Search Results (550)

Artificial intelligence computing systems increasingly demand high-bandwidth, high-extinction-ratio, chip-to-chip optical transceivers. Silicon microring modulators (MRMs) are attractive for such transmitters due to their compact footprint and wavelength-division multiplexing capability. However, for a specified extinction ratio, the optical bandwidth for high-Q MRMs and the driver’s RC time constant prevent conventional single-segment MRM drivers from supporting 100 GBaud class PAM4 transmission. This work presents a broadband driver exploiting the feedforward technique for dual-segment MRMs. It extends electro-optical bandwidth while maintaining a high Q-factor and extinction ratio. The input signal is split into low- and high-frequency components that drive the long and short segments of the MRM, respectively. The long segment uses a broadband low-pass driver, whereas the short segment employs a driver with a programmable bandpass response near the Nyquist frequency. The design space is obtained from an equivalent electro-optical model under constant group-delay constraints. Simulations at 1310 nm show that the 3 dB electro-optical bandwidth improves from ~50 to >70 GHz and that a 200 Gb/s PAM4 optical eye diagram exhibits an open eye; the energy efficiency is 1.44 pJ/bit, and the extinction ratio improves from 2 dB to 4.1 dB. The proposed technique provides a tunable electro-optical co-design approach for high-bandwidth-density, high-extinction-ratio silicon photonic transmitters. Full article

Traditional approaches to university-level history education often fail to provide immersive and interactive environments that foster deep cognitive engagement. To address these limitations, we developed an AI-enabled virtual museum system that integrates AI-generated content with knowledge graphs through a multi-layered architecture. The system architecture follows a three-tier framework: a front-end interaction layer (Unity/Unreal Engine) for real-time user engagement, a core service layer for intelligent event scheduling and response control (Chat General Language Model/Stable Diffusion), and a data and model layer (My Structured Query Language/MongoDB) to provide structured knowledge. To evaluate the system’s effectiveness, a four-week controlled experiment was conducted with 83 university students. The experimental group using the AI virtual museum showed a significantly higher mean post-test score (84.5 ± 6.8) than that of the control group (71.6 ± 7.9), with statistical significance at p < 0.001, starting from nearly identical baseline scores (61.2 and 60.4 for the experimental and control groups). Correlation analysis was conducted to identify scenario simulations (r = 0.59) and deep inquiry tasks (r = 0.54) as key drivers of learning mastery. By aligning advanced system engineering with educational theory, the results of this study offer a solution for high-fidelity, intelligent digital educational platforms, proposing a validated model for integrated system innovation in education. Full article

Sustainable entrepreneurship has emerged as a critical driver of long-term economic resilience and innovation in the digital era. This study examines how artificial intelligence (AI) propensity and risk awareness influence entrepreneurial alertness and, subsequently, sustainable entrepreneurial intentions among university students. Using a quantitative design, data were collected from 377 students in Türkiye using a structured questionnaire and analyzed using structural equation modeling and PROCESS Macro. The findings indicate that AI propensity positively predicts both risk awareness and entrepreneurial alertness, while these cognitive factors significantly enhance sustainable entrepreneurial intention. Moreover, subjective norms strengthen the relationship between entrepreneurial alertness and intention, highlighting the importance of social context in shaping sustainability-oriented entrepreneurial behavior. By integrating cognitive and social drivers within a digital sustainability framework, this study contributes to the growing literature on AI-enabled sustainable entrepreneurship. The results offer practical implications for universities and policymakers seeking to foster sustainability-driven entrepreneurial ecosystems through AI-focused education and awareness-building initiatives. This study investigates how artificial intelligence propensity influences entrepreneurial alertness and sustainable entrepreneurial intentions among university students, while examining the mediating role of risk awareness and the moderating role of subjective norms. Full article

The rapid growth of electric vehicles (EVs) is reshaping transport systems and accelerating the sustainable digital transformation of smart mobility. EV battery-swapping, delivered through platform-based, data-driven service networks, offers a low-carbon alternative to conventional refueling and plug-in charging by shortening replenishment time and enabling centralized battery management. However, the behavioral mechanisms driving user adoption of this digitally enabled infrastructure remain insufficiently understood. This study develops a socio-technical system (STS) model in which social and technical drivers influence users’ intention to adopt EV battery-swapping services via the dual mediation of perceived trust and perceived risk. Using a three-stage mixed-methods design that combines a PRISMA-based literature review, expert interviews with user-journey mapping, and a large-scale user survey, the study identifies six social and technical antecedents of EV battery-swapping adoption. Based on 565 valid responses from EV users in the Beijing–Tianjin–Hebei region, partial least squares structural equation modeling and multi-group analysis are employed to test the proposed framework. The results show that all six antecedents significantly affect perceived trust and perceived risk, which in turn mediate their impacts on adoption intention, with notable heterogeneity across income and usage-frequency groups. The findings provide a mechanism-based extension of STS theory for digitally mediated battery-swapping infrastructure by showing how socio-technical conditions shape adoption via trust and risk, and they offer actionable implications for operators and policymakers to build secure, user-centered swapping services within intelligent transport systems. Full article

The main objective of this study is to automatically detect real-time snow-related road surface conditions using imagery captured from existing roadside webcams along interstate freeways. Blowing snow is considered one of the most hazardous roadway weather phenomena because it significantly reduces driver visibility and adversely affects vehicle operation. A comprehensive image preprocessing and reduction process was conducted to construct two reference datasets. The first dataset consisted of two categories (blowing snow and no blowing snow), while the second dataset included five surface condition categories: blowing snow, dry, slushy, snow covered, and snow patched. Eight pre-trained convolutional neural networks (CNNs), including AlexNet, SqueezeNet, ShuffleNet, ResNet18, GoogleNet, ResNet50, MobileNet-V3, and EfficientNet-B0, were evaluated for roadway surface condition classification. For Dataset 1, ResNet50 achieved the highest detection accuracy of 97.88%, while AlexNet demonstrated competitive performance with 97.56% accuracy and significantly shorter training time. Among the lightweight architectures, MobileNet-V3 achieved 95.56% accuracy, demonstrating strong computational efficiency. EfficientNet-B0 achieved 93.56% accuracy while maintaining reduced model complexity. For Dataset 2, ResNet18 achieved the highest multi-class detection accuracy of 96.10%, while AlexNet required the shortest training time among the evaluated models. A comparative analysis between deep CNN models and traditional machine learning approaches showed that deep CNNs significantly outperform feature-based methods in detecting blowing snow conditions. The proposed framework provides an automated, accurate, and scalable solution for roadway surface condition monitoring and supports real-time applications in intelligent transportation systems. Full article

Retaining the green workforce, employees driving sustainability and environmental innovation, is essential for organizational resilience and long-term environmental goals. While prior Green HRM research has primarily relied on survey-based methodologies and theoretical frameworks to examine retention factors, these approaches lack predictive capability and fail to provide actionable, employee-specific insights. This study advances beyond descriptive and correlational analyses by employing explainable artificial intelligence (XAI) to develop a transparent, data-driven framework for identifying attrition drivers and quantitatively evaluating retention strategies. Unlike existing studies that rely on self-reported perceptions, our approach leverages objective HR data and machine learning to predict individual-level attrition risk with calibrated probabilities. Leveraging the IBM HR Analytics dataset as a proxy for sustainability-focused roles, we construct an interpretable logistic regression model with strong predictive performance and isotonic regression calibration. Global and local interpretability techniques, including SHAP, LIME, and permutation importance, show that non-monetary factors, such as excessive overtime, frequent business travel, and limited promotion opportunities, have a greater impact on turnover risk than salary levels. These findings align with Green Human Management (Green HRM) principles, which emphasize work–life balance and employee well-being. Crucially, our policy simulation framework, absent from prior Green HRM studies, demonstrates that eliminating overtime could reduce predicted attrition probability by 17.35% for affected employees, potentially retaining 31 staff members, substantially outperforming modest salary adjustments. This work expands the value of predictive AI into HR analytics by consolidating HR analytics with Green HRM through a novel methodology that bridges the gap between prediction and actionable intervention. It represents the first systematic integration of XAI-based predictive modeling with counterfactual policy simulation in environmentally conscious sustainable organizations. Full article

Precise forecasting and physical elucidation of seepage behavior are crucial for maintaining the operational safety of concrete dams. Nonetheless, current monitoring methodologies frequently fail to adequately encompass nonlinear temporal relationships in seepage processes and exhibit a deficiency in straightforward interpretability. This paper provides an explainable monitoring approach that combines an alpha-evolution Bidirectional Gated Recurrent Unit (AE-BiGRU) with Shapley Additive Explanations (SHAP)-based interpretability analysis to solve these shortcomings. An AE-BiGRU prediction model is first developed, in which the BiGRU architecture exploits bidirectional temporal dependencies to enhance prediction accuracy and robustness. The alpha-evolution algorithm is then employed to optimize key hyperparameters of the neural network, thereby further improving model performance. Subsequently, SHAP interpretability analysis is applied to quantify the contribution of individual input variables and to elucidate the physical drivers of seepage variation. Validation utilizing long-term seepage monitoring data from a roller-compacted concrete (RCC) gravity dam indicates that the proposed AE-BiGRU model substantially surpasses benchmark models, including LSTM and traditional GRU variations. Furthermore, SHAP interpretability analysis reveals the predominant influences of reservoir water level fluctuations and cumulative temporal factors on seepage evolution patterns. The suggested approach attains high-precision seepage prediction while ensuring physically meaningful interpretability, thus providing a dependable foundation for safety evaluation and intelligent monitoring of concrete dams. Full article

Vertical farming requires precise environmental control, yet long-term multivariable analyses linking environmental dynamics and crop growth remain limited. This study analyzes a two-year operational dataset from a commercial vertical farm in South Korea to evaluate the suitability of advanced artificial intelligence models for harvest yield prediction. Conventional machine learning models and recent deep learning architectures were systematically benchmarked under identical conditions. Among them, the patch-based Transformer model achieved the highest predictive accuracy (R² = 0.942; RMSE = 5.81 g per plant). The variable-importance analysis revealed that daily light integral and CO₂ concentration were the dominant drivers of harvest yield variability, jointly accounting for more than 76% of total contribution. These findings demonstrate the effectiveness of Transformer-based architectures for long-term multivariate time series modeling and provide actionable insights for the data-driven optimization of vertical farming systems. Full article

Precision oncology has been evolving rapidly, with increasing emphasis on early detection and personalized diagnostic approaches that translate into tailored treatment algorithms. The integration of molecular markers, quantitative imaging approaches and artificial intelligence (AI) in the diagnostic workflow of cutaneous squamous cell carcinoma (cSCC) has increased accuracy and has the potential to improve early detection rates in these cancers. Sun exposure is the primary etiologic factor in the development of cSCC. The primary objective of this review is to evaluate the current state and future directions of modalities and practices in diagnostic techniques for cSCC. Specifically, this review summarizes the key genetic alterations and potential molecular targets in cSCC. High-risk genetic mutations and pathways implicated in the pathogenesis of cSCC include p53, NOTCH, RAS/MAPK, cell-cycle, and adhesion pathways. This review further explores current and emerging modalities in optical imaging techniques and molecular-based diagnostic modalities in cSCC. Further, we discuss the role of radiomics and AI in the diagnostic work-up of cSCC. These techniques have the potential to enable more accurate risk models that refine conventional histopathology and guide personalized interventions. However, there are limitations to the clinical application of several of these modalities, with cost being an important driver. These challenges have been discussed in detail within this review. Nevertheless, ongoing research is focused on improving the workflow and initiating a shift in clinical practice with application of precision diagnostics as a standard of care. Full article

This study investigates the impact of urban meteorological factors on road crash severity in Dhaka, Bangladesh. Using police crash data, and meteorological data from NASA POWER database for years 2011–2022, a generalized ordered logit model was used to analyze crash severity, and interpreted using odds ratio, log odds ratio, predicted probabilities and marginal effects. The results show that land surface temperature (LST), relative humidity, precipitation, surface pressure, and wind speed have significant association with crash severity. Relative humidity, surface pressure and LST exhibited positive relation with higher severity levels of crashes, whereas precipitation had a negative relation. We recommend three actions to lessen the severity of crashes during inclement weather based on the findings: (i) weather-responsive transport safety policies, which incorporate real-time weather data into intelligent transport systems; (ii) law enforcement-oriented policy implications, which include using automated speed cameras and red-light violation cameras to improve compliance consistency and updating driver training courses to include modules on risk perception across various environmental conditions; and (iii) infrastructure and vehicle-related policy implications, which include designing road geometries and surface conditions to prevent the effects of adverse weather conditions and utilizing safety equipment, such as electronic stability control and anti-lock braking systems. Full article

Against the backdrop of China’s integrated rural revitalization and digitalization strategies, advancing the digital transformation of rural emergency management has become crucial for enhancing grassroots governance capabilities. This study aims to systematically examine the underlying mechanisms through which digital technologies empower rural emergency management. By developing an analytical framework that integrates digital infrastructure, collaborative governance networks, emergency response capacity, and comprehensive rural resilience, and applying a multi-criteria decision-making model, we identify the causal structures and driving pathways among key factors. The findings indicate that residents’ safety resilience, the level of digital equipment in rescue teams, and industrial recovery capacity serve as core drivers within the system. Meanwhile, the intelligent dispatch capability of emergency supplies acts as a central hub linking technological application with operational effectiveness. Pathway analysis further reveals a progressive empowerment logic described as “strengthening foundational resilience, enhancing coordinated dispatch, improving industrial recovery.” This study not only deepens the understanding of the complex process of digital empowerment but, more importantly, offers policymakers a clear action plan: in resource allocation and capacity building, priority should be given to synergistically advancing the above key drivers and hub elements to achieve systemic improvement in the effectiveness and resilience of rural emergency management. Full article

According to in-depth research on the perception ability of dangerous omens of excellent drivers, references can be provided for the development of brain-like intelligence and its transplantation, as well as applications in the field of autonomous driving, which will improve the active safety and intelligence level of vehicles. Previous studies have shown that there is indeed a dangerous omen before an accident occurs. However, current studies are still unclear about the bio-psychophysiological characteristics exhibited by drivers with high levels of sensory agility when they anticipate potential warning signs, and there is no method for screening such drivers who can perceive dangerous omens proposed by any research. To address the above issues, this paper conducts in-depth research. Firstly, through designing dangerous scenarios and conducting hazard perception tests, we collect physiological, psychological, and physical data, such as drivers’ bioelectrical signals (electroencephalogram and electrocardiogram) and eye movements. Secondly, through playing back experimental videos, actively questioning drivers, and analyzing local changes in their electroencephalogram data, the driver’s ability to identify a dangerous omen and the moment of perception are determined. Thirdly, based on techniques such as the Kolmogorov–Smirnov test and the Mann–Whitney U test, the differences in bioelectrical and eye movement characteristics between drivers who can perceive a dangerous omen and others can be further revealed. Finally, the driver’s bioelectrical and eye movement characteristics are used as latent variables, and their corresponding data are utilized as observation indicators. We construct a structural equation model for screening drivers capable of perceiving a dangerous omen and conduct calibration and validation. This study provides inspirational ideas for empowering vehicles to identify potential hazards, advancing end-to-end and other higher-level autonomous driving technologies, and further enhancing road traffic safety. Full article

Road target detection is a crucial aspect of current research in automotive advanced driver assistance systems and intelligent transportation systems, where accuracy, speed, and lightweight design are key considerations. Compared to various sensors employed in driving assistance systems, millimeter-wave radar offers advantages such as all-weather operation, low hardware cost, strong penetration capability, and the ability to extract rich spatial information about targets. This paper tackles the challenges posed by the characteristics of Range-Angle map data from 77 GHz Frequency-Modulated Continuous Wave radar—namely, non-visible light imagery, abstract representation, rich fine details, and overlapping features. To this end, this paper proposes MMPFNet, a lightweight model based on the hypergraph mechanism with attention enhancement, as an extension of YOLOv13. First, an M-DSC3k2 module is proposed based on the hypergraph mechanism to enhance attention toward small targets. Second, a detection head with a double-bottleneck inverted MBConv-block structure is designed to improve the model’s accuracy and generalization capability. Third, a lightweight PPLConv module is customized to transform the backbone network, enhancing the model’s lightweight design while slightly reducing its accuracy. Considering the differences from traditional visible light datasets, the Focus Expansion-IoU loss function is introduced into the model to focus attention on different regression samples. The MMPFNet model achieves significant improvements in detecting common road targets such as pedestrians, bicycles, cars, and trucks on the Frequency-Modulated Continuous Wave radar Range-Angle dataset compared to the baseline YOLOv13n model: mAP50-95 increases by 16%, precision improves by 6%, and recall rises by 8.7%. MMPFNet is also evaluated on other non-visible light datasets such as CRUW-ONRD and soundprint datasets. Compared to commonly used detection models like FCOS and RetinaNet, MMPFNet achieves significant performance gains, attaining state-of-the-art results. Full article

Interchange merging areas are critical safety hotspots in urban road networks, where complex vehicle interactions challenge traffic safety and efficiency. Improving safety performance at these locations is essential for developing sustainable, resilient, and intelligent urban transportation systems. To overcome the limitations of single-driver simulators, this study developed a multi-driver simulation platform based on Unity3D (Version 2022.3.1f1c1), enabling real-time interaction among multiple human drivers. High-resolution trajectory data were collected from 231 valid interaction events. An eight-direction relative position model was employed to classify behaviors into four patterns: longitudinal, lateral, front cut-in, and rear cut-in. Risk was quantified using time-exposed and time-integrated Anticipated Collision Time metrics, with events subsequently clustered into low (n = 138), medium (n = 67), and high-risk (n = 26) categories. An ordered logit regression model identified key risk factors. The results quantitatively demonstrate that interaction risk escalates significantly with abrupt speed changes (OR = 16.22) and late-stage occurrence of speed extremes (OR = 6.76) in the interacting vehicle, as well as large initial speed differences (OR = 2.45). Conversely, stable speed regulation and adaptive acceleration by the subject vehicle proved to be potent mitigating factors. These findings provide actionable insights for the development of intelligent collision warning systems and the sustainable design of interchange infrastructure. Full article

In the post-pandemic era, student mental health challenges have emerged as a critical issue in higher education. However, conventional assessment approaches often treat at-risk populations as a monolithic entity, thereby limiting intervention effectiveness. This study proposes a novel computational framework that integrates explainable artificial intelligence (XAI) with unsupervised learning to decode the latent heterogeneity of psychological risk mechanisms. We developed a “predict-explain-discover” pipeline leveraging TreeSHAP and Gaussian Mixture Models to identify distinct risk subtypes based on a 2556-dimensional feature space encompassing lexical, linguistic, and affective indicators. Our approach identified three theoretically-grounded subtypes: academically-driven (28.46%), socio-emotional (43.85%), and internal regulatory (27.69%) risks. Sensitivity analysis using top-20 core features further validated the structural stability of these mechanisms, proving that the subtypes are anchored in the model’s primary decision drivers rather than high-dimensional noise. The framework demonstrates how black-box classifiers can be transformed into diagnostic tools, bridging the gap between predictive accuracy and mechanistic understanding. Our findings align with the Research Domain Criteria (RDoC) and establish a foundation for precision interventions targeting specific risk drivers. This work advances computational mental health research through methodological innovations in mechanism-based subtyping and practical strategies for personalized student support. Full article