Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
595
result(s) for
"Hammad, Mohamed"
Sort by:
Internet of Medical Things and Healthcare 4.0: Trends, Requirements, Challenges, and Research Directions
Healthcare 4.0 is a recent e-health paradigm associated with the concept of Industry 4.0. It provides approaches to achieving precision medicine that delivers healthcare services based on the patient’s characteristics. Moreover, Healthcare 4.0 enables telemedicine, including telesurgery, early predictions, and diagnosis of diseases. This represents an important paradigm for modern societies, especially with the current situation of pandemics. The release of the fifth-generation cellular system (5G), the current advances in wearable device manufacturing, and the recent technologies, e.g., artificial intelligence (AI), edge computing, and the Internet of Things (IoT), are the main drivers of evolutions of Healthcare 4.0 systems. To this end, this work considers introducing recent advances, trends, and requirements of the Internet of Medical Things (IoMT) and Healthcare 4.0 systems. The ultimate requirements of such networks in the era of 5G and next-generation networks are discussed. Moreover, the design challenges and current research directions of these networks. The key enabling technologies of such systems, including AI and distributed edge computing, are discussed.
Journal Article
Enhancing Smart Home Security: Anomaly Detection and Face Recognition in Smart Home IoT Devices Using Logit-Boosted CNN Models
Internet of Things (IoT) devices for the home have made a lot of people’s lives better, but their popularity has also raised privacy and safety concerns. This study explores the application of deep learning models for anomaly detection and face recognition in IoT devices within the context of smart homes. Six models, namely, LR-XGB-CNN, LR-GBC-CNN, LR-CBC-CNN, LR-HGBC-CNN, LR-ABC-CNN, and LR-LGBM-CNN, were proposed and evaluated for their performance. The models were trained and tested on labeled datasets of sensor readings and face images, using a range of performance metrics to assess their effectiveness. Performance evaluations were conducted for each of the proposed models, revealing their strengths and areas for improvement. Comparative analysis of the models showed that the LR-HGBC-CNN model consistently outperformed the others in both anomaly detection and face recognition tasks, achieving high accuracy, precision, recall, F1 score, and AUC-ROC values. For anomaly detection, the LR-HGBC-CNN model achieved an accuracy of 94%, a precision of 91%, a recall of 96%, an F1 score of 93%, and an AUC-ROC of 0.96. In face recognition, the LR-HGBC-CNN model demonstrated an accuracy of 88%, precision of 86%, recall of 90%, F1 score of 88%, and an AUC-ROC of 0.92. The models exhibited promising capabilities in detecting anomalies, recognizing faces, and integrating these functionalities within smart home IoT devices. The study’s findings underscore the potential of deep learning approaches for enhancing security and privacy in smart homes. However, further research is warranted to evaluate the models’ generalizability, explore advanced techniques such as transfer learning and hybrid methods, investigate privacy-preserving mechanisms, and address deployment challenges.
Journal Article
Deep CNN-based detection of cardiac rhythm disorders using PPG signals from wearable devices
Cardiac rhythm disorders can manifest in various ways, such as the heart rate being too fast (tachycardia) or too slow (bradycardia), irregular heartbeats (like atrial fibrillation-AF, ventricular fibrillation-VF), or the initiation of heartbeats in different areas from the norm (extrasystole). Arrhythmias can disrupt the balanced circulation, leading to serious complications like heart attacks, strokes, and sudden death. Medical devices like electrocardiography (ECG) and Holter monitors are commonly used for diagnosing and monitoring cardiac rhythm disorders. However, in recent years, the development of wearable devices has played a significant role in the detection and diagnosis of rhythm disorders through the use of photoplethysmography (PPG) signals. Wearable devices enable patients to continuously monitor their health status and allow doctors to provide earlier diagnoses and interventions. In this study, a 1D-CNN model is proposed to detect arrhythmias using PPG signals. A dataset prepared by the University of Massachusetts Medical Center (UMMC) containing both ECG and PPG signal data was utilized. In this dataset, ECG signals are filtered with a bandpass filter and raw PPG signals are divided into 30-second segments. Accuracy values were obtained by classifying ECG and PPG signals using a 1D CNN model. ECG signals were used as a reference. The proposed model achieved a 95.17% accuracy rate in detecting normal sinus rhythm (NSR), atrial fibrillation (AF), and premature atrial contractions (PAC) from PPG signals. Datasets are available for download on https://www.synapse.org/pulsewatch . The codes used in this study are available on the https://github.com/miraygunay/PPG-Code.git website.
Journal Article
Enhancing machine learning-based sentiment analysis through feature extraction techniques
A crucial part of sentiment classification is featuring extraction because it involves extracting valuable information from text data, which affects the model’s performance. The goal of this paper is to help in selecting a suitable feature extraction method to enhance the performance of sentiment analysis tasks. In order to provide directions for future machine learning and feature extraction research, it is important to analyze and summarize feature extraction techniques methodically from a machine learning standpoint. There are several methods under consideration, including Bag-of-words (BOW), Word2Vector, N-gram, Term Frequency- Inverse Document Frequency (TF-IDF), Hashing Vectorizer (HV), and Global vector for word representation (GloVe). To prove the ability of each feature extractor, we applied it to the Twitter US airlines and Amazon musical instrument reviews datasets. Finally, we trained a random forest classifier using 70% of the training data and 30% of the testing data, enabling us to evaluate and compare the performance using different metrics. Based on our results, we find that the TD-IDF technique demonstrates superior performance, with an accuracy of 99% in the Amazon reviews dataset and 96% in the Twitter US airlines dataset. This study underscores the paramount significance of feature extraction in sentiment analysis, endowing pragmatic insights to elevate model performance and steer future research pursuits.
Journal Article
Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions
Education is crucial for the growth of effective life skills and the allocation of needed resources. Higher education institutions are adopting advanced technologies, such as artificial intelligence (AI), to enhance traditional teaching methods. Predicting academic performance has become increasingly important, improving university rankings and expanding student opportunities. This study addresses challenges in performance analysis, quality education delivery, and student evaluation through machine learning (ML) models. Ten regression models including K-Nearest Neighbors Regressor, Linear Regression, CatBoost, XGBoost, AdaBoost, and ensemble voting regression (VR) algorithm based on the top five heterogeneous regressors as base models are employed to predict academic outcomes. Two datasets with distinct feature sets and sizes were used to evaluate the generalizability of the models. The first dataset comprises 10,000 samples and six features focused on study behaviors, prior performance, and extracurricular activities. The second dataset includes 6,607 records and 20 features encompassing academic habits, demographic attributes, and institutional factors such as attendance, teacher quality, and parental involvement. Best model performance goes to the linear regression in standalone ML models. Then, the proposed ensemble VR model was built using weighted averages based on the performances of the base models. The local interpretable model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP) are then used to explain the predictions produced by the proposed ensemble VR model. For the first dataset, the VR model achieved an RMSE of 0.1050, MAE of 0.0837, and R² of 0.9890. On the second, more complex dataset, the VR model also performed best with an R² of 0.7716 using the full feature set, highlighting its robustness and adaptability across diverse academic contexts. These results offer actionable insights for educators, administrators, and policymakers to better understand student performance drivers and support data-informed educational strategies.
Journal Article
Overcoming small-bandgap charge recombination in visible and NIR-light-driven hydrogen evolution by engineering the polymer photocatalyst structure
Designing an organic polymer photocatalyst for efficient hydrogen evolution with visible and near-infrared (NIR) light activity is still a major challenge. Unlike the common behavior of gradually increasing the charge recombination while shrinking the bandgap, we present here a series of polymer nanoparticles (Pdots) based on ITIC and BTIC units with different π-linkers between the acceptor-donor-acceptor (A-D-A) repeated moieties of the polymer. These polymers act as an efficient single polymer photocatalyst for H2 evolution under both visible and NIR light, without combining or hybridizing with other materials. Importantly, the difluorothiophene (ThF) π-linker facilitates the charge transfer between acceptors of different repeated moieties (A-D-A-(π-Linker)-A-D-A), leading to the enhancement of charge separation between D and A. As a result, the PITIC-ThF Pdots exhibit superior hydrogen evolution rates of 279 µmol/h and 20.5 µmol/h with visible (>420 nm) and NIR (>780 nm) light irradiation, respectively. Furthermore, PITIC-ThF Pdots exhibit a promising apparent quantum yield (AQY) at 700 nm (4.76%).
Designing an organic polymer photocatalyst for efficient hydrogen evolution in the near-infrared (NIR) light region is still a major challenge. The authors present here a series of polymer nanoparticles for a efficient hydrogen evolution under visible and NIR light irradiation, without combining or hybridizing with other materials.
Journal Article
Improving sentiment classification using a RoBERTa-based hybrid model
Several attempts have been made to enhance text-based sentiment analysis's performance. The classifiers and word embedding models have been among the most prominent attempts. This work aims to develop a hybrid deep learning approach that combines the advantages of transformer models and sequence models with the elimination of sequence models' shortcomings.
In this paper, we present a hybrid model based on the transformer model and deep learning models to enhance sentiment classification process. Robustly optimized BERT (RoBERTa) was selected for the representative vectors of the input sentences and the Long Short-Term Memory (LSTM) model in conjunction with the Convolutional Neural Networks (CNN) model was used to improve the suggested model's ability to comprehend the semantics and context of each input sentence. We tested the proposed model with two datasets with different topics. The first dataset is a Twitter review of US airlines and the second is the IMDb movie reviews dataset. We propose using word embeddings in conjunction with the SMOTE technique to overcome the challenge of imbalanced classes of the Twitter dataset.
With an accuracy of 96.28% on the IMDb reviews dataset and 94.2% on the Twitter reviews dataset, the hybrid model that has been suggested outperforms the standard methods.
It is clear from these results that the proposed hybrid RoBERTa-(CNN+ LSTM) method is an effective model in sentiment classification.
Journal Article
Detection of myocardial infarction based on novel deep transfer learning methods for urban healthcare in smart cities
One of the common cardiac disorders is a cardiac attack called Myocardial infarction (MI), which occurs due to the blockage of one or more coronary arteries. Timely treatment of MI is important and slight delay results in severe consequences. Electrocardiogram (ECG) is the main diagnostic tool to monitor and reveal the MI signals. The complex nature of MI signals along with noise poses challenges to doctors for accurate and quick diagnosis. Manually studying large amounts of ECG data can be tedious and time-consuming. Therefore, there is a need for methods to automatically analyze the ECG data and make diagnosis. Number of studies has been presented to address MI detection, but most of these methods are computationally expensive and faces the problem of overfitting while dealing real data. In this paper, an effective computer-aided diagnosis (CAD) system is presented to detect MI signals using the convolution neural network (CNN) for urban healthcare in smart cities. Two types of transfer learning techniques are employed to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed feature extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the VGG-MI1 model, the last layer of the VGG-Net model is replaced with a specific layer according to our requirements and various functions are optimized to reduce overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is selected as a feature descriptor of the ECG images to describe it with informative features. Considering the limited availability of dataset, ECG data is augmented which has increased the classification performance. A standard well-known database Physikalisch-Technische Bundesanstalt (PTB) Diagnostic ECG is used for the validation of the proposed framework. It is evident from experimental results that the proposed framework achieves a high accuracy surpasses the existing methods. In terms of accuracy, sensitivity, and specificity; VGG-MI1 achieved 99.02%, 98.76%, and 99.17%, respectively, while VGG-MI2 models achieved an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49%.
Journal Article
Explainable AI for lung cancer detection via a custom CNN on CT images
Lung cancer, which claims 1.8 million lives annually, is still one of the leading causes of cancer-related deaths globally. Patients with lung cancer frequently have a bad prognosis because of late-stage detection, which severely limits treatment options and decreases survival rates. Early detection is essential for better outcomes, but traditional CT image analysis is time-consuming, prone to error, and relies on subjective judgments. To overcome these issues, we propose a custom convolutional neural network (CNN) combined with explainable AI (XAI) techniques, particularly gradient-weighted class activation mapping (Grad-CAM). This approach is intended to reliably classify lung cancer into squamous cell carcinoma, large cell carcinoma, or adenocarcinoma. Unlike conventional methods, our approach not only achieves highly accurate classification of lung cancer subtypes but also incorporates clinically validated interpretability features to ensure alignment with medical diagnostics. Our model trained on a comprehensive dataset of CT images achieved an overall accuracy of 93.06%. This performance demonstrates the model’s robustness in detecting even subtle malignancies, with strong precision, recall, and F1-scores across all cancer types. Including interpretable Grad-CAM visualizations ensures reliability and transparency, aiding clinicians in understanding the model’s predictions. This innovative method demonstrates the potential to revolutionize early lung cancer detection and improve patient survival rates by combining state-of-the-art accuracy with explainability tailored for clinical application.
Journal Article