way to the destination.
Customer Data Prediction and Analysis in E-commerce Using Machine Learning
(Institute of Advanced Engineering and Science (IAES), 2024-08-15) Rahib, Md Abdullah Al; Saha, Nirjhor; Sattar, Abdus
Customer churn is a major challenge faced by e-commerce companies, as it leads to loss of revenue and decreased customer loyalty. In recent years, for predicting and reducing client churn machine learning techniques are powerful tools. This research aims to explore the use of machine learning algorithms for predicting customer churn, annual spending, and product on-time delivery in e-commerce. The study first conducted a comprehensive review of the literature on customer churn in machine learning. The literature showed that customer churn has been predicted successfully using a variety of machine learning algorithms, including support vector machine (SVM), random forest, and decision tree in various industries. To address this gap in the literature, the study conducted an empirical analysis of customer churn in e-commerce using machine learning algorithms. The data were then pre-processed and analyzed utilizing machine learning techniques for prediction. According to the study’s findings, machine learning algorithms are effective in predicting customer churn, and product on-time delivery in e-commerce. The best-performing algorithm SVM achieved an accuracy of 83.45% in predicting customer churn and 68.42% for product on-time delivery prediction.
Deployment of E-Services Based Contextual Smart Agro System Using Internet of Things
(Daffodil International University, 2022-02-01) Sattar, Abdus; Shampod, Yeasin Arafat; Ahmed, Md. Tanjid; Akter, Nasrin; Mahmud, Arif
Climate change's effects are becoming more apparent, and farmers are bearing the brunt of the consequences. As a result, by 2050, food production is expected to decline by 18%. Therefore, the study's goal is to develop effective and well-organized roadmap for context-based smart agricultural systems using a pre-determined ICT framework. Following that, this study offers a four-level conceptual framework for an e-services-based smart agro system utilizing internet of things (IoT). Here, each level optimizes the IoT infrastructure to accept e-services based on contextual information supplied by the e-services. Furthermore, the proposed ICTization process intends to broaden the role of ICT technology development. Besides, the system's views decrease misunderstandings about technology, growth, and connectivity while also enhancing raw data, administration, and service synchronization. Farmers, agricultural officers, and network operators, for example, are all included in the proposed roadmap, which includes omnipresent farm treatment services. Precision farming, on the other hand, need new knowledge and innovation in order to achieve an integrated and comprehensive approach to technology.