A5064639847- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Video Surveillance and Tracking Methods
- COVID-19 diagnosis using AI
- Computer Graphics and Visualization Techniques
- Voice and Speech Disorders
- Autonomous Vehicle Technology and Safety
- Dental Erosion and Treatment
- Digital literacy in education
- Endometriosis Research and Treatment
- Optical Wireless Communication Technologies
- Face and Expression Recognition
- Traffic Prediction and Management Techniques
- Music and Audio Processing
- Vehicle License Plate Recognition
- Human Motion and Animation
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Data Visualization and Analytics
- Cutaneous Melanoma Detection and Management
- Vaccine Coverage and Hesitancy
- Uterine Myomas and Treatments
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Health Literacy and Information Accessibility
West University of Timişoara
2018-2024
Parkinson's disease is a progressive neurodegenerative disorder caused by dopaminergic neuron degeneration. Parkinsonian speech impairment one of the earliest presentations and, along with tremor, suitable for pre-diagnosis. It defined hypokinetic dysarthria and accounts respiratory, phonatory, articulatory, prosodic manifestations. The topic this article targets artificial-intelligence-based identification from continuous recorded in noisy environment. novelty work twofold. First, proposed...
Emergency remote teaching replaced face-to-face education almost everywhere in the world at onset of Covid-19 pandemic.Romania switched to online March 2020 as a recommendation that became an obligation teach late April 2020.Teachers saw themselves confronted with need adapt completely new infrastructure for and learning digital sphere.Building on qualitative data (interviews focus groups), collected part participatory action research project aiming support school teachers adapting...
The aim of this study is to evaluate salivary remineralisation versus chemical remineralisation/infiltration enamel, using different dentistry materials. enamel changes were studied confocal laser scanning microscopy (CLSM), and the depth lesions demineralisation/remineralisation/infiltration percentage calculated. Additionally, macro elemental composition teeth was performed atomic absorption spectroscopy (AAS). Two studies performed: (i) demineralisation in 3% citric acid infiltration...
Purpose of the articleto carry out an epidemiological study on use sealing as a method preventing dental caries and to assess tightness integrity over time composite resins used seal pits fissures using VistaCam iX intraoral fluorescence camera. Based premise that dentists do not have enough confidence in caries, we assessed if is current practice prevention metod tooth decay, measured, with high performance camera such device, resin seals.
As devices get ever so interconnected, the concept of Smart City is becoming less a distant aspiration and more reality. One major discomfort which persistent in traditional cities, from perspective vehicle motorist, lack guidance or coordination when need parking space, be it shopping center, at airport, work any other overcrowded point interest. Motorists are frequently presented with little to no adequate information regarding space availability within lot, turn end up spending excessive...
Background: Parkinson’s disease (PD) has transitioned from a rare condition in 1817 to the fastest-growing neurological disorder globally. The significant increase cases 2.5 million 1990 6.1 2016, coupled with predictions of further doubling by 2040, underscores an impending healthcare challenge. This escalation aligns global demographic shifts, including rising life expectancy and growing population. economic impact, notably U.S., reached $51.9 billion 2017, projections suggesting 46% 2037,...
Access to the internet and online resources changes concept of health increases people's autonomy. In this context, Health Literacy (HL) is a critical determinant health-related choices. At World Organization (WHO) level, M-POHL (Action Network on Measuring Population Organizational WHO-Europe) created validated European population four questionnaires: digital HL (HLS19-DIGI), communication (with doctors from care services - HLS19-COM-P-Q11 long version HLS19-COM-P-Q6 short version),...
One of the objectives deep learning is to solve high complex tasks such as perception. In recent years, it has been demonstrated that can overcome traditional algorithms in image classification well object recognition and face tasks. this paper we are inspecting techniques deals with topical issues field Computer Vision: real-time detection using embedded system GPU processing on NVidia Tegra X2 (Jetson TX2). first part our work proposing a novel experimental research problem autonomous...
Road accidents are directly proportional to the number of cars on market. Without car safety systems, this will keep rising. The main factor for drowsiness and fatigue. These can be detected by analysing images with driver so, an example a monitoring system may include camera, mounted in front driver. A method based machine learning computer vision solution solve problem safety. objectives our work includes analysis different approaches systems implementation convolutional neural networks...
As far as the problem of processing real time images studies showed that there can be two ways analyze. On one hand is about central unit (CPU) and other graphics (GPU). To obtain highest possible performance they have to used at same time. Comparing processes, result in CPU, assignments sequential operations input-output are involved, contrast GPU which for processes made Transposing these concepts real-time medical digital proved an image a response aproved within certain The we speaking...
In the last few years filed of deep learning and in general machine medical imaging has become state-of-the-art terms image analysis processing. our experimental work, we try to provide a high-level approach fully connected neural networks applied segmentation (lung CT scans), by using Deep Learning GPU Training System (DIGITS) avoiding rigorous mathematical formalism networks. For this purpose concept solving problems from experiences is necessary. The goal work design an particular methods...
The following topics are dealt with: learning (artificial intelligence); neural nets; image classification; computer vision; formal logic; feature extraction; graph theory; symbol manipulation; mathematics computing; object detection.
In Romania it is estimated that there are half a million patients with endometriosis. The main symptoms pain (70% of chronic pelvic have endometriosis) and infertility (50% infertile endometriosis). It difficult to make an accurate diagnosis. Numerous studies show 7-10-year delay in diagnosis women developing countries. 47% should be seen by more than 5 physicians over time until the established. treatment for endometriosis surgical procedure most often performed laparoscopically. present...
In this paper we are discussing the possibility of a hybrid approach in renderable scenes. The main idea presented experiment is to render human actors by using existing videos characters. input video first converted sprite dataset. dataset generated with supervised techniques but intervention also required. After that extract body and pose parameters. Lastly, novel poses GAN-based similar pix2pix.