Nowadays, the unmanned aerial vehicle (UAV) has a wide application in transportation. For instance, by leveraging it, we are able to perform accurate and real-time speed detection an IoT-based smart city. Although numerous estimation methods exist, most of them lack different situations scenarios. To fill gap, this paper introduces novel low-altitude detector system using UAVs for remote sensing applications cities, forging increase traffic safety security. aim, (1) have found best possible...

Session-based travel packages recommendation aims to predict users’ next click based on their current and historical sessions recorded by Online Travel Agencies (OTAs). Recently, an increasing number of studies attempted apply Graph Neural Networks (GNNs) the session-based obtained promising results. However, most them do not take full advantage explicit latent structure from attributes items, making learned representations items less effective difficult interpret. Moreover, they only...

In response to the challenges posed by low detection accuracy resulting from a wide range of surface defects, intricate textures, and minute defect targets in steel surfaces, this paper introduces an innovative model called DCS-YOLOv8, which builds upon foundation YOLOv8. Firstly, Real-ESRGAN (Real-Enhanced Super-Resolution GAN) is used enhance image resolution, effectively addressing challenge identifying minuscule defects within dataset. Furthermore, DCN (Deformable Convolutions) are...

Traffic flow prediction, one of the essential problems in traffic control and guidance systems, is still drawing increasing attention recent years with new methods tipped by success AI. In this paper, we propose a novel model, namely self-attention generative adversarial networks for time-series prediction (SATP-GAN). The SATP-GAN method based on (GAN) mechanisms, which are composed GAN module reinforcement learning (RL) module. module, apply layer to capture pattern data instead RNNs...

The Internet of Vehicles (IoV) is one important application scenarios for the development things. software-defined network (SDN) and fog computing could effectively improve IoV dynamics, which enables to achieve better performance by offloading some tasks node or cloud center. Current computation approaches mostly focus on resource utilization. However, energy-aware has not been adequately addressed, especially systems with many battery-powered roadside units (RSU) electric vehicles (EV). In...

Travel time prediction is critical for advanced traveler information systems (ATISs), which provides valuable enhancing the efficiency and effectiveness of urban transportation systems. However, in area bus trips, existing studies have focused on directly using structured data to predict travel a single trip. For state-of-the-art public systems, journey generally has multiple trips. Additionally, due lack study fusion, it even inadequate development underlying intelligent In this paper, we...

Recent advances in the steel industry have encountered challenges soliciting decision making solutions for quality control of products based on data mining techniques. In this paper, we present a prediction system encompassing with real-world as well comprehensive analysis results. The core process is cautiously designed regression problem, which then best handled by grouping various learning algorithms their massive resource historical production datasets. characteristics currently most...

With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative global light (MARL) and protocol edge computing architecture. MAAC algorithm combines with MARL, allowing...

Due to the low detection accuracy in steel surface defect and constraints of limited hardware resources, we propose an improved model for detection, named CBiF-FC-EFC-YOLOv8s (CFE-YOLOv8s), including CBS-BiFormer (CBiF) modules, Faster-C2f (FC) EMA-Faster-C2f (EFC) modules. Firstly, because potential information loss that convolutional neural networks (CNN) may encounter when dealing with miniature targets, CBiF combines CNN Transformer optimize local global features. Secondly, address...

Different from the existing train delay studies that had strived to explore sophisticated algorithms, this paper focuses on finding bound of improvements predicting multi-scenario delays with different machine learning methods. Motivated by observation deep methods failing improve prediction performance if occurs rarely, we present a novel augmented approach overall accuracy further. Our solution proposes rule-driven automation (RDA) method, including status labeling (DSL) algorithm, and...

With advanced artificial intelligence and deep learning techniques, a growing number of data sources are playing more critical roles in planning operating transportation services. The General Transit Feed Specification (GTFS), with standard open-source both static real-time formats, is being widely used public transport operation management. However, compared to other extensively studied such as smart card GPS trajectory data, the GTFS lacks proper investigation yet. Utilization challenging...

Nowadays a large amount of data is collected from sensor devices across the cyber-physical networks. Accurate and reliable primary delay predictions are essential for rail operations management planning. However, very few existing `big data' methods meet specific needs in railways. We propose comprehensive general data-driven Primary Delay Prediction System (PDPS) framework, which combines General Transit Feed Specification (GTFS), Critical Point Search (CPS), deep learning models to...

In many big cities, train delays are among the most complained-about events by public. Although various models have been proposed for delay prediction, prior studies on both primary and secondary prediction limited in number. Recent advances deep learning approaches increasing availability of data sources has created new opportunities more efficient accurate prediction. this study, we propose a hybrid solution integrating long short-term memory (LSTM) Critical Point Search (CPS). LSTM deals...

Computer Supported Cooperative Work (CSCW) in design is an essential facilitator for the development and implementation of smart cities, where modern cooperative transportation integrated mobility are highly demanded. Owing to greater availability different data sources, fusion problem intelligent systems (ITS) has been very challenging, machine learning modelling approaches promising offer important yet comprehensive solution. In this paper, we provide overview recent advances Mobility as a...

In this paper, we demonstrate how probabilistic model checking can be applied to a study of dependability analysis for Software-Defined Network with the PRISM tool checking.Based on checking, is modelled using large and complex Markov chains.In order improve reliability system, propose multi-controller architecture.The results designed system are verified visualized PRISM.

Traffic signal control is an essential and chal-lenging real-world problem, which aims to alleviate traffic congestion by coordinating vehicles' movements at road in-tersections. Deep reinforcement learning (DRL) combines deep neural networks (DNNs) with a framework of learning, promising method for adaptive in complex urban networks. Now, multi-agent (MARL) has the potential deal large scale. However, current systems still rely heavily on simplified rule- based methods practice. In this...

Traffic signal control (TSC) systems are one essential component in intelligent transport systems. However, relevant studies usually independent of the urban traffic simulation environment, collaborative TSC algorithms and communication. In this paper, we propose (1) an integrated cooperative Internet-of-Things architecture, namely General City Computing System (GCTCS), which simultaneously leverages algorithms, communication; (2) a general multi-agent reinforcement learning algorithm,...

The ongoing rapid growth of electricity over the past few decades greatly promotes necessity accurate load forecasting. However, despite a great number studies, forecasting is still an enormous challenge for its complexity. Recently, developments machine learning technologies in different research areas have demonstrated their advantages. General vector (GVM) new model, which has been proven very effective time series prediction. In this article, we apply it A detailed comparison with...