[Fatigue feature extraction and classification algorithm of forehead single-channel electroencephalography signals].

Aiming at the problem that the feature extraction ability of forehead single-channel electroencephalography (EEG) signals is insufficient, which leads to decreased fatigue detection accuracy, a fatigue feature extraction and classification algorithm based on supervised contrastive learning is proposed. Firstly, the raw signals are filtered by empirical modal decomposition to improve the signal-to-noise ratio. Secondly, considering the limitation of the one-dimensional signal in information expression, overlapping sampling is used to transform the signal into a two-dimensional structure, and simultaneously express the short-term and long-term changes of the signal. The feature extraction network is constructed by depthwise separable convolution to accelerate model operation. Finally, the model is globally optimized by combining the supervised contrastive loss and the mean square error loss. Experiments show that the average accuracy of the algorithm for classifying three fatigue states can reach 75.80%, which is greatly improved compared with other advanced algorithms, and the accuracy and feasibility of fatigue detection by single-channel EEG signals are significantly improved. The results provide strong support for the application of single-channel EEG signals, and also provide a new idea for fatigue detection research.

Engineering thioesterase as a driving force for novel itaconate production via its degradation scheme.

Incorporation of irreversible steps in pathway design enhances the overall thermodynamic favorability and often leads to better bioconversion yield given functional enzymes. Using this concept, here we constructed the first non-natural itaconate biosynthesis pathway driven by thioester hydrolysis. Itaconate is a commercially valuable platform chemical with wide applications in the synthetic polymer industry. Production of itaconate has long relied on the decarboxylation of TCA cycle intermediate cis-aconitate as the only biosynthetic route. Inspired by nature's design of itaconate detoxification, here we engineered a novel itaconate producing pathway orthogonal to native metabolism with no requirement of auxotrophic knock-out. The reversed degradation pathway initiates with pyruvate and acetyl-CoA condensation forming (S)-citramalyl-CoA, followed by its dehydration and isomerization into itaconyl-CoA then hydrolysis into itaconate. Phenylacetyl-CoA thioesterase (PaaI) from Escherichia coli was identified via screening to deliver the highest itaconate formation efficiency when coupled to the reversible activity of citramalate lyase and itaconyl-CoA hydratase. The preference of PaaI towards itaconyl-CoA hydrolysis over acetyl-CoA and (S)-citramalyl-CoA also minimized the inevitable precursor loss due to enzyme promiscuity. With acetate recycling, acetyl-CoA conservation, and condition optimization, we achieved a final itaconate titer of 1 g/L using the thioesterase driven pathway, which is a significant improvement compared to the original degradation pathway based on CoA transferase. This study illustrates the significance of thermodynamic favorability as a design principle in pathway engineering.

Characteristics and driving forces of the soil microbial community during 35 years of natural restoration in abandoned areas of the Daxin manganese mine, China.

The restoration of mining wastelands, particularly in karst regions contaminated by heavy metals, is an environmental challenge in need of urgent attention. Soil microbes play a vital role in nutrient cycling and ecosystem recovery, yet the long-term evolution of soil microbial communities in such settings remains poorly understood. This study explored the dynamics and influencing factors of soil microbial communities during 35 years of natural restoration in abandoned manganese (Mn) mine areas in Guangxi Province, China. The results revealed that the concentrations of Mn, Cd, Zn, and Cu were significantly (p < 0.05) reduced by 80.4-85.3%, 55.3-70.0%, 21.0-38.1%, and 29.4-49.4%, respectively, in the mid-late restoration periods (R19 and R35) compared with R1. The α diversities of the bacterial and fungal communities significantly increased in the middle-late restoration periods (R19 and R35), indicating increased microbial diversity as restoration progressed. The bacterial community structure exhibited more pronounced changes than did the fungal community structure, with significant shifts observed in dominant phyla such as Proteobacteria, Actinobacteria, Acidobacteriota, and Ascomycota. Notably, the relative abundances of Rhizobiales, Burkholderiales, and Hypocreales increased gradually with succession. Co-occurrence network analysis revealed that bacterial interactions became stronger over time, whereas interactions between bacteria and fungi weakened. Mantel tests and partial least squares path modeling (PLS‒PM) identified soil pH, heavy metals (Mn, Cd, Zn, and Cu), and nutrients (SOM and TN) as key drivers shaping the microbial community composition. These factors were more strongly correlated with bacterial communities than with fungal communities, underscoring the different responses of microbial groups to environmental changes during natural restoration. These findings enhance our understanding of the ecological processes governing microbial community succession in heavy metal-contaminated soils undergoing natural restoration.

A comprehensive approach to evaluate human-machine conflicts in shared steering systems.

The shared control authority between drivers and the steering system may lead to human-machine conflicts, threatening both traffic safety and driving experience of collaborative driving systems. Previous evaluation methods relied on subjective judgment and had a singular set of evaluation criteria, making it challenging to obtain a comprehensive and objective assessment. Therefore, we propose a two-phase novel method that integrates eye-tracking data, electromyography signals and vehicle dynamic features to evaluate human-machine conflicts. Firstly, through driving simulation experiments, the correlations between subjective driving experience and objective indices are analyzed. Strongly correlated indices are screened as the effective criteria. In the second phase, the indices are integrated through sparse principal component analysis (SPCA) to formulate a comprehensive objective measure. Subjective driving experience collected from post-drive questionnaires was applied to examine its effectiveness. The results show that the error between the two sets of data is less than 7%, proving the effectives of the proposed method. This study provides a low-cost, high-efficiency method for evaluating human-machine conflicts, which contributes to the development of safer and more harmonious human-machine collaborative driving.

Development and application of a comprehensive evaluation index system for groundwater quality evolution patterns.

In recent years, driven by rapid socio-economic development and intensified human activities, the groundwater quality has exhibited a concerning trend of degradation. The challenge lies in integrating the impacts of both natural and anthropogenic factors to establish a scientific evaluation framework for the evolution of groundwater quality. This study adopts the model of driving forces - pressures - state - impacts - responses (DPSIR) proposed by the European Environment Agency, in conjunction with the Analytic Hierarchy Process (AHP) and Information Entropy Theory (IET), and the Water Quality Index (WQI) evaluation methods, to construct an evaluation index system for groundwater quality evolution that encompasses driving forces, state, and response systems. Initially, twelve indicators relevant to groundwater quality are quantified by screening across three systems, and a functional relationship between the categorization and scoring of each indicator is established. Subsequently, the weights for each system and indicator are obtained through the AHP, and the objective weights of the indicators are determined using the IET. The scores of each indicator are then comprehensively calculated. Finally, based on the defined types of groundwater quality evolution patterns, an integrated assessment of the evolution of groundwater quality over various time periods is conducted. Taking the Shijiazhuang region as a case study and analyzing the hydrochemical data of groundwater from 1985 to 2015, the results indicate a shift in the groundwater quality evolution pattern from one dominated by natural factors to one primarily influenced by human activities (The comprehensive score of the evaluation index system has increased from 1.84 to 3.25). Among these, the application of fertilizers emerges as the most important driving factors affecting groundwater quality. Particularly, nitrate and total hardness (TH) have emerged as the most salient indicators of quality degradation, with a significant escalation in their composite scores. At the outset, nitrate registered a score of 0.408, while TH scored 0.326; yet, these values have sharply ascended to 0.716 and 0.467, respectively, by the advanced stage. The study concludes with a discussion on the accuracy, strengths, limitations, and applicability of the evaluation index system. The establishment of this evaluation framework provides a scientific basis for the management and protection of groundwater resources and serves as a reference for identifying groundwater quality evolution patterns in other regions.

Elevated blood-ethanol concentration promotes reduction of aliphatic ketones (acetone and ethyl methyl ketone) to secondary alcohols along with slower oxidation to aliphatic diols.

Many people convicted for drunken driving suffer from an alcohol use disorder and some traffic offenders consume denatured alcohol for intoxication purposes. Venous blood samples from people arrested for driving under the influence of alcohol were analyzed in triplicate by headspace gas chromatography (HS-GC) using three different stationary phases. The gas chromatograms from this analysis sometimes showed peaks with retention times corresponding to acetone, ethyl methyl ketone (2-butanone), 2-propanol, and 2-butanol in addition to ethanol and the internal standard (1-propanol). Further investigations showed that these drink-driving suspects had consumed an industrial alcohol (T-Red) for intoxication purposes, which contained > 90% w/v ethanol, acetone (~ 2% w/v), 2-butanone (~ 5% w/v) as well as Bitrex to impart a bitter taste. In n = 75 blood samples from drinkers of T-Red, median concentrations of ethanol, acetone, 2-butanone, 2-propanol and 2-butanol were 2050 mg/L (2.05 g/L), 97 mg/L, 48 mg/L, 26 mg/L and 20 mg/L, respectively. In a separate GC analysis, 2,3-butanediol (median concentration 87 mg/L) was identified in blood samples containing 2-butanone. When the redox state of the liver is shifted to a more reduced potential (excess NADH), which occurs during metabolism of ethanol, this favors the reduction of low molecular ketones into secondary alcohols via the alcohol dehydrogenase (ADH) pathway. Routine toxicological analysis of blood samples from apprehended drivers gave the opportunity to study metabolism of acetone and 2-butanone without having to administer these substances to human volunteers.

Cognitive load during driving: EEG microstate metrics are sensitive to task difficulty and predict safety outcomes.

Engaging in phone conversations or other cognitively challenging tasks while driving detrimentally impacts cognitive functions and has been associated with increased risk of accidents. Existing EEG methods have been shown to differentiate between load and no load, but not between different levels of cognitive load. Furthermore, it has not been investigated whether EEG measurements of load can be used to predict safety outcomes in critical events. EEG microstates analysis, categorizing EEG signals into a concise set of prototypical functional states, has been used in other task contexts with good results, but has not been applied in the driving context. Here, this gap is addressed by means of a driving simulation experiment. Three phone use conditions (no phone use, hands-free, and handheld), combined with two task difficulty levels (single- or double-digit addition and subtraction), were tested before and during a rear-end collision conflict. Both conventional EEG spectral power and EEG microstates were analyzed. The results showed that different levels of cognitive load influenced EEG microstates differently, while EEG spectral power remained unaffected. A distinct EEG pattern emerged when drivers engaged in phone tasks while driving, characterized by a simultaneous increase and decrease in two of the EEG microstates, suggesting a heightened focus on auditory information, potentially at a cost to attention reorientation ability. The increase and decrease in these two microstates follow a monotonic sequence from baseline to hands-free simple, hands-free complex, handheld simple, and finally handheld complex, showing sensitivity to task difficulty. This pattern was found both before and after the lead vehicle braked. Furthermore, EEG microstates prior to the lead vehicle braking improved predictions of safety outcomes in terms of minimum time headway after the lead vehicle braked, clearly suggesting that these microstates measure brain states which are indicative of impaired driving. Additionally, EEG microstates are more predictive of safety outcomes than task difficulty, highlighting individual differences in task effects. These findings enhance our understanding of the neural dynamics involved in distracted driving and can be used in methods for evaluating the cognitive load induced by in-vehicle systems.

What would affect drivers' stop-and-go decisions at yellow dilemma zones? A driving simulator study in Hong Kong.

Yellow dilemma, at which a driver can neither stop nor go safely after the onset of yellow signals, is one of the major crash contributory factors at the signal junctions. Studies have visited the yellow dilemma problem using observation surveys. Factors including road environment, traffic conditions, and driver characteristics that affect the driver behaviours are revealed. However, it is rare that the joint effects of situational and attitudinal factors on the driver behaviours at the yellow dilemma zone are considered. In this study, drivers' propensity to stop after the onset of yellow signals is examined using the driving simulator approach. For instances, the association between driver propensity, socio-demographics, safety perception, traffic signals, and traffic and weather conditions are measured using a binary logit model. Additionally, variations in the effect of influencing factors on driver behaviours are accommodated by adding the interaction terms for driver characteristics, traffic flow characteristics, traffic signals, and weather conditions. Results indicate that weather conditions, traffic volume, position of yellow dilemma in the sequence, driver age and safety perception significantly affect the drivers' propensity to stop after the onset of yellow signals. Furthermore, there are remarkable interactions for the effects of driver gender and location of yellow dilemma.

Condensable and filterable particulate matter emitted from typical diesel vehicles in steady and transient driving conditions.

Condensable particulate matter (CPM) and filterable particulate matter (FPM) emitted from industrial sources have been well studied, but their emissions from vehicles have not yet been covered. This study explores the emission characteristics of CPM and FPM from typical diesel vehicles under various driving conditions. The emission factors (EFs) of CPMs under driving conditions were 5.4-10.4 times higher than those of FPMs, while CPMs EFs under transient driving conditions were about 2.5 times higher than those under steady driving conditions. CPM and FPM are mainly composed of organic matter accounting for 53.3 %-92.9 %, while the intermediate and semi-volatile organic compounds dominate the organic matter accounting for 86.3 %-98.6 %. Similar to industrial sources, alkanes are the predominant organic species emitted by diesel vehicles, comprising 42.0 %-64.0 % of the detected organic components. Inorganic CPM is primarily composed of NH4+ , representing 84.9 %-87.6 % of the total, in contrast to industrial sources where SO42- and Cl- dominate. Interestingly, the air pollution control devices installed on diesel vehicles under steady driving conditions perform better in removing organic CPM and producing higher inorganic CPM emissions than those under transient driving conditions. These findings will enhance the comprehensive understanding of particulate matter emitted from diesel vehicles and provide a scientific foundation for the development of related control technologies.

Ventilatory pressure parameters impact the association between acute gastrointestinal injury and all-cause mortality in mechanically ventilated patients.

Acute gastrointestinal injury (AGI) is common in mechanically ventilated (MV) patients, but the potential association between ventilatory pressure parameters and AGI grade and their impact on mortality remains unclear. This study aimed to explore the association between ventilatory pressure parameters and AGI grade, and their interaction on all-cause mortality in MV patients. This study was a secondary analysis of a multicenter, prospective, observational study that enrolled adult patients with an expected duration of mechanical ventilation ≥ 48 h from 14 general intensive care units in Zhejiang Province between March and August 2014. The AGI grade was assessed daily on the basis of gastrointestinal symptoms, intra-abdominal pressures, and feeding intolerance in the first week of admission to the ICU. This study included 331 patients (69.2% men; mean age, 64.6 ± 18.9 years). Multivariate regression analysis showed that plateau pressure (Pplat) (OR 1.044, 95% CI 1.009-1.081, P = 0.013), serum creatinine (OR 1.003, 95% CI 1.001-1.006, P = 0.042) and APACHE II score (OR 1.035, 95% CI 1.021-1.072, P = 0.045) were independently associated with global AGI grade III/IV within 7 days of ICU admission. Moreover, global AGI grade (HR 2.228, 95% CI 1.561-3.182, P < 0.001), serum creatinine (HR 1.002, 95% CI 1.001-1.003, P = 0.012) and APACHE II score (HR 1.039, 95% CI 1.015-1.063, P = 0.001) were independently associated with 60-day mortality. In addition, there were significant (Pint ≤ 0.028) interactions of Pplat and DP with AGI grade in relation to 60-days mortality, whereas no interaction (Pint = 0.061) between PEEP and AGI grade on 60-days mortality was observed. In the presence of Pplat ≥ 19 cmH2O, the patients with AGI grade III/IV had 60-day mortality rate of 72.2%, significantly higher than those with AGI grade I/II (48.7%, P = 0.018), whereas there were no significant differences (27.9% vs. 33.7%, P = 0.39) in 60-days mortality between AGI grade I/II and III/IV among the patients with Pplat < 19 cmH2O. In comparison with Pplat, DP had a similar interaction (Pint = 0.028) with AGI grade on 60-day mortality. Ventilatory pressure parameters (Pplat and DP) are independent risk factors of AGI grade III/IV. Pplat and DP interact with AGI grade on 60-days mortality, highlighting the importance of optimizing ventilatory pressure parameters to improve gastrointestinal function and survival outcomes of MV patients.Trial registration: ChiCTR-OCS-13003824.

AI-Equipped Scanning Probe Microscopy for Autonomous Site-Specific Atomic-Level Characterization at Room Temperature.

An advanced scanning probe microscopy system enhanced with artificial intelligence (AI-SPM) designed for self-driving atomic-scale measurements is presented. This system expertly identifies and manipulates atomic positions with high precision, autonomously performing tasks such as spectroscopic data acquisition and atomic adjustment. An outstanding feature of AI-SPM is its ability to detect and adapt to surface defects, targeting or avoiding them as necessary. It is also designed to overcome typical challenges such as positional drift and tip apex atomic variations due to the thermal effects, ensuring accurate, site-specific surface analysis. The tests under the demanding conditions of room temperature have demonstrated the robustness of the system, successfully navigating thermal drift and tip fluctuations. During these tests on the Si(111)-(7 × 7) surface, AI-SPM autonomously identified defect-free regions and performed a large number of current-voltage spectroscopy measurements at different adatom sites, while autonomously compensating for thermal drift and monitoring probe health. These experiments produce extensive data sets that are critical for reliable materials characterization and demonstrate the potential of AI-SPM to significantly improve data acquisition. The integration of AI into SPM technologies represents a step toward more effective, precise and reliable atomic-level surface analysis, revolutionizing materials characterization methods.

How do long combination vehicles perform in real traffic? A study using Naturalistic Driving Data.

This paper evaluates the performance of two different types of long combination vehicles (A-double and DuoCAT) using naturalistic driving data across four scenarios: lane changes, manoeuvring through roundabouts, turning in intersections, and negotiating tight curves. Four different performance-based standards measures are used to assess the stability and tracking performance of the vehicles: rearward amplification, high-speed transient offtracking, low-speed swept path, and high-speed steady-state offtracking. Also, the steering reversal rate metric is employed to estimate the cognitive workload of the drivers in low-speed scenarios. In the majority of the identified cases of the four scenarios, both combination types have a good performance. The A-double shows slightly better stability in high-speed lane changes, while the DuoCAT has slightly better manoeuvrability at low-speed scenarios like roundabouts and intersections.

Reaction-Driven Migration Dynamics of Nano-Metal Particles Unraveled by Quantitative Electron Microscopies.

The stability of supported nano-metal catalysts holds significant importance in both scientific and economic practice, beyond the long pursuit of enhanced activity. While previous efforts have concentrated on augmenting the interaction between nano-metals and carriers, in the thermodynamic macro-perspective, to achieve optimized repression upon particle migration coalescence and Ostwald ripening, nevertheless, the microscale kinetics of migrating catalyst particles driven by the reaction remains unknown. In this work, the migration of nano-copper particles is investigated during hydrogen oxidation reaction by utilizing high spatiotemporal resolution of environmental transmission electron microscopy. It is shown that there exists a delicate correlation between the migration dynamics of nano-copper particles and the evolution of asymmetrically distributed Cu and Cu2O phases over the particle surface. It is found that the interplay of reduction and oxidation near the surface areas filled with Cu and Cu2O phases can facilitate the pressure gradient, which drives the migration of nano-particles. A driving force model is therefore established which is capable of qualitatively explaining the influences of reaction conditions such as temperature and hydrogen-to-oxygen ratio on the reaction-driven particle migration. This work adds a potential yet critical perspective to understanding particle migration and thus the nano-metal catalyst particle sintering in heterogeneous catalysis.

Real-time accident anticipation for autonomous driving through monocular depth-enhanced 3D modeling.

The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. We rigorously evaluate the performance of our framework on three benchmark datasets - Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset - demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA).

AIE-YOLO: Effective object detection method in extreme driving scenarios via adaptive image enhancement.

The widespread research and implementation of visual object detection technology have significantly transformed the autonomous driving industry. Autonomous driving relies heavily on visual sensors to perceive and analyze the environment. However, under extreme weather conditions, such as heavy rain, fog, or low light, these sensors may encounter disruptions, resulting in decreased image quality and reduced detection accuracy, thereby increasing the risk for autonomous driving. To address these challenges, we propose adaptive image enhancement (AIE)-YOLO, a novel object detection method to enhance road object detection accuracy under extreme weather conditions. To tackle the issue of image quality degradation in extreme weather, we designed an improved adaptive image enhancement module. This module dynamically adjusts the pixel features of road images based on different scene conditions, thereby enhancing object visibility and suppressing irrelevant background interference. Additionally, we introduce a spatial feature extraction module to adaptively enhance the model's spatial modeling capability under complex backgrounds. Furthermore, a channel feature extraction module is designed to adaptively enhance the model's representation and generalization abilities. Due to the difficulty in acquiring real-world data for various extreme weather conditions, we constructed a novel benchmark dataset named extreme weather simulation-rare object dataset. This dataset comprises ten types of simulated extreme weather scenarios and is built upon a publicly available rare object detection dataset. Extensive experiments conducted on the extreme weather simulation-rare object dataset demonstrate that AIE-YOLO outperforms existing state-of-the-art methods, achieving excellent detection performance under extreme weather conditions.

Rapid nanomolar detection of cocaine in biofluids by electrochemical aptamer-based sensor with low-temperature effect for drugged driving screening.

Cocaine is one of the most abused illicit drugs, and its abuse damages the central nervous system and can even lead directly to death. Therefore, the development of simple, rapid and highly sensitive detection methods is crucial for the prevention and control of drug abuse, traffic accidents and crime. In this work, an electrochemical aptamer-based (EAB) sensor based on the low-temperature enhancement effect was developed for the direct determination of cocaine in bio-samples. The signal gain of the sensor at 10 °C was greatly improved compared to room temperature, owing to the improved affinity between the aptamer and the target. Additionally, the electroactive area of the gold electrode used to fabricate the EAB sensor was increased 20 times by a simple electrochemical roughening method. The porous electrode possesses more efficient electron transfer and better antifouling properties after roughening. These improvements enabled the sensor to achieve rapid detection of cocaine in complex bio-samples. The low detection limits (LOD) of cocaine in undiluted urine, 50% serum and 50% saliva were 70 nM, 30 nM and 10 nM, respectively, which are below the concentration threshold in drugged driving screening. The aptasensor was simple to construct and reusable, which offers potential for drugged driving screening in the real world.

Chinese adaptation of the reckless driving behaviour scale: Testing its psychometric properties and links with safe driving climate among family and peers.

Purpose: The present study aimed to revise the Reckless Driving Behaviour Scale (RDBS) and examined its reliability and validity among young Chinese drivers. Methods: The RDBS, the Safe Driving Climate among Friends Scale (SDCaF), the Family Climate for Road Safety Scale (FCRSS) and a social desirability scale were administrated to 560 young drivers. Exploratory factor analysis (EFA, n = 250) and confirmatory factor analysis (CFA, n = 250) were conducted to examine the factorial structure of the RDBS. Results: The Chinese version of the RDBS has 18 items that are divided into 4 factors: distraction, substance use, extreme behaviour and positioning. Both the results of EFA and CFA confirmed its factorial structure. The reliability of the RDBS was acceptable and the concurrent validity of the scale was supported by its significant associations with the SDCaF and FCRSS factors. Finally, drivers who had violation involvement scored higher on all four factors than their peers who did not have violation involvement, providing evidence for its known-group validity. Conclusion: The revised RDBS has similar structure with the original version and its reliability and validity were satisfactory. It is an effective tool to measure the reckless driving behaviour of young drivers in China and interventions that incorporated joint efforts of family and peers should be developed.

RCRFNet: Enhancing Object Detection with Self-Supervised Radar-Camera Fusion and Open-Set Recognition.

Robust object detection in complex environments, poor visual conditions, and open scenarios presents significant technical challenges in autonomous driving. These challenges necessitate the development of advanced fusion methods for millimeter-wave (mmWave) radar point cloud data and visual images. To address these issues, this paper proposes a radar-camera robust fusion network (RCRFNet), which leverages self-supervised learning and open-set recognition to effectively utilise the complementary information from both sensors. Specifically, the network uses matched radar-camera data through a frustum association approach to generate self-supervised signals, enhancing network training. The integration of global and local depth consistencies between radar point clouds and visual images, along with image features, helps construct object class confidence levels for detecting unknown targets. Additionally, these techniques are combined with a multi-layer feature extraction backbone and a multimodal feature detection head to achieve robust object detection. Experiments on the nuScenes public dataset demonstrate that RCRFNet outperforms state-of-the-art (SOTA) methods, particularly in conditions of low visual visibility and when detecting unknown class objects.

Combining Optimization and Simulation for Next-Generation Off-Road Vehicle E/E Architectural Design.

The automotive industry, with particular reference to the off-road sector, is facing several challenges, including the integration of Advanced Driver Assistance Systems (ADASs), the introduction of autonomous driving capabilities, and system-specific requirements that are different from the traditional car market. Current vehicular electrical-electronic (E/E) architectures are unable to support the amount of data for new vehicle functionalities, requiring the transition to zonal architectures, new communication standards, and the adoption of Drive-by-Wire technologies. In this work, we propose an automated methodology for next-generation off-road vehicle E/E architectural design. Starting from the regulatory requirements, we use a MILP-based optimizer to find candidate solutions, a discrete event simulator to validate their feasibility, and an ascent-based gradient method to reformulate the constraints for the optimizer in order to converge to the final architectural solution. We evaluate the results in terms of latency, jitter, and network load, as well as provide a Pareto analysis that includes power consumption, cost, and system weight.

Overview of Radar Alignment Methods and Analysis of Radar Misalignment's Impact on Active Safety and Autonomous Systems.

The rapid development of active safety systems in the automotive industry and research in autonomous driving requires reliable, high-precision sensors that provide rich information about the surrounding environment and the behaviour of other road users. In practice, there is always some non-zero mounting misalignment, i.e., angular inaccuracy in a sensor's mounting on a vehicle. It is essential to accurately estimate and compensate for this misalignment further programmatically (in software). In the case of radars, imprecise mounting may result in incorrect/inaccurate target information, problems with the tracking algorithm, or a decrease in the power reflected from the target. Sensor misalignment should be mitigated in two ways: through the correction of an inaccurate alignment angle via the estimated value of the misalignment angle or alerting other components of the system of potential sensor degradation if the misalignment is beyond the operational range. This work analyses misalignment's influences on radar sensors and other system components. In the mathematically proven example of a vertically misaligned radar, pedestrian detectability dropped to one-third of the maximum range. In addition, mathematically derived heading estimation errors demonstrate the impact on data association in data fusion. The simulation results presented show that the angle of misalignment exponentially increases the risk of false track splitting. Additionally, the paper presents a comprehensive review of radar alignment techniques, mostly found in the patent literature, and implements a baseline algorithm, along with suggested key performance indicators (KPIs) to facilitate comparisons for other researchers.