Symptoms such as vasculitis, myocarditis and coronary dilatation are possible consequences of Kawasaki disease. Damage to the blood vessels caused by these symptoms can lead to long-term heart problems. It is the most common acquired heart disease affecting young children in developed countries. One way to detect abnormalities in the coronary arteries caused by this disease is by monitoring patients with 2D echocardiograms. This monitoring must be performed manually due to the great difficulty of automation, as the spectrum of heart size and shape in infants can be very diverse. This paper presents a solution to help diagnose Kawasaki disease in a faster and simpler way by using convolutional neural networks. More specifically, this work can automatically segment coronary arteries from 2D echocardiography images. These frames are relevant as Kawasaki disease can be detected by measuring the opening of the coronary artery. Different U-net based models have been developed and evaluated. In addition, an echocardiogram dataset specific for Kawasaki disease has been created in collaboration with the Hospital 12 de Octubre in Madrid. This solution can be considered as another step in the development of a fully automated solution for diagnosis [1].
Pathologies in the valves in the heart contribute to a large proportion of global cardiac deaths reduce the quality of lives for millions of others. Here, we investigate the effects of variations in the opening and closing times of the valves of the left ventricle at the same time as pathologies in the mechano-electric feedback. To this end, we utilize our synergistic cardio-vascular model without having to use time-varying elastance method. The latter prescribes the pressure-volume relationship in the ventricle directly using a periodic function, neglecting cardiac feedback and regulating mechanisms and is therefore unsuitable for investigating the mechano-electric feedback. We find that the closing time of valves has the greatest effect. A slower closing period of the aortic valve delays the onset of complications caused by the mechano-electric feedback, reducing the susceptibility to systolic stretch. For diastolic stretch, slow mitral valve closing time drastically increases the rise in heartrate and lessens the decline in stroke volume.
It is essential to automatically distinguish epileptic seizure forms of electroencephalography (EEG) signals in assisting in clinical diagnosis and monitoring of epilepsy. We found there is a special phenomenon that limits the ability to accurately identify epileptic forms. Some non-epileptic EEG signals show similar features to that of epileptic ones. We call such epileptic-like abnormalities boundary-type signals. Considering the existence of such type of signals, in this work a novel workflow employing deep learning is put forward for an automated seizure detection and epilepsy diagnosis. To distinguish the boundary type prior to the classification, a generative model, deep convolutional generative adversarial network, is employed, which is trained to find a representative time frequency diagram for the non-epileptic data, so as to distinguish more implicit boundary-type signals. Next, a structure-modified VGG16, a deep convolutional neural network is trained to detect normal and seizure classes. Tested on the Bonn University database, the proposed method achieved good performance.
The article describes a study run in 2021 on self-control in teens who study drama at ‘Dinu Lipatti’ Art College in Bucharest. The research introduces an online platform managed by artificial intelligence networks aimed to educate self-control for the target group that consisted of 90 students aged between 14 and 17 who study drama at the aforementioned institution. The purpose of the study was to identify if the techniques and exercises uploaded on the platform could produce any change in the teens' self-control after the period of three months of online practice. At the beginning of the program, the target group applied the Barratt questionnaire for impulsivity and the scores became referential for the analyses. After that, the adolescents made accounts on the platforms and worked the exercises for three months and at the end of the program they filled in the Barratt impulsivity questionnaire again. The initial scores were compared to the final scores using statistical methods. The results emphasized a good efficiency of the platform assisted by artificial intelligence. These findings encourage the following research to design platforms or applications dedicated to the needs that teenagers identify in order to help them improve the resilience during harsh periods or crises in their lives and to enhance self-development, as well.
In the new era of Internet Services development we have integrate vineyard application in Cloud Computing Information System. Our vineyard application is based on IoT Things that sends data to Cloud Server where we are using SaaS application for data management and analysis. To ensure data continuity and to minimize losing of data we are using FOG technology. We have implemented a FOG computer and install it on Cloud Border between vineyard local network and Internet. This computer will receive-store-push data from IoT Things to cloud server. This electronic document describes how we are implementing a FOG Computing for Vineyard Application. By implementing FOG server solution between IoT Things and IoT Cloud the data send from things are stored locally on FOG server and will be pushed to IoT Cloud Server. If Internet connection is broken the data are memorized locally and will be delivered to the IoT Cloud Server when Internet connection is restored. By using this solution we have minimized data lost between IoT Thing and IoT Server and we optimized transfer over Internet connection.
