Browsing by Author "Azad, AKM"

Now showing 1 - 6 of 6

An Intelligent Thyroid Diagnosis System Utilising Multiple Ensemble and Explainable Algorithms with Medical Supported Attributes
(Elsevier, 2023-01-15) Sutradhar, Ananda; Al Rafi, Mustahsin; Ghosh, Pronab; Shamrat, F. M.Javed Mehedi; Moniruzzaman, Md.; Ahmed, Kawsar; Azad, AKM; Bui, Francis M.; Chen, Li; Moni, Mohammad Ali
The widespread impact of thyroid disease and its diagnosis is a challenging task for healthcare experts. The conventional technique for predicting such a vital disease is complex and time-consuming. A data-driven approach may offer predictive solutions, but it relies on all relevant attributes, which are computationally expensive. Hence, we propose a novel machine learning (ML) based disease prediction system that could potentially predict it by considering three crucial steps. First, to reduce the dimension of the dataset, three feature selection techniques were employed, including Feature Importance (FIS), Information Gain Selections (IGS), and Least Absolute Shrinkage and Selection Operator (LAS). Moreover, recommended medical references were considered while developing a feature set having the identical attributes as High-Risk Factors (HRF). Second, the models, including the Three Stage Hybrid Classifier (3SHC) and the Three Stage Hybrid Artificial Neural Network (3SHANN), are used as classifiers on the training data set. Third, a Local Interpretable Model-agnostic Explanations (LIME) to the 3SHC with the HRF samples was applied to individually explain the predictions. Then, the overall behaviors of both gender and age categories were explored with the help of a Partial Dependence Plot (PDP). Finally, the proposed system is validated with extensive experiments where the 3SHC achieves an accuracy (ACC) of 99.29%, which can play a crucial role in preventing thyroid disease and alleviating stress in the healthcare sector.
Automation, heat loss reduction and optimum positioning of solar hot water system with storage tank in Bangladesh
(© 2016 Published by BRAC University, 2016) Ferdous, Jannatul; Swjo, Rafiur Rahman; Hasan, Raied; Azad, AKM
Since time immemorial, the necessity for hot water has been indispensable regardless of the advent of modem technology. In the dawn of the 21st century, only the means to heat the water has changed - now we mostly use electricity and gas in place of woods and other natural fuel. With that being said, lots of gas and electricity is being devoted to heat up the liquid for uses in hospitals, industries and households and the dernaod for hot water is ever climbing. Natural resources like fuel and coal are in liruited amouots and will not be able to sustain forever. Conseqoently, renewable energy is starting to gaio popularity in countries like Bangladesh. As a commitment to the development of the energy sector of Bangladesh, Control and Applications Research Centre (CARC) ofBRAC University has developed a Solar Hot Water System (SHWS) that would utilize solar energy to heat water, which could be used for several purposes like sterilization of medical equipment, cleaning of dishes, etc. An automated pilot project haa been implemented on the rooftop of BRAC University and research work haa been conducted for increasing the efficiency of the whole system by increasing the captured insolation and reducing wastage of heat overnight through insulation of the storage tank. With regard to procedural perspectives, this paper contemplates on highlighting the techoology implemented in the system and the improvisations made to elevate the efficiency and present a viable comparison between commercially available hot water systems with the developed automated uninterruptable SHWS.
Cancer Classification Utilizing Voting Classifier With Ensemble Feature Selection Method and Transcriptomic Data
(MDPI Publications, 2023-09-14) Khatun, Rabea; Akter, Maksuda; Islam, Md. Manowarul; Uddin, Md. Ashraf; Talukder, Md. Alamin; Kamruzzaman, Joarder; Azad, AKM; Paul, Bikash Kumar; Almoyad, Muhammad Ali Abdulllah; Aryal, Sunil; Moni, Mohammad Ali
Biomarker-based cancer identification and classification tools are widely used in bioinformatics and machine learning fields. However, the high dimensionality of microarray gene expression data poses a challenge for identifying important genes in cancer diagnosis. Many feature selection algorithms optimize cancer diagnosis by selecting optimal features. This article proposes an ensemble rank-based feature selection method (EFSM) and an ensemble weighted average voting classifier (VT) to overcome this challenge. The EFSM uses a ranking method that aggregates features from individual selection methods to efficiently discover the most relevant and useful features. The VT combines support vector machine, k-nearest neighbor, and decision tree algorithms to create an ensemble model. The proposed method was tested on three benchmark datasets and compared to existing built-in ensemble models. The results show that our model achieved higher accuracy, with 100% for leukaemia, 94.74% for colon cancer, and 94.34% for the 11-tumor dataset. This study concludes by identifying a subset of the most important cancer-causing genes and demonstrating their significance compared to the original data. The proposed approach surpasses existing strategies in accuracy and stability, significantly impacting the development of ML-based gene analysis. It detects vital genes with higher precision and stability than other existing methods.
Exploring Gene Regulatory Interaction Networks and Predicting Therapeutic Molecules for Hypopharyngeal Cancer and Egfr-mutated Lung Adenocarcinoma
(John Wiley & Sons Ltd, 2024-04-16) Bhattacharjya, Abanti; Islam, Md Manowarul; Uddin, Md Ashraf; Talukder, Md Alamin; Azad, AKM; Aryal, Sunil; Paul, Bikash Kumar; Tasnim, Wahia; Almoyad, Muhammad Ali Abdulllah; Moni, Mohammad Ali
Hypopharyngeal cancer is a disease that is associated with EGFR-mutated lung adenocarcinoma. Here we utilized a bioinformatics approach to identify genetic commonalities between these two diseases. To this end, we examined microarray datasets from GEO (Gene Expression Omnibus) to identify differentially expressed genes, common genes, and hub genes between the selected two diseases. Our analyses identified potential therapeutic molecules for the selected diseases based on 10 hub genes with the highest interactions according to the degree topology method and the maximum clique centrality (MCC). These therapeutic molecules may have the potential for simultaneous treatment of these diseases.
Multi-View Soft Attention-Based Model for the Classification of Lung Cancer-Associated Disabilities
(2024-10-14) Esha, Jannatul Ferdous; Islam, Tahmidul; Pranto, Md. Appel Mahmud; Borno, Abrar Siam; Faruqui, Nuruzzaman; Abu Yousuf, Mohammad; Azad, AKM; Al-Moisheer, Asmaa Soliman; Alotaibi, Naif; Alyami, Salem A.; Ali Moni, Mohammad
The detection of lung nodules at their early stages may significantly enhance the survival rate and prevent progression to severe disability caused by advanced lung cancer, but it often requires manual and laborious efforts for radiologists, with limited success. To alleviate it, we propose a Multi-View Soft Attention-Based Convolutional Neural Network (MVSA-CNN) model for multi-class lung nodular classifications in three stages (benign, primary, and metastatic). Initially, patches from each nodule are extracted into three different views, each fed to our model to classify the malignancy. A dataset, namely the Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI), is used for training and testing. The 10-fold cross-validation approach was used on the database to assess the model’s performance. The experimental results suggest that MVSA-CNN outperforms other competing methods with 97.10% accuracy, 96.31% sensitivity, and 97.45% specificity. Conclusions: We hope the highly predictive performance of MVSA-CNN in lung nodule classification from lung Computed Tomography (CT) scans may facilitate more reliable diagnosis, thereby improving outcomes for individuals with disabilities who may experience disparities in healthcare access and quality.
SafetyMed: A Novel IoMT Intrusion Detection System Using CNN-LSTM Hybridization
(MDPI Publications, 2023-08-22) Faruqui, Nuruzzaman; Yousuf, Mohammad Abu; Whaiduzzaman, Md.; Azad, AKM; Alyami, Salem A.; Liò, Pietro; Kabir, Muhammad Ashad; Moni, Mohammad Ali
The Internet of Medical Things (IoMT) has become an attractive playground to cybercriminals because of its market worth and rapid growth. These devices have limited computational capabilities, which ensure minimum power absorption. Moreover, the manufacturers use simplified architecture to offer a competitive price in the market. As a result, IoMTs cannot employ advanced security algorithms to defend against cyber-attacks. IoMT has become easy prey for cybercriminals due to its access to valuable data and the rapidly expanding market, as well as being comparatively easier to exploit.As a result, the intrusion rate in IoMT is experiencing a surge. This paper proposes a novel Intrusion Detection System (IDS), namely SafetyMed, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to defend against intrusion from sequential and grid data. SafetyMed is the first IDS that protects IoMT devices from malicious image data and sequential network traffic. This innovative IDS ensures an optimized detection rate by trade-off between False Positive Rate (FPR) and Detection Rate (DR). It detects intrusions with an average accuracy of 97.63% with average precision and recall, and has an F1-score of 98.47%, 97%, and 97.73%, respectively. In summary, SafetyMed has the potential to revolutionize many vulnerable sectors (e.g., medical) by ensuring maximum protection against IoMT intrusion.