Search

Human activity recognition (HAR) is one of those research areas whose importance and popularity have notably increased in recent years. HAR can be seen as a general machine learning problem which requires feature extraction and feature selection. In previous articles different features were extracted from time, frequency and wavelet domains for HAR but it is not clear that, how to determine the best feature combination which maximizes the performance of a machine learning algorithm. The aim of this paper is to present the most relevant feature extraction methods in HAR and to compare them with widely-used filter and wrapper feature selection algorithms. This work is an extended version of [1]a where we tested the efficiency of filter and wrapper feature selection algorithms in combination with artificial neural networks. In this paper the efficiency of selected features has been investigated on more machine learning algorithms (feed-forward artificial neural network, k-nearest neighbor and decision tree) where an independent database was the data source. The result demonstrates that machine learning in combination with feature selection can overcome other classification approaches. [ABSTRACT FROM AUTHOR]

In this paper we present the implementation of an activity recognition system based on a data acquisition system with sensors for acceleration and physiological parameters. In order to recognize more complex activities we need data acquisition from multiple sensors. Based on our previous experience gained in designing acquisition systems for activity recognition, we have designed and developed a system with three sensors. We developed two possible configurations: one using three acceleration sensors, and one with two acceleration sensors and one heart rate sensor. In the experimental phase we found that the third accelerometer that we've placed on the waist does not provide relevant data to improve the rate of recognition significantly. Thus we opted for the second option, considering that the integration of a physiological sensor provides additional information regarding activities, health status and detecting abnormal states. Starting from the experimental phase, we designed and developed a module integrating the three sensors, with additional functionalities such as an SD card to store the acquired data, and a Bluetooth module for connect to portable devices. In addition, we have integrated a RTC (Real Time Clock) module in order to add time label. [ABSTRACT FROM AUTHOR]

The aim of this paper is to present the implementation of an activity recognition system based on a data acquisition system with inertial sensors. One of the requirement of data acquisition systems used in human activity recognition is their level of acceptability or their level of obstruction [2, 4]. Starting from this important requirement, we designed a few wearable data acquisition systems using inertial sensors. The idea from which we started, takes into account the need to obtain more complete information about the studied human subject, in complex activities recognition systems. In our experiment we used inertial sensor built into so called "9DOF inertial module". Our systems contain, on the wearable side, a maximum of three inertial sensors, a microcontroller module, and a communication module which can be one of the three solutions. For data reception, on the fixed part of the system, we have a communication module corresponding to the one on wearable parts and a microcontroller module connected to a PC through a serial port. For activity recognition, data files are transferred to a PC, and data is processed in Matlab using artificial neural networks as classifier. The networks have been configured according to the number of sensors that acquired data and the number of activities that we want to recognize. [ABSTRACT FROM AUTHOR]

In this paper we have proposed to present a wearable system for automatic recording of the main physiological parameters of the human body: body temperature, galvanic skin response, respiration rate, blood pressure, pulse, blood oxygen content, blood glucose content, electrocardiogram (ECG), electromyography(EMG), and patient position. To realize this system, we have developed a program that can read and automatically save in a file, the data from specialized sensors. The results can be later interpreted, by comparing them with known normal values and thus offering the possibility for a primary health status diagnosis by specialized personnel. The data received from the wearable sensors is taken by an interface circuit, provided with signal conditioning (filtering, amplification, etc). A microcontroller controls the data acquisition. In this applications we used an Arduino Uno standard development platform. The data are transferred to a PC, using serial communication port of Arduino platform and a communications shield. The whole process of health assessment is commissioned by a program developed by us in the Python programming language. The program provides automatic recording of the aforementioned parameters in a predetermined sequence, or only certain parameters are registered. [ABSTRACT FROM AUTHOR]

This paper presents an innovative implementation of a data acquisition, which is able to communicate with a chest belt in order to obtain the heart rate value and accelerometer data from a EZ Chronos watch. The main goal of the work presented is to implement an embedded system, which can be used in various life assisted or medical applications. [ABSTRACT FROM AUTHOR]

Today a general need for robots assisting different human activities rises. The goal of the present project is to develop a prototyping robot, which provides facilities for attaching and fitting different kinds of sensors and actuators. This robot provides an easy way to turn a general purpose robot into a special function one. [ABSTRACT FROM AUTHOR]

This paper presents a study of using telepresence and assistance robots in caring for elderly people. We have presented the requirements for these types of robots and possible application fields. Few models of robots will be presented, analyzing technical requirements of assistance robots and their applications. Hereinafter is presented a robot model being under design and development. [ABSTRACT FROM AUTHOR]

This paper presents the design and implementation of a full size assistance robot. Its main purpose it to assist a person and eventually avoid a life threatening situation. Its implementation revolves around a chipKIT Arduino board that interconnects a robotic base controller with a 7 inch TABLET PC and various sensors. Due to the Android and Arduino combination, the robot can interact with the person and provide an easy development platform for future improvement and feature adding. The TABLET PC is Webcam, WIFI and Bluetooth enabled, offering a versatile platform that is able to process data and in the same time provide the user a friendly interface. [ABSTRACT FROM AUTHOR]

This paper presents hardware implementation of Artificial Neural Networks (ANN) that are used for human hand's natural gestures recognition. Main goal of this project is to implement a recognition system that recognizes data gathered from various sensors placed on a bracelet. This easy to use interface can be used even by elderly or impaired people to control electronic/electric devices only with hand gestures. [ABSTRACT FROM AUTHOR]

The transient no-load regime and transient sudden short-circuit regime, of a small power shell-type transformer, will be studied in this paper. Will be determined the current variation in the primary circuit both analytically and by numerical analysis based on finite elements method (FEM). The software used for study is MagNet, developed by the Infolytica Company. [ABSTRACT FROM AUTHOR]

Due to the emergence of antimicrobial resistance, new antibiotics or anti-pathogenic drugs are strongly needed. In this context, 15 new 4,2 and 5,2 bisthiazole derivatives were investigated in order to determine their antimicrobial activity and influence on microbial biofilm development and subsequent inert substratum colonization. The obtained compounds were tested on five bacterial strains and one fungal strain. The antimicrobial activity was assessed by using both qualitative (an adapted disk diffusion technique) and quantitative assays (broth micro-dilution and biofilm microtiter methods). The compounds showed a low to good antimicrobial activity especially against Escherichia coli ATCC 25922. A moderate anti-biofilm effect was exhibited against Pseudomonas aeruginosa ATCC 27857 and E. coli ATCC 25922 strains. Five of the tested compounds exhibited good antibacterial and anti-biofilm activities against E. coli ATCC 25922. [ABSTRACT FROM AUTHOR]

Quaternary ammonium compounds are considered among the substances which can influence the contractility of smooth muscles from the digestive tract, acting via cholinergic mechanisms. Based on structural considerations, we synthesized twelve new compounds, derivatives of 2-aryl-thiazole, being substituted in the 2 and 4 positions. In order to elucidate the structure of the obtained compounds, MS determinations and 1HNMR spectra were realized. The effect on the smooth muscles was tested using the guinea pig isolated ileum experimental model. The obtained results showed that the contractile effects or the antispasmodic activity of the compounds are influenced by the nature of the substituent in the 4 position, and the intensity of the effect is related to the type of substituent on the phenyl, from the 2 position of the thiazolic nucleus. [ABSTRACT FROM AUTHOR]

Introduction. There is an increasing need to obtain new anti-inflammatory molecules that act either as COX-2 selective inhibitors or as iNOS inhibitors. To that effect, we synthesized some 2-(trimethoxyphenyl)-4-R1-5-R2-thiazoles and evaluated their antiinflammatory properties. Experimental. The main synthesis route involved the Hantzsch condensation of the 3,4,5-trimethoxy-benzothioamide with various α-halo-ketones. For all synthesized compounds, the anti-inflammatory activity was evaluated in vivo on an experimental acute inflammation at rats thought the acute phase bone marrow response, phagocytic capacity, and nitro-oxidative stress status. Results. A total of 13 new compounds were synthesized and all of them have various degrees of anti-inflammatory activity. All tested compounds reduced the acute phase bone marrow response, the phagocytic capacity and the nitro-oxidative stress. Conclusions. Two of the compounds had a more potent action than meloxicam in all studied areas. [ABSTRACT FROM AUTHOR]

Herein, we report the synthesis of a series of new compounds by combining 2-aminobenzothiazole with various profens. The compounds were characterized using techniques such as 1 H- and 13 C-NMR, FT-IR spectrometry, and high-resolution mass spectrometry (HRMS), with detailed HRMS analysis conducted for each molecule. Their biological activities were tested in vitro, revealing significant anti-inflammatory and antioxidant effects, comparable to those of standard reference compounds. Lipophilicity was experimentally determined through partition coefficient (R M ) measurements. To understand their binding affinity, molecular docking studies were perfsormed to analyze interactions with human serum albumin (HSA). The stability of these predicted complexes was further evaluated through molecular dynamics simulations. The results highlight the compounds' promising biological activity and strong affinity for HSA. The new hybrid molecule between 2-ABT and ketoprofen 3b demonstrates significant promise based on the experimental data and is further supported by in silico calculations. Compound 3b exhibits the best hydrogen peroxide scavenging activity among the tested compounds, with an IC 50 of 60.24 μg/mL. Furthermore, 3b also displays superior anti-inflammatory activity, with an IC 50 of 54.64 μg/mL, making it more effective than the standard ibuprofen (76.05 μg/mL).

In this paper, we present the implementation of an artificial intelligence health assistant designed to complement a previously built eHealth data acquisition system for helping both patients and medical staff. The assistant allows users to query medical information in a smarter, more natural way, respecting patient privacy and using secure communications through a chat style interface based on the Matrix decentralized open protocol. Assistant responses are constructed locally by an interchangeable large language model (LLM) that can form rich and complete answers like most human medical staff would. Restricted access to patient information and other related resources is provided to the LLM through various methods for it to be able to respond correctly based on specific patient data. The Matrix protocol allows deployments to be run in an open federation; hence, the system can be easily scaled.

This paper comprehensively reviews hardware acceleration techniques and the deployment of convolutional neural networks (CNNs) for analyzing electroencephalogram (EEG) signals across various application areas, including emotion classification, motor imagery, epilepsy detection, and sleep monitoring. Previous reviews on EEG have mainly focused on software solutions. However, these reviews often overlook key challenges associated with hardware implementation, such as scenarios that require a small size, low power, high security, and high accuracy. This paper discusses the challenges and opportunities of hardware acceleration for wearable EEG devices by focusing on these aspects. Specifically, this review classifies EEG signal features into five groups and discusses hardware implementation solutions for each category in detail, providing insights into the most suitable hardware acceleration strategies for various application scenarios. In addition, it explores the complexity of efficient CNN architectures for EEG signals, including techniques such as pruning, quantization, tensor decomposition, knowledge distillation, and neural architecture search. To the best of our knowledge, this is the first systematic review that combines CNN hardware solutions with EEG signal processing. By providing a comprehensive analysis of current challenges and a roadmap for future research, this paper provides a new perspective on the ongoing development of hardware-accelerated EEG systems.