Oakland University

Deepfake detection has become increasingly important in recent years owing to the widespread availability of deepfake generation technologies. Existing deepfake detection methods present two primary limitations i.e., trained on a specific type of deepfake dataset, which renders them vulnerable to unseen deepfakes; and they regard deepfakes as a “black-box” with limited explainability, making it difficult for non-AI experts to understand and trust the decisions. Hence, this paper proposes a novel neurosymbolic deepfake detection framework that exploits the fact that human emotions cannot be imitated easily owing to their complex nature. We argue that deep fakes typically exhibit inter- or intra- modality inconsistencies in the emotional expressions of the person being manipulated. Thus, the proposed framework performs inter- and intra- modality reasoning on emotions extracted from audio and visual modalities using a psychological and arousal-valence model for deepfake detection. In addition to fake detection, the proposed framework provides textual explanations for its decisions. The results obtained using Presidential Deepfakes Dataset and World Leaders Dataset of real and manipulated videos demonstrate the effectiveness of our approach in detecting deepfakes and highlight the potential of neurosymbolic approach for expandability.

The advent of electric and flying vehicles (EnFVs) has brought significant advancements to the transportation industry, offering improved sustainability, reduced congestion, and enhanced mobility. However, the efficient routing of messages in EnFVs presents unique challenges that demand specialized algorithms to address their specific constraints and objectives. This study analyzes several case studies that investigate the effectiveness of genetic algorithms (GAs) in optimizing routing for EnFVs. The major contributions of this research lie in demonstrating the capability of GAs to handle complex optimization problems with multiple objectives, enabling the simultaneous consideration of factors like energy efficiency, travel time, and vehicle utilization. Moreover, GAs offer a flexible and adaptive approach to finding near-optimal solutions in dynamic transportation systems, making them suitable for real-world EnFV networks. While GAs show promise, there are also limitations, such as computational complexity, difficulty in capturing real-world constraints, and potential sub-optimal solutions. Addressing these challenges, the study highlights several future research directions, including the integration of real-time data and dynamic routing updates, hybrid approaches with other optimization techniques, consideration of uncertainty and risk management, scalability for large-scale routing problems, and enhancing energy efficiency and sustainability in routing. By exploring these avenues, researchers can further improve the efficiency and effectiveness of routing algorithms for EnFVs, paving the way for their seamless integration into modern transportation systems.

The aim of this research is to determine the antecedents that cause domestic disputes to devolve into high conflict domestic disputes (HCDs) in couples with children. Little is known about how antecedents can cause conflict to progress from low to high levels, comprehensive assessment of existing and potential conflicts, or the effectiveness of interventions that may help cou- ples in HCDs. Using a qualitative, grounded theory approach, a theory that identifies the antecedents that cause regular conflict to devolve into a HCD was developed. This theory increases understanding of early identification of antecedents, and the use of proactive and targeted interventions to specifically address these antecedents could help reduce or eliminate HCDs by allowing the root cause of the conflict to be addressed before it escalates to high conflict. The purposes of this study were, therefore, to (1) explore the perceptions of family counselors about assessment of and interventions for antecedents that can cause conflicts to progress to HCDs in couples with children and (2) develop a conceptual framework and theory to explain how antecedents can create barriers to conflict resolution and describe a process for decreasing the potential for the development or continuation of HCDs in couples with children.

States often use reservations to modify their treaty obligations. Prior research demonstrates why states enter reservations and why states object to reservations, but little work explains why states withdraw them. We argue that states withdraw reservations in response to international social pressure. Using novel data on reservations and reservation withdrawals for the nine core international human rights treaties , our analyses reveal two factors that compel states to withdraw reservations: (1) pressure from peer states and (2) pressure from human rights treaty bodies conducting periodic reviews. While previous work emphasizes domestic factors, our research shows that the international community encourages states to withdraw reservations and strengthen their commitments to human rights and international law.

Empirical research establishes systemic racism and implicit bias disproportionately impact academic achievement of Black students. Black students are disadvantaged by negative perceptions, harsher punishments, and reduced opportunities compared to White peers. We utilize conversation categories of course selection, college attendance, occupational choice, and personal problems to illustrate impacts of systemic racism and implicit bias in academic conversations with school counselors. We conducted a covariate analysis of data from 14,528 Black and White students from 944 US schools while controlling for social class, mathematical achievement, and problem behavior. White students engaged in more academic conversations with school counselors when controlling for social class and problem behavior but were fully mediated by mathematics performance. Black students were unseen and underserved unless they were exceptional in social class, academic achievement, or behavioral referrals. Through academic conversations with school counselors, we demonstrate subtleties of systemic racism and implicit bias embedded in educational systems.

In semi‐arid regions where drought and wildfire events often co‐occur, such as in Southern California chaparral, relationships between plant hydration, drought‐ and fire‐adapted traits may explain landscape‐scale wildfire dynamics. To examine these patterns, fire scientists and plant physiologists quantify hydration in plants via mass‐based metrics of water content, including live fuel moisture, or pressure‐based metrics of physiological status, such as xylem water potential; however, relationships across these metrics, plant traits and flammability remain unresolved. To determine the impact of hydration on tissue‐level flammability (leaves and stems), we conducted laboratory dehydration tests across wet and dry seasons in which we simultaneously measured xylem water potential, live fuel moisture and flammability. We tested two widespread chaparral shrubs, Adenostoma fasciculatum and Ceanothus megacarpus . Live fuel moisture showed a threshold‐type relationship with tissue flammability (increased ignitability and combustibility at specific hydration levels) that aligned with drought‐response traits (turgor loss point) and fire behaviour (increased fire likelihood and spread) identified at the landscape scale. Water potential was the better predictor of flammability in linear statistical models. A. fasciculatum was more flammable than C. megacarpus , and both species were more flammable during the wet growing season, suggesting seasonal growth or drought‐related tissue characteristics other than moisture content, such as lignin or chemical content, are critical for determining flammability. Our results suggest a mechanism for landscape‐scale increases in flammability at specific levels of drought stress. Integration of drought‐related traits, such as the turgor loss point, might improve models of wildfire risk in drought‐ and fire‐prone systems. Read the free Plain Language Summary for this article on the Journal blog.

Fecal pollution of surface water is a pervasive problem that negatively affects waterbodies concerning both public health and ecological functions. Current assessment methods monitor fecal indicator bacteria (FIB) to identify pollution sources using culture-based quantification and microbial source tracking (MST). These types of information assist stakeholders in identifying likely sources of fecal pollution, prioritizing them for remediation, and choosing appropriate best management practices. While both culture-based quantification and MST are useful, they yield different kinds of information, potentially increasing uncertainty in prioritizing sources for management. This study presents a conceptual framework that takes separate human health risk estimates based on measured MST and E. coli concentrations as inputs and produces an estimate of the overall fecal impairment risk as its output. The proposed framework is intended to serve as a supplemental screening tool for existing monitoring programs to aid in identifying and prioritizing sites for remediation. In this study, we evaluated the framework by applying it to two primarily agricultural watersheds and several freshwater recreational beaches using existing routine monitoring data. Based on a combination of E. coli and MST results, the proposed fecal impairment framework identified four sites in the watersheds as candidates for remediation and identified temporal trends in the beach application. As these case studies demonstrate, the proposed fecal impairment framework is an easy-to-use and cost-effective supplemental screening tool that provides actionable information to managers using existing routine monitoring data, without requiring specialized expertize.

This conceptual paper takes a dynamic view of culture to reexamine the tradeoffs between positive and negative aspects of guanxi in China. Because of cross-border collaboration and the wide use of the internet, Chinese employees are now exposed to more diverse values. Considering this cultural shift, the current paper discusses how the widely publicized negative aspect of guanxi relations in Chinese organizations can be mitigated. We suggest that employees are likely to withdraw from peer-to-peer guanxi relations that involve ethical concerns, and the likelihood and speed of this relation change would vary in part on the focal party's heritage of Confucian cultural values. This paper contributes to the literature by offering a dynamic approach to reconcile the controversy about peer-to-peer guanxi's role in Chinese organizations. This dynamic examination can invite further research on the complicated evolution of guanxi.