Search Results (1,713)

The ‘black box’ nature of machine learning (ML) approaches makes it challenging to understand how most artificial intelligence (AI) models make decisions. Explainable AI (XAI) aims to provide analytical techniques to understand the behavior of ML models. XAI utilizes counterfactual explanations that indicate how variations in input features lead to different outputs. However, existing methods must also highlight the importance of features to provide more actionable explanations that would aid in the identification of key drivers behind model decisions—and, hence, more reliable interpretations—ensuring better accuracy. The method we propose utilizes feature weights obtained through adaptive feature weight genetic explanation (AFWGE) with the Pearson correlation coefficient (PCC) to determine the most crucial group of features. The proposed method was tested on four real datasets with nine different classifiers for evaluation against a nonweighted counterfactual explanation method (CERTIFAI) and the original feature values’ correlation. The results show significant enhancements in accuracy, precision, recall, and F1 score for most datasets and classifiers; this indicates the superiority of the feature weights selected via AFWGE with the PCC over CERTIFAI and the original data values in determining the most important group of features. Focusing on important feature groups elaborates the behavior of AI models and enhances decision making, resulting in more reliable AI systems. Full article

This study introduces Fin-ALICE (Artificial Linguistic Intelligence Causal Econometrics), a framework designed to forecast financial time series by integrating multiple analytical approaches including co-occurrence networks, supply chain analysis, and emotional sentiment analysis to provide a comprehensive understanding of market dynamics. In our co-occurrence analysis, we focus on companies that share the same emotion on the same day, using a much shorter horizon than our previous study of one month. This approach allows us to uncover short-term, emotion-driven correlations that traditional models might overlook. By analyzing these co-occurrence networks, Fin-ALICE identifies hidden connections between companies, sectors, and events. Supply chain analysis within Fin-ALICE will evaluate significant events in commodity-producing countries that impact their ability to supply key resources. This analysis captures the ripple effects of disruptions across industries and regions, offering a more nuanced prediction of market movements. Emotional sentiment analysis, powered by the Fin-Emotion library developed in our prior research, quantifies the emotional undertones in financial news through metrics like “emotion magnitude” and “emotion interaction”. These insights, when integrated with Temporal Convolutional Networks (TCNs), significantly enhance the accuracy of financial forecasts by capturing the emotional drivers of market sentiment. Key contributions of Fin-ALICE include its ability to perform month-by-month company correlation analysis, capturing short-term market fluctuations and seasonal patterns. We compare the performance of TCNs against advanced models such as LLMs and LSTMs, demonstrating that the Fin-ALICE model outperforms these models, particularly in sectors where emotional sentiment and supply chain dynamics are critical. Fin-ALICE provides decision-makers with predictive insights and a deeper understanding of the underlying emotional and supply chain factors that drive market behaviors. Full article

Distracted driving remains a major concern on highways, with it contributing to severe and fatal crashes, particularly on high-speed routes, prompting numerous states to implement targeted initiatives aimed at combating traffic violations that significantly contribute to fatal and injury-inducing crashes. Among these initiatives is the highway safety corridor program, a collaborative endeavor between the state departments of transportation and law enforcement agencies. Highway safety corridors employ a combination of engineering interventions and heightened law enforcement presence to address risky driver behavior and mitigate the occurrence of crashes. Despite the longstanding existence of safety corridors, research on their effectiveness remains relatively limited, with existing studies indicating only moderate success rates. This study is dedicated to evaluating the effectiveness of ten highway safety corridors in Ohio, where the state recently launched its inaugural highway safety corridor program targeting distracted driving. Utilizing 2023 crash data, this Empirical Bayes’ before-and-after study seeks to gauge the impact of these safety corridors on enhancing roadway transportation safety. Upon assessing all crash types within Ohio’s distracted driving safety corridors that provided sufficient data for a before–after study, it was determined that the adoption of safety corridors generally led to a reduction in crashes ranging from 2% to 49%. The significance and magnitude of crash reduction may vary if specific crash types or severity levels are considered. Full article

Background and Objectives: Invasive breast cancer (BC) was traditionally investigated visually, and no technique could identify the key molecular drivers of patient survival. However, essential molecular drivers of invasive BC have now been discovered using innovative genomic, transcriptomic, and proteomic methodologies. Nevertheless, few evaluations of the prognostic factors of BC in Saudi Arabia have been performed. Evaluating the biomarkers associated with the development of early-stage BC could help determine the risk of metastasis and guide treatment decisions. In a previous study, using large BC cohorts and artificial neural network techniques, DNA replication and sister chromatid cohesion 1 (DSCC1) was found to be one of the principal genes in invasive BC samples. To date, no studies have addressed the prognostic significance of DSCC1 in invasive BC and its association with aggressive tumor behavior. This research aimed to address this gap. Materials and Methods: The association of clinicopathological features and patient outcomes with DSCC1 expression at the mRNA level was assessed using the Molecular Taxonomy Breast Cancer International Consortium (METABRIC; n = 1980) and The Cancer Genome Atlas (TCGA; n = 854) cohorts. DSCC1 was also evaluated at the protein level using immunohistochemistry on samples from invasive BC patients (n = 100) presenting to King Abdul Aziz Specialist Hospital in Saudi Arabia. The association of clinicopathological parameters (including patient age, tumor grade, tumor size, and patient outcome) with protein level was also evaluated. Results: In both METABRIC and TCGA cohorts, high expression of DSCC1 was significantly associated with high histological grade, large tumor size, lymphovascular invasion positivity, and hormone receptor negativity (all p < 0.001). A high DSCC1 mRNA level was associated with poor outcomes (p < 0.001 for METABRIC, p = 0.23 for TCGA). At the protein level, high DSCC1 expression was associated with high histological grade (p = 0.001), lymph node presence (p = 0.008), hormone receptor negativity (p = 0.005), high Ki67 expression (p = 0.036), and shorter survival (p = 0.008). Conclusions: This study confirmed the prognostic significance of DSCC1 in invasive BC patients. DSCC1 could be a therapeutic target in BC cases with poor outcomes. Full article

Climate change is an irreversible crisis that urgently calls for social transformation to protect human livelihood and environmental stability. Establishing awareness, building environmental literacy, and citizens’ mobilization are the steps toward sustainable change in giving a legacy of hope to future generations. This research explores major psychological and social drivers of pro-environmental behavior, considering the influence of HEXACO personality traits, climate anxiety (CCW), and social media engagement (SMI) on sustainable consumption (SC) and climate action intentions (CCI). Our findings revealed th eco-guilt (EGQ) and environmental empathy (EE) are immediate drivers for climate action, while long-term nurturance of eco-grief (ECOG) leads to engagement, supporting the notion that different emotions uniquely contribute to pro-environmental intentions. In terms of personality predictors, HEXACO’s traits of emotionality (E), honesty-humility (HH), and openness (O) are revealed to be significant, with emotionality also moderating the relationship between eco-grief and climate change action. The results reveal that connectedness to nature (CTN) and moderate levels of climate anxiety synergistically promote sustainable consumption intentions, while demographic factors such as gender, education levels, and exposure to social media moderate these intentions. Females also show a higher level of climate action intention in response to eco-guilt and eco-grief, while individuals with higher levels of education are more responsive to climate-related social media content, increasing their sustainable consumption behaviors. In exploring such interactions, this study aims to add to the understanding of what drives people toward valued environmental behaviors and, in turn, to inform effective climate advocacy, education, and personality-driven strategies to promote environmental engagement. Full article

Nowadays, driving accidents are considered one of the most crucial challenges for governments and communities that affect transportation systems and peoples lives. Unfortunately, there are many causes behind the accidents; however, drowsiness is one of the main factors that leads to a significant number of injuries and deaths. In order to reduce its effect, researchers and communities have proposed many techniques for detecting drowsiness situations and alerting the driver before an accident occurs. Mostly, the proposed solutions are visually-based, where a camera is positioned in front of the driver to detect their facial behavior and then determine their situation, e.g., drowsy or awake. However, most of the proposed solutions make a trade-off between detection accuracy and speed. In this paper, we propose a novel Visual-based Alerting System for Detecting Drowsy Drivers (VAS-3D) that ensures an optimal trade-off between the accuracy and speed metrics. Mainly, VAS-3D consists of two stages: detection and classification. In the detection stage, we use pre-trained Haar cascade models to detect the face and eyes of the driver. Once the driver’s eyes are detected, the classification stage uses several pre-trained Convolutional Neural Network (CNN) models to classify the driver’s eyes as either open or closed, and consequently their corresponding situation, either awake or drowsy. Subsequently, we tested and compared the performance of several CNN models, such as InceptionV3, MobileNetV2, NASNetMobile, and ResNet50V2. We demonstrated the performance of VAS-3D through simulations on real drowsiness datasets and experiments on real world scenarios based on real video streaming. The obtained results show that VAS-3D can enhance the accuracy detection of drowsy drivers by at least $7.5\%$ (the best accuracy reached was $95.5\%$) and the detection speed by up to $57\%$ (average of $0.25$ ms per frame) compared to other existing models. Full article

The COVID-19 pandemic has had an unprecedented impact on public travel and has significantly altered people’s travel behavior. By comparing the travel behaviors of ride-hailing passengers before and after the pandemic (i.e., the pre-pandemic era and the post-pandemic era), it is possible to effectively identify the changes in their travel patterns and thus deeply understand the changes in individual travel habits in the post-pandemic era. Using data collected in Nanjing, China, this paper develops two ordered logit models to examine the impact mechanism of multi-dimensional influential factors on the trip frequency of ride-hailing users before and after the pandemic. The results reveal the following: (1) Before the pandemic, the increase in waiting time promoted the usage frequency of ride-hailing users, while in the post-pandemic era, the increase in waiting time reduces the travel frequency of ride-hailing users. (2) Before the pandemic, the increase in prices led to a decrease in ride-hailing users’ usage frequency, while it presents a push effect in the post-pandemic era. (3) In the post-pandemic era, ride-hailing users are more concerned about personal safety, avoiding conversing with the driver and touching objects in the car. Finally, some strategies, such as increasing awareness of personal information protection and security, optimizing waiting times, and improving the hygiene standards of ride-hailing, are proposed to assist transportation network companies in operating and restoring ride-hailing services in the post-pandemic era. Full article

Transport Demand Management (TDM) is crucial in shaping travel behavior and enhancing urban mobility by promoting sustainable transport options. This study represents a comprehensive analysis of employee commuting behavior across seventy-seven cities in Italy, with a focus on Rome as a case study. It investigates some requirements of the workplace travel plan as a TDM strategy for promoting sustainable commuting. An online survey conducted in June 2022 yielded 2314 valid responses, including 1320 from private car drivers. K-means clustering was used to identify distinct behavioral patterns among commuters, revealing four clusters based on demographic factors and transport preferences, such as age, gender, family circumstances, vehicle ownership, willingness to walk, ride bicycles, or e-scooters, and reasons for mode choice. This study analyzed Rome’s public transport network, land use, and private car use. Results underscore the need for tailored transport policies that enhance inclusivity and accessibility, especially for employees with family members who cannot commute independently. A spatial analysis of Rome reveals significant infrastructure deficiencies, such as complicated transfers and inaccessible stations, which discourage PT use. Future research should explore the impact of remote work and psychological factors and conduct in-depth subgroup analyses to inform inclusive transport policy development. Full article

As the global pursuit of sustainable agricultural practices continues, organic farming is gaining increasing attention. In Pu’er, one of China’s major tea-producing regions, the factors influencing tea farmers’ willingness to adopt organic agriculture have not yet been fully studied. This study integrates the diffusion of innovations theory and the theory of planned behavior, using field surveys to thoroughly analyze the key factors and reasons affecting tea farmers in Pu’er in adopting organic farming practices. The findings indicate that perceptions of the economic benefits of organic farming are the primary drivers of farmers’ willingness to adopt. Experience with organic agriculture training and positive views on environmental and health benefits also significantly enhance the willingness to adopt organic farming. Contrary to common assumptions, education level, age, and household income have minimal influence on adoption willingness. However, low-income families that rely on tea cultivation are more inclined to adopt organic farming. Policymakers should prioritize economic incentives, strengthen training support, and enhance the promotion of the benefits of organic agriculture, while simplifying certification processes and expanding market channels to facilitate the transition of tea farmers to organic agriculture. This study offers insights into the sustainable tea industry and organic farming promotion. Full article

High-quality, reproducible tip coatings are essential for minimizing faradaic currents in electrochemical scanning tunneling microscopy (EC-STM), especially during in situ and operando measurements. The variability inherent in manual coating methods, influenced by the operator’s skill and a lack of standardization, can lead to inconsistent results, increased research costs, and a greater workload. This study introduces an Automated Tip Coater (ATC) designed to automate and standardize the tip coating process. The ATC features a tip movement system using stepper motors, a rotation module with a DC motor, and a heating block based on a soldering iron. It is controlled by an Arduino development board, supported by motor drivers, and has a user-friendly interface with an OLED display and encoder. The ATC coating mechanism includes a redesigned plate with a reduced gap size and a milled tray to precisely control the amount of insulating material applied to the tip. A fast cyclic voltammetry test in a 0.1 M HClO₄ electrolyte demonstrated that over 75% of ATC-coated tips achieved excellent insulation with leakage currents below ±50 pA—and 30% below ±10 pA—suitable for highly sensitive experiments. Further measurements with EC-STM using the newly coated tips investigated the electrochemical behavior of highly oriented pyrolytic graphite (HOPG), revealing detailed atomic structures under dynamic electrochemical conditions. The ATC significantly enhances reproducibility, reduces dependency on operator skills, and lowers research costs while improving the accuracy and reliability of EC-STM measurements. Full article

At present, achieving efficient, sustainable, and safe transportation has led to increasing attention on driving behavior recognition and advancements in autonomous driving. Identifying diverse driving styles and corresponding types is crucial for providing targeted training and assistance to drivers, enhancing safety awareness, optimizing driving costs, and improving autonomous driving systems responses. However, current studies mainly focus on specific driving scenarios, such as free driving, car-following, and lane-changing, lacking a comprehensive and systematic framework to identify the diverse driving styles. This study proposes a novel, data-driven approach to driving-style recognition utilizing naturalistic driving data NGSIM. Specifically, the NGSIM dataset is employed to categorize car-following and lane-changing groups according to driving-state extraction conditions. Then, characteristic parameters that fully represent driving styles are optimized through correlation analysis and principal component analysis for dimensionality reduction. The K-means clustering algorithm is applied to categorize the car-following and lane-changing groups into three driving styles: conservative, moderate, and radical. Based on the clustering results, a comprehensive evaluation of the driving styles is conducted. Finally, a comparative evaluation of SVM, Random Forest, and KNN recognition indicates the superiority of the SVM algorithm and highlights the effectiveness of dimensionality reduction in optimizing characteristic parameters. The proposed method achieves over 97% accuracy in identifying car-following and lane-changing behaviors, confirming that the approach based on naturalistic driving data can effectively and intelligently recognize driving styles. Full article

The transport sector, and especially the increase in individual vehicle ownership, contribute significantly to air pollution. The transition to electric vehicles (EVs) is seen as a sustainable alternative to reduce emissions of polluting gases. However, in Brazil, the EV market has not yet reached a significant size. Given this scenario, this study aims to analyze the factors that influence the decision to buy EVs in Brazil, highlighting personal, psychological, economic, performance, and environmental variables and barriers. The aim is also to develop a model with guidelines that can help stakeholders. The quantitative stage of the study involved a survey of 514 respondents. The data were analyzed using statistical methods, including structural equation modeling (SEM), which allowed for a deeper investigation of the proposed hypotheses. The survey findings reveal that, in the Brazilian context, performance factors—such as autonomy, availability of recharging infrastructure, and maintenance—are the main drivers influencing EV purchase decisions. Environmental factors, including energy reuse, pollution reduction, and minimizing environmental impacts, have also gained significant importance. Economic factors are crucial, particularly concerning cost–benefit perceptions. The differences between Brazil and other regions highlight the importance of accounting for cultural and economic variations when analyzing consumer behavior towards EVs. Full article

Attentional deficits have tragic consequences on road safety. These deficits are not solely caused by distraction, since they can also arise from other mental impairments such as, most frequently, mental fatigue. Fatigue is among the most prevalent impairing conditions while driving, degrading drivers’ cognitive and physical abilities. This issue is particularly relevant for professional drivers, who spend most of their time behind the wheel. While scientific literature already documented the behavioral effects of driving fatigue, most studies have focused on drivers under sleep deprivation or anyhow at severe fatigue degrees, since it is difficult to recognize the onset of fatigue. The present study employed an EEG-driven approach to detect early signs of fatigue in professional drivers during a simulated task, with the aim of studying visual attention as fatigue begins to set in. Short-range and long-range professional drivers were recruited to take part in a 45-min-long simulated driving experiment. Questionnaires were used to validate the experimental protocol. A previously validated EEG index, the MDrow, was adopted as the benchmark measure for identifying the “fatigued” spans. Results of the eye-tracking analysis showed that, when fatigued, professional drivers tended to focus on non-informative portions of the driving environment. This paper presents evidence that an EEG-driven approach can be used to detect the onset of fatigue while driving and to study the related visual attention patterns. It was found that the onset of fatigue did not differentially impact drivers depending on their professional activity (short- vs. long-range delivery). Full article

On-demand ride-sharing services change our travel behavior, which threatens the survival of taxi services. Motivated by this, this paper examines the impact of on-demand ride-sharing services on taxi services and how to achieve the coexistence of two services from a service quality perspective. This paper analyzes the coexistence condition of two services considering the network effect. First, the profit target for taxi drivers is nonnegative. A Stackelberg model is built in which the taxi service is the leader and the on-demand ride-sharing service is the follower. Then, the reference dependency theory is introduced to modify the profit target of taxi drivers. And the new coexistence condition is compared with the benchmark status. The results find that the coexistence of the two services depends on the type of riders and the quality difference in both cases. When two services and riders are highly heterogenous, two services are more likely to coexist. Services with different qualities could better satisfy the diverse preferences of riders. Considering taxi profit without competition as the profit reference point, the requirement of service quality difference and the diversity of rider composition is increased. In terms of the network effect, the negative network effect is more beneficial to the coexistence of two services. Full article

It is increasingly common for simulation and AI tools to aid in the vehicle design process. The IPG CarMaker uses a multibody vehicle model and a learning algorithm for the virtual driver. The goal is to discover the behavior of the learning algorithm from the point of view of reliability and convergence. Simulations demonstrate that the lap time converges reliably. We also report that small changes in the vehicle parameters induce small changes in the simulated lap time, i.e., the lap time is a differentiable function of the vehicle parameters. Part 2 of this paper explains the aerodynamics and Drag Reduction System optimization. Full article