The conducted research aims to develop a computer vision system for a small-sized mobile humanoid robot. The decentralization of the servomotor control and the computer vision systems investigated based on the hardware solution point of view, moreover, the required software level to achieve an efficient matched design is obtained. A computer vision system using the upgraded tiny-YOLO network model is developed to allow recognizing and identifying objects and making decisions on interacting with them, which is recommended for crowd environment. During the research, a concept of a computer vision system was developed, which describes the interaction between the main elements, on the basis of which hardware modules were selected to implement the task. A structure of information interaction between hardware modules is proposed, and a connection scheme is developed, on the basis of which a model of a computer vision system is assembled for research, with the required algorithmic and software for solving the problem. To ensure the high speed of the computer vision system based on the ESP32-CAM module, the neural network was improved by replacing the VGG-16 network as the base network for extracting the functions of the Single Shot Detector (SSD) network model with the tiny-YOLO lightweight network model, which made it possible to preserve the multidimensional structure of the network model feature graph, resulting in increasing the detection accuracy, while significantly reducing the amount of calculations generated by the network operation, thereby significantly increasing the detection speed, due to a limited set of objects. Finally, a number of experiments were carried out, both in static and dynamic environments, which showed a high accuracy of identifications.

This study investigates the problematic characteristics of contemporary methods for remote and portable patient monitoring. The consideration is based on recent breakthroughs in information technology and progressive strategies for processing and storing biomedical data. The proposed system represents the Medicine 4.0 concept’s next technological leap. Existing methods for remote and portable monitoring of a patient’s status have several vital disadvantages in system flexibility and the convenience of processing and evaluating biomedical data, according to an analysis of these systems. The authors have created a new concept for a Remote Patient Monitoring System (RPMS) that allows for undetectable wear during the patient’s daily activities. Small modules comprising a microcontroller and a collection of medical sensors transfer data in real-time via wireless Internet of Things (IoT) technologies to a cloud service for the attending physician’s processing and visualization convenience. Based on the proposed concept, the authors created a structural diagram of the experimental RPMS and its built prototype. Amazon Web Services (AWS) is used for the real-time processing of biomedical patient data and its subsequent analysis using a graph-based information visualization system. The performed experimental procedure confirmed that the developed experimental RPMS has minimal latency in transmitting data to AWS; it can alert both the patient and the physician about the need for emergency intervention or treatment adjustments, even if critical indicators are detected. Additionally, the proposed system can incorporate components of expert systems and Artificial Intelligence (AI) systems. The authors advocate using the accomplished system for functional diagnostics specialists, paramedics, and cardiologists in medical facilities and the military medical system for rapid diagnosis and direct monitoring of troops’ health state on the battlefield.

The network switches in the data plane of Software Defined Networking (SDN) are empowered by an elementary process, in which enormous number of packets which resemble big volumes of data are classified into specific flows by matching them against a set of dynamic rules. This basic process accelerates the processing of data, so that instead of processing singular packets repeatedly, corresponding actions are performed on corresponding flows of packets. In this paper, first, we address limitations on a typical packet classification algorithm like Tuple Space Search (TSS). Then, we present a set of different scenarios to parallelize it on different parallel processing platforms, including Graphics Processing Units (GPUs), clusters of Central Processing Units (CPUs), and hybrid clusters. Experimental results show that the hybrid cluster provides the best platform for parallelizing packet classification algorithms, which promises the average throughput rate of 4.2 Million packets per second (Mpps). That is, the hybrid cluster produced by the integration of Compute Unified Device Architecture (CUDA), Message Passing Interface (MPI), and OpenMP programming model could classify 0.24 million packets per second more than the GPU cluster scheme. Such a packet classifier satisfies the required processing speed in the programmable network systems that would be used to communicate big medical data.

In the construction industry, to prevent accidents, non-destructive tests are necessary and cost-effective. Electrical impedance tomography is a new technology in non-invasive imaging in which the image of the inner part of conductive bodies is reconstructed by the arrays of external electrodes that are connected on the periphery of the object. The equipment is cheap, fast, and edge compatible. In this imaging method, the image of electrical conductivity distribution (or its opposite; electrical impedance) of the internal parts of the target object is reconstructed. The image reconstruction process is performed by injecting a precise electric current to the peripheral boundaries of the object, measuring the peripheral voltages induced from it and processing the collected data. In an electrical impedance tomography system, the voltages measured in the peripheral boundaries have a non-linear equation with the electrical conductivity distribution. This paper presents a cheap Electrical Impedance Tomography (EIT) instrument for detecting impurities in the concrete. A voltage-controlled current source, a micro-controller, a set of multiplexers, a set of electrodes, and a personal computer constitute the structure of the system. The conducted tests on concrete with impurities show that the designed EIT system can reveal impurities with a good accuracy in a reasonable time.

Energy management in smart homes is one of the most critical problems for the Quality of Life (QoL) and preserving energy resources. One of the relevant issues in this subject is environmental contamination, which threatens the world’s future. Green computing-enabled Artificial Intelligence (AI) algorithms can provide impactful solutions to this topic. This research proposes using one of the Recurrent Neural Network (RNN) algorithms known as Long Short-Term Memory (LSTM) to comprehend how it is feasible to perform the cloud/fog/edge-enabled prediction of the building’s energy. Four parameters of power electricity, power heating, power cooling, and total power in an office/home in cold-climate cities are considered as our features in the study. Based on the collected data, we evaluate the LSTM approach for forecasting parameters for the next year to predict energy consumption and online monitoring of the model’s performance under various conditions. Towards implementing the AI predictive algorithm, several existing tools are studied. The results have been generated through simulations, and we find them promising for future applications.