Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users—pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups—for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.
Maritime management is a crucial concern for movable bridge safety. Irregular management of water vehicles near movable bridges may lead to collision among ships and bridge infrastructures, causing massive losses of life and property. The paper presents a theoretical framework and simulation of an intelligent water vehicle management system for movable bridges corresponding to vehicle traffic responses. The water regime around the bridge is considered in virtually separated domains to estimate the desired safety actions based on the position of the approaching ships. An emergency clash avoidance control system is represented to prevent ship-infrastructure collision and ensure transportation safety. In addition, a simulation platform is developed specifically adaptable for movable bridge maritime and dynamic traffic management. The proposed theory is experimented using the simulation platform for different ship speeds and bridge-vehicle traffic volumes. Based on analyzing the velocity profile of approaching ships at different incidents, the bridge is found incapable of evacuating vehicles and unable to open promptly in case of speeding ships and high traffic density of vehicles on the bridge. Computational results show that the emergency control system is effective in reducing ship speed and prevent certain collisions. Lastly, the transportation policy for the newly proposed maritime management system is validated by real-world implementation in movable bridges across the world.
This paper presents a detailed design of an on-grid PV system that meets the electrical needs of a typical domestic building in the southern corner (i.e. Khulna) of Bangladesh. The system comprising of the photovoltaic array to capture solar energy, a power converter to change over between AC and DC, grid connection and lead acid battery to store energy. The modelling is completed by assessing the required load, choosing and deciding the proper specifications of the components associated with the system. Different factors, for example, the geographic area, atmospheric condition, solar irradiance and load consumption upon which the whole work depends are all considered. The cost optimization of the system is performed as per the system’s net present cost, cost of energy, operating expense and initial capital. Additionally, an efficient algorithm to manage the system energy along with power flow is proposed. The techno-economic analysis of the proposed system is performed by using HOMER simulation software. Simulated results indicate that the proposed model meet the load demand and show tasteful execution.
This paper focuses on research works of control engineering field and aims at impenetrable security system especially in case of medication, jewelry, documents & others valuable items and mandatorily in the higher intelligence agency. Here, a developed security system with automatic sensing is introduced by the use of both Radio frequency identification (RFID) card tagging system and fingerprint sensing biometric security system to maintain the valid access of a person to a secured place. RFID reader and fingerprint sensing device work as a locker of the security and RFID tag and a validly ratified finger is considered as the key of the locker. In case of access granted entity, door bar gets opened with a servo mechanism system connected with door bar. On the contrary, no action is taken as cavalcade if the entity is considered invalid in the sensing system. These knock out the necessity for keeping track of keys or remembering a combination of password or pin. A prototype of the security system is also designed and the performance of it is tested. The satisfactory results of its performance show the validity of the system and indicate a better solution for the future security system.
Trajectory movement labelling is an important pre-stage for predicting connected vehicle (CV) movement at intersections. Drivers' movement prediction and warning at intersections ensure advanced transportation safety and researchers use machine learning-based data-driven approaches to implement these technologies. However, prediction of drivers' movements at intersections requires labelling the train and test dataset accurately with different vehicle movements at intersections to evaluate the performance of the prediction model by comparing the actual and predicted intersection movements. Moreover, due to GPS detection error or missing co-operative awareness messages (CAM), the data resides with many abnormal trajectories which are unable to be matched with regular straight or any turning movements. Especially for big data with million trajectories, it is tedious to label the movements manually.To solve this problem, we have created an automated trajectory movement classification technique using a dual approach of map matching technique and deep transfer learning modelling. Data of connected vehicle trajectory information is taken from the Ipswich Connected Vehicle Pilot (ICVP) Project, which is one of the largest connected vehicle pilots within a naturalistic driving environment in Australia. Map matching approach is performed as initial labelling by analysing the origin and destination of the vehicle CAM messages at intersections and then was converted as image datasets of 19202 samples. The map matching error and abnormal trajectories are identified by visual inspection. With properly labelled 9496 training images, 10 transfer learning models are built and tested through the remaining 9706 testing images. The maximum testing accuracy (99.73%) is achieved from the Densenet169 model, and the result shows satisfactory accuracy for individual classes: straight (99.85%), turn left (99.59), turn right (99.25), u-turn (100%), abnormal (98.63%). This model becomes a routine tool that is used daily to automatically classify thousands of trajectory movements of the C-ITS data in the ICVP project.
In this paper, a door locking system with some remarkable features is proposed which makes the locking or unlocking of a door more reliable to the user than the conventional system. Robust security access with accurate detection system is provided here. It's a global ranged operation process that can be operated by simple mobile phone through short message service (SMS) transferring operation from any corner of the world where mobile network is available. A smooth and durable locking mechanism is provided and the inscrutable door moving control device is used for the efficient operation of controlling the door. This developed system provides a notification to the user if any person is intended to pass the door. The system also has the ability to provide information about the current condition of the door by sending simple text messages. Also, the user will be able to operate the system with more than one subscriber identity module (SIM) card. Most advantageously, this device is proposed with lowest cost estimation benefit. Finally, the performance of the designed system is analyzed by performing some real-time operation of it and found satisfactory performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.