Journal of Science and Transport Technology

Violation Detection on Traffic Light Area Based on Image Classification Using Dimensionality Reduction and Deep Learning

2024-07-12T09:22:59+00:00

The smart city concept is closely related to efficient traffic management, especially using technology to improve safety and smooth traffic flow, including at traffic lights. In this context, traffic light integration into a smart city system uses sensors, surveillance cameras, and intelligent algorithms to adaptively manage traffic based on vehicle volume and real-time traffic conditions. The CCTV already installed in several junction road at Bandung City, Indonesia. Image classification using deep learning is an essential and rapidly growing application in artificial intelligence. When the number of images in the dataset collected from CCTV gets larger, the total dimension of the data will also increase significantly. The large dimension of image datasets makes the data analysis and processing process more complex and requires extensive computational resources. To reduce computational resource, dimensionality reduction using Principal Component Analysis (PCA) can handle high-dimensional data. PCA is used to process and analyze image datasets efficiently. We proposed combination of deep learning and PCA to solve classification problem to high dimensional traffic image dataset. Experimental result showed that the non-PCA deep learning model achieved an accuracy of 73.11%, while the deep learning model with PCA achieved an accuracy of 72.73%. In other hand, the combination of deep learning and PCA showed a much shorter training time of only 2.95 seconds compared to the non-PCA deep learning model, which took 80.43 seconds.

Engineering Evaluation of Freshwater Lake Coastal Sand Dunes: A Study of Sandbanks Provincial Park, Kingston, Canada

2024-10-21T03:01:35+00:00

This study provides a comprehensive engineering evaluation of the freshwater coastal sand dunes at Sandbanks Provincial Park, located on the southern edge of Prince Edward County, Kingston, Ontario, Canada. Sandbanks is renowned for its extensive and dynamic sand dune system, which plays a crucial role in coastal management by absorbing wave energy, mitigating storm surges, and preventing sand deposition on infrastructure. Shaped by historical glacial activities, wind, and wave action, these dunes are critical for stabilizing the beach environment, controlling wind erosion, and supporting diverse plant and animal communities. This research uniquely combines historical data with recent field studies to offer new insights into the engineering properties, geomorphological processes, and ecological dynamics that govern the formation, stability, and resilience of the dunes. The study addresses contemporary challenges such as climate change, human impact, and erosion, and proposes actionable conservation strategies that balance ecological preservation with practical land management. While focused on a specific section of Ontario’s coastal dunes, the findings contribute to a deeper understanding of coastal dune systems more broadly, offering valuable guidance for their long-term sustainability and management across similar environments.

Comparative Study on the Probabilistic Safety of Truss Structures Designed Using U.S. and Vietnamese Codes

2024-12-03T02:43:17+00:00

This study evaluates and compares the reliability of a truss designed according to the Vietnamese TCVN 5575-2012 and the American AISC 360-16 steel design codes. The same truss configuration and applied loads are considered, with sections designed according to each standard. Their probabilistic safety levels are then evaluated to provide deeper insights into the differences between the design codes. Results indicate that, under identical loading, trusses designed with AISC are lighter than those designed with TCVN, as TCVN requires larger sections for compression members. Reliability indexes (RIs) for tension behavior are similar between codes; however, TCVN yields higher RIs for buckling, indicating a conservative approach for compression members compared to AISC. Although TCVN does not specify a target RI, its deterministic and probabilistic safety levels exceed those of AISC, suggesting a target RI above AISC’s 3.0. Consequently, TCVN-based designs generally involve higher costs, emphasizing the importance of understanding safety implications in code selection. Finally, the conservative results from TCVN are examined through equivalent safety factors, providing insights into its design assumptions.

An analytical approach for nonlinear thermo-mechanical buckling behavior of Porous FG-GPLRC circular plates and spherical caps

2025-02-28T08:35:32+00:00

This paper presents an analytical approach for the nonlinear thermo-mechanical stability analysis of porous functionally graded graphene platelets reinforced composite (Pr-FG-GPLRC) circular plates (CPs) and shallow spherical caps (SCs) resting on nonlinear elastic foundation. Pr-FG-GPLRC is considered to have three different types of foam distribution. The applied load includes uniform external pressure and uniform thermal loads. The governing formulations are established by the first-order shear deformation theory (FSDT) and the von Kármán geometrical nonlinearities. The deformation compatibility equations are established and the stress function is introduced to reduce the equilibrium equation system into three equations with three function variables (deflection, rotation, and stress function). The chosen solution form approximately satisfies the clamped boundary conditions and the Ritz energy method is applied to obtain the equilibrium equation system in nonlinear algebraic form. The explicit expressions of buckling loads and thermo-mechanical post-buckling curves can be obtained. Numerical investigations are performed to discuss the remarkable effects of nonlinear foundation stiffness, material, and geometrical properties imperfection on the nonlinear thermo-mechanical buckling behavior and load-carrying capacity of CPs and SCs.

Enhancing construction safety management efficiency with AI-Powered real-time helmet detection

2025-03-28T08:20:08+00:00

To address the critical need for improved safety management in the construction industry, an AI-powered system for real-time safety helmet detection was developed in this study. A comprehensive dataset of 19,456 images was compiled and the YOLO object detection algorithm was employed to accurately identify workers who are not wearing helmets, thereby enabling prompt intervention and reducing the risk of head injuries on construction sites. The model's performance was further optimized through the application of transfer learning techniques, and rigorous evaluation procedures were conducted, which resulted in the achievement of 89% mAP, 89.6% precision, and 83.8% recall. This automated system is designed to improve safety management practices in the construction industry by automating the monitoring process, enabling real-time detection of non-compliance, and facilitating timely interventions. These features aim to reduce workplace accidents and promote a proactive approach to safety management. The study provides a practical tool for construction management professionals to enhance worker safety and support the adoption of preventive safety measures on construction sites.

Exploring artificial intelligence applications in construction and demolition waste management: a review of existing literature

2025-02-25T09:43:39+00:00

This study presents a comprehensive analysis of artificial intelligence (AI) applications in construction and demolition waste management (CDWM), examining current trends, limitations, and opportunities for enhanced sustainability. Through a systematic literature review and bibliometric analysis across multiple academic databases, the research identifies eight major subfields where AI significantly impacts CDWM processes, particularly in planning, design, forecasting, and monitoring activities. The findings reveal that while AI demonstrates considerable potential in various aspects of waste management, its application in waste collection remains constrained by dependence on physical machinery. The study highlights the versatility of machine learning and natural language processing technologies, while emphasising the need for expanded research into innovative recycling approaches to maximise material reuse. Despite limitations regarding literature selection bias and context-specific generalisability, this research provides valuable insights for practitioners and policymakers by illustrating how AI technologies can improve operational efficiency, minimise environmental impact, and enhance resource recovery in construction projects. The study's unique contribution lies in its comprehensive review of AI applications in CDWM, addressing research gaps while proposing new perspectives on optimising waste management practices through emerging technologies. This work serves as a foundation for future research, particularly in exploring AI applications for recycling processes and examining their implications for sustainable waste management practices across all operational stages.

Flexural performance of prestressed concrete I-shaped bridge girders exposed to hydrocarbon fire

2025-03-20T03:16:23+00:00

This study examines the flexural performance of identical I-shaped bridge girders with different prestressing arrangements and methods under fire conditions. A finite element model was developed to simulate the temperature evolution in the bridge girders exposed to fire. Temperature data from the model were used to assess the degradation in the ultimate strength of prestressing strands, as well as the reduction in flexural strength and the subsequent rating factor of both girders over time. The results reveal that the flexural capacity of the post-tensioned girder remained relatively stable for the first 90 minutes of fire exposure but gradually decreased thereafter. In contrast, the flexural strength of the pre-tensioned girder degraded more rapidly than that of the post-tensioned girder. Specifically, the pre-tensioned girder lost up to 51% of its initial flexural capacity, while the post-tensioned girder only lost 26% after four hours of exposure to a hydrocarbon fire. Additionally, the pre-tensioned girder lost its ability to carry the design live load after 100 minutes of fire exposure, whereas the post-tensioned girder retained this capacity for 190 minutes. The findings highlight that the prestressing arrangement is a crucial factor influencing the degradation of flexural capacity in prestressed girders under fire. Pre-tensioned girders, with strands located near the soffits, are significantly more vulnerable to strength loss compared to post-tensioned girders, which have cables positioned farther from the soffit. Additionally, fire intensity plays a critical role in determining the extent of degradation in the flexural strength of prestressed concrete bridge girders under fire conditions.

Cable tension estimation by Rayleigh’s method considering restraint boundary conditions

2025-03-27T09:48:24+00:00

This paper introduces a method for accurately estimating cable tension, combining the energy approach with the cable’s mode shape. The method simultaneously accounts for the bending rigidity of the cable and the rotational stiffness at both ends. Rayleigh’s energy-based method is applied to analytically derive a formula for cable tension, while the mode shape is approximated using a nonlinear regression analysis algorithm. The accuracy of the method is validated through comparison with available experimental data. The approach is applied to the An Dong Extradosed Bridge in Vietnam, demonstrating its effectiveness in evaluating cable forces for similar bridge structures. Notably, a significant difference of up to 13.13% in cable forces is observed when considering the rotational stiffness at cable ends, highlighting the importance of this factor in structural analysis.