NENoureldin Elmadany

Noureldin Elmadany

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Noureldin Elmadany has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Impact of Sensor Placement and Gait Dynamics on Off-Body MBAN Channel Characteristics: A Comprehensive Performance Evaluation of BER and Data Throughput at 2.36–2.39 GHz

    by Nada Elmaradany, Heba A. Shaban, Noureldin Elmadany

    Medical body area networks (MBANs) operating in the 2360–2390 MHz band enable continuous health monitoring across a wide range of clinical and home-care applications. This paper presents a comprehensive performance evaluation of off-body MBAN links based on Monte Carlo simulations using empirically derived channel models from the IEEE 802.15.6 standard. Two transmitter locations, chest mounted and right wrist mounted sensors, are investigated under standing and walking conditions for distances ranging from 1 m to 4 m and angular orientations of 0°, 90°, 180°, and 270°. The impact of sensor placement and gait dynamics on bit error rate (BER) and theoretical maximum achievable throughput is analyzed. Constraints and practical hardware limitations are considered by restricting transmit power to specific absorption rate (SAR) and by analyzing energy consumption using parameters from commercial wearable transceivers. The obtained Eb/N0 values range from 10 dB to 76 dB at n=2, while throughput varies between 68.5 bps and 270 Mbps depending on distance, activity, and orientation. High Eb/N0 values observed under severe fading conditions are shown to be impractical under realistic power and energy constraints. The results indicate that transmission distance is the dominant performance factor in static scenarios, whereas sensor placement becomes more important under dynamic conditions. In general, chest mounted sensors outperform wrist mounted sensors due to reduced body shadowing in the first case. Furthermore, the use of equal gain combining (EGC) is shown to overcome mobility induced performance degradation for chest mounted nodes, enabling reliable support of a 1 Mbps data rate in all considered scenarios considering the chest as the Tx. Robustness analysis under obstructed indoor propagation (n = 3.5) confirms that although absolute throughput decreases with higher path loss, the relative performance ranking between placement and mobility scenarios remains unchanged. These findings provide quantitative design guidance for reliable and energy efficient MBAN deployment in indoor healthcare environments.

  • MeDiTate: A Deep Learning Framework for Mental Disorder State Detection in the Era of Social Media

    by Shorouk Adel, Noureldin Elmadany, Omneya Attallah, Maha Sharkas

    This article presents MeDiTate, a hybrid deep learning framework proposed to detect mental health disorders by analyzing social media content. The Menta dataset is collected, consisting of user-labeled mental health issues across 13 different disorders. The proposed framework employs various natural language processing techniques for data preprocessing and integrates deep learning models, specifically convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and transformer architectures. Ablation studies are conducted to find the top performing architecture. The proposed MeDiTate achieves an accuracy of 88.32%, an F1-score of 88.51%, precision of 88.61%, and recall of 88.45% on Menta dataset. The framework surpasses state-of-the-art methods on two publicly available datasets, namely Kim et al. (2020) and Low et al. (2020) datasets, by $\sim$ 2%. Additionally, we leverage the effectiveness of transfer learning from models trained on user-labeled datasets on the performance. The results demonstrate a noticeable improvement. Furthermore, we empirically investigate cross dataset evaluation to assess the framework’s generalizability. Comprehensive quantitative and qualitative analyses further validate the framework’s discriminatory performance. 1 1 The code and dataset are available at https://github.com/NourElmadany/MeDiTate.

  • Open Access

    Categorizing Crises From Social Media Feeds via Multimodal Channel Attention

    by Mariham Rezk, Noureldin Elmadany, Radwa K. Hamad, Ehab F. Badran

    In the era of advanced computer vision and natural language processing, the use of social media as a source of information has become even more valuable in directing aid and rescuing victims. Consequently, millions of texts and images can be processed in real-time, allowing emergency responders to efficiently assess evolving crises and appropriately allocate resources. The majority of the previous detection studies are text-only or image-only based, overlooking the potential benefits of integrating both modalities. In this paper, we propose Multimodal Channel Attention (MCA) block, which employs an adaptive attention mechanism, learning to assign varying importance to each modality. We then propose a novel Deep Multimodal Crisis Categorization (DMCC) framework, which employs a two-level fusion strategy for better integration of textual and visual information. The DMCC framework consists of feature-level fusion, which is accomplished through the MCA block, and score-level fusion, whereby the decisions made by the individual modalities are integrated with those of the MCA model. Extensive experiments on publicly available datasets demonstrate the effectiveness of the proposed framework. Through a comprehensive evaluation, it was found that the proposed framework achieves a performance enhancement compared to unimodal methods. Furthermore, it outperforms the current state-of-the-art methods on crisis-related categorization tasks.


  • Multimodal Learning for Human Action Recognition Via Bimodal/Multimodal Hybrid Centroid Canonical Correlation Analysis

    by Nour El Din Hassan Elmadany, Yifeng He, Ling Guan

    In this paper, we study the problem of human action recognition from multiple feature modalities. We propose Bimodal Hybrid Centroid Canonical Correlation Analysis (BHCCCA) and Multimodal Hybrid Centroid Canonical Correlation Analysis (MHCCCA) to learn the discriminative and informative shared space, by considering the correlation among different classes across two modalities (BHCCCA) and three or more modalities (MHCCCA). We then introduce a new human action recognition framework by using BHCCCA/MHCCCA for fusing different modalities (RGB, depth, skeleton, and accelerometer data). Performance evaluation on four publicly accessible datasets (MSR Action3D, UTD-MHAD, UTD-MHAD-Kinect V2, and Berkeley MHAD) demonstrated the effectiveness of the proposed framework.


  • Information Fusion for Human Action Recognition via Biset/Multiset Globality Locality Preserving Canonical Correlation Analysis

    by Nour El Din Elmadany, Yifeng He, Ling Guan

    In this paper, we study the problem of human action recognition, in which each action is captured by multiple sensors and represented by multisets. We propose two novel information fusion techniques for fusing the information from multisets. The first technique is biset globality locality preserving canonical correlation analysis (BGLPCCA), which aims to learn the common feature subspace between two sets. The second technique is multiset globality locality preserving canonical correlation analysis (MGLPCCA), which aims to deal with three or more sets. The proposed BGLPCCA and MGLPCCA are able to learn a low-dimensional common subspace that preserves the local and global structures of data samples. Moreover, two novel descriptors are presented for both depth and skeleton. We then propose a new human action recognition framework employing the proposed BGLPCCA or MGLPCCA to learn the shared subspace from multiple sets of features including skeleton, depth, and optical flow. Extensive experiments on five publicly available datasets (MSR Action3D, UTD multimodal human action dataset, multimodal action database, Kinect activity recognition dataset, and SBU Kinect interaction dataset) demonstrate the effectiveness of the proposed framework.