Approximate reinforcement learning to control beaconing congestion in distributed networks

In vehicular communications, the increase of the channel load caused by excessive periodical messages (beacons) is an important aspect which must be controlled to ensure the appropriate operation of safety applications and driver-assistance systems. To date, the majority of congestion control solutions involve including additional information in the payload of the messages transmitted, which may jeopardize the appropriate operation of these control solutions when channel conditions are unfavorable, provoking packet losses. This study exploits the advantages of non-cooperative, distributed beaconing allocation, in which vehicles operate independently without requiring any costly road infrastructure. In particular, we formulate the beaconing rate control problem as a Markov Decision Process and solve it using approximate reinforcement learning to carry out optimal actions. Results obtained were compared with other traditional solutions, revealing that our approach, called SSFA, is able to keep a certain fraction of the channel capacity available, which guarantees the delivery of emergency-related notifications with faster convergence than other proposals. Moreover, good performance was obtained in terms of packet delivery and collision ratios.

Bioactivity of Essential Oils for Mitigation of Listeria monocytogenes Isolated from Fresh Retail Chicken Meat

Listeria monocytogenes is one of the most severe foodborne pathogens found in several habitats. Therefore, this study aims to investigate the antilisterial activity of different essential oils (EOs) against multidrug-resistant (MDR) L. monocytogenes strains isolated from fresh chicken meat. Our results showed that the prevalence of L. monocytogenes in the examined samples was 48%. Seventy-eight isolates were identified as L. monocytogenes. Out of these, 64.1% were categorized as MDR and were categorized in 18 patterns with 50 MDR isolates. One isolate was selected randomly from each pattern to investigate their biofilm-forming ability, resistance, and virulence genes incidence. Out of 18 MDR isolates, 88.9% showed biofilm-forming ability. Moreover, the most prevalent resistance genes were ermB (72%), aadA (67%), penA (61%), and floR genes (61%). However, the most prevalent virulence genes were inlA (94.4%), prfA (88.9%), plcB (83.3%), and actaA (83.3%). The antilisterial activity of EOs showed that cinnamon bark oil (CBO) was the most effective antilisterial agent. CBO activity could be attributed to the bioactivity of cinnamaldehyde which effects cell viability by increasing the bacterial cell electrical conductivity, ion leakage, and salt tolerance capacity loss. Therefore, CBO could be an effective alternative natural agent for food safety applications.

Driver perceptions of advanced driver assistance systems: A case study

Background: Automobile manufacturers need to have an insight and understand how consumers, specifically drivers, respond to the advanced driver assistance systems (ADAS) technology in their manufactured vehicles. This study reveals drivers’ perceptions of Malaysia’s advanced driver assistance systems, which is currently lacking in the literature. So far, other studies have focused on countries that are unlike Malaysia’s multi-culture environment. Methods: A survey was designed and distributed using convenience sampling to obtain responses from licensed drivers. Questions included demographic and driving questions, the perceptions of benefits and obstacles relevant to ADAS use, vehicle decision-making, and technology use. Data were collected from 818 respondents who were licensed drivers in Malaysia. Results were then analysed using statistical approaches. Results: The findings indicated that 76.8% of drivers have a positive attitude towards ADAS technology, particularly safety applications when they are available. Regardless of the accuracy of these systems, acceptance of the technology may shift upon viewing or hearing messages of possible problems with ADAS. Conclusions: It can be concluded that the safety advantages of ADAS technology are less valued by drivers who do not have experience of road traffic accidents. Furthermore, acceptance of the technology could be undermined by assuming that the safety applications could be compromised.