Control Area Research Articles

A dynamic temporal and spatial speed control strategy for partially connected automated vehicles at a signalized arterial

The connected and automated vehicle (CAV) is able to acquire the global intelligence in advance by communicating with other CAVs and roadside units (RSU), thus integrated speed control has the potential of easing the traffic wave, reducing the fuel consumption and emissions. In this paper, a dynamic temporal and spatial speed control framework is proposed to optimize the travel speed of CAVs along the signalized arterial under the mixed traffic flow including CAVs and human driven vehicles (HDVs). A speed control optimization method is proposed to minimize the number of stops of the ego CAV and its follower HDV with considering the signal status and queuing. A secondary speed control method based on the dynamic control areas is introduced in the mentioned framework to guide the CAV to the targeted positions. The corresponding dynamic variable parameter model is then designed to optimize the operational parameters of the corresponding control area to minimize the total fuel consumption of all vehicles under different market penetration rates. Finally, the simulation platform of Urban Mobility (SUMO) is used to test the proposed speed control strategy. The results indicate that the total stop delays are reduced by 60.9 % and saving 6.5 % total fuel consumption under the 30 % penetration rate.

Impact of different illegal Artisanal Small-Scale Mining techniques on soil properties in a major mining landscape in Ghana

The widespread prevalence of illegal Artisanal Small-Scale Mining has raised significant concerns about its environmental and health impacts. This study investigates the effects of two mining methods (alluvial and chamfi) on soil physical, chemical, and microbial properties four years after mining in three municipalities of the Western Region of Ghana. The study identified four species of Aspergillus fungi (niger, flavus, ochraceous and fumigatus) and Trichoderma species in both mined and control soils. The quantity of A. fumigatus was significantly higher in control plots compared to mined plots. In alluvial sites, bacterial numbers were significantly higher in control plots than in mined plots, while in chamfi sites, bacterial numbers did not differ significantly between mined and control plots. Soil texture in both mined sites was predominantly sandy loam and loamy sand, with a generally high silt to clay ratio. Mined plots at both sites were significant and more acidic (p < 0.05) than the control plots. Additionally, cation exchange capacity (CEC), electrical conductivity (EC), organic carbon (OC), total nitrogen (TN), phosphorus (P), potassium (K+), calcium (Ca2+), and magnesium (Mg2+) levels were significantly higher in control plots compared to mined plots. The control plots also exhibited higher base saturation and lower exchangeable acidity than mined plots. Bacteria count at Chamfi sites was generally higher at mined areas than the control sites, with the reverse being the case for Alluvial sites. Soil chemical parameters were higher at control areas than at mined sites, irrespective of the mining approach used. However, there was no clear pattern of differences in soil chemical properties at Chamfi and Alluvial mined sites. This study provides insights and additional perspectives for improving decision-making and guiding the potential restoration of these areas.

Antimicrobial Resistance in the Terrestrial Environment of Agricultural Landscapes in Norway.

The abundance and diversity of antimicrobial-resistant bacteria (ARB) and antimicrobial resistance genes (ARGs) in agricultural landscapes may be important for the spread of antimicrobial resistance (AMR) in the environment. The aim of this study was to apply screening methods for ARB and ARGs to investigate the impact of farming on the prevalence of AMR in a country with low antibiotic usage. We have analyzed samples (n = 644) from soil and wild terrestrial animals and plants (slugs, snails, mice, shrews, earthworms, and red clover) collected over two years in agricultural fields accompanied by nearby control areas with low human activity. All samples were investigated for the occurrence of 35 different ARGs using high-throughput quantitative PCR (HT-qPCR) on a newly developed DNA array. In addition, samples from the first year (n = 415) were investigated with a culture-based approach combined with whole-genome sequencing (WGS) to identify antimicrobial-resistant E. coli (AREC). ARGs were detected in 59.5% of all samples (2019 + 2020). AREC, which was only investigated in the 2019 samples, was identified in 1.9% of these. Samples collected in the autumn showed more ARGs and AREC than spring samples, and this was more pronounced for organic fields than for conventional fields. Control areas with low human activity showed lower levels of ARGs and a lack of AREC. The use of livestock manure was correlated with a higher level of ARG load than other farming practices. None of the soil samples contained antibiotics, and no association was found between AMR and the levels of metals or pesticides. High qualitative similarity between HT-qPCR and WGS, together with the positive controls to the validation of our 35 ARG assays, show that the microfluid DNA array may be an efficient screening tool on environmental samples. In conclusion, even in a country with a very low consumption of antimicrobials by production animals, our results support the hypothesis of these animals being a source of AREC and ARGs in agricultural environments, primarily through the use of manure.

Whole-brain mechanism of neurofeedback therapy: predictive modeling of neurofeedback outcomes on repetitive negative thinking in depression

Real-time fMRI neurofeedback (rtfMRI-NF) has emerged as a promising intervention for psychiatric disorders, yet its clinical efficacy remains underexplored due to an incomplete mechanistic understanding. This study aimed to delineate the whole-brain mechanisms underpinning the effects of rtfMRI-NF on repetitive negative thinking in depression. In a double-blind randomized controlled trial, forty-three depressed individuals underwent NF training targeting the functional connectivity (FC) between the posterior cingulate cortex and the right temporoparietal junction, linked to rumination severity. Participants were randomly assigned to active or sham groups, with the sham group receiving synthesized feedback mimicking real NF signal patterns. The active group demonstrated a significant reduction in brooding rumination scores (d = −1.52, p < 0.001), whereas the sham group did not (d = −0.23, p = 0.503). While the target FC did not show discernible training effects or group differences, connectome-based predictive modeling (CPM) analysis revealed that the interaction between brain activity during regulation and brain response to the feedback signal was the critical factor in explaining treatment outcomes. The model incorporating this interaction successfully predicted rumination changes across both groups. The FCs significantly contributing to the prediction were distributed across brain regions, notably the frontal control, salience network, and subcortical reward processing areas. These results underscore the importance of considering the interplay between brain regulation activities and brain response to the feedback signal in understanding the therapeutic mechanisms of rtfMRI-NF. The study affirms rtfMRI-NF’s potential as a therapeutic intervention for repetitive negative thinking and highlights the need for a nuanced understanding of the whole-brain mechanisms contributing to its efficacy.

Differential Cellular Response to Mercury in Non-Farmed Fish Species Based on Mitochondrial DNA Copy Number Variation Analysis.

Mercury (Hg) pro-oxidant role on biological systems and its biogeochemical cycle represent a serious threat due to its persistence in marine environment. As the mitochondrial genome is exposed to reactive oxygen species (ROS), the aim of the present study is the validation of the variation in the number of mitochondrial DNA copies (mtDNAcn) as biomarker of oxidative stress in aquatic environment. During summer 2021, three selected fish species (Mullus barbatus, Diplodus annularis and Pagellus erythrinus) were collected in Augusta Bay, one of the most Mediterranean contaminated areas remarkable by past Hg inputs, and in a control area, both in the south-east of Sicily. The relative mtDNAcn was evaluated by qPCR on specimens of each species from both sites, characterized respectively by higher and lower Hg bioaccumulation. M. barbatus and P. erythrinus collected in Augusta showed a dramatic mtDNAcn reduction compared to their control groups while D. annularis showed an incredible mtDNAcn rising suggesting a higher resilience of this species. These results align with the mitochondrial dynamics of fission and fusion triggered by environmental toxicants. In conclusion, we suggest the implementation of the mtDNAcn variation as a valid tool for the early warning stress-related impacts in aquatic system.

NATURAL EXPOSURE TO ARSENIC-INDUCED GENOTOXIC EFFECTS IN DIABETIC AND NON-DIABETIC INDIVIDUALS

Arsenic contamination in drinking water is a global health issue linked to various adverse health outcomes, including genotoxic effects. Understanding these effects in different populations, including diabetic and non-diabetic individuals, is critical for developing targeted public health interventions. Objective: This study aimed to investigate the genotoxic effects of arsenic exposure in diabetic and non-diabetic individuals residing in arsenic-contaminated and control areas. Methods: In this cross-sectional study conducted from January to June 2024, 100 participants were recruited from areas with known differences in arsenic water contamination levels. Participants were divided equally between arsenic-contaminated and non-contaminated regions, with 15 diabetic and 20 non-diabetic individuals selected from each group. A standard questionnaire was administered to collect demographic data and medical history. Additionally, 12 water samples from the contaminated area were analyzed for arsenic concentration. Genotoxic effects were assessed using the comet assay, and DNA damage was quantified using an empirical numerical rating system. Results: Significant DNA damage was observed in the blood cells of individuals from the arsenic-contaminated area compared to those from the non-contaminated area. Diabetic individuals showed similar patterns of DNA damage to non-diabetics within the same exposure group. Even in the non-contaminated group, slight DNA damage was detected, suggesting potential contributions from other environmental factors. Conclusion: The findings demonstrate that arsenic exposure is associated with significant genotoxic effects in both diabetic and non-diabetic populations. DNA damage in non-contaminated areas also indicates a possible impact of other environmental factors. These results highlight the need for ongoing monitoring and mitigation strategies to address arsenic contamination and its health impacts.

Simulation and prediction of land subsidence in Decheng District under the constraint of InSAR deformation information

Land subsidence, marked by a decline in surface elevation, poses a significant threat to urban infrastructure and safety. Accurate subsidence information and a reliable prediction model are crucial for prevention and control. In this study, we used persistent scatterer interferometric synthetic aperture radar (PS-InSAR) technology to obtain long-term land subsidence data and analyzed subsidence characteristics in Decheng District. By integrating hydrogeological and groundwater data, we developed a three-dimensional groundwater flow and one-dimensional compaction model through numerical simulation. Furthermore, the subsidence data monitored by PS-InSAR were used to further constrain and validate the model. The evolution trend of land subsidence under different groundwater exploitation scenarios was predicted and analyzed. The results showed that from May 2017 to December 2021, the cumulative maximum subsidence in Decheng District reached −173 mm. The subsidence area is mainly concentrated in the northern area, and its subsidence center is near Qiaoyuan Town. According to the Land Subsidence Prevention and Control Plan of Dezhou City, Shandong Province (2018–2025), we set up different groundwater mining scenarios with the goal that the rate of land subsidence in the key prevention and control area is less than 35 mm/yr in 2025.The Fluid-solid coupled model prediction analysis results indicated that a 30% reduction in groundwater exploitation is reasonable.

Femtosecond laser controllable annealing for color centers based on ion-implanted silicon carbide substrate

As a representative of third-generation semiconductors, silicon carbide serves as a new platform for quantum nano-optics with readable paramagnetic color centers such as silicon vacancies. The potential applications include biomedical imaging, quantum sensing and micro/nano environment detection. Color centers are usually prepared based on ion-irradiated substrates, then annealed at high temperature to increase the yield. Currently, annealing furnaces have been the main method to heat the substrate and achieve annealing of the whole sample. However, further exploration is still necessary for fine processing requirements such as specialized annealing regions with certain shapes. In this work, we applied femtosecond laser to achieve controllable annealing at micron scale, based on silicon carbide substrate after ion injection. The whole process of point, line and pattern annealing was realized. The annealing area demonstrates enhanced photoluminescence, attributed to silicon vacancy color centers. Raman and photoluminescence spectra reveal that the annealing effect is primarily influenced by the number of pulses per unit area. The mechanism of femtosecond laser annealing was introduced. Finally, the controllable annealing areas with various shapes were prepared based on the comprehensive optimal parameters (100 kHz pulse repetition frequency, 105 point annealing pulses, 10 μm/s line scanning speed). This annealing strategy demonstrates excellent stability and uniformity, as well as micron scale accuracy. Additionally, the excited state lifetime of silicon vacancy was extracted and quantified. The result means that femtosecond laser annealing enhances the optical properties and quantum application potential of color centers. This work can be further extended to other semiconductors as well as patterned modification of local surface/planes at some depth, and helpful to explore the mechanism and applications of femtosecond laser annealing.

The potential synergy between air pollution control and employment growth

Public service sectors play crucial roles in maintaining societal functioning through the provision of essential services. However, amidst the backdrop of air pollution, their developmental trajectories may veer off course from their intended goals. Quantifying the impact of air pollution on public service sectors, particularly from an employment perspective, offers valuable insights for policymakers aiming to foster the sustainable growth of these sectors and expand the analysis framework on air pollution externalities. Drawing on monthly data spanning from January 2015 to December 2019 across 269 prefecture cities, this paper therefore explores the impact of air pollution on public service sector employment using a cross-lagged panel model with fixed effects. I find that air pollution negatively affects the employment scales in public service sectors. This negative employment shock is also unevenly distributed across areas and sub-sectors and intensifies over time. Cities belong to key areas for air pollution prevention and control, small and medium-sized cities, and secondary-industry dominated cities, suffer disproportionately negative employment shocks in their public service sectors. These findings offer actionable insights for policymakers to implement targeted measures supporting the continued growth of public service sectors and deepen understanding of the economic ramifications of air pollution.

Appropriateness of antibiotic prescribing in paediatrics: retrospective controlled study assessing a multifaceted intervention in Northern Italy in a 7-year period

BackgroundAcademic detailing, audit and feedback, and peer comparison have been advocated as effective ways to promote appropriateness of prescribing and antimicrobial stewardship (AMS). This study explored the effectiveness of a...

WITHDRAWN: Characterization of soil response in mining with grouting into overburden bed-separation based on similar material simulation

Revealing the response laws of soils under various mining conditions is of significance for the scientific protection of farmland in mining areas. To avoid the interference from the spatial heterogeneity of natural soil on the research results, similar simulation experiments were employed. Two models for soil responses under mining with and without grouting into overburden bed-separation were designed, and monitoring was conducted for soil quality factors (moisture content, silt and clay content, and bulk density) and surface deformation factors (subsidence, inclined, and horizontal deformation). The results indicate that it can significantly control surface subsidence in mining with grouting into overburden bed-separation, the maximum subsidence value was reduced by 66.67%, the average subsidence value of each measuring point in the main section was reduced by 78.92%, and the subsidence area was reduced by 34.68%. The coefficient of variation of soil quality factors in the mining-affected area was obviously higher than that in the control area and the initial value before mining. Compared with mining without grouting, the variation coefficient of soil quality factor under mining with grouting was reduced by 2.71-6.79%. Soil quality factors and surface deformation factors show a significant quadratic function relationship, among which horizontal deformation has the greatest influence on soil quality factors, followed by subsidence and inclination. Therefore, it can effectively control surface subsidence and protect cultivated land when mining with grouting into overburden bed-separation.

Judicial control over the observance of human rights and freedoms during the consideration of the prosecution’s motions for permission to conduct covert investigative (search) actions in terms of observance of the principles of the right to a fair trial

The article is devoted to the problematic issues of regulation of judicial control during consideration of applications for permission to conduct covert investigative (detective) actions and use their results for other purposes, in terms of ensuring the right to a fair trial guaranteed by Article 6 of the Convention for the Protection of Human Rights and Fundamental Freedoms. The principle of fairness of a trial is interpreted in certain judgments of the European Court of Human Rights as the proper administration of justice, the right of access to justice, equality of parties, adversarial nature of the trial, reasonableness of the trial, etc. The construction of Article 6 of the Convention indicates the existence of the following key elements of the right to judicial protection: 1) the right to a hearing; 2) fairness of the hearing; 3) publicity; 4) reasonable time; 5) hearing by a court established by law; 6) independence and impartiality of the court. The author examines the key issues affecting the objectivity of court decisions in this area, imperfections of the procedures provided for in the criminal procedure legislation in terms of ensuring the fairness of the trial, reasonableness and motivation of the court decision. Special attention is paid to the problems of ensuring the independence and impartiality of the court as a factor that significantly affects the legality of such decisions, and the author suggests ways to improve the effectiveness of judicial control in this area. According to the author the legal regulation provided for by criminal procedure legislation in the area of judicial control over covert investigative (detective) actions, both in terms of consideration of applications for permission to conduct activities related to interference with private life and the use of the information obtained in another criminal proceeding or for another purpose, does not ensure compliance with the guarantees of the right to a fair trial provided for in Article 6 of the European Convention. Along with the need to take effective measures aimed at ensuring the independence of the judiciary and the impartiality of judges, criminal procedure legislation also needs to be improved. In particular, the article suggests that reforms should be aimed at overcoming “formalism” in the course of consideration of applications for permission to conduct covert investigative (detective) actions.

Nutritional status of the reservoir tributary backwater area and implications for nutrient control

Understanding the spatial and temporal distribution and driving factors of the nutritional status in the backwater area of typical tributaries in the Three Gorges Reservoir Region (TGRR) is important for the prevention and control measures. In this study, the Environmental Fluid Dynamics Code (EFDC) was used to extend in situ monitoring data, followed by the application of hydrogen and oxygen isotope data and scoring methods to predict the nutritional status in the backwater area of the Daning River. The results indicated that the nutritional status-sensitive period mainly ranged from May-October and was distributed at the end of the backwater area and tributary bay. The water temperature and intermediate density flow were identified as the key factors inducing deterioration in the nutritional status at the end of the backwater area and tributary bay, respectively. Nutrient reduction in the mainstream and tributary areas significantly affected the nutritional status in the backwater area. Notably, hydrodynamic adjustment under reservoir objectives is indispensable for improving the water environment in tributary bay after reaching the water quality standard. Our findings highlight the necessity of focusing on the upper reaches of the tributaries and reservoir for nutrient control and emphasize the importance of combining reservoir operation strategies to mitigate the deterioration in the nutritional status.

CAN Bus: The Future of Additive Manufacturing (3D Printing)

Additive Manufacturing (AM) is gaining renewed popularity and attention due to low-cost fabrication systems proliferating the market. Current communication protocols used in AM limit the connection flexibility between the control board and peripherals; they are often complex in their wiring and thus restrict their avenue of expansion. Thus, the Controller Area Network (CAN) bus is an attractive pathway for inter-hardware connections due to its innate quality. However, the combination of CAN and AM is not well explored and documented in existing literature. This article aims to provide examples of CAN bus applications in AM.

An 'alcohol health champions' intervention to reduce alcohol harm in local communities: a mixed-methods evaluation of a natural experiment.

Globally alcohol consumption is a leading risk factor for premature death and disability and is associated with crime, social and economic consequences. Local communities may be able to play a role in addressing alcohol-related issues in their area. To evaluate the effectiveness and cost-benefit of an asset-based community development approach to reducing alcohol-related harm and understand the context and factors that enable or hinder its implementation. A mixed-methods evaluation. Area-level quasi-experimental trial analysed using four different evaluation methods (a stepped-wedge design where each area was a control until it entered the intervention, comparison to matched local/national controls and comparison to synthetic controls), alongside process and economic evaluations. Ten local authorities in Greater Manchester, England. The outcomes evaluation was analysed at an area level. Ninety-three lay persons representing nineareas completed questionnaires, with 12 follow-up interviews in five areas; 20 stakeholders representing ten areas were interviewed at baseline, with 17 follow-up interviews in eight areas and 26 members of the public from two areas attended focus groups. Professionals in a co-ordinator role recruited and supported lay volunteers who were trained to become alcohol health champions. The champion's role was to provide informal, brief alcohol advice to the local population and take action to strengthen restrictions on alcohol availability. Numbers of alcohol-related hospital admissions, accident and emergency attendances, ambulance call-outs, street-level crime and antisocial behaviour in the intervention areas (area size: 1600-5500 residents). Set-up and running costs were collected alongside process evaluation data exploring barriers and facilitators. Routinely collected quantitative data on outcome measures aggregated at the intervention area and matched control and synthetic control areas. Data from policy documents, licensing registers, meeting notes, invoices, time/cost diaries, training registers, questionnaires, interviews, reflective diaries and focus groups. The intervention rolled out in nine out of ten areas, seven of which ran for a full 12 months. Areas with better-established infrastructure at baseline were able to train more champions. In total, 123 alcohol health champions were trained (95 lay volunteers and 28 professionals): lay volunteers self-reported positive impact. Champions engaged in brief advice conversations more readily than taking action on alcohol availability. There were no consistent differences in the health and crime area-level indicators between intervention areas and controls, as confirmed by using three different analysis methods for evaluating natural experiments. The intervention was not found to be cost-beneficial. Although the sequential roll-out order of the intervention was randomised, the selection of the intervention areas was not. Self-reported impact may have been subject to social desirability bias due to the project's high profile. There was no measurable impact on health and crime outcomes. Possible explanations include too few volunteers trained, volunteers being unwilling to get involved in licensing decisions, or that the intervention has no direct impact on the selected outcomes. Future similar interventions should use a coproduced community outcomes framework. Other natural experiment evaluations should use methodological triangulation to strengthen inferences about effectiveness. This trial is registered as ISRCTN81942890. This award was funded by the National Institute for Health and Care Research (NIHR) Public Health Research programme (NIHR award ref: 15/129/03) and is published in full in Public Health Research; Vol. 12, No. 9. See the NIHR Funding and Awards website for further award information.

A lightweight distributed ELM-based security framework for the internet of vehicles

The fast growth of internet of vehicles (IoV) has created a new area of connectedness, with promising safety and efficiency in transportation. However, this advancement in vehicle technology has come with significant cybersecurity risks, specifically through control area network (CAN) protocol and other communication techniques within vehicles. This experimental study suggests a machine learning (ML) based security approach based on the extreme learning machine (ELM) algorithm to address these challenges. Unlike customary neural networks, ELM is known for its fast processing, minimal training time, and high accuracy, making it preferably suitable for dynamic IoV environments. The methodology involves data preprocessing, feature selection, and employing ELM for attack classification; the algorithm’s performance is evaluated using CARHacking, NSL-KDD, and EdgeIIoT datasets. We also examine the significance of distributed processing to enhance the computational efficiency of the model, obtaining 89% accuracy in 3 ms run-time for external networks, and 83% accuracy with 9 ms run-time for intra-vehical networks. This newly proposed security mechanism using ELM shows very accurate results in detecting intrusions with a high recall rate and reduced computation time through distributed processing.

Construction of a photovoltaic low-voltage grid connected power regulation system based on partition control

Abstract Photovoltaic power generation is a green and renewable power generation mode and has been widely used. However, the power fluctuation of photovoltaic power generation has a significant impact on the power grid, which is very important. Based on the concept of regional control, this paper studies the photovoltaic low-voltage grid-connected power regulation system. The photovoltaic power generation system is divided into multiple regions, and each region is provided with an independent control unit and regulation strategy under the control of multiple control areas. The regional factors are combined, such as light intensity and power voltage. In the case of the city, the impact of the area on the whole is dynamically adjusted to achieve the overall balance of power and the stability of the system. The experimental results show that the photovoltaic low-voltage grid-connected power regulation system constructed by regional control performs well and has a high degree of stability. According to the change in light intensity and load demand, the system can achieve accurate control and distribution of photovoltaic power generation.

Development of an Automatic Feature Point Classification Method for Three-Dimensional Mapping Around Slewing and Derricking Cranes

Crane automation requires a three-dimensional (3D) map around cranes that should be reconstructed and updated quickly.In this study, a high-precision classification method was developed to distinguish stationary objects from moving objects in moving images captured by a monocular camera to stabilize 3D reconstruction. To develop the method, a moving image was captured while the crane was slewed with a monocular camera mounted vertically downward at the tip of the crane. The boom length and angle data were output from a control device, a controller area network. For efficient development, a simulator that imitated the environment of an actual machine was developed and used. The proposed method uses optical flow to track feature points. The classification was performed successfully, independent of derricking motion. Consequently, the proposed method contributes to stable 3D mapping around cranes in construction sites.

인천항 대기오염물질 배출량 산정 및 저감효과 분석

As global awareness of air pollution issues caused by ports increases, international organizations and developed countries are monitoring pollution levels and establishing various eco-friendly policies to reduce emissions. Domestically, the relevant laws were enacted in 2020 to systematically manage the sources of port pollutants in the five major ports. This study aims to estimate the emissions of air pollutants generated by Incheon Port and analyze the effects of major eco-friendly policies such as Emission Control Areas (ECA), Vehicle Speed Reduction (VSR), and Alternative Maritime Power (AMP). For the year 2023, activity data for all ships, cargo handling equipment, and vehicles were collected, applying methodologies from reputable institutions such as the European Environment Agency (EEA) and the Environmental Protection Agency (EPA). According to national guidelines, air pollutants are categorized into eight types: CO, NOx, SOx, TSP, PM10, PM2.5, VOC, and NH3. The analysis revealed that the total emissions of air pollutants from Incheon Port were approximately 6,362 tons, with ships accounting for over 60% of the total emissions. Among the pollutants, NOx was the highest at 4,597.4 tons, followed by CO at 862.4 tons, and TSP at 314.6 tons. Among the ports, emissions were highest at the New Port, followed by the South Port, Inner Port, and North Port. The results of this study provide essential baseline data for monitoring the air pollution levels of Incheon Port and serve as critical evidence for environmental management and policy development. For sustainable future management, it is crucial to secure reliable data and develop a platform that links data collection, analysis, and visualization functions for more systematic operation.

A robust multi-stage intrusion detection system for in-vehicle network security using hierarchical federated learning

As connected and autonomous vehicles proliferate, the Controller Area Network (CAN) bus has become the predominant communication standard for in-vehicle networks due to its speed and efficiency. However, the CAN bus lacks basic security measures such as authentication and encryption, making it highly vulnerable to cyberattacks. To ensure in-vehicle security, intrusion detection systems (IDSs) must detect seen attacks and provide a robust defense against new, unseen attacks while remaining lightweight for practical deployment. Previous work has relied solely on the CAN ID feature or has used traditional machine learning (ML) approaches with manual feature extraction. These approaches overlook other exploitable features, making it challenging to adapt to new unseen attack variants and compromising security. This paper introduces a cutting-edge, novel, lightweight, in-vehicle, IDS-leveraging, deep learning (DL) algorithm to address these limitations. The proposed IDS employs a multi-stage approach: an artificial neural network (ANN) in the first stage to detect seen attacks, and a Long Short-Term Memory (LSTM) autoencoder in the second stage to detect new, unseen attacks. To understand and analyze diverse driving behaviors, update the model with the latest attack patterns, and preserve data privacy, we propose a theoretical framework to deploy our IDS in a hierarchical federated learning (H-FL) environment. Experimental results demonstrate that our IDS achieves an F1-score exceeding 0.99 for seen attacks and exceeding 0.95 for novel attacks, with a detection rate of 99.99%. Additionally, the false alarm rate (FAR) is exceptionally low at 0.016%, minimizing false alarms. Despite using DL algorithms known for their effectiveness in identifying sophisticated and zero-day attacks, the IDS remains lightweight, ensuring its feasibility for real-world deployment. This makes our model robust against seen and unseen attacks.