People with Alzheimer's disease are at risk of malnutrition, overeating, and dehydration because short-term memory loss can lead to confusion. They need a caregiver to ensure they adhere to the main meals of the day and are properly hydrated. The purpose of this paper is to present an artificial intelligence system prototype based on deep learning algorithms aiming to help Alzheimer's disease patients regain part of the normal individual comfort and independence. The proposed system uses artificial intelligence to recognize human activity in video, being able to identify the times when the monitored person is feeding or hydrating, reminding them using audio messages that they forgot to eat or drink or that they ate too much. It also allows for the remote supervision and management of the nutrition program by a caregiver. The paper includes the study, search, training, and use of models and algorithms specific to the field of deep learning applied to computer vision to classify images, detect objects in images, and recognize human activity video streams. This research shows that, even using standard computational hardware, neural networks' training provided good predictive capabilities for the models (image classification 96%, object detection 74%, and activity analysis 78%), with the training performed in less than 48 h, while the resulting model deployed on the portable development board offered fast response times-that is, two seconds. Thus, the current study emphasizes the importance of artificial intelligence used in helping both people with Alzheimer's disease and their caregivers, filling an empty slot in the smart assistance software domain.

People with Alzheimer's disease are at risk for malnutrition, overeating and dehydration because short-term memory loss can be confusing. They need a caregiver to make sure they adhere to the main meals of the day and are properly hydrated. The purpose of this paper is to present the need for a developed surveillance system that has the role of regaining their independence through artificial intelligence. The system is based on a unique concept that involves the use of artificial intelligence to recognize human activity in video. The system identifies the times when the monitored person is feeding or hydrating and reminds them by sound messages that they forgot to eat, drink or eat too much. It also allows for the remote supervision and management of the nutrition program by a caregiver. The paper includes the study, search, training and use of models and algorithms specific to the field of computer vision in order to classify images, detect objects in images and recognize human activity in video. The study shows that artificial intelligence used to help people with Alzheimer's is a new concept, but a real help for both them and their caregivers.

The paper addresses the detection of floating and underwater marine mines from images recorded from cameras (taken from drones, submarines, ships, boats). Due to the lack of image datasets, images were taken from the Internet and by using the technique of augmentation and synthetic image generation (by overlapping images with different types of mines over water backgrounds) 2 data sets were built (one for floating mines and one for underwater mines). The networks were trained and compared using 3 types of Deep Learning models Yolov5, SSD and EfficientDet (Yolov5, SSD for floating mines and Yolov5 and EfficientDet for underwater mines). The networks were also tested in the context of an IoT device (RaspberryPi 4, RPi camera).

In the context of new geopolitical tensions due to the current armed conflicts, safety in terms of navigation has been threatened due to the large number of sea mines placed, in particular, within the sea conflict areas. Additionally, since a large number of mines have recently been reported to have drifted into the territories of the Black Sea countries such as Romania, Bulgaria Georgia and Turkey, which have intense commercial and tourism activities in their coastal areas, the safety of those economic activities is threatened by possible accidents that may occur due to the above-mentioned situation. The use of deep learning in a military operation is widespread, especially for combating drones and other killer robots. Therefore, the present research addresses the detection of floating and underwater sea mines using images recorded from cameras (taken from drones, submarines, ships and boats). Due to the low number of sea mine images, the current research used both an augmentation technique and synthetic image generation (by overlapping images with different types of mines over water backgrounds), and two datasets were built (for floating mines and for underwater mines). Three deep learning models, respectively, YOLOv5, SSD and EfficientDet (YOLOv5 and SSD for floating mines and YOLOv5 and EfficientDet for underwater mines), were trained and compared. In the context of using three algorithm models, YOLO, SSD and EfficientDet, the new generated system revealed high accuracy in object recognition, namely the detection of floating and anchored mines. Moreover, tests carried out on portable computing equipment, such as Raspberry Pi, illustrated the possibility of including such an application for real-time scenarios, with the time of 2 s per frame being improved if devices use high-performance cameras.

This paper presents an analysis of the behavioural and temperamental changes of children in non-formal education lessons within the Logic Games discipline. The experimental setup was made using 2 video cameras that alternatively recorded and monitored groups of 2 children during the lessons from the Logic Games discipline for the entire scholar year. Emotion plays an important role in the lesson of non-formal education. Chess as part of the Logic Games involves the training of qualities such as will, ambition, perseverance, attention to detail, distributive attention, patience, evaluation and anticipation of many alternatives and possibilities to move both your own and your opponent's and to choose the moves. optimal. It is very important to be mentally trained to deal with the negative emotions generated by losing or losing the match. Therefore, before learning how to win you must learn how to lose. The sentiment analysis in this paper refers only to the automatic recognition and identification of facial expressions. The images extracted from the video recordings were processed, and then classified into the categories: happy, sad, angry, disappointed, pleasantly surprised, proud, panicked / worried or stressed Deep Learning techniques such as Convolutional Neuronal Network, RCNN, Faster RCNN and Mask RCNN and Transfer Learning technique were used to classify the images. The contribution of the paper is given by the application of these image classification algorithms in the non-formal education process. There was a correlation between the feelings detected, frequency of occurrence and the end result of the game in order to improve the educational process to optimize the automatic feedback needed by the teacher to adjust the instructional-educational process, benefiting from the support of an automatic assistant. The results were illustrated in graphs regarding the evolution of the behavioural states/the flow of feelings of the children during lessons throughout the experiment.

Non-formal education consists in the expression of personal interests through the voluntary participation of the young person in activities that are of interest or attract him directly in order either to spend free time in a constructive manner, or to develop personality or to grasp special talents in - an institutionalized framework. As a rule, non-formal education does not make literacy, but works on the student's apperceptive background (built up by formal education), strengthening the general knowledge of the young person in his / her areas of interest, along with the development of motivation, will, selfcontrol and self-confidence. Our analysis had focused on tackling chess as a logical game in nonformal education by studying few groups of preschoolers who do not yet know how to read and write, in order to be able to record during the play their own moves on the game board. It has been noticed during the time that all these small age groups often commit mistakes, either on an involuntarily manner or deliberately, cheating for the purpose of winning at any cost, generating this way a controversy between opponents seeking the teacher's immediate support or assistance. One of the major limitations of the lesson is given by the fact that the teacher can't simultaneously watch the game on multiple chess boards in order to intervene in real time whenever his pedagogical assistance is needed. So, to alleviate these shortcomings, a system based on deep learning techniques is used that allows, based on image analysis, to detect the positioning of each chess piece on the game board. Upon completion of a move a button is pressed by each player at which point an image is taken with a camera and the new position of the pieces is determined and compared to the previous one, to detect if any of the game's rules have been violated. Then the notation of the move is recorded and in the case of a violation of the game's rules, the system produces a warning sound, giving this way to the teacher the opportunity to intervene promptly. The experiment consisted in recording the number of interventions necessary to correct the game first in a classic manner and then using the automated system, making this way a comparison between the two approaches. It has been noticed that using the automated system more errors could be detected in addition allowing an implied evaluation of the lesson in a manner which is more effective and objective then the classic one.

The non-formal education consists in the expression of personal interests through the voluntary participation of the young person in activities that are of interest or attract him directly in order either to spend free time in a constructive manner, or to develop personality or to grasp special talents in - an institutionalized framework. Attention is the process that ensures the active orientation of the body to the message selection, the anticipatory reception and executory adjustment, as well as the intermittent focusing. In general, in the educational instructive process, attention is monitored by direct observation of students. A neurofeedback device (mini-electroencephalograph) has been used in our study to measure attention, a Neurosky device called MindWave Mobile 2 designed to record the electrical impulses emanating from different brain areas (areas G for ground and A1/FP1 of the 1020 system - on standardized placement of electrodes on the head for EEG measurements). With the help of the device and its related software, the level of attention has been recorded from several students over multiple lessons for Logic Games subject, first using a classical teaching method, and then using predominantly didactic play, the transmission of learning contents in interdisciplinary ways through computer-assisted instruction or using musical background. The MindWave Mobile 2 headset connects wireless to computer through Bluetooth and, using the built-in electrode, raw EEG power spectrum is analyzed and an integer value per second in interval 0 and 100 is delivered for attention. Distraction, lack of focus, or anxiety can reduce the level attention. To facilitate further input data analysis, we considered the following reference intervals: - under 40 = lack of concentration; - between 40-60 = diffuse attention; - between 60-80 = state of concentration; - between 80-100 = state of maximum concentration. To complete the experiment, we counted, analyzed, and compared the total number of minutes with different levels of attention within each lesson type - classical and computer-assisted instruction - per student, and the resulted data was illustrated in a graph. As a result, it was observed that the average level of attention was increased on the use of assisted training. Through this device, the teacher will know exactly what each student's intellectual effort curve is, when, how, and how much to intervene to resuscitate students' interest in the lesson.

In this article, having regard to the European and national women entrepreneurship, we attempted to identify the women entrepreneurs' management styles. As a concept, the management style is very important to the organizational management as a whole because it represents the very essence of same, in my opinion. Defining the management style as a manager's own and personal means of networking both professionally and personally with their direct subordinates to determine them to observe his/her instructions, we included in this definition the essence of management, which is nothing other than the achievement of goals and the resolution of tasks through one's subordinates. To identify these styles, we opted for the questionnaire developed by Fiedler, an advocate for situational approaches, in the form of a questionnaire-based qualitative research. Basically, Fiedler assumes that a manager asked to characterize their least preferred co-workers through a set of adjectives, if they have a task orientation, they will tend to rate their least preferred co-workers by picking the negative adjectives from a series of bipolar scales (between tense and relaxed, they will choose tense). If the manager has human relations orientation, they will understand that their least preferred co-worker may be relaxed, sociable, willing to oblige, etc. For all the debates it generated, this questionnaire remains an interest tool for the identification of leadership styles.

In this article, the author examines the role of risk management within the organizational management of economic entities in general and the economic entities undergoing insolvency, in particular. Analysing risk management from a structural standpoint, for the purpose of the topic stated hereinabove, the author argues that the framework plan of substantiation might be important for risk management. In furtherance of her doctoral research in which she outlined the structure of a general plan for the substantiation of risk management from the perspective of an insolvency practitioner, the author subjects this document to the management of the companies in insolvency, in a pilot survey, so that it may be improved and supplemented with specifics of the management of that organization. The document thus structured, referred to as the framework plan to document risk management, was submitted to a new quality research in the form of a questionnaire self-administered by 50 managers of economic entities which underwent or undergo insolvency, in an attempt to identify the elements related to each item of the plan. This quality research lead to a theoretical substantiation of the framework plan of substantiation as an instrument of intervention within risk management. The concrete outcome of the qualitative research was identification of the specifics of each constitutive element of the plan of substantiation, which shall lead to new researches that will detail and elaborate on issues with immediate beneficial effect in rendering efficient the risk management of the companies in insolvency.

In this article I have tried to analyze the manner in which risk management, as a branch of organizational management, can be applied in insolvency proceedings. In order to reach this general objective, I have structured a few specific objectives: the identification of the type activities in insolvency proceedings and the identification of the risk generating sub-activities; the drafting of a matrix for risk ranking; identification of the elements of the risk management process in insolvency proceedings and also of the elements of the risk documentation plan. Using the Delphi technique, through a questionnaire administered to the insolvency practitioners, in a first stage, I have identified the type activities specific to the insolvency proceedings, which, in my opinion, can be constituted in an insolvency management. In the second stage of the research, I have identified, for each type activity, the risk generating sub-activities in insolvency proceedings. Starting from the classic risk indicators (frequency and effect), I have built a matrix for the ranking of the risk generating sub-activities in insolvency proceedings. In the third stage of the research, I have proposed, based on the answers offered by the questioned persons, the elements of the risk management process in insolvency proceedings. Starting from the importance of risk analysis, I have considered adequate to structure a risk documentation plan, questioning the insolvency practitioners through the Delphi technique and, also, for 10 of them, I have administered, in order, a brainstorming and a focus-group.