We introduce a wearable-based system for real-time ECG anomaly detection and contextual interpretation within a mobile-health framework. Twenty-four-hour Holter ECG data are synchronized over wireless/mobile networks with e.g. Apple Health streams (iPhone + iWatch), including activity states (walking, running, resting, sleeping) and heart rate history. A hybrid preprocessing pipeline extracts instantaneous frequency (Hilbert), spectral entropy, and RMS energy, concatenated into fixed-length multichannel tensors for deep-learning models deployed via edge or cloud SaaS. The model detects critical cardiac anomalies correlating each with user activity and exertion context. This multimodal approach distinguishes physiological deviations during motion from pathological events at rest or sleep and suppresses motion artifacts. Experiments with subjects wearing both Holter and Apple devices demonstrate improved sensitivity and specificity versus ECG-only baselines. Our system exemplifies wearable computing, mobile health, ML-enabled mobile systems, and edge/cloud mobile analytics. Fig. 1 shows a complete system for recording and classifying ECG signals, including a Holter ECG with electrodes, a smartphone and a smartwatch [1].

Damp walls are a significant problem that affects not only historical buildings. The effects of moisture inside walls include premature degradation of the structure and paintwork as well as health hazards for people staying inside the rooms (fungi, microorganisms, allergens). To effectively remove moisture, it is necessary to identify the areas where it occurs. Tomography is the only nondestructive method that allows for imaging the interior of walls. It is not common due to the low image resolution [1]. The aim of the research presented is to present a new concept of impedance tomography, taking into account many measurement sequences at different frequencies of electric current. A neural network with LSTM (Long Short-Term Memory) layers was used to transform the measurements into images. A comparison of the results of the new approach proves the advantage of the multi-frequency method over the traditional method, which brings closer the breakthrough moment in the dissemination of tomography as the main method of imaging moisture in walls.

The study investigates the effectiveness of a differential neural network architecture in ultrasonic tomography (UST) for industrial applications. The proposed model employs a dual-branch structure, where each branch independently processes identical input data before passing the outputs to a differential layer. This approach enhances the model's ability to capture residual components, improving the reconstruction of tomographic images. Experiments were conducted using a tomographic system with 16 transducers, generating training and validation datasets. Comparative analysis between a differential LSTM-based network and a standard LSTM model demonstrated that the differential architecture achieved superior reconstruction quality. The results confirm that this approach enhances accuracy, sharpness, and overall image clarity, making it a promising solution for improving UST image reconstruction.

The main goal of the research was to develop an effective, highresolution tomographic apparatus capable of non-invasively capturing real-time internal images of industrial tank reactors. For this purpose, a prototype of an ultrasonic tomograph (UST) was developed, which combines innovative design solutions and modern algorithmic techniques. A special feature of the presented solution is the use of a neural network with an unusual architecture. A deep, multi-branch neural network consisting of two inputs was used. The first input is a 120-element vector (sequence) of raw measurements. The third input consists of three sequences obtained as a result of the transformation of raw measurements: instantenous frequency (IF), approximation coefficients (Ca), and detail coefficients (Cd). The prototype was tested on a real model. The tomographic reconstructions obtained using the innovative neural architecture were compared with images obtained using a standard neural network. The results clearly confirm the high effectiveness of the presented approach.

This study presents a novel technique for reconstructing the internal structures of industrial tank reactors using electrical impedance tomography (EIT). The method uses three different measurement vectors, each corresponding to different electrical frequencies---100 kHz, 50 kHz, and 10 kHz---to improve the accuracy and reliability of EIT reconstructions. The goal was to get the most out of both the resistive and reactive data from the EIT system by using machine learning methods that took frequency-specific data into account. This data was shown as complex numbers. To process the multi-frequency data collected from the measurements, an LSTM network was used. The results show that the multi-frequency model significantly outperforms single-frequency methods in terms of reconstruction accuracy.

This study aims to improve the resolution of reconstructed images from industrial ultrasonic tomography (UST) by determining the most effective neural network structure for solving the inverse problem based on the measurements taken. The study analyzed three types of neural networks: Artificial Neural Networks, Convolutional Neural Networks (CNNs) and a hybrid of CNNs and Long Short-Term Memory networks (LSTM). After evaluating the reconstructions and quality indicators, the CNN-LSTM combination provided the most accurate image reconstructions of the industrial ultrasound tomography, highlighting the importance of selecting an appropriate neural network to improve the resolution of the reconstructed images.

Damp walls of buildings are a serious problem due to the social and economic consequences. Moisture causes accelerated wear of facades, paint coatings, weakening of the wall structure, and high maintenance and renovation costs. The growth of fungi and bacteria worsens the indoor microclimate [1]. Effective identification of moisture inside the walls enables effective preventive actions. The paper presents an algorithmic concept that increases the quality of tomographic images showing the distribution of moisture inside the walls. The method solves the problem of monitoring the dampness of historical buildings and walls susceptible to moisture. The research focuses on solving the inverse problem of converting electrical measurements into spatial images. The study used a proprietary electrical impedance tomography system with specially designed electrodes. The measurement vector is converted to images in two stages. In the first stage, the Long Short-Term Memory (LSTM) neural network was used, which generates raw reconstructions. The task of the second LSTM network is to convert the raw images obtained in the first stage into enhanced images. The application of the presented method is not limited to one type of narrow-sphere tomography. The two-stage approach can be easily adapted to, e.g., medical and industrial or process tomography. Therefore, it is a generic, universal method with great implementation potential, which is its great advantage.