This paper presents a novel Human Activity Recognition (HAR) framework using wearable sensors, specifically targeting applications in gait rehabilitation and assistive robots. The new methodology includes the usage of an open-source dataset. This dataset includes surface electromyography (sEMG) and inertial measurement units (IMUs) signals for the lower limb of 22 healthy subjects. Several activities of daily living (ADLs) were included, such as walking, stairs up/down and ramp walking. A new framework for signal conditioning, denoising, filtering, feature extraction and activity classification is proposed. After testing several signal conditioning approaches, such as Wavelet transform (WT), Principal Component Analysis (PCA) and Empirical Mode Decomposition (EMD), an autocepstrum analysis (ACA)-based approach is chosen. Such a complex and effective approach enables the usage of supervised classifiers like K-nearest neighbor (KNN), neural networks (NN) and random forest (RF). The random forest classifier has shown the best results with an accuracy of 97.63% for EMG signals extracted from the soleus muscle. Additionally, RF has shown the best results for IMU signals with 98.52%. These results emphasize the potential of the new framework of wearable HAR systems in gait rehabilitation, paving the way for real-time implementation in lower limb assistive devices.

Smart cities like Neom require efficient and reliable transportation systems to support their vision of sustainable and interconnected urban environments. High-speed trains (HSTs) play a crucial role in connecting different areas of the city and facilitating seamless mobility. However, to ensure uninterrupted communication along the rail lines, advanced communication systems are essential to expand the coverage range of each base station (BS) while reducing the handover frequency. This paper presents the dual transceiver free space optical (FSO) communication system as a solution to achieve these objectives in the operational environment of HSTs in Neom city. Our channel model incorporates log-normal (LN) and gamma–gamma (GG) distributions to represent channel impairments and atmospheric turbulence in the city. Furthermore, we integrated the siding loop model, providing valuable insights into the system in real-world scenarios. To assess the system’s performance, we formulated the received signal-to-noise ratio (SNR) of the network under assumed fading conditions. Additionally, we analyzed the system’s bit error rate (BER) analytically and through Monte Carlo simulation. A comparative analysis with reconfigurable intelligent surfaces (RIS) and relay-assisted FSO communications shows the superior coverage area and efficiency of the dual transceiver model. A significant reduction of up to 76% and 99% in the number of required BSs compared to RIS and relay, respectively, is observed. This reduction leads to fewer handovers and lower capital expenditure (CAPEX) costs.

Accurate recognition of lower limb activities is essential for wearable rehabilitation systems and assistive robotics like exoskeletons and prosthetics. This study introduces SDALLE, a custom hardware data acquisition system that integrates surface electromyography sensors (EMGs) and inertial measurement sensors (IMUs) into a wireless, portable platform for locomotor monitoring. Using this system, data were collected from nine healthy subjects performing four fundamental locomotor activities: walking, jogging, stair ascent, and stair descent. The recorded signals underwent an offline structured preprocessing pipeline consisting of time-series augmentation (jittering and scaling) to increase data diversity, followed by wavelet-based denoising to suppress high-frequency noise and enhance signal quality. A temporal one-dimensional convolutional neural network (1D-TCNN) with three convolutional blocks and fully connected layers was trained on the prepared dataset to classify the four activities. Classification using IMU sensors achieved the highest performance, with accuracies ranging from 0.81 to 0.95. The gyroscope X-axis of the left Rectus Femoris achieved the best performance (0.95), while accelerometer signals also performed strongly, reaching 0.93 for the Vastus Medialis in the Y direction. In contrast, electromyography channels showed lower discriminative capability. These results demonstrate that the combination of SDALLE hardware, appropriate data preprocessing, and a temporal CNN provides an effective offline sensing and activity classification pipeline for lower limb activity recognition and offers an open-source dataset that supports further research in human activity recognition, rehabilitation, and assistive robotics.

This paper describes a novel image encryption scheme that combines Lorenz chaotic maps, the secure Hash Algorithm 256 (SHA-256), and Discrete-Time Quantum Walks (DTQWs). It exploits their sensitivity to their initial conditions, their innate capacity to produce complex randomness, and their adaptability for rapid computational procedures. The chaotic sequences resulting from the Lorenz maps undergoes are utilized in bitwise modular addition operations, for diffusion. DTQWs develop dynamic Substitution Boxes (S-Boxes), that increase confusion by modifying the adaptability of rows/columns. To achieve stronger security, SHA-256 is used to encrypt the plaintext in successive stages, producing hash-dependent quantum coin rotation angles and thereby injects plaintext sensitivity into S-Box construction. It guarantees high-level randomness, low correlation coefficients close to zero, and high immunity to statistical and differential attacks. Outcomes demonstrate better security and computation efficiency compared to available methods, qualifying it as an efficient and reliable solution for secure image transmission within present-day communication systems.