Risky Interactions Research Articles

Concept of Speaker Age Estimation Using Neural Networks to Reduce Child Grooming

This paper focusses on using neural network models to predict the age of social media users based on their voice recordings. The objective is to identify potential risky interactions between minors and adults by comparing the declared and predicted age groups of the users. The paper addresses the selection and training of suitable models and evaluates their effectiveness in age prediction. The results are demonstrated in sample data, where performance metrics are analysed, and possible limitations of the method are identified. Finally, the implications of the results for the safety of minors on social networks are discussed, and suggestions for future research in this area are provided.

Contactless logging and disinfection solution with automated face mask detection

Coronavirus disease-19 (COVID-19) mitigation includes health screening procedures at entrances of public and private establishments. Conventional methods include manual operations on temperature and face mask checking, personal identification, and hand disinfection. In this paper, a gateway kiosk is designed by integrating and automating the primary screening procedures. It uses radio-frequency identification (RFID) for contactless access control and attendance, with an infrared thermometer for body temperature monitoring. Face mask detection is automated through artificial intelligence (AI), while proximity sensors activate the disinfection system. Internet-of-things (IoT) interfaces these subsystems, and local access is available via an Internet browser. RFID overcomes the slower response rate of the quick response (QR) code-based solution. The repeated-measure analyses showed that the system’s thermometer has only +0.28 °C error while its residual neural network-10 (ResNet-10) and MobileNetV2 models for detecting masked faces achieved a 98.2% accuracy. The system reduces the primary key performance indicators–service and queuing times by 56.86% and 79.95%, respectively. Its audio and visual notifications ensure the proper screening implementation, thus reducing unnecessary and risky interactions with entrance personnel. It improves the screening procedures by significantly reducing human interactions and enhancing queuing.

Exploring interacting effects of risk factors on run-off-road crash severity: An interpretable machine learning model joint with latent class clustering

Run-Off-Road (ROR) crashes are frequent and pose a significant risk of injury and fatality. Given the complexity of their mechanisms and the interaction of multiple factors, this study aims to comprehensively investigate the factors influencing the severity of ROR crashes, which have been understudied. Furthermore, addressing the current methodological challenge in machine learning (ML) crash modeling, this study proposes an approach to tackle unobserved heterogeneity in ML. An interpretable ML joint with prior latent class clustering is implemented. The significant risk factors and interactions are interpreted using SHAP (SHapley Additive exPlanations) method across clusters. This study utilizes ROR crash records, traffic, and geometric data from main suburban freeways in Iran collected over a 5-year period. The key interacting factors associated with severe ROR during adverse weather (cluster 1) are: co-occurrence of low congestion and higher speed variation; low congestion, nighttime darkness and rollover; roadway departure by buses and mini-buses and rollover occurrence; vehicle departure and collision with fixed objects. Moreover, the critical interactions for nighttime condition (cluster 2) are: curve sections combined with longitudinal slope; inside shoulder width <1.5 m and a hit median concrete NewJersey barrier. The risky interactions for crashes occurred in curves (cluster 3) are: departing in two-lane sections in low congestion conditions; vehicles collisions with the median concrete NewJersey barriers. The findings of this study enhance comprehension of the significant effects of interactions under various conditions, offering valuable insights for policymakers. Additionally, recommendations are offered to mitigate the risk of severe ROR crashes.

Rapid facial mimicry as a regulator of play in a despotic macaque species

During risky interactions like social play, motor resonance phenomena such as facial mimicry can be highly adaptive. Here, we studied Rapid Facial Mimicry (RFM, the automatic mimicking of a playmate’s facial expression, play faces) during play fighting between young rhesus macaques (Macaca mulatta) living in a large zoo-housed group. For the first time and in contrast to previous data on highly despotic-intolerant macaques, we found RFM to be present at high frequency in young rhesus macaques, especially when the trigger was dominant over the responder and when both players were subadults. The hierarchical modulation of RFM may be associated with the increased uncertainty and riskiness of play involving a higher-ranking playmate. This highlights the importance of mimicry in improving communication and coordination during such interactions. Interestingly, RFM prolonged playful sessions, possibly indicating a more effective fine-tuning of motor patterns. Moreover, the occurrence of RFM had an effect on shortening the latency to restart playing after a break, possibly acting as an engine to potentially maintain playmates’ arousal. When investigating if bystanders could replicate play faces emitted by the playing subjects, we failed to find RFM, thus highlighting that being directly involved in the interaction might be crucial for RFM activation in monkeys. Even though further comparative studies should investigate the role of RFM across tolerant and despotic-intolerant species, our findings offer valuable insights into the communicative and adaptive value of motor resonance phenomena in regulating social play in despotic societies.Significance statementIn risky interactions involving competition and vigorous physical contact, such as play fighting, replicating partners’ facial expressions can serve as a strategy to convey positive mood and intentions. Here we investigated the presence and possible roles of Rapid Facial Mimicry (RFM) in rhesus macaques (Macaca mulatta). For the first time, our study demonstrates that communicative strategies, including Rapid Facial Mimicry (RFM), can be both present and frequent in despotic-intolerant macaque species. We demonstrate that the role of mimicry not only prolongs playful interactions but can also be linked to the reinforcement and/or transmission of playful arousal. Our study shows how the adaptive value of motor resonance phenomena may have driven their evolution to cope with challenges during social interactions also for despotic-intolerant species.

Static Program Analysis for IoT Risk Mitigation in Space-Air-Ground Integrated Networks

The space-air-ground integrated networks(SAGINs) are pivotal for modern communication and surveillance, with a growing number of connected devices. The proliferation of IoT devices within these networks introduces new risks due to potential erroneous synergistic interactions that could compromise system integrity and security. This paper addresses the challenges in coordination, synchronization, and security within SAGINs by introducing a novel static program analysis (SPA) technique using zero-knowledge (ZK) proofs. This approach ensures the detection of risky interactions without compromising sensitive source code, thus safeguarding intellectual property and privacy. The proposed method overcomes the incompatibility between SPA and ZK systems by developing an imperative programming language for SAGINs and a specialized abstract domain for interaction threats. The system translates network control algorithms into arithmetic circuits suitable for ZK analysis, maintaining high accuracy in detecting risks. Evaluations on real-world scenarios demonstrate the system's efficacy in identifying risky interactions with minimal computational overhead. This research presents the first ZK-based SPA scheme for SAGINs, enhancing security and confidentiality in network analysis while adhering to privacy regulations.

Simulation of pedestrian interaction with autonomous vehicles via social force model

Simulation of pedestrian motion in urban traffic networks is crucial for designing autonomous vehicle systems. In a mixed traffic system, a complex interaction occurs between a pedestrian and a vehicle. To understand this interaction pattern and evaluate traffic safety analysis, a simulation tool can be useful. It can help autonomous vehicle designers to visualize pedestrian and vehicle trajectory, extract velocity and acceleration profile of both agents, test different autonomous vehicle planning algorithms, and assess the traffic safety in severe traffic conflicts. This paper presents a rule-based social force model to simulate pedestrian trajectories during interaction with an autonomous vehicle. The social force model is then integrated with an autonomous vehicle control and planning algorithm for simulating the behavior of both pedestrian and vehicle in traffic conflicts by varying different parameters such as agent's initial speed, different vehicle sensor types (error percentage of pedestrian detection varies), different pedestrian types (risk-taking, cautious, and distracted), etc. This simulation tool provides minimum distance accepted by a pedestrian during a road crossing scenario as output. Additionally, the simulation illustrates the impact of vehicle initial speed on crossing decision and minimum distance accepted by pedestrians before crossing. The simulation tool can be useful to simulate risky interaction scenarios to understand the effectiveness of autonomous vehicle planning algorithm while interacting with different types of pedestrians.

Мотивационно-смысловые характеристики участия в секстинге несовершеннолетних девочек

&lt;p style="text-align: justify;"&gt;In Russia, the number of sexual crimes against minors committed using the Internet is increasing. One way to obtain pornographic products depicting children and teenagers is sexting. To prevent the involvement of minors in such activities, it is important to know their motivation and understanding of their own participation in sexting. In a qualitative study of a complete sample of 27 girls aged 12 to 18 who were victims of molestation, the main motivational and semantic characteristics related to their sexualized activities on the Internet were considered. Three groups have been identified that differ in the motivational orientation of interactions: those who are actively interested in sexual topics and willingly engage in risky interactions without the formation of interpersonal relationships; focused on communication and friendships; seeking to form and develop romantic relationships. The typical features of girls of each group and the nature of their actual emotional response are described. It is proposed to take into account these characteristics in preventive programs.&lt;/p&gt;

NON-COMMUNICABLE DISEASE SYNDEMICS AMONG LOW-INCOME POPULATIONS: PAKISTAN AND WAY FORWARD

Non-communicable diseases (NCDs) have substantially contributed to morbidity and mortality of populations. The emergence of the novel coronavirus SARS-CoV2 pandemic took centre stage toppling over the global health and economies leading to high morbidity and mortality rates. Presently as many as one in five with underlying NCDs are at risk of severe Covid-19[3].In May 2020, the World Health Organization (WHO) undertook a fast evaluation survey, which revealed that 75% of nations have experienced service outages related to NCDs. Public health campaigns and NCD surveillance programmes were among the hardest damaged. Gains against COVID-19 are hollow wins when the risky interactions between NCDs and virus infection are not perceived as syndemics along with social and economic disparities.

Detecting Safety Anomalies in pHRI Activities via Force Myography.

The potential application of using a wearable force myography (FMG) band for monitoring the occupational safety of a human participant working in collaboration with an industrial robot was studied. Regular physical human-robot interactions were considered as activities of daily life in pHRI (pHRI-ADL) to recognize human-intended motions during such interactions. The force myography technique was used to read volumetric changes in muscle movements while a human participant interacted with a robot. Data-driven models were used to observe human activities for useful insights. Using three unsupervised learning algorithms, isolation forest, one-class SVM, and Mahalanobis distance, models were trained to determine pHRI-ADL/regular, preset activities by learning the latent features' distributions. The trained models were evaluated separately to recognize any unwanted interactions that differed from the normal activities, i.e., anomalies that were novel, inliers, or outliers to the normal distributions. The models were able to detect unusual, novel movements during a certain scenario that was considered an unsafe interaction. Once a safety hazard was detected, the control system generated a warning signal within seconds of the event. Hence, this study showed the viability of using FMG biofeedback to indicate risky interactions to prevent injuries, improve occupational health, and monitor safety in workplaces that require human participation.

Using random forest to test if two-wheeler experience affects driver behaviour when interacting with two-wheelers

Car drivers are primarily responsible for crashes between cars and bicycle and motorcycle riders (two-wheelers; TWs). A lack of exposure and riding experience with TWs among car drivers may contribute to the occurrence of these crashes. The current research investigates if car drivers with different TW riding experience levels act differently during risky interactions with both types of TWs. A total of 69 drivers completed a 10-minute driving session using the CARRS-Q advanced driving simulator, which included five interactions with TWs based on common crash types. These interactions involve driving manoeuvres in which TWs were initially positioned in front of or at a right angle to the driver. The drivers were divided into two categories based on whether they possessed TW riding experience or not. For analysis, several response features were calculated using the speed and time to collision (TTC) during the time window covering the interaction. Then, a random forest algorithm used the extracted features from the predefined window to classify the drivers. Classification accuracy was calculated using leave one out cross-validation. To test the association between the speed, TTC features and experience as a TW rider, the drivers’ labels were randomly permuted. The random forest models were trained using these permuted labels, and the average classification accuracy was calculated. Overall, the comparison between the average of the original data classification accuracy and the randomly permuted data revealed a statically significant difference. This study found that two-wheeler experience influences driver behaviour when interacting with two-wheelers.

Modeling shield immunity to reduce COVID-19 transmission in long-term care facilities

PurposeNursing homes and long-term care facilities have experienced severe outbreaks and elevated mortality rates of COVID-19. When available, vaccination at-scale has helped drive a rapid reduction in severe cases. However, vaccination coverage remains incomplete among residents and staff, such that additional mitigation and prevention strategies are needed to reduce the ongoing risk of transmission. One such strategy is that of “shield immunity”, in which immune individuals modulate their contact rates and shield uninfected individuals from potentially risky interactions. MethodsHere, we adapt shield immunity principles to a network context, by using computational models to evaluate how restructured interactions between staff and residents affect SARS-CoV-2 epidemic dynamics. ResultsFirst, we identify a mitigation rewiring strategy that reassigns immune healthcare workers to infected residents, significantly reducing outbreak sizes given weekly testing and rewiring (48% reduction in the outbreak size). Second, we identify a preventative prewiring strategy in which susceptible healthcare workers are assigned to immunized residents. This preventative strategy reduces the risk and size of an outbreak via the inadvertent introduction of an infectious healthcare worker in a partially immunized population (44% reduction in the epidemic size). These mitigation levels derived from network-based interventions are similar to those derived from isolating infectious healthcare workers. ConclusionsThis modeling-based assessment of shield immunity provides further support for leveraging infection and immune status in network-based interventions to control and prevent the spread of COVID-19.

Drug utilization in patients with SARS-CoV-2 in an intensive care unit

Context: Prescription indication studies allow identifying the problems that arise during the use of the drug. Aims: To evaluate the treatments used in patients diagnosed with SARS-CoV-2 infection hospitalized in critical care service, through a prescription indication study. Methods: A longitudinal observational study of medication use of the indication-prescription type with elements of the therapeutic scheme and practical consequences was carried out. The sample was characterized from the sociodemographic, clinical, and pharmacotherapeutic points of view. The prescription was evaluated through the indicators: indication, therapeutic scheme, treatment individualization, and drug combinations. The detected adverse reactions were classified according to their causality by the Naranjo Algorithm, their severity, their clinical significance, and according to their mechanism by Rawlins and Thompson. Results: In the sample (n = 77), the male gender predominated (79%) between 27-59 years old (64%), alcohol consumer (62%), hypertensive (33%) with long hospital stay (51%). A total of 417 medications were analyzed, being antibiotics (50.6%) the most prescribed. 73.4% of the therapeutic schemes were correct; however, 26.6% had problems with the therapeutic schemes due to incorrect doses, intervals, duration of treatment, and risky interactions. According to Rawlins and Thompson, two probable adverse reactions were detected, mild, non-serious, and type A and B. Conclusions: The results obtained will allow the pharmaceutical professional to create risk matrices that guarantee a timely intervention in the health team to contribute to the rational and safe use of medicines in patients infected with SARS-CoV-2.

‘The game is on!’ Eventness at a distance at a livestream concert during lockdown

In many countries the lockdown measures in response to the Covid-19 pandemic forbade social gatherings, including for performing arts. Numerous artists developed projects, often attempting to reach audiences in cyberspace. We offer an ethnographic study of such a project: a jazz concert played live for a particular audience, who attended it from home. We seek to understand how musicians, audience, and the material setting made it possible to engage with music in a way that gave these moments a particular density. What made this experience meaningful, we argue, was the eventness of the performance: the ‘game was on’, happening in the moment, in the unpredictable, risky interactions between musicians, and with the ‘push of the audience’ listening to the gig in real time. The eventness of this online concert was created in such a way it made possible a collective engagement with and through live music, notwithstanding the physical distance.

Reducing risky interactions: Identifying barriers to the successful management of human–wildlife conflict in an urban parkland

Abstract Managing activities that result in human–wildlife conflict is a challenging goal for modern scientists and managers. In recent years, the self‐motivated feeding of wildlife by humans has garnered popularity but with consequent risks for the health and safety of both parties. This has resulted in calls for management in areas of high contact, for example, parklands. Traditional controls are typically utilised (i.e. signage, patrols), yet their success is varied, leading to a rise in research aiming to improve them. This research has primarily focused on language and design, with little attention paid to the role that audience type (i.e. international tourists vs. locals/residents) may play in their success. Proportions in audience type present can vary both between parks and spatially within a single park, however, controls are usually applied homogeneously with no consideration for how response may vary between these groups. Here, we performed a robust before–after study across two summers using a wild fallow deer population in a public park that are commonly fed by visitors as our model. We deployed controls, following best practice as outlined by the literature, and tested their overall effectiveness. We then identified key areas with differences in visitor type proportions and tested for variation in success between them. We found that the numbers of visitors feeding the deer significantly decreased overall after the introduction of controls, although interactions were not eliminated entirely. We discovered that the effectiveness of these controls varied with changes in visitor type, with the most positive effects occurring in areas with more international tourists and no significant effect occurring in areas dominated by resident visitors. Notably, of the food offerings remaining, the proportion of foods that could be perceived as ‘nutritionally beneficial’ increased in both sites, marking overall changes in the behaviours of even those visitors who refused to stop feeding. These findings highlight the importance of target audience research in human–wildlife conflict management. We recommend that authorities aiming to reduce these interactions perform systematic surveys to identify the audience type present and cater controls accordingly to maximise their success. Read the free Plain Language Summary for this article on the Journal blog.

Same Behaviors, Different Outcomes: Mothers' and Fathers' Observed Challenging Behaviors Measured Using a New Coding System Relate Differentially to Children's Social-Emotional Development.

This study used a newly developed coding system for measuring the quality of parenting behavior to examine associations with children’s social-emotional development. The Risky Interaction Support and Challenge Scale (RISCS) measures the extent to which parents engage in behaviors that present physical and regulatory challenges to children, as well as parents’ tendency to allow children to pursue action goals autonomously. These behaviors were observed while parents (n = 57 fathers; n = 55 mothers; n = 50 pairs) interacted with their 1-year-olds who played on a structure that included a slide, a small climbing wall, and a tunnel. Trained raters reliably used the RISCS to measure several dimensions of parent behaviors related to children’s exploration, and all but one of the dimensions captured adequate variability in parent behavior. Although mothers and fathers did not differ in any of the dimensions, the associations between parent behavior and children’s social-emotional development did not overlap. Fathers who engaged in greater autonomy allowance and lower overprotection had toddlers with lower levels of internalizing behavior, whereas mothers who challenged children’s regulatory competence had toddlers with lower levels of externalizing behavior and greater competence. We discuss the implications of the findings for the literature on attachment theory and father-child relationships.

Masks, Empathy, and a Pediatric Cancer Diagnosis During COVID-19.

Masks, Empathy, and a Pediatric Cancer Diagnosis During COVID-19.

Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning

Autonomous car racing is a challenging task in the robotic control area. Traditional modular methods require accurate mapping, localization and planning, which makes them computationally inefficient and sensitive to environmental changes. Recently, deep-learning-based end-to-end systems have shown promising results for autonomous driving/racing. However, they are commonly implemented by supervised imitation learning (IL), which suffers from the distribution mismatch problem, or by reinforcement learning (RL), which requires a huge amount of risky interaction data. In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs. The driving knowledge is acquired from both IL and model-based RL, where the agent can learn from human teachers as well as perform self-improvement by safely interacting with an offline world model. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation. The evaluation results demonstrate that our method outperforms previous IL and RL methods in terms of sample efficiency and task performance. Demonstration videos are available at https://caipeide.github.io/autorace-dirl/.

Prescription of statins and pharmacokinetic interactions in Colombian patients

ABSTRACT Background: Statins have extensive hepatic metabolism and can have multiple pharmacological interactions. The aim was to identify the main pharmacokinetic interactions between statins and their comedications in a group of patients from Colombia. Research design and methods: A cross-sectional study of pharmacokinetic interactions in patients treated with statins who were identified from a population database. The interactions were documented using the Lexicomp® database. Results: A total of 123,026 patients with statin prescriptions were identified, with a mean age of 68.4 ± 11.5 years; 57.1% were women, and 81.6% received atorvastatin. A total of 19.4% (n = 23.831) of patients presented pharmacological interactions. Some 15,474 (12.6%) had interactions classified as category C, 7.4% (n = 9077) as category D, and 0.5% (n = 660) as category X. 36.8% of the patients with lovastatin prescriptions had some interaction. Age older than 65 years, male sex, residence in capital cities, comorbidities, endocrine pathologies and HIV were associated with an increase in the probability of having contraindicated or risky interactions. Conclusions: Important interactions between statins and other medications were more common in adults over 65 years of age and those with endocrine comorbidities or HIV infection. This knowledge should help when proposing solutions that reduce the risk of adverse reactions.

Robotics system interfaces – development trajectories

The features of the creation of robotics system interfaces that provide effective interaction with external complex systems are considered. The features of complex systems, factors leading to the risky interaction of structures and processes are given. The main effects arising from information interaction of complex systems are listed. A scheme for monitoring the underwater information situation is given. The system interfaces of robotics are enumerated; the problems associated with their creation are given. An approach to the standardization of technical solutions for interfaces and the organization of system interfaces development is presented. A strategy is proposed that combines the advantages of the autonomous and systemic approaches. It is proposed to consider a horizontal network with self-organization and open access as a reasonable organizational development scheme. The need to concentrate efforts on the issues of compatibility, intelligence and physical simulation is noted. An option of experimental development of technical solutions using a modernized model of the underwater hangar developed by JSC SPMDB Malakhit is proposed.

Stochastic Filtrate of Essential Workers to Reactivate the World Economy Safely

There is a rapidly emerging risk that essential supply chains could collapse during the COVID-19 pandemic. Therefore, strategies to protect essential workers regardless of whether they have symptoms should be implemented by governments. We propose a “stochastic filtrate” of such workers, based on periodic real-time-RT-PCR-testing to reduce risky physical interactions with workers infected with SARS-CoV-2. Such a focused strategy, when combined with other preventive measures, could be successfully replicated in many countries to reactivate the world’s economy safely. We present a mathematical framework, conceptual model, and simulation of this stochastic filtrate process to support its viability.