RESUMO
Self-driving cars and autonomous vehicles are revolutionizing the automotive sector, shaping the future of mobility altogether. Although the integration of novel technologies such as Artificial Intelligence (AI) and Cloud/Edge computing provides golden opportunities to improve autonomous driving applications, there is the need to modernize accordingly the whole prototyping and deployment cycle of AI components. This paper proposes a novel framework for developing so-called AI Inference Engines for autonomous driving applications based on deep learning modules, where training tasks are deployed elastically over both Cloud and Edge resources, with the purpose of reducing the required network bandwidth, as well as mitigating privacy issues. Based on our proposed data driven V-Model, we introduce a simple yet elegant solution for the AI components development cycle, where prototyping takes place in the cloud according to the Software-in-the-Loop (SiL) paradigm, while deployment and evaluation on the target ECUs (Electronic Control Units) is performed as Hardware-in-the-Loop (HiL) testing. The effectiveness of the proposed framework is demonstrated using two real-world use-cases of AI inference engines for autonomous vehicles, that is environment perception and most probable path prediction.
RESUMO
Introduction: Telemedicine is the use of Information and Communication Technologies (ICT) to improve patient outcomes by increasing access to care, medical information and services. The aim of this pilot study was to evaluate and support the implementation of screening and early detection programs in the prevention of breast cancer and cardiovascular diseases with the establishment of a remote diagnosis through the use of ICT in mobile units. Materials and Methods: A total of 430 individuals were recruited in an area of Southern Italy. Particularly, 321 women were recruited to undergo breast cancer screening in accordance with Italian guidelines. Likewise, cardiovascular screening interested 109 subjects. A self-contained mobile unit with connectivity was provided to offer breast and cardiovascular screenings. To maximize the benefit, we have evaluated the return of investment. Results: The telemedicine screening program allowed the detection of early pathologies. In breast cancer screening, 40.8% of cases were negative to lesions, 34.9% were positive to benign lesions, and 3.1% presented suspicious malignant lesions; these lesions were further checked by histological analyses, which showed a positive response in 70% of cases. The cardiovascular screening concerned 109 participants based on age and other risk factors. We observed a significant difference among risk factors in patients with cardiac disease (p < 0.001); particularly, hypertension was significantly the most present risk factor (51.4%, p < 0.05), followed by smoking (28.4%, p < 0.05). A cardiovascular pathology was detected in 40.4% of enrolled subjects. A 3.3:1 return on investment was calculated. Conclusion: Our findings demonstrate that telemedicine may represent a promising approach to deliver several health services, such as screening programs, with users who cannot utilize services in their locations. The use of telemedicine on diagnostic campers greatly reduces the costs of screening for breast cancer and major cardiovascular diseases within the Southern Italian Health Service. We believe that public investment can have a further significant return on investment by implementing the principles of precision medicine.
