Corneliu Zaharia

Smart cities and 6G are technological areas that have the potential to transform the way we live and work in the years to come. Until this transformation comes into place, there is the need, underlined by research and market studies, for a critical reassessment of the entire wireless communication sector for smart cities, which should include the IoT infrastructure, economic factors that could improve their adoption rate, and strategies that enable smart city operations. Therefore, from a technical point of view, a series of stringent issues, such as interoperability, data privacy, security, the digital divide, and implementation issues have to be addressed. Notably, to concentrate the scrutiny on smart cities and the forthcoming influence of 6G, the groundwork laid by the current 5G, with its multifaceted role and inherent limitations within the domain of smart cities, is embraced as a foundational standpoint. This examination culminates in a panoramic exposition, extending beyond the mere delineation of the 6G standard toward the unveiling of the extensive gamut of potential applications that this emergent standard promises to introduce to the smart cities arena. This paper provides an update on the SC ecosystem around the novel paradigm of 6G, aggregating a series of enabling technologies accompanied by the descriptions of their roles and specific employment schemes.

Computer vision algorithms implementations, especially for real-time applications, are present in a variety of devices that we are currently using (from smartphones or automotive applications to monitoring/security applications) and pose specific challenges, memory bandwidth or energy consumption (e.g., for mobility) being the most notable ones. This paper aims at providing a solution to improve the overall quality of real-time object detection computer vision algorithms using a hybrid hardware–software implementation. To this end, we explore the methods for a proper allocation of algorithm components towards hardware (as IP Cores) and the interfacing between hardware and software. Addressing specific design constraints, the relationship between the above components allows embedded artificial intelligence to select the operating hardware blocks (IP cores)—in the configuration phase—and to dynamically change the parameters of the aggregated hardware resources—in the instantiation phase, similar to the concretization of a class into a software object. The conclusions show the benefits of using hybrid hardware–software implementations, as well as major gains from using IP Cores, managed by artificial intelligence, for an object detection use-case, implemented on a FPGA demonstrator built around a Xilinx Zynq-7000 SoC Mini-ITX sub-system.

Teenage pregnancy is associated with an increased risk of adverse pregnancy outcomes. The objective of this research is to determine the profile of the pregnant teenager and the medical complications associated with pregnancy at this young age. A cross-sectional study based on a 29-item questionnaire was conducted in 2019 and 2020 in Ploiești, Romania. The participants were divided into two groups, namely, Group A, consisting of 100 minor, teenage childbearing women under the age of 18, and Group B, consisting of 100 childbearing women over 18 years of age. Group A had a mean age of 16.56 ± 1.65. The percentage of births in very young girls (13-15 years) from group A is 28%. In 65 adolescents, sexual intercourse began at the age of 14. Pregnancy monitoring, expressed by the number of medical examinations, shows significant differences between the studied groups. The Short Assessment of Health Literacy (SAHL) test applied to both groups revealed a low level of health literacy in group A. Also in this group A, teenagers gave birth to low-birth-weight children, the percentage is statistically significant (14% vs. 4%). The gestational age in this group had an average of 36.88 ± 2.13 weeks, compared to the gestational age in the control group of 38.41 ± 1.57 weeks. In Romania, there are teenagers who became mothers at an early age. There should be educational programs in rural and urban schools and communities. Poverty leads to inadequate medical supervision with significant consequences for the health of the mother and child, lack of education (school dropout, illiteracy), and inability to find a job. The midwife can play a key role in rural communities through health education conducted on specific communication channels and with different forms of presentation of messages, adapted to their needs. A good target would be the parents of adolescent mothers and better communication with them.

The recent emergence of deep learning algorithms has radically influenced the object detection performances by providing very precise and robust approaches. However, the disadvantage of the recently proposed object detectors is that they are computationaly extremely intensive, making them unsuitable for being used in portable devices. In this paper we propose six models which optimize an existent deep learning-based object detector - presenting also the results obtained on current benchmarks - for the particular task of person detection. We demonstrate that we may reduce the computational requirements of the existing algorithm by using several strategies for neural network architecture optimization, while still obtaining comparable results with the state-of-the-art approaches. Moreover, on the particular pedestrian detection task, we show that we matched state-of-the-art results.