A New Speed Limit Recognition Methodology Based on Ensemble Learning:Hardware Validation

Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the road.Traffic Sign Recognition System(TSRS)is one of themost important components ofADAS.Among the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing time.Accordingly,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed modules.Firstly,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured frames.Secondly,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise recognition.In addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting technique.Through rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,respectively.Furthermore,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.

A local rainfall-triggered giant landslide occurred in a region along a high-speed railway on the Qinghai‒Tibetan Plateau

An increasing number of geological hazards along high-speed railways on the Qinghai‒Tibetan Plateau have occurred and have resulted in a profound influence on old infrastructure,which has attracted increasing attention.The landslide event that occurred on September 15,2022,in Jiujiawan village,Xining city,Qinghai Province,is a typical case.Based on field investigations and remote sensing interpretations,a comprehensive analysis was conducted on the landslide.Additionally,the potential secondary failure of the current Jiujiawan landslide was assessed using Fast Lagrangian Analysis of Continua in Three Dimensions(FLAC3D).Based on the application of the small baseline subset-interferometric synthetic aperture radar(SBAS-InSAR)technique to SAR images from February 24,2017 to September 14,2022,a significant westward horizontal deformation was found to have been formed prior to the occurrence of the landslide.The maximum annual average deformation rate in the line of sight(LOS)direction reached-45 mm/yr,with a maximum cumulative deformation of-178 mm.This value was consistent with the continual increase in annual precipitation(2.51 mm/yr)prior to the occurrence of the landslide.The accumulated precipitation before the landslide was 279.8 mm,accounting for 54.2%of the total annual precipitation,with a particularly notable surge in monthly precipitation observed during August(250.3 mm).Additionally,the occurrence of a seismic event with a magnitude of Ms 6.9 in Menyuan County,80 km away from Xining,could be a potential triggering factor to the landslide,as evidenced by an abrupt subsidence alteration observed prior to and following the earthquake.The maximum subsidence in the line of sight(LOS)direction exceeded 11 mm,exhibiting a highly consistent spatial distribution with the occurrence range of landslides.These results suggest that the Jiujiawan landslide was likely induced by earthquake events in the early stage and heavy rainfall in the later stage.The FLAC3D numerical simulation show that after the landslide,the slope remained marginally stable under natural conditions;however,it is susceptible to reactivation with heavy rainfall.

Overexpression of wild-type HRAS drives non-alcoholic steatohepatitis to hepatocellular carcinoma in mice

Hepatocellular carcinoma(HCC),a prevalent solid carcinoma of significant concern,is an aggressive and often fatal disease with increasing global incidence rates and poor therapeutic outcomes.The etiology and pathological progression of non-alcoholic steatohepatitis(NASH)-related HCC is multifactorial and multistage.However,no single animal model can accurately mimic the full NASH-related HCC pathological progression,posing considerable challenges to transition and mechanistic studies.Herein,a novel conditional inducible wild-type human HRAS overexpressed mouse model(HRAS-HCC)was established,demonstrating 100%morbidity and mortality within approximately one month under normal dietary and lifestyle conditions.Advanced symptoms of HCC such as ascites,thrombus,internal hemorrhage,jaundice,and lung metastasis were successfully replicated in mice.In-depth pathological features of NASH-related HCC were demonstrated by pathological staining,biochemical analyses,and typical marker gene detections.Combined murine anti-PD-1 and sorafenib treatment effectively prolonged mouse survival,further confirming the accuracy and reliability of the model.Based on protein-protein interaction(PPI)network and RNA sequencing analyses,we speculated that overexpression of HRAS may initiate the THBS1-COL4A3 axis to induce NASH with severe fibrosis,with subsequent progression to HCC.Collectively,our study successfully duplicated natural sequential progression in a single murine model over a very short period,providing an accurate and reliable preclinical tool for therapeutic evaluations targeting the NASH to HCC continuum.

OSMR is a potential driver of inflammation in amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis is a neurodegenerative disease,and the molecular mechanism underlying its pathology remains poorly understood.However,inflammation is known to play an important role in the development of this condition.To identify driver genes that affect the inflammatory response in amyotrophic lateral sclerosis,as well as potential treatment targets,it is crucial to analyze brain tissue samples from patients with both sporadic amyotrophic lateral sclerosis and C9orf72-related amyotrophic lateral sclerosis.Therefore,in this study we used a network-driven gene analysis tool,NetBID2.0,which is based on SJARACNe,a scalable algorithm for the reconstruction of accurate cellular networks,to experimentally analyze sequencing data from patients with sporadic amyotrophic lateral sclerosis.The results showed that the OSMR gene is pathogenic in amyotrophic lateral sclerosis and participates in the progression of amyotrophic lateral sclerosis by mediating the neuroinflammatory response.Furthermore,there were differences in OSMR activity and expression between patients with sporadic amyotrophic lateral sclerosis and those with C9orf72-related amyotrophic lateral sclerosis.These findings suggest that OSMR may be a diagnostic and prognostic marker for amyotrophic lateral sclerosis.

Factors Influencing the Spatial Variability of Air Temperature Urban Heat Island Intensity in Chinese Cities

Few studies have investigated the spatial patterns of the air temperature urban heat island(AUHI)and its controlling factors.In this study,the data generated by an urban climate model were used to investigate the spatial variations of the AUHI across China and the underlying climate and ecological drivers.A total of 355 urban clusters were used.We performed an attribution analysis of the AUHI to elucidate the mechanisms underlying its formation.The results show that the midday AUHI is negatively correlated with climate wetness(humid:0.34 K;semi-humid:0.50 K;semi-arid:0.73 K).The annual mean midnight AUHI does not show discernible spatial patterns,but is generally stronger than the midday AUHI.The urban–rural difference in convection efficiency is the largest contributor to the midday AUHI in the humid(0.32±0.09 K)and the semi-arid(0.36±0.11 K)climate zones.The release of anthropogenic heat from urban land is the dominant contributor to the midnight AUHI in all three climate zones.The rural vegetation density is the most important driver of the daytime and nighttime AUHI spatial variations.A spatial covariance analysis revealed that this vegetation influence is manifested mainly through its regulation of heat storage in rural land.

A Hybrid Model for Improving Software Cost Estimation in Global Software Development

Accurate software cost estimation in Global Software Development(GSD)remains challenging due to reliance on historical data and expert judgments.Traditional models,such as the Constructive Cost Model(COCOMO II),rely heavily on historical and accurate data.In addition,expert judgment is required to set many input parameters,which can introduce subjectivity and variability in the estimation process.Consequently,there is a need to improve the current GSD models to mitigate reliance on historical data,subjectivity in expert judgment,inadequate consideration of GSD-based cost drivers and limited integration of modern technologies with cost overruns.This study introduces a novel hybrid model that synergizes the COCOMO II with Artificial Neural Networks(ANN)to address these challenges.The proposed hybrid model integrates additional GSD-based cost drivers identified through a systematic literature review and further vetted by industry experts.This article compares the effectiveness of the proposedmodelwith state-of-the-artmachine learning-basedmodels for software cost estimation.Evaluating the NASA 93 dataset by adopting twenty-six GSD-based cost drivers reveals that our hybrid model achieves superior accuracy,outperforming existing state-of-the-artmodels.The findings indicate the potential of combining COCOMO II,ANN,and additional GSD-based cost drivers to transform cost estimation in GSD.

Leading Pattern of Spring Drought Variability over East Asia and Associated Drivers

Drought events have become more frequent and intense over East Asia in recent decades,leading to huge socioeconomic impacts.Although the droughts have been studied extensively by cases or for individual regions,their leading variability and associated causes remain unclear.Based on the Standardized Precipitation Evapotranspiration Index(SPEI)and ERA5 reanalysis product from 1979 to 2020,this study evealuates the severity of spring droughts in East Asia and investigates their variations and associated drivers.The results indicate that North China and Mongolia have experienced remarkable trends toward dryness during spring in recent decades,while southwestern China has witnessed an opposite trend toward wetness.The first Empirical Orthogonal Function mode of SPEI variability reveals a similar seesawing pattern,with more severe dryness in northwestern China,Mongolia,North China,South Korea,and Japan but increased wetness in Southwestern China and southeast Asia.Further investigation reveals that the anomalously dry(wet)surface in North(Southwestern)China is significantly associated with anomalously high(low)temperature,less(more)precipitation,and reduced(increased)soil moisture during the previous winter and early spring,regulated by an anomalous anticyclone(cyclone)and thus reduced(increased)water vapor convergence.The spring dry-wet pattern in East Asia is also linked to cold sea surface temperature anomalies in the central-eastern Pacific.The findings of this study have important implications for improving the prediction of spring drought events in East Asia.

Influence of upstream solar wind on magnetic field distribution in the Martian nightside ionosphere

Using over eight years of Mars Atmosphere and Volatile Evolutio N(MAVEN)data,from November 2014 to May 2023,we have investigated the Martian nightside ionospheric magnetic field distribution under the influence of upstream solar wind drivers,including the interplanetary magnetic field intensity(∣BIMF∣),solar wind dynamic pressure(PS W),solar extreme ultraviolet flux(EUV),and Martian seasons(L s).Our analysis reveals pronounced correlations between magnetic field residuals and both∣BIMF∣and PS W.Correlations observed with EUV flux and Ls were weaker—notably,magnetic field residuals increased during periods of high EUV flux and at Mars perihelion.We find that the IMF penetrates to an altitude of 200 km under a wide range of upstream conditions,penetrating notably deeper under high∣BIMF∣andPSWconditions.Our analysis also indicates that EUV flux and IMF cone angle have minimal impact on IMF penetration depth.Those findings provide useful constraints on the dynamic nature of Martian atmospheric escape processes and their evolution,suggesting that historical solar wind conditions may have facilitated deeper IMF penetration and higher rates of ionospheric escape than are observed now.Moreover,by establishing criteria for magnetic‘quiet’conditions,this study offers new insights into the planet’s magnetic environment under varying solar wind influences,knowledge that should help refine models of the Martian crustal magnetic field.

Research on Innovation-Driven Expansion of Regional OFDI: New Evidence From a Business Environment Perspective

This paper investigates the impact of provincial innovation-driven efficiency on the expansion of regional Outward Foreign Direct Investment(OFDI)flows within the context of China’s economy during the period 2011 to 2020 by measuring the innovation-driven efficiency and business environment index using the DEA-Malmquist index and the combined CRITIC weighting method from the new perspective of business environment improvement.The findings reveal that:(a)There is an inverted U-shaped relationship between provincial innovation-driven efficiency and regional OFDI flows.This increase in innovation-driven efficiency can promote OFDI expansion of the region by improving its business environment.(b)The improvement of the business environments plays a significant intermediary and synergistic role in OFDI expansion driven by improved innovation efficiency.(c)The study of regional heterogeneity suggests that the central region enjoys the longest window period in terms of innovation-driven OFDI expansion,followed by the eastern region while the western region has the shortest window period.The improvement of the business environment in the western region is more effective in driving regional OFDI expansion.This conclusion remained true after the robustness test.In conclusion,this paper offers a few policy recommendations that can help Chinese capital of various kinds go global more effectively.

Land Use and Land Cover Dynamics in the Eseka Alluvial Gold Mining District, Centre Region, Cameroon

Local populations in Cameroon thrive on forest resources and the flow of ecosystem services they provide are pivotal in sustaining national economy, improving people’s lives, safeguarding biodiversity, and mitigating the impacts of environmental changes. The exploitation of these resources invariably leads to deforestation and forest degradation. This study was designed to evaluate land use land cover change (LULCC) in the Eseka alluvial gold mining district with the aid of Landsat images. In the investigation of forest cover change, four Landsat satellite images for (1990, 2002, 2015 and 2022) were used. Ground-truthing also helped to identify the activities carried out by the local population and to determine agents, drivers and pressures of land use and land cover change. Four main land cover classes namely: forest, agricultural land, settlement/mining camps and water bodies were selected. Between 1990 and 2022, the proportion of forest decreased from 98% to 34% while those of agricultural land and settlement/mining camps increased from 2% to 60% and 0.54% to 6% respectively. Analysis showed ongoing deforestation with forest cover loss of ~98,263 ha in 32 years giving a cover change percentage of 63.94%. Kappa coefficient for the study period ranged from 0.92 to 0.99. Forest cover loss could be attributed to farming activities, wood extraction and alluvial gold mining activities. Economic motives notably the need to increase household income from a frequent demand for farm and wood products in neighbouring towns and the quest for gold were the main drivers of these activities. Hence, this study assesses the impact of human activities from the mining sector on the forest ecosystem in a bid to inform mitigation policies.

Knowledge, Attitudes and Practices Relating to HIV among Motorbike Taxi Drivers in Parakou, Benin, in 2021

Background and Objective: HIV infection is a major global Public Health threat worldwide, particularly in Sub-Saharan Africa of which Benin. The level of knowledge determines the attitudes and behaviors of the populations towards this infection. The study objective was to assess knowledge, attitudes and practices related to HIV infection among motorbike taxi drivers (MTD) in Parakou in 2021. Methods: This was a descriptive cross-sectional study targeting MTD in Parakou in 2021. Participants were selected by cluster sampling. Pretested Digitized questionnaire using KoboCollect@ applicationserved as a data collection tool. Knowledge, attitudes and practices variable were treated on a score scale. A knowledge score was considered to reflect a good knowledge of HIV if at least two-thirds of the knowledge statements had been correctly answered provided the subject recognized the sexual route as one of modes of HIV transmission, identified at least one preventive measure and meant the incurability of the disease. Quantitative and qualitative variables were appropriately described using the EPI Info 7.1.3.3 software. The participant was classified at positive attitude/practice for HIV prevention, when it has a score of at least 80% and suggests a good preventive measure face a risk of exposure to HIV. Results: A total of 374 subjects were recruited into the study. The mean age was 31.51 ± 7.76 years. Most participants (86.06%) had good knowledge of condom use as an HIV prevention method. The sources of information mentioned were mainly the media (77.07%), relatives or friends (63.38%), and field-workers from non-governmental organizations (37.26%). Routine HIV testing was 50.53%. Among participants, 76.10% reported at least two different sexual partners. Condom use was 59.18 % during the casual sexual intercourse. Within the client-provider relationship with female sex workers, 33.17% had had sexual intercourse with them. The sexual route was the most cited (92.99%), and 90.23% stated that HIV infection can be stabilized by medication in a health structure. Conclusion: The level of knowledge of motorbike taxi drivers in Parakou does not match their behavior with regard to HIV prevention. Appropriate strategies are needed to develop prevention skills in this population. To effectively comb at HIV, it will be necessary to strengthen the targeted HIV preventive interventions at key and bridge populations including motorbike taxi drivers in Benin.

A Framework for Driver DrowsinessMonitoring Using a Convolutional Neural Network and the Internet of Things

One of the major causes of road accidents is sleepy drivers.Such accidents typically result in fatalities and financial losses and disadvantage other road users.Numerous studies have been conducted to identify the driver’s sleepiness and integrate it into a warning system.Most studies have examined how the mouth and eyelids move.However,this limits the system’s ability to identify drowsiness traits.Therefore,this study designed an Accident Detection Framework(RPK)that could be used to reduce road accidents due to sleepiness and detect the location of accidents.The drowsiness detectionmodel used three facial parameters:Yawning,closed eyes(blinking),and an upright head position.This model used a Convolutional Neural Network(CNN)consisting of two phases.The initial phase involves video processing and facial landmark coordinate detection.The second phase involves developing the extraction of frame-based features using normalization methods.All these phases used OpenCV and TensorFlow.The dataset contained 5017 images with 874 open eyes images,850 closed eyes images,723 open-mouth images,725 closed-mouth images,761 sleepy-head images,and 1084 non-sleepy head images.The dataset of 5017 images was divided into the training set with 4505 images and the testing set with 512 images,with a ratio of 90:10.The results showed that the RPK design could detect sleepiness by using deep learning techniques with high accuracy on all three parameters;namely 98%for eye blinking,96%for mouth yawning,and 97%for head movement.Overall,the test results have provided an overview of how the developed RPK prototype can accurately identify drowsy drivers.These findings will have a significant impact on the improvement of road users’safety and mobility.

Quantifying the Impact of In-Cab Alerts on Truck Speed Reductions in Ohio

In-cab alerts warn commercial vehicle drivers of upcoming roadway incidents, slowdowns and work zone construction activities. This paper reports on a study evaluating the driver response to in-cab alerts in Ohio. Driver response was evaluated by measuring the statistical trends of vehicle speeds after the in-cab alerts were received. Vehicle speeds pre and post in-cab alert were collected over a 47 day period in the fall of 2023 for trucks traveling on interstate roadways in Ohio. Results show that approximately 22% of drivers receiving Dangerous Slowdown alerts had reduced their speeds by at least 5 mph 30 seconds after receiving such an alert. Segmenting this analysis by speed found that of vehicles traveling at or above 70 mph at the time of alerting, 26% reduced speeds by at least 5 mph. These speed reductions suggest drivers taking actional measures after receiving alerts. Future studies will involve further analysis on the impact of the types of alerts shown, roadway characteristics and overall traffic conditions on truck speeds passing through work zones.

Seroprevalence Survey of HIV and Hepatitis B Virus and Behavioral Characteristics among Heavy Truck Drivers along Port Sudan-Khartoum Highways

The prevalence of human immunodeficiency virus (AIDS) and hepatitis B virus among heavy truck drivers and their assistants has been well documented globally in correlation with their behavioral characteristics. The present study aimed to screen for human immunodeficiency virus (HIV), hepatitis B virus (HBV), and behavioral characteristics among heavy truck drivers in Port Sudan. A cross-sectional study was conducted on 274 heavy truck drivers and their assistants who used the highway Port Sudan-Khartoum in Port Sudan city during 2019-2021. Data on behavioral characteristics and substance use habits were collected using a structured questionnaire, and an ELISA test was used to screen for HIV and HBV infections in the study participants. The chi-square test, odds ratio, and confidence intervals were used to find the association between behavioral characteristics and seropositive HIV/HBV. Of the 274 enrolled participants, the seroprevalence rates of HIV were 2.7% and HBV was 23.7%. Ninety-four (34.3%) of them had a history of high-risk sexual behavior outside of marriage;only two (0.7%) used condoms;14.2% of participants reported alcohol use;and 1.1% reported drug use. Univariate analysis revealed that having a sex history outside of marriage with ≥1 sex partner and never using a condom with a spouse or casual partner were significant risk factors for HIV and HBV among drivers. Fortunately, we found that most of the drivers reported low alcohol and drug use. Concerning this study, the seroprevalence of HIV and HBV is highly associated with a history of having sex outside of marriage and sexual behavior among truck drivers and assistances. Additional studies are needed to further investigate other STIs and behavioral characteristics associated with factors in truck drivers/assistance in different truck stop regions in Sudan.

BOB(Bosa On Board)设计研究

采用bosa on board的方式,将光通信电路直接铺设在PCB板上,替代传统的光模块独立器件,实现GPON/EPON产品的低成本高性能。

Statistical Analysis of Accident Proneness of Drivers

A mathematical model describing the risks of road accidents has been built on the basis of statistical data of drivers’ accident rate. It has been revealed that drivers can be divided by the degree of their accident proneness into four categories with sharply differing probabilities of road accidents. It has been shown that there is a possibility of classification of drivers in accordance with specified categories.

Sonam Wangta:A Driver on the Worlds Highest Train Line

In midsummer,the banks of the Yarlung Zangbo River were covered in lush green.Bathed in the bright plateau sunshine,the Fuxing bullet train ran through the mountains and valleys like a long green dragon.In the cab,Sonam Wangdrak was holding the brake handle,his eyes fixed on the horizon ahead and his handsome face full of confidence.

Analysis of Traffic Accidents in Vietnam

Understanding the causes and solutions of road traffic accidents is important for developing road and action plans in a country. In Vietnam, awareness of traffic participants is the main cause of serious traffic accidents. In recent years, the number of road traffic accidents in Tuyen Quang province with deaths has decreased, but the number of accidents has increased significantly. The article uses data on traffic accidents in Tuyen Quang over the (2016-2023) has been analytically reviewed. From there, analyze accident characteristics and causes of traffic accidents in Tuyen Quang province, and propose solutions to improve traffic safety in Tuyen Quang, Vietnam. The findings can be information for managers and researchers interested in studying the province of Tuyen Quang, Vietnam road traffic safety. Additionally, the findings have led the government to achieve national targets in reducing the number of accidents and serious injuries.

Research trends in methods for controlling macro-micro motion platforms

With ongoing economic,scientific,and technological developments,the electronic devices used in daily lives are developing toward precision and miniaturization,and so the demand for high-precision manufacturing machinery is expanding.The most important piece of equipment in modern high-precision manufacturing is the macro-micro motion platform(M3P),which offers high speed,precision,and efficiency and has macro-micro motion coupling characteristics due to its mechanical design and composition of its driving components.Therefore,the design of the control system is crucial for the overall precision of the platform;conventional proportional–integral–derivative control cannot meet the system requirements,and so M3Ps are the subject of a growing range of modern control strategies.This paper begins by describing the development history of M3Ps,followed by their platform structure and motion control system components,and then in-depth assessments of the macro,micro,and macro-micro control systems.In addition to examining the advantages and disadvantages of current macro-micro motion control,recent technological breakthroughs are noted.Finally,based on existing problems,future directions for M3P control systems are given,and the present conclusions offer guidelines for future work on M3Ps.

Whale Optimization Algorithm-Based Deep Learning Model for Driver Identification in Intelligent Transport Systems

Driver identification in intelligent transport systems has immense demand,considering the safety and convenience of traveling in a vehicle.The rapid growth of driver assistance systems(DAS)and driver identification system propels the need for understanding the root causes of automobile accidents.Also,in the case of insurance,it is necessary to track the number of drivers who commonly drive a car in terms of insurance pricing.It is observed that drivers with frequent records of paying“fines”are compelled to pay higher insurance payments than drivers without any penalty records.Thus driver identification act as an important information source for the intelligent transport system.This study focuses on a similar objective to implement a machine learning-based approach for driver identification.Raw data is collected from in-vehicle sensors using the controller area network(CAN)and then converted to binary form using a one-hot encoding technique.Then,the transformed data is dimensionally reduced using the Principal Component Analysis(PCA)technique,and further optimal parameters from the dataset are selected using Whale Optimization Algorithm(WOA).The most relevant features are selected and then fed into a Convolutional Neural Network(CNN)model.The proposed model is evaluated against four different use cases of driver behavior.The results show that the best prediction accuracy is achieved in the case of drivers without glasses.The proposed model yielded optimal accuracy when evaluated against the K-Nearest Neighbors(KNN)and Support Vector Machines(SVM)models with and without using dimensionality reduction approaches.