Browsing by Author "Hossain, Shahed"

Now showing 1 - 20 of 22

A Deep Learning Approach to Detect Breast Cancer Disease from Mammogram Images
(IEEE, 2023-12-15) Sohel, Amir; Hossain, Shahed; Hasan, Md Umaid; Islam, Onamika; Das, Utpal Chandra; Rahman, Md. Mahfuzur
Breast cancer is a significant cause of mortality among women. Breast cancer is regarded as the most severe concern among women. The early detection of breast cancer can potentially impact mortality rates significantly. The implementation of deep learning techniques has the potential to mitigate the death rate associated with breast cancer by the early detection of the disease. This study used several transfer learning models for a specific task and assessed the specificity of each model’s predictions. The dataset was collected from a publicly available resource that contains mammogram images of breasts. We have used several image preprocessing techniques to enhance image quality. The primary objective is to evaluate the precision and usefulness of each algorithm in accurately classifying data, using factors such as efficiency, accuracy, recall, specificity, and F1-score. The MobileNet model showed remarkable performance compared to other models. Our proposed model’s training and validation accuracy were reported as 99.54%, which indicates that this model is a best-fit model
A Digital Data Hiding Technique with Missing Puzzle and Seek Algorithm
(IEEE, 2020-11) Islam, Md. Ashiqul; Tabassum, Tasfia; Hossen, Md. Sagar; Hossain, Shahed; Hossain, Mosharof; Jony, Anik Hassan
presently a day’s data dissemination over the world become progressively simpler because of quick web and advancement of various kind of technology, for this explanation individuals become increasingly stressed about their information security. For this nowadays people use steganography to make the information secure by hiding and blending the data that make them hard to perceive by hackers. For concealing mystery data in content and pictures, there exists a huge assortment of Steganography methods some are more mind-boggling than others and every one of them has particular solid and feeble focuses. We are looking for the calculation to discover the missing puzzle word which otherwise called mystery calculation by using seek algorithm. For improving the security of mystery message, the message is mixed utilizing onetime cushion plot before being covered and Figure content is at that point hidden in the spread. This is the most efficient data hiding security system and probably its increases the data security all over the world and maintain our privacy.
A New Approach to Hiding Data in the Images Using Steganography Techniques Based on AES and RC5 Algorithm Cryptosystem
(IEEE, 2020-09) Hossen, Md. Sagar; Islam, Md. Ashiqul; Khatun, Tania; Hossain, Shahed; Rahman, Md. Mahfujur
In the new era of modern science and technology is developing day by day, data confidentiality is risky, all over the world and it increases rapidly. In this paper, a new approach to hiding the data using steganography techniques is proposed based on AES and RC5 algorithm cryptosystem. Steganography is the beauty of hiding secret data behind the digital images, videos, audios and text to cover the secret communication. A cryptosystem is the process which given our method more perfection. The visual quality of the cover image nice, no one can think about it how confidential data are transmitted using this method. This proposed method and algorithm capacity is highly flexible than other published algorithm. The AES and RC5 algorithm had no complexity and it looks like very well to hide the confidential data.
A Predictive Analysis Framework of Heart Disease Using Machine Learning Approaches
(Daffodil International University, 22-06-29) Molla, Shourav; Shamrat, F. M. Javed Mehedi; Rafi, Raisul Islam; Umaima, Umme; Umaima, Umme; Hossain, Shahed; Mahmud, Imran
Heart disease is among the leading causes for death globally. Thus, early identification and treatment are indispensable to prevent the disease. In this work, we propose a framework based on machine learning algorithms to tackle such problems through the identification of risk variables associated to this disease. To ensure the success of our proposed model, influential data pre-processing and data transformation strategies are used to generate accurate data for the training model that utilizes the five most popular datasets (Hungarian, Stat log, Switzerland, Long Beach VA, and Cleveland) from UCI. The univariate feature selection technique is applied to identify essential features and during the training phase, classifiers, namely extreme gradient boosting (XGBoost), support vector machine (SVM), random forest (RF), gradient boosting (GB), and decision tree (DT), are deployed. Subsequently, various performance evaluations are measured to demonstrate accurate predictions using the introduced algorithms. The inclusion of Univariate results indicated that the DT classifier achieves a comparatively higher accuracy of around 97.75% than others. Thus, a machine learning approach is recognize, that can predict heart disease with high accuracy. Furthermore, the 10 attributes chosen are used to analyze the model's outcomes explain ability, indicating which attributes are more significant in the model's outcome.
Addressing Missed Opportunities for Service Provisions in Primary Healthcare Clinics
(2003) Hossain, Shahed; Mercer, Alec; Khatun, Jahanara; Hasan, Yousuf; Uddin, Jasim; Kabir, Humayun; Uddin, Nowsher; Saha, Nirod Chandra
Addressing missed opportunities in primary health care clinics
(2003-07-30) Hossain, Shahed; Mercer, Alec; Khatun, Jahanara; Hasan, Yousuf; Uddin, Jasim; Kabir, Humayun; Uddin, A.H. Nowsher; Saha, Nirod Chandra
An Online E-Cash Scheme with Digital Signature Authentication Cryptosystem
(Springer, 2021-01-26) Islam, Md. Ashiqul; Hossen, Md. Sagar; Hossain, Mosharof; Nime, Jannati; Hossain, Shahed; Dutta, Mithun
This paper is intended to enlighten the curious minds on how to use cryptocurrency easily in our day-to-day life. What bitcoin really is? The relation between bank and the user, who has bitcoin, describes potential system design, basic payment method using cryptocurrency, the payment gateway and explains it in the simplest way, and finally the conclusion. Cryptocurrency is one type of digital virtual currencies that have not physically existed. This proposed research work is mainly focused on bitcoin, which is the decentralized digital currency, and it conducts peer-to-peer connection, to make it safe and secure than other digital currency types or hand cash. This paper has proposed an online E-cash scheme with a digital signature authentication cryptosystem that has the tendency to replace the traditional fiat currency, and bitcoin is used instead of the conventional currency and payment system. We can exchange bitcoin to E-cash and E-cash to bitcoin also. This system will find a new way to protect the users from unauthorized transactions in online and offline E-cash system.
An Online E-Cash Scheme with Digital Signature Authentication Cryptosystem
(Scopus, 2021) Islam, Md. Ashiqul; Hossen, Md. Sagar; Hossain, Mosharof; Nime, Jannati; Hossain, Shahed; Dutta, Mithun
This paper is intended to enlighten the curious minds on how to use crypto currency easily in our day-to-day life. What bit coin really is? The relation between bank and the user, who has bit coin, describes potential system design, basic payment method using crypto currency, the payment gateway and explains it in the simplest way, and finally the conclusion. Crypto currency is one type of digital virtual currencies that have not physically existed. This proposed research work is mainly focused on bitcoin, which is the decentralized digital currency, and it conducts peer-to-peer connection, to make it safe and secure than other digital currency types or hand cash. This paper has proposed an online E-cash scheme with a digital signature authentication cryptosystem that has the tendency to replace the traditional fiat currency, and bitcoin is used instead of the conventional currency and payment system. We can exchange bitcoin to E-cash and E-cash to bitcoin also. This system will find a new way to protect the users from unauthorized transactions in online and offline E-cash system.
Automated Breast Tumor Ultrasound Image Segmentation With Hybrid UNet and Classification Using Fine-Tuned CNN Model
(Elsevier, 2023-10-20) Hossain, Shahed; Azam, Sami; Montaha, Sidratul; Karim, Asif; Chowa, Sadia Sultana; Mondol, Chaity; Hasan, Md Zahid; Jonkman, Mirjam
Introduction Breast cancer stands as the second most deadly form of cancer among women worldwide. Early diagnosis and treatment can significantly mitigate mortality rates. Purpose The study aims to classify breast ultrasound images into benign and malignant tumors. This approach involves segmenting the breast's region of interest (ROI) employing an optimized UNet architecture and classifying the ROIs through an optimized shallow CNN model utilizing an ablation study. Method Several image processing techniques are utilized to improve image quality by removing text, artifacts, and speckle noise, and statistical analysis is done to check the enhanced image quality is satisfactory. With the processed dataset, the segmentation of breast tumor ROI is carried out, optimizing the UNet model through an ablation study where the architectural configuration and hyperparameters are altered. After obtaining the tumor ROIs from the fine-tuned UNet model (RKO-UNet), an optimized CNN model is employed to classify the tumor into benign and malignant classes. To enhance the CNN model's performance, an ablation study is conducted, coupled with the integration of an attention unit. The model's performance is further assessed by classifying breast cancer with mammogram images. Result The proposed classification model (RKONet-13) results in an accuracy of 98.41 %. The performance of the proposed model is further compared with five transfer learning models for both pre-segmented and post-segmented datasets. K-fold cross-validation is done to assess the proposed RKONet-13 model's performance stability. Furthermore, the performance of the proposed model is compared with previous literature, where the proposed model outperforms existing methods, demonstrating its effectiveness in breast cancer diagnosis. Lastly, the model demonstrates its robustness for breast cancer classification, delivering an exceptional performance of 96.21 % on a mammogram dataset. Conclusion The efficacy of this study relies on image pre-processing, segmentation with hybrid attention UNet, and classification with fine-tuned robust CNN model. This comprehensive approach aims to determine an effective technique for detecting breast cancer within ultrasound images.
EAH-Net: A Novel Ensemble Attention-Based Hybrid Architecture for Breast Cancer Diagnosis Utilizing Ultrasound Images
(Scopus, 2024-10-31) Hasan, Md. Zahid; Hossain, Shahed; Jim, Risul Islam; Bulbul, Abdullah Al-Mamun; Rahman, Md. Tanvir; Moni, Mohammad Ali
Breast cancer is a complex and often fatal malignancy in women worldwide, requiring thorough medical examinations. Accurately detecting breast cancer is challenging due to its diverse forms, stages, symptoms, and diagnostic techniques. With advancements in artificial intelligence, an automated computerized method can potentially aid radiologists in the early detection of breast cancer. This study presents a novel and robust deep neural network, EAH-Net, for breast cancer diagnosis using ultrasound images. The EAH-Net architecture comprises an ensemble attention module, a modified UNet model that performs segmentation by isolating regions of interest, and a hybrid approach to classify breast cancers accurately. Besides, we employed explainable AI techniques to highlight the most significant regions, assisting radiologists in making more informed decisions. The proposed segmentation framework yields promising outcomes across Jaccard, Precision, Recall, Specificity, and Dice metrics, averaging 89.26 ± 0.36, 91.79 ± 1.13, 92.98 ± 1.08, 99.38 ± 0.35, and 95.26 ± 0.45 percents, respectively. The hybrid classification framework demonstrates outstanding performance with an accuracy of 98.48 ± 0.18%. Overall, EAH-Net offers a reliable and robust computer-aided solution for automated breast cancer diagnosis.
GDRNet: A Novel Graph Neural Network Architecture for Diabetic Retinopathy Detection
(2024-01-24) Hossain, Shahed; Hasan, Md. Zahid; Jim, Risul Islam; Bulbul, Abdullah Al-Mamun; Khan, Risala Tasin; Kaise, M. Shamim; Ali Moni, Mohammad
Diabetic retinopathy is a significant cause of global blindness, requiring practical early detection approaches that could save vision loss in millions of people. However, manual DR analysis is time-consuming and requires skilled clinicians. The advancement of artificial intelligence can facilitate early DR predictions. This study proposed GDRNet, a novel AI-empowered diagnosis system that utilizes graph theory for effective feature selection in DR grading classification. The EyePACS, Messidor, APTOS, IDRid, and DDR datasets are initially balanced using the nearest neighbor oversampling approach. A deep graph correlation network (DGCN) extracts unique features from color eye fundus images by identifying intra-class connections. Then, an iterative random forest algorithm is employed for feature curation, ranking the most significant features from the DGCN. Subsequently, the iterative random forest enhances classification robustness by refining feature representations and aggregating multi-scale contextual information. Finally, a classifier using extreme gradient boosting based on a decision tree algorithm is trained with the optimized features to predict the outcomes. Experimental results reveal that GDRNet outperforms state-of-the-art DR grading classification methods with outstanding performance across various datasets: 100% specificity, 99.67% sensitivity, and 99.80% accuracy on Messidor; 100% specificity, 99.61% sensitivity, and 99.41% accuracy on APTOS; and comparable results on IDRid and DDR datasets. On the EyePACS dataset, it achieves 100% specificity, 99.20% sensitivity, and 99.50% accuracy. Based on these numerical findings, we expect that GDRNet could be utilized in healthcare for early and automated DR detection.
Healthcare-seeking behaviour and BCC needs for urban population : a qualitative study
(International Centre for Diarrhoeal Diseases Research Bangladesh:Dhaka, 2000) Alam, S.M. Nurul; Khanam, Rasheda; Hossain, Shahed
Healthcare-Seeking Behaviour and BCC Needs for Urban Population: A Qualitative Study
(2000) Alam, S.M. Nurul; Khanam, Rasheda; Hossain, Shahed
Impact of low-cost bidding on a Contracted-Out (CO) : urban primary health care project in Bangladesh: Implications for change
(Health Systems & Population Studies Division, icddr,b, 2018-05) Khan, Shaan Muberra; Islam, Rubana; Hossain, Shahed; Bashar, Farzana; Yusuf, Sifat S; Sikder, Adel A. S.; Adams, Alayne
Infectious diseases and vaccine sciences: strategic directions
(2008-09) Luby, Stephen P.; Brooks, W. Abdullah; Zaman, K.; Hossain, Shahed; Ahmed, Tahmeed
Operations research on ESP Delivery : addressing missed oppertunities for service provisions in Primary Health Clinics
(International Centre for Diarrhoeal Diseases Research Bangladesh:Dhaka, 2003) Hossain, Shahed; Mercer, Alec; Khatun, Jahanara; Hasan, Yousuf; Uddin, Jasim; Kabir, Humayun; Uddin, Nowsher; Saha, Nirod Chandra
Operations research on ESP delivery and community clinics in Bangladesh : preliminary assessment of performance of two selected community clinics
(Dhaka: ICDDR,B, 2002, 2002) Sarker, Sukumar; Islam, Ziaul; Hossain, Shahed; Saifi, Rumana Akhter; Saha, Nirod Chandra; Jahan, Monowar; Begum, Hosne Ara
Operations Research on ESP Delivery in Urban Areas
(2002) Hossain, Shahed; Sarker, Sukumar; Khanam, Rasheda; Islam, Ziaul; Saha, Nirod Chandra; Routh, Subrata
Operations research on ESP delivery in urban areas : operationalizing an urban essential services package clinic ; findings and implications
(Dhaka: ICDDR,B, 2002, 2002) Hossain, Shahed; Sarker, Sukumar; Khanam, Rasheda; Islam, Ziaul; Saha, Nirod Chandra; Routh, Subrata
Preliminary Assessment of Performance of Two Selected Community Clinics
(2002) Sarker, Sukumar; Islam, Ziaul; Hossain, Shahed; Saifi, Rumana Akhter; Saha, Nirod Chandra; Jahan, Monowar; Begum, Hosne Ara; Routh, Subrata