In order to accurately predict the short-term traffic flow, this paper presents a k-nearest neighbor (KNN) model. Short-term urban expressway flow prediction system based on k-NN is established in three aspects: historical database, search mechanism and algorithm parameters, predication plan. At first, preprocess original data then standardized effective avoid magnitude difference of sample improve accuracy. last, nonparametric regression model developed Matlab platform. Utilizing Shanghai...

Recently, a remote-sensing platform based on wireless interconnection of tiny ECG sensors called telecardiology sensor networks (TSN) provided promising approach to perform low-cost real-time cardiac patient monitoring at any time in community areas (such as elder nursing homes or hospitals). The contribution this research is the design practical TSN hardware/software for typical U.S. healthcare scenario large with many patients) data collections. On other hand, due radio broadcasting nature...

Vehicular ad hoc network (VANET) is an emerging technology for future on-the-road applications. However, because of the vehicle mobility uncertainty, temporal fragmentation influences communication connectivity. The roadside unit (RSU) has been considered to support Vehicle-to-Infrastructure (V2I) and increase vehicle-to-vehicle (V2V) Currently, it impossible deploy a large number RSUs at initial stage VAENT due expensive installation cost, authority limitation. This paper proposes...

Turnout is one key fundamental infrastructure in the railway signal system, which has great influence on safety of systems. Currently, turnout fault diagnoses are conducted manually China; engineers obliged to observe signals and make problem solving decisions. Thus, accuracies totally depend engineers’ experience although massive data produced real time by microcomputer-based monitoring This paper aims develop an intelligent diagnosis method for through Dynamic Time Warping (DTW). We...

Fault diagnosis for turnouts is crucial to the safety of railways. Existing studies on fault depend human experiences select reference curves and require type information beforehand. Therefore, we proposed a turnout method, named similarity function fuzzy c-means based two-stage algorithm detect faults identify types in real time. First, curve selected from current representing actions by K-means algorithm; then, called Fréchet distance used distinguish normal abnormal curves. Second, an...

A turnout, a device to guide tracks, is critical the safety of high-speed railways. Detecting gaps in switch machines can monitor turnout’s working performance. Existing gap-detection systems, however, barely perform at high accuracy and with low false alarm rate for long time due complex operating conditions machines. This study proposes an approach combining YOLO-based object detection architecture image processing algorithms, which YOLO deep learning network detection. First, detects...

The absolute positioning technique based on cross coding inductive loop wire has been recognized as the most suitable one to be applied in medium-low speed maglev train system, and measuring method which utilizes information collected from lowest address code line also a reliable way for such system. Consider that system is kind of wireless communication it sure affected interfered by complicated electromagnetic environment along track engineering application. Many related research have...

Accurate prediction of train delay recovery is critical for railway incident management and providing passengers with accurate journey time. In this paper, a two-stage model proposed to predict the time primary-delay based on real records from High-Speed Railway (HSR). Stage 1, two models are built study influence feature space framework accuracy buffer in each section or station. It found that explicitly inputting attribute features stations sections model, instead implicit simulation, will...

The vehicular ad hoc network (VANET) is an emerging and promising technology for on-road applications in road safety traffic efficiency. Temporal fragmentation may occur as a result of vehicle mobility uncertainties impact communication connectivity. roadside unit (RSU) has been considered to support vehicle-to-infrastructure (V2I) vehicle-to-vehicle (V2V) communication. Currently, it impossible deploy many RSUs at the initial stage VANET because high installation costs, authority...

Automatic license plate recognition (ALPR) has made great progress, yet is still challenged by various factors in the real world, such as blurred or occluded plates, skewed camera angles, bad weather, and so on. Therefore, we propose a method that uses cascade of object detection algorithms to accurately speedily recognize plates’ contents. In our method, YOLOv3-Tiny, an end-to-end network, used locate areas, YOLOv3 characters. According type position recognized characters, logical judgment...

Pay-how-you-drive (PHYD), which has already been recognized as the most promising differentiated commercial vehicle insurance product in usage based (UBI), can objectively analyze risk level of each insured by analyzing its driving style from raw data collected on-board diagnosis (OBD) module set up on it. Finding certain kinds styles, or modes for vehicles, is very important companies to get a rough understand types contract holders and do preliminary premium actuary work. Consider that...

IEEE 802.11p is an improved edition of the 802.11 protocol which serves specifically for vehicle to infrastructure (V2I) communication. It can realize a fast V2I wireless communication connection in urban road environment and ensure transportation safety reliability moving vehicles. However, effectiveness access based on highway still need be verified even if this could work complicated condition. In paper, simulation system built by NS-2 simulation, several key indices that reflect...

Medium-low speed maglev, as a form of urban rail transportation system, has already drawn lot attention from researchers and engineers for its advantages low noise, strong climbing ability flexible route planning. The train positioning matter fact, is very important part in operation control system (OCS) medium-low maglev transportation, it collects real-time position data, helps OCS to send correct dispatching order so ensure safety. Cross coding inductive loop wire, which suitable the...

Pay-how-you-drive (PHYD), which is a driving behavior related premium rate setting method in usage based insurance (UBI), has drawn widespread attention commercial vehicle as well internet-of-vehicle (IoV) industry nowadays, for it can not only help companies to fully master the information of all insured vehicles, but establish corresponding strategy according that well. However, implementation PHYD may undergo complicated process, stage with contract and traditional coexisted market will...

Pay-how-you-drive (PHYD), which is an advanced product form in usage based insurance (UBI) for vehicle, takes not only driving habit and behavior into consideration its actuary process, but geographical factors, sociological psychological even meteorological factors as well. PHYD supported by refinement analysis on raw data of insured vehicles, the very big algorithms, helps to recognize risk level each finding relationship between them. Even if studies determination have been done...

This paper has focused on the analysis of pedestrian flow characteristics for 3 different groups walking facilities including two-way escalator, ascending escalator combined with descending stairway, and stairway between platform concourse layer in an L-shaped interchange metro station. Data were collected by field observations to develop flow-density-speed relationship each group facility been done compare behavior various facilities. It shown that station discussed are not properly used...

According to the deficiency of traditional Markov chain approach in dynamic fault tree analysis, a new modular method for system reliability analysis is proposed. This paper focuses on dividing into independent subtrees using linear-time algorithm, and processing different subtrees: Binary decision diagram solution static Bayesian Network subtrees, respectively. In addition, an also provided mapping some logic gates discrete-time network. At last, has been applied assess satellite key device...

OD matrix is the basic data in researches of urban rail transit system. estimation an important way to obtain matrix, especially for transit. So model researched this paper, and main content article include following aspects. First, we selected probability calculate station numbers travelled by passengers. Then, revised method according passenger flow characteristics built based on method. Finally, studied algorithm process At same time, example Shanghai line 1 demonstrated rationality...

In order to meet the ever-increasing freight capacity demand, operation of heavy-haul trains with a 50,000 t has been widely studied for decade in China. A typical train large employs multiple locomotives that are evenly distributed along train, and each locomotive, or two more locomotives, hauls certain amount cars. The synchronicity among is great importance safety. 50,000-t developed China will be pulled by 10 uneven distribution traction brake force, caused asynchronous command execution...

This paper presents the modelling and analysis of capacity expansion urban road traffic network (ICURTN). Thebilevel programming model is first employed to ICURTN, in which utility entire maximized with optimal travelers' route choice. Then, an improved hybrid genetic algorithm integrated golden ratio (HGAGR) developed enhance local search simple algorithms, proposed solved by combination HGAGR Frank-Wolfe algorithm. Taking traditional one-way bidirectional as study case, three numerical...

For compensating the deficiency of dissolved gases analysis (DGA) method traction transformer fault diagnosis, a global diagnosis based on improved fuzzy cellular neural network (IFCNN) is introduced in model building mode. Global comprised input space, rule and output space. Input space symptom set type set. As to enriched by increasing water oil, key device resistance electric current besides using DGA content. Fault depended integrated judging combination between IFCNN designed this...

For making up the deficiency of fault diagnosis method train-ground wireless communication unit based train control (CBTC), a global on model building is introduced. Global mainly comprised symptom, rule and types. Fault symptom seemed as input space types are output space. rules have two sorts that can interconvert with each other. Firstly, single was designed by fuzzy neural network. Secondly, regarding numerical value variation vector characteristic, depending increasing values range...