Hafeez Ur Rehman Siddiqui

Incorporating energy generated from regular human movement into wearable electronics offers a promising alternative to conventional batteries, enabling devices to power themselves by harvesting energy from motion and the surrounding environment. Ambient energy harvesting provides a pathway toward limitless, self-sustaining power and supports the development of cleaner, smarter wearable systems. Among various approaches, integrating hybrid mechanisms into footwear represents a transformative solution for sustainable power generation. In this work, a piezoelectric generator (PEG), an electromagnetic generator (EMG), and a triboelectric generator (TEG) were hybridized within a single architecture to harvest biomechanical energy from walking, jogging, and running. The device incorporates pressure-sensitive Lead Zirconate Titanate (PZT) sheets, a spiral spring with dual neodymium (NdFeB) magnets with wound copper coils, and a nickel foam with polytetrafluoroethylene (PTFE) for triboelectricity operating in contact–separation mode. A dedicated energy-management circuit comprising independent rectification, DC bus energy aggregation, supercapacitor storage, and voltage regulation was implemented to efficiently utilize the harvested energy. The system was optimized through simulation using SOLIDWORKS 2023 and validated experimentally by using LabVIEW-NI myRIO FPGA system and treadmill. The proposed hybrid device achieved an exceptional peak output power of 58 mW and a voltage of 7.4 V, enough to charge low-power wearable devices, significantly surpassing the performance of most reported standalone and hybrid insole energy harvesters. These results demonstrate the effectiveness of multimodal integration in broadening operational bandwidth, increasing energy density, and enhancing compatibility with wearable applications. Piezoelectric, Electromagnetic and Triboelectric Insole Energy Harvesting (PET-IEH) establishes a new benchmark in biomechanical energy harvesting and paves the way for next-generation self-powered and sustainable wearable electronics.

Human activity recognition (HAR) is essential in many applications, such as smart homes, assisted living, healthcare monitoring, rehabilitation, physiotherapy, and geriatric care. Conventional methods of HAR use wearable sensors, e.g., acceleration sensors and gyroscopes. However, they are limited by issues such as sensitivity to position, user inconvenience, and potential health risks with long-term use. Optical camera systems that are vision-based provide an alternative that is not intrusive; however, they are susceptible to variations in lighting, intrusions, and privacy issues. The paper uses an optical method of recognizing human domestic activities based on pose estimation and deep learning ensemble models. The skeletal keypoint features proposed in the current methodology are extracted from video data using PoseNet to generate a privacy-preserving representation that captures key motion dynamics without being sensitive to changes in appearance. A total of 30 subjects (15 male and 15 female) were sampled across 2734 activity samples, including nine daily domestic activities. There were six deep learning architectures, namely, the Transformer (Transformer), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Multilayer Perceptron (MLP), One-Dimensional Convolutional Neural Network (1D CNN), and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture. The results on the hold-out test set show that the CNN–LSTM architecture achieves an accuracy of 98.78% within our experimental setting. Leave-One-Subject-Out cross-validation further confirms robust generalization across unseen individuals, with CNN–LSTM achieving a mean accuracy of 97.21% ± 1.84% across 30 subjects. The results demonstrate that vision-based pose estimation with deep learning is a useful, precise, and non-intrusive approach to HAR in smart healthcare and home automation systems.

Forest fires pose significant threats to ecosystems, human life, and the global climate, necessitating rapid and reliable detection systems. Traditional fire detection approaches, including sensor networks, satellite monitoring, and centralized image analysis, often suffer from delayed response, high false positives, and limited deployment in remote areas. Recent deep learning-based methods offer high classification accuracy but are typically computationally intensive and unsuitable for low-power, real-time edge devices. This study presents an autonomous, edge-based forest fire and smoke detection system using a lightweight MobileNetV2 convolutional neural network. The model is trained on a balanced dataset of fire, smoke, and non-fire images and optimized for deployment on resource-constrained edge devices. The system performs near real-time inference, achieving a test accuracy of 97.98% with an average end-to-end prediction latency of 0.77 s per frame (approximately 1.3 FPS) on the Raspberry Pi 5 edge device. Predictions include the class label, confidence score, and timestamp, all generated locally without reliance on cloud connectivity, thereby enhancing security and robustness against potential cyber threats. Experimental results demonstrate that the proposed solution maintains high predictive performance comparable to state-of-the-art methods while providing efficient, offline operation suitable for real-world environmental monitoring and early wildfire mitigation. This approach enables cost-effective, scalable deployment in remote forest regions, combining accuracy, speed, and autonomous edge processing for timely fire and smoke detection.

Cervical cancer remains a significant global public health challenge, affecting over half a million women annually, with a mortality rate of approximately 60%, especially in resource-limited regions. This study presents an advanced methodology for cervical cancer diagnosis through deep learning techniques. Utilizing a publicly available cervical cancer image dataset, the research introduces a novel classification framework that integrates a Neural Feature Extractor (NFE) based on a pre-trained VGG16 architecture and an AutoInt model for automatic feature interaction learning. The extracted features are processed through machine learning classifiers such as KNN, LGBM, Extra Trees, and others for classification tasks. Among these classifiers, KNN achieved the highest accuracy of 99.96%, followed closely by LGBM at 99.92%. This study also assesses the computational complexity of various models, demonstrating that simpler models like LDA exhibit faster prediction times, while more complex models, such as KNN and LGBM, provide higher accuracy. These findings highlight the potential of deep learning frameworks in improving cervical cancer classification accuracy, especially in resource-limited environments.

Power networks are vital to modern society, yet service outages and faults can have devastating consequences. This study introduces a novel integration of machine learning and data augmentation techniques for fault detection and classification, addressing gaps in data diversity and imbalance. Unlike traditional approaches, the research utilizes an Auxiliary Classifier Generative Adversarial Network (ACGAN) to generate synthetic data representative of underrepresented fault types, enhancing model training and performance. By extracting both spectral and statistical features from the Grid Event Signature Library (GESL) dataset, a comprehensive representation of power system signals is achieved. A comparative evaluation of models including Decision Trees, Random Forest, Extra Tree Classifier, Gradient Boosting Classifier, and K-Nearest Neighbors revealed the Extra Tree Classifier achieving the highest testing accuracy of 93.85%. The methodologies demonstrated scalability by using a dataset augmented to 9,000 samples and validated robustness through 10-fold cross-validation with a standard deviation of 0.00659. These results highlight the proposed framework's potential for real-world implementation in modern power grids, offering enhanced fault prediction and resilience. This research establishes a pathway for integrating advanced data augmentation and machine learning techniques into operational power grid systems, ensuring stability and reliability.

Cervical cancer remains a significant global public health challenge, affecting over half a million women annually, with a mortality rate of approximately 60%, especially in resource-limited regions. This study presents an advanced methodology for cervical cancer diagnosis through deep learning techniques. Utilizing a publicly available cervical cancer image dataset, the research introduces a novel classification framework that integrates a Neural Feature Extractor (NFE) based on a pre-trained VGG16 architecture and an AutoInt model for automatic feature interaction learning. The extracted features are processed through machine learning classifiers such as KNN, LGBM, Extra Trees, and others for classification tasks. Among these classifiers, KNN achieved the highest accuracy of 99.96%, followed closely by LGBM at 99.92%. The study also assesses the computational complexity of various models, demonstrating that simpler models like LDA exhibit faster prediction times, while more complex models, such as KNN and LGBM, provide higher accuracy. These findings highlight the potential of deep learning frameworks in improving cervical cancer classification accuracy, especially in resource-limited environments.

The perception and recognition of objects around us empower environmental interaction. Harnessing the brain’s signals to achieve this objective has consistently posed difficulties. Researchers are exploring whether the poor accuracy in this field is a result of the design of the temporal stimulation (block versus rapid event) or the inherent complexity of electroencephalogram (EEG) signals. Decoding perceptive signal responses in subjects has become increasingly complex due to high noise levels and the complex nature of brain activities. EEG signals have high temporal resolution and are non-stationary signals, i.e., their mean and variance vary overtime. This study aims to develop a deep learning model for the decoding of subjects’ responses to rapid-event visual stimuli and highlights the major factors that contribute to low accuracy in the EEG visual classification task.The proposed multi-class, multi-channel model integrates feature fusion to handle complex, non-stationary signals. This model is applied to the largest publicly available EEG dataset for visual classification consisting of 40 object classes, with 1000 images in each class. Contemporary state-of-the-art studies in this area investigating a large number of object classes have achieved a maximum accuracy of 17.6%. In contrast, our approach, which integrates Multi-Class, Multi-Channel Feature Fusion (MCCFF), achieves a classification accuracy of 33.17% for 40 classes. These results demonstrate the potential of EEG signals in advancing EEG visual classification and offering potential for future applications in visual machine models.

Telephysiotherapy has emerged as a vital solution for delivering remote healthcare, particularly in response to global challenges such as the COVID-19 pandemic. This study seeks to enhance telephysiotherapy by developing a system capable of accurately classifying physiotherapeutic exercises using PoseNet, a state-of-the-art pose estimation model. A dataset was collected from 49 participants (35 males, 14 females) performing seven distinct exercises, with twelve anatomical landmarks then extracted using the Google MediaPipe library. Each landmark was represented by four features, which were used for classification. The core challenge addressed in this research involves ensuring accurate and real-time exercise classification across diverse body morphologies and exercise types. Several tree-based classifiers, including Random Forest, Extra Tree Classifier, XGBoost, LightGBM, and Hist Gradient Boosting, were employed. Furthermore, two novel ensemble models called RandomLightHist Fusion and StackedXLightRF are proposed to enhance classification accuracy. The RandomLightHist Fusion model achieved superior accuracy of 99.6%, demonstrating the system’s robustness and effectiveness. This innovation offers a practical solution for providing real-time feedback in telephysiotherapy, with potential to improve patient outcomes through accurate monitoring and assessment of exercise performance.