Abdelilah Jilbab

This study compares the performance of twenty-one machine learning algorithms for the automatic identification of cardiac abnormalities using single-lead ECG signals, aiming to determine the most suitable model for connected cardiac monitoring devices. We specifically examine five cardiac conditions: normal rhythm (NOR), premature atrial contraction (APC), left bundle branch block (LBBB), right bundle branch block (RBBB), and premature ventricular contraction (VPC). Single-lead ECG signals were extracted from the MIT-BIH Arrhythmia Database. The data underwent systematic preprocessing, including class balancing, normalization, and wavelet-based denoising. Selected algorithms were trained and evaluated using standard metrics such as confusion matrix, precision, recall, F1-score, ROC-AUC curve, and computation time. A comparative statistical analysis was conducted using the Friedman test to assess the significance of differences among models. Experimental results showed significant variations among the evaluated machine learning models in terms of predictive accuracy and computational efficiency. Several algorithms were identified as particularly suitable, combining high performance and low computational cost. This study underscores the importance of careful selection of machine learning algorithms for remote cardiac monitoring, particularly in resource-constrained environments such as Internet of Medical Things (IoMT) settings. Practical recommendations are provided to guide developers and practitioners in selecting the most appropriate models for embedded biomedical applications considering operational and energy constraints.

Objectives: Parkinson’s disease (PD) is a chronic neurodegenerative disorder characterized by central nervous system dysfunction. Early identification may enable prompt treatment and help slow the progression of disabling symptoms. Previous studies have reported that clinical assessments based on visual interpretation may be insufficiently accurate and often miss early PD. Therefore, this study aimed to develop an automated single-photon emission computed tomography-based model for binary classification of healthy controls and patients with early PD.Methods: We analyzed 514 DaTSCAN images from the Parkinson’s Progression Markers Initiative database, using one unique scan per individual. The workflow comprised three main stages: image processing; computation of 23 features, including radial, threshold, boundary, and striatal binding ratio features; and image classification using machine learning algorithms.Results: The medium Gaussian support vector machine achieved an accuracy of 97.09% ± 1.53% (95% confidence interval, 95.11%–99.07%), sensitivity of 98.18% ± 1.48%, specificity of 93.85% ± 3.44%, and area under the receiver operating characteristic curve of 98.49% ± 1.31%. This performance was significantly higher than that of the three-dimensional convolutional neural network baseline model (accuracy, 94.55% ± 2.98%; p = 0.045), while requiring substantially less training time.Conclusions: In this dataset, carefully designed feature engineering combined with classical machine learning outperformed the deep-learning baseline when the training data were limited and the selected features aligned with clinical diagnostic criteria. This approach achieved high accuracy for early PD detection and may provide computational efficiency and interpretability suitable for clinical implementation.

The early diagnosis of Parkinson's disease (PD) using SPECT imaging continues to be challenging due to the subtle dopaminergic deficits present in the early stages of the disease. This study proposes a novel hybrid approach combining conventional and deep learning features to improve PD classification, and applies it to reclassify scans without evidence of dopaminergic deficit (SWEDD) cases. We used SPECT images from early PD patients and healthy controls (HC) and extracted SBR metrics, morphometric, and deep learning features. Our multi-stage feature selection pipeline employed near-zero variance filtering, ANOVA F-test analysis, correlation-based feature elimination, and Random Forest importance scoring. We evaluated multiple machine learning algorithms and selected Linear Discriminant Analysis as the optimal classifier, then applied this model to reclassify 79 SWEDD cases. Feature selection reduced 79 significant features to 15 optimal features: 1 SBR metric (6.7%), 7 morphometric (46.7%), and 7 deep features (46.7%). The hybrid Linear Discriminant model achieved the best performance, outperforming individual feature approaches with 97.40% test accuracy, 96.25% sensitivity, 98.65% specificity, and 99.59% AUC. Statistical analysis revealed morphometric features had the highest mean importance (0.0699 ± 0.0539), followed by deep (0.0400 ± 0.0570) and SBR features (0.0206 ± 0.019). SWEDD reclassification identified 5 cases (6.3%) with imaging patterns consistent with early PD, while 74 cases (93.7%) maintained HC characteristics. This study presents a proof-of-concept demonstration of the effectiveness of integrating conventional measures with deep learning techniques for improving the early diagnosis of PD, while offering new insights into SWEDD case reclassification.

Water utilities continue to lose a lot of Non-Revenue Water (NRW) because of leaks that go undetected. This makes it necessary to find accurate but easy-to-use monitoring solutions. This paper presents FiT-WST+, a wavelet-guided Frequency-Informed Transformer (FiT) designed for the classification of five distinct leak types utilising accelerometer measurements. The proposed architecture combines the spectral modelling ability of a FIT with the stable translation-invariant representation of the Wavelet Scattering Transform (WST). The model uses a guided attention mechanism to combine spectral and scattering cues that work well together to make classes more distinct, especially for fault types that are similar. On the held-out test set, FiT-WST+ achieves 99.6% accuracy, 99.6% balanced accuracy, and a 99.6% macro-averaged F1-score. Comparative benchmarking against recent methods tested on the same dataset shows that this method works at a low sampling rate (1 kHz), which greatly lowers bandwidth needs and allows for scalable deployment on edge devices with limited resources for real-time monitoring of important water infrastructure.

Parkinson's disease (PD) is a progressive neurodegenerative disorder that primarily impairs motor functions, leading to symptoms such as tremors and micrographia. Even though early identification of PD is crucial for effective intervention, existing methods of diagnosis are highly invasive and not very sensitive to the early stages of the diseases. The goal of this research is to determine if handwriting could be a non-invasive way to diagnose PD at an early stage. We employed a dataset of 3,264 hand-drawn waves and spirals to evaluate the performance of hybrid machine learning and deep learning models which included Support Vector Machine (SVM), Random Forest (RF), Visual Geometry Group-16 (VGG-16) and MobileNetV2. Combing SVM with VGG-16 for the task reached a stunning 99.00% accuracy for identifying PD, performing the best out of all tested models, demonstrating superior performance in the early identification of PD. The proposed approach not only outperforms existing diagnostic methods but also underscores the transformative potential of handwriting analysis tools in PD diagnosis, aiding in automatic PD detection and enhancing patient outcomes.

Parkinson's disease (PD) is a progressive neurological disorder that affects millions worldwide, leading to motor dysfunction and significant reductions in quality of life. Early diagnosis is pivotal for initiating timely treatment and improving long-term patient outcomes, yet existing diagnostic methods, which often rely on clinical evaluations and imaging, are prone to delays and varying accuracy. This study presents an innovative, non-invasive approach to early PD detection through the analysis of handwriting patterns, offering a potential alternative to traditional diagnostic techniques. Leveraging a publicly available and meticulously normalized handwriting dataset, our approach applies advanced data processing methods to identify subtle neuromotor impairments associated with PD. Through the integration of robust feature selection processes and cutting-edge machine learning models, we achieved a high accuracy rate of 83.02%, highlighting the method’s reliability. The findings suggest that this approach could significantly enhance early PD detection, leading to more personalized therapeutic strategies that align with the stages of disease progression and potentially delaying the onset of severe symptoms.

This article investigates the integration of the Internet of Things (IoT), digital twin (DT), and augmented reality (AR) technologies to advance digital services in the management, monitoring, and control of agricultural greenhouses, addressing the sector's technological demands. By leveraging advanced technologies, this research aims to enhance efficiency across various fields, including industry, logistics, and commerce. The core objective is to develop a prototype IoT system, incorporating DT and AR, to create a digital transformation environment. This system provides real-time visualization and monitoring of sensor data from physical IoT devices, enabling user interaction and control through microcontroller-based sensor nodes installed in the greenhouse. Data transmission is achieved using the MQTT protocol, while an AR application facilitates greenhouse visualization and control. The findings demonstrate the system's effectiveness in enabling real-time communication between IoT devices and the AR application, with users successfully performing tasks without prior experience, thereby validating the system's usability and efficiency.