A Novel Green IoT-Based Pay-As-You-Go Smart Parking System

The better management of resources and the potential improvement in traffic congestion via reducing the orbiting time for parking spaces is crucial in a smart city, particularly those with an uneven correlation between the increase in vehicles and infrastructure. This paper proposes and analyses a novel green IoT-based Pay-As-You-Go (PAYG) smart parking system by utilizing unused garage parking spaces. The article also presents an intelligent system that offers the most favorable prices to its users by matching private garages’ pricing portfolio with a garage’s current demand. Malta, the world’s fourth-most densely populated country, is considered as a case of a smart city for the implementation of the proposed approach. The results obtained confirm that apart from having a high potential system in such countries, the pricing generated correctly forecasts the demand for a particular garage at a specific time of the day and year. The proposed PAYG smart parking system can effectively contribute to the macro solution to traffic congestion by encouraging potential users to use the system’s services and reducing the orbiting time for parking.     

Autonomous Parking-Lots Detection with Multi-Sensor Data Fusion Using Machine Deep Learning Techniques

The rapid development and progress in deep machine-learning techniques have become a key factor in solving the future challenges of humanity. Vision-based target detection and object classification have been improved due to the development of deep learning algorithms. Data fusion in autonomous driving is a fact and a prerequisite task of data preprocessing from multi-sensors that provide a precise, well-engineered, and complete detection of objects, scene or events. The target of the current study is to develop an in-vehicle information system to prevent or at least mitigate traffic issues related to parking detection and traffic congestion detection. In this study we examined to solve these problems described by (1) extracting region-of-interest in the images (2) vehicle detection based on instance segmentation, and (3) building deep learning model based on the key features obtained from input parking images. We build a deep machine learning algorithm that enables collecting real video-camera feeds from vision sensors and predicting free parking spaces. Image augmentation techniques were performed using edge detection, cropping, refined by rotating, thresholding, resizing, or color augment to predict the region of bounding boxes. A deep convolutional neural network F-MTCNN model is proposed that simultaneously capable for compiling, training, validating and testing on parking video frames through video-camera. The results of proposed model employing on publicly available PK-Lot parking dataset and the optimized model achieved a relatively higher accuracy 97.6% than previous reported methodologies. Moreover, this article presents mathematical and simulation results using state-of-the-art deep learning technologies for smart parking space detection. The results are verified using Python, TensorFlow, OpenCV computer simulation frameworks.     

我国城市地下停车场发展现状及修建技术研究

目前,"停车难、乱停车"现象不断加剧,严重影响了城市环境与交通秩序,而通过挖潜、改造、新建等方式大力推进城市地下停车场建设无疑是解决"停车难、乱停车"现象最为有效的办法。本文主要通过对国内外城市地下停车场建设典型案例进行调研,系统分析我国地下停车场建设管理、规划设计及施工方面存在的问题,提出停车场的规划与设计方案、运营模式和投融资模式的建设意见,为我国解决城市交通拥堵和城市地下停车场的综合规划与建设提供参考。     

Spatial econometrics models for congestion prediction with in-vehicle route guidance

The congestion dependence relationship among links using microsimulation is explored, based on data from a real road network. The work is motivated by recent innovations to improve the reliability of Dynamic Route Guidance (DRG) systems. The reliability of DRG systems can be significantly enhanced by adding a function to predict the congestion in the road network. The application of spatial econometrics modelling to congestion prediction is also explored, by using historical traffic message channel (TMC) data stored in the vehicle navigation unit. The nature of TMC data is in the form of a time series of geo-referenced congestion warning messages, which is generally collected from various traffic sources. The prediction of future congestion could be based on the previous year of TMC data. Synthetic TMC data generated by microscopic traffic simulation for the network of Coventry are used in this study. The feasibility of using spatial econometrics modelling techniques to predict congestion is explored. The results are presented at the end.     

A Neuro-Fuzzy Approach to Road Traffic Congestion Prediction

The fast-paced growth of artificial intelligence applications provides unparalleled opportunities to improve the efficiency of various systems. Such as the transportation sector faces many obstacles following the implementation and integration of different vehicular and environmental aspects worldwide. Traffic congestion is among the major issues in this regard which demands serious attention due to the rapid growth in the number of vehicles on the road. To address this overwhelming problem, in this article, a cloud-based intelligent road traffic congestion prediction model is proposed that is empowered with a hybrid Neuro-Fuzzy approach. The aim of the study is to reduce the delay in the queues, the vehicles experience at different road junctions across the city. The proposed model also intended to help the automated traffic control systems by minimizing the congestion particularly in a smart city environment where observational data is obtained from various implanted Internet of Things (IoT) sensors across the road. After due preprocessing over the cloud server, the proposed approach makes use of this data by incorporating the neuro-fuzzy engine. Consequently, it possesses a high level of accuracy by means of intelligent decision making with minimum error rate. Simulation results reveal the accuracy of the proposed model as 98.72% during the validation phase in contrast to the highest accuracies achieved by state-of-the-art techniques in the literature such as 90.6%, 95.84%, 97.56% and 98.03%, respectively. As far as the training phase analysis is concerned, the proposed scheme exhibits 99.214% accuracy. The proposed prediction model is a potential contribution towards smart cities environment.     

Deep learning and machine learning-based early survival predictions of glioblastoma patients using pre-operative three-dimensional brain magnetic resonance imaging modalities

To propose and implement an automated machine learning (ML) based methodology to predict the overall survival of glioblastoma multiforme (GBM) patients. In the proposed methodology, we used deep learning (DL) based 3D U-shaped Convolutional Neural Network inspired encoder-decoder architecture to segment the brain tumor. Further, feature extraction was performed on these segmented and raw magnetic resonance imaging (MRI) scans using a pre-trained 2D residual neural network. The dimension-reduced principal components were integrated with clinical data and the handcrafted features of tumor subregions to compare the performance of regression-based automated ML techniques. Through the proposed methodology, we achieved the mean squared error (MSE) of 87 067.328, median squared error of 30 915.66, and a SpearmanR correlation of 0.326 for survival prediction (SP) with the validation set of Multimodal Brain Tumor Segmentation 2020 dataset. These results made the MSE far better than the existing automated techniques for the same patients. Automated SP of GBM patients is a crucial topic with its relevance in clinical use. The results proved that DL-based feature extraction using 2D pre-trained networks is better than many heavily trained 3D and 2D prediction models from scratch. The ensembled approach has produced better results than single models. The most crucial feature affecting GBM patients' survival is the patient's age, as per the feature importance plots presented in this work. The most critical MRI modality for SP of GBM patients is the T2 fluid attenuated inversion recovery, as evident from the feature importance plots.     

An Optimal Classification Model for Rice Plant Disease Detection

Internet of Things (IoT) paves a new direction in the domain of smart farming and precision agriculture. Smart farming is an upgraded version of agriculture which is aimed at improving the cultivation practices and yield to a certain extent. In smart farming, IoT devices are linked among one another with new technologies to improve the agricultural practices. Smart farming makes use of IoT devices and contributes in effective decision making. Rice is the major food source in most of the countries. So, it becomes inevitable to detect rice plant diseases during early stages with the help of automated tools and IoT devices. The development and application of Deep Learning (DL) models in agriculture offers a way for early detection of rice diseases and increase the yield and profit. This study presents a new Convolutional Neural Network-based inception with ResNset v2 model and Optimal Weighted Extreme Learning Machine (CNNIR-OWELM)-based rice plant disease diagnosis and classification model in smart farming environment. The proposed CNNIR-OWELM method involves a set of IoT devices which capture the images of rice plants and transmit it to cloud server via internet. The CNNIR-OWELM method uses histogram segmentation technique to determine the affected regions in rice plant image. In addition, a DL-based inception with ResNet v2 model is engaged to extract the features. Besides, in OWELM, the Weighted Extreme Learning Machine (WELM), optimized by Flower Pollination Algorithm (FPA), is employed for classification purpose. The FPA is incorporated into WELM to determine the optimal parameters such as regularization coefficient C and kernel . The outcome of the presented model was validated against a benchmark image dataset and the results were compared with one another. The simulation results inferred that the presented model effectively diagnosed the disease with high sensitivity of 0.905, specificity of 0.961, and accuracy of 0.942.     

城市停车政策研究

介绍了停车政策制定应坚持的原则，以武威市为例介绍了两种停车供应的模式，在制定停车政策的时候应将停车需求与城市土地开发相结合，合理增加停车泊位数量。通过制定合理的停车收费标准，使交通的发展顺应城市的发展。     

Traffic Management in Internet of Vehicles Using Improved Ant Colony Optimization

The Internet of Vehicles (IoV) is a networking paradigm related to the intercommunication of vehicles using a network. In a dynamic network, one of the key challenges in IoV is traffic management under increasing vehicles to avoid congestion. Therefore, optimal path selection to route traffic between the origin and destination is vital. This research proposed a realistic strategy to reduce traffic management service response time by enabling real-time content distribution in IoV systems using heterogeneous network access. Firstly, this work proposed a novel use of the Ant Colony Optimization (ACO) algorithm and formulated the path planning optimization problem as an Integer Linear Program (ILP). This integrates the future estimation metric to predict the future arrivals of the vehicles, searching the optimal routes. Considering the mobile nature of IOV, fuzzy logic is used for congestion level estimation along with the ACO to determine the optimal path. The model results indicate that the suggested scheme outperforms the existing state-of-the-art methods by identifying the shortest and most cost-effective path. Thus, this work strongly supports its use in applications having stringent Quality of Service (QoS) requirements for the vehicles.     

Fee collection plan for plug-in electric vehicles charged in nonresidential parking lots with minimum hardware investment: a study of Asian megacities

This paper presents a fair and effective fee collection plan for owners of plug-in electric vehicles (PEVs) who charge their vehicles in nonresidential parking lots. The charging fee serves as a surcharge on the parking fee. From the parking lot administrator’s point of view, reducing hardware investment costs and increasing profit are two crucial issues when considering providing nonfree charging services in nonresidential parking lots. Drivers are concerned with fairness. The proposed method shows an advantageous balance between the two sides. This study also develops a method for fairly determining the suitable number of PEV spaces in a parking lot for vehicles with and without charging requirements.     

Artificial Intelligence Based Data Offloading Technique for Secure MEC Systems

Mobile edge computing (MEC) provides effective cloud services and functionality at the edge device, to improve the quality of service (QoS) of end users by offloading the high computation tasks. Currently, the introduction of deep learning (DL) and hardware technologies paves a method in detecting the current traffic status, data offloading, and cyberattacks in MEC. This study introduces an artificial intelligence with metaheuristic based data offloading technique for Secure MEC (AIMDO-SMEC) systems. The proposed AIMDO-SMEC technique incorporates an effective traffic prediction module using Siamese Neural Networks (SNN) to determine the traffic status in the MEC system. Also, an adaptive sampling cross entropy (ASCE) technique is utilized for data offloading in MEC systems. Moreover, the modified salp swarm algorithm (MSSA) with extreme gradient boosting (XGBoost) technique was implemented to identification and classification of cyberattack that exist in the MEC systems. For examining the enhanced outcomes of the AIMDO-SMEC technique, a comprehensive experimental analysis is carried out and the results demonstrated the enhanced outcomes of the AIMDO-SMEC technique with the minimal completion time of tasks (CTT) of 0.680.     

Travel time prediction under heterogeneous traffic conditions using global positioning system data from buses

Travel time information is a vital component of many intelligent transportation systems (ITS) applications. In recent years, the number of vehicles in India has increased tremendously, leading to severe traffic congestion and pollution in urban areas, particularly during peak periods. A desirable strategy to deal with such issues is to shift more people from personal vehicles to public transport by providing better service (comfort, convenience and so on). In this context, advanced public transportation systems (APTS) are one of the most important ITS applications, which can significantly improve the traffic situation in India. One such application will be to provide accurate information about bus arrivals to passengers, leading to reduced waiting times at bus stops. This needs a real-time data collection technique, a quick and reliable prediction technique to calculate the expected travel time based on real-time data and informing the passengers regarding the same. The scope of this study is to use global positioning system data collected from public transportation buses plying on urban roadways in the city of Chennai, India, to predict travel times under heterogeneous traffic conditions using an algorithm based on the Kalman filtering technique. The performance of the proposed algorithm is found to be promising and expected to be valuable in the development of APTS in India. The work presented here is one of the first attempts at real-time short-term prediction of travel time for ITS applications in Indian traffic conditions.     

基于AIS数据的航运物流港口调度优化研究

目的 针对宁波舟山港区的复杂航道水域与密集物流交通流,研究更加有效的调度方案,达成调度时间和等待时间最小化,即效率最大化。方法 分析宁波舟山港区航道的航行情况,提出交会处复杂航道水域存在的问题,以调度时间和等待时间最小为目标的多目标函数,建立复杂航道水域船舶调度模型。针对大量的船舶AIS数据,构建基于神经网络的航道水域调度模型,对不同类型、不同大小的船舶建立速度变化和船舶预测模型,实现对船舶调度状态的预测。设计以传统粒子群算法为基础的改良版船舶调度算法。结果 算法对模型求解表明,根据不同船长与间距可判别交通流拥挤程度进而对船舶进行调度。通过模型预测到可能产生拥挤,则应当选择小型船只走条帚门航道,大型船只走虾峙门航道,并且尽量避免产生拥堵。结论 使用该模型与算法可以有效地提升船舶调度效率,为复杂航运物流港口调度优化研究提供了一定理论基础。     

Management of traffic congestion in adaptive traffic signals using a novel classification-based approach

Traffic congestion is a critical problem which makes roads busy. Traffic congestion challenges traffic flow in urban areas. A growing urban area creates complex traffic problems in daily life. Congestion phenomena cannot be resolved only by applying physical constructs such as building bridges and motorways and increasing road capacity. It is necessary to build technological systems for transportation management to control the traffic phenomenon. In this article, a new idea is proposed to tackle traffic congestion with the aid of machine learning approaches. A new strategy based on a tree-like configuration (i.e. a decision-making model) is suggested to handle traffic congestion at intersections using adaptive traffic signals. Different traffic networks with different sizes, varying from nine to 400 intersections, are examined. Numerical results and discussion are presented to prove the efficiency and application of the proposed strategy to alleviate traffic congestion.     

Parking Availability Prediction with Coarse-Grained Human Mobility Data

Nowadays, the anticipation of parking-space demand is an instrumental service in order to reduce traffic congestion levels in urban spaces. The purpose of our work is to study, design and develop a parking-availability predictor that extracts the knowledge from human mobility data, based on the anonymized human displacements of an urban area, and also from weather conditions. Most of the existing solutions for this prediction take as contextual data the current road-traffic state defined at very high temporal or spatial resolution. However, access to this type of fine-grained location data is usually quite limited due to several economic or privacy-related restrictions. To overcome this limitation, our proposal uses urban areas that are defined at very low spatial and temporal resolution. We conducted several experiments using three Artificial Neural Networks: Multilayer Perceptron, Gated Recurrent Units and bidirectional Long Short Term Memory networks and we tested their suitability using different combinations of inputs. Several metrics are provided for the sake of comparison within our study and between other studies. The solution has been evaluated in a real-world testbed in the city of Murcia (Spain) integrating an open human-mobility dataset showing high accuracy. A MAPE between 4% and 10% was reported in horizons of 1 to 3 h.     

Big data driven jobs remaining time prediction in discrete manufacturing system: a deep learning-based approach

Implementing advanced big data (BD) analytic is significant for successful incorporation of artificial intelligence in manufacturing. With the widespread deployment of smart sensors and internet of things (IOT) in the job shop, there is an increasing need for handling manufacturing BD for predictive manufacturing. In this study, we conceive the jobs remaining time (JRT) prediction during manufacturing execution based on deep learning (DL) with production BD. We developed a procedure for JRT prediction that includes three parts: raw data collection, candidate dataset design and predictive modelling. First, the historical production data are collected by the widely deployed IOT in the job shop. Then, the candidate dataset is formalised to capture various contributory factors for JRT prediction. Further, a DL model named stacked sparse autoencoder (S-SAE) is constructed to learn representative features from high dimensional manufacturing BD to make robust and accurate JRT prediction. Our work represents the first DL model for the JRT prediction at run time during production. The proposed methods are applied in a large-scale job shop that is equipped with 44 machine tools and produces 13 types of parts. Lastly, the experimental results show the S-SAE model has higher accuracy than previous linear regression, back-propagation network, multi-layer network and deep belief network in JRT prediction.     

Percolation-based health management of complex traffic systems

System health management, which aims to ensure the safe and efficient operation of systems by reducing uncertain risks and cascading failures during their lifetime, is proposed for complex transportation systems and other critical infrastructures, especially under the background of the New Infrastructure Projects launched in China. Previous studies proposed numerous approaches to evaluate or improve traffic reliability or efficiency. Nevertheless, most existing studies neglected the core failure mechanism (i.e., spatio–temporal propagation of traffic congestion). In this article, we review existing studies on traffic reliability management and propose a health management framework covering the entire traffic congestion lifetime, from emergence, evolution to dissipation, based on the study of core failure modes with percolation theory. Aiming to be “reliable, invulnerable, resilient, potential, and active”, our proposed traffic health management framework includes modeling, evaluation, diagnosis, and improvement. Our proposed framework may shed light on traffic management for megacities and urban agglomerations around the world. This new approach may offer innovative insights for systems science and engineering in future intelligent infrastructure management.     

Optimal Deep Convolutional Neural Network for Vehicle Detection in Remote Sensing Images

Object detection (OD) in remote sensing images (RSI) acts as a vital part in numerous civilian and military application areas, like urban planning, geographic information system (GIS), and search and rescue functions. Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions. The latest advancements in deep learning (DL) approaches permit the design of effectual OD approaches. This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection (AEODCNN-VD) model on Remote Sensing Images. The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly. To detect vehicles, the presented AEODCNN-VD model employs single shot detector (SSD) with Inception network as a baseline model. In addition, Multiway Feature Pyramid Network (MFPN) is used for handling objects of varying sizes in RSIs. The features from the Inception model are passed into the MFPN for multiway and multiscale feature fusion. Finally, the fused features are passed into bounding box and class prediction networks. For enhancing the detection efficiency of the AEODCNN-VD approach, AEO based hyperparameter optimizer is used, which is stimulated by the energy transfer strategies such as production, consumption, and decomposition in an ecosystem. The performance validation of the presented method on benchmark datasets showed promising performance over recent DL models.     

Mitigating and Monitoring Smart City Using Internet of Things

The present trends in smart world reflects the extensive use of limited resources through information and communication technology. The limited resources like space, mobility, energy, etc., have been consumed rigorously towards creating optimized but smart instances. Thus, a new concept of IoT integrated smart city vision is yet to be proposed which includes a combination of systems like noise and air loss monitoring, web monitoring and fire detection systems, smart waste bin systems, etc., that have not been clearly addressed in the previous researches. This paper focuses on developing an effective system for possible monitoring of losses, traffic management, thus innovating smart city at large with digitalized and integrated systems and software for fast and effective implementations. In our proposed system, a real time data analysis is performed. These data are collected by various sensors to analyze different factors that are responsible for such losses. The proposed work is validated on a real case study.     

Energy-saving operation approaches for urban rail transit systems

With the accelerated urbanization in China, passenger demand has dramatically increased in large cities, and traffic congestion has become serious in recent years. Developing public urban rail transit systems is an indispensable approach to overcome these problems. However, the high energy consumption of daily operations is an emerging issue due to increased rail transit networks and passenger demands. Thus, reducing the energy consumption and operational cost by using advanced optimization methodologies is an urgent task for operation managers. This work systematically introduces energy-saving approaches for urban rail transit systems in three aspects, namely, train speed profile optimization, utilization of regenerative energy, and integrated optimization of train timetable and speed profile. Future research directions in this field are also proposed to meet increasing passenger demands and network-based urban rail transit systems.