Вероятностное прогнозирование и оценка достоверности данных в интеллектуальных транспортных системах

Transportation has evolved to a topic which is highly regarded in multi aspects. Partly, the contribution to its increasing complexity and everlasting significance has some correlation to the continuous rising demands of public transportation. Transportation systems are now urged to break through the boundaries using communication technology. The integration of communication and computing in the realm of transportation is coined Intelligent Transportation Systems (ITS). The reliability of transportation systems have yet to mature as there are still problems that require support or restructuring. The current new fleets of public transport lacks of proper communication assistance which could potentially identify traffic conditions instantly. The dynamic environments of transportation regions will always pose challenges to wireless communications. Accordingly, there is a need for reliable, uninterrupted and high speed communication systems for the application in ITS. The objective of this paper is to demonstrate a wireless communication protocol suitable for vehicular scenarios. The wireless communication scheme exhibits ad-hoc behavior and coupled with adaptive capabilities. Together, with multiple communication units, they are able to deliver reliable point-to-point wireless communication within a network. With good planning, the communication system can help with the improvements of the efficiency and safety public transportation systems.

With the advancement of artificial intelligence technology, unmanned vehicle (UV) systems, including unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV), have been appearing in many scenarios with wide-ranging applications. It is a crucial factor for enhancing human-computer collaboration efficiency to analyze the impact of unmanned vehicle system combinations on operators. The research in this paper presents the effects of different combinations of UAVs and UGVs (1UAV + 1UGV, 1UAV + 2UGVs, 2UAVs + 1UGV, 2UAVs + 2UGVs) on searching performance and operator’s mental workload for accomplishing search tasks. Completion times for tasks and subjective data with operators (N=16) were collected by using Psychopy and questionnaires, respectively. The results in this research indicate that binary growth of controllable unmanned vehicles doesn’t improve the UV utilization rate, but costing longer completion time and increasing operator’s mental workload. Since an excessive number of unmanned vehicles could have a negative impact on task performance, the insights in the paper are helpful for the design of unmanned vehicle systems and the research of human-computer collaboration.

Intelligent Transport Systems consists of applications such as accident warning and avoidance systems. This is an area of interest to us in this research. The accident detection and alert system in the field of ITS (intelligent transportation system) are implemented and analyzed using many statistical methods for proving the accident detection point, GPS Coordinates points search, etc. In this paper, the analysis is performed on how accidents can be prevented using statistical analysis applied to the flow of vehicles in the construction area. This study helps to compare different statistical methods for vehicle detection in accident warning systems. Different statistical methods like Poisson’s probability distribution, Binomial distribution and Negative Binomial probability distributions were evaluated considering the count of vehicles and their distances from the area near or far from the prone area considered in the construction site. The aim of this paper is to evaluate and compare the statistical methods on the real-time datasets collected by hardware configuration of Arduino-Mega, Node-MCU and cloud service thingsspeak.com and shows that Poisson’s statistical distribution performs better than other methods in terms of probability of success. The different statistics like mean, standard deviation, and variance for different statistical methods are evaluated, out of these Poisson performs better.KeywordsAccident avoidanceIntelligent transportation system (ITS)Poisson’s distributionBinomial distributionNegative binomial distribution

Nowadays, IoT technology has become an essential part of many aspects of life and business. Nevertheless, such widespread application has come at the cost of many security concerns that threaten data privacy and diminish IoT utilization momentum in critical applications such as the smart grid and intelligent transportation systems. To address this challenge, several approaches have been proposed to detect and prevent IoT cyberthreats from materializing. Anomaly detection is one of these approaches that defines the boundaries of legitimate (normal) behavior. Any behavior that falls outside these boundaries is considered anomalous. However, these solutions should have the capability to adapt and adjust to environmental changes that prompt IoT nodal behavioral aberrations, except they only assume that these nodes show the same behavior. This assumption does not hold due to the heterogeneity of IoT nodes and the dynamic nature of an IoT network topology. Furthermore, existing adaptive solutions rely on static (pre-defined) thresholds to control the moment for retraining updates. The cost is heavy for highly dynamic environments like IoT as it leads to an unnecessary higher frequency of retraining. Consequently, the model becomes unstable and adversely affects its accuracy and robustness. This paper addresses these problems by offering an improved Adaptive Anomaly Detection (AAD) methodology that resolves the heterogeneity issues by building local profiles that define normal behavior at each IoT node. The One Class Support Vector Machines (OC-SVM) was used to build these profiles. Then, K-Means clustering was used to build a global profile that represents all network nodes. A Local-Global Ratio-Based (LGR) Anomaly Detection scheme is advanced and was enlisted to control the adaptation process by adjusting the threshold of adaptive functionality dynamically based on the “current” situation to prevent unnecessary retraining. An Ensemble of Deep Belief Networks (EDBN) is developed and used to train the anomaly detection model. Additionally, this study's proposes a new Minimized Redundancy Discriminative Feature Selection (MRD-FS) technique to resolve the issue of redundant features. The MRD-FS experimental evaluation shows detection accuracy higher than those of the related solutions including lower false alarm rates. This validates the efficacy of the proposed model for various IoT applications such as smart grids, smart homes, smart cities and intelligent transportation systems.

Performance measures play a critical role in the operation of Intelligent Transportation Systems (ITS), because they provide feedback to the operators regarding system operations and efficiency. Traffic management systems use archived data, provided by various sensors, as a basis for describing normal conditions and predicting traffic conditions that may be expected at a particular time and place in the highway system. However, data quality is one of the principal concerns of archived ITS data users for the following reasons: 1) Manual inspection techniques are unable to detect significant errors because of the large volume of ITS data; 2) Only minimal error detection can be performed as the data is being collected; 3) Sensors may only fail intermittently and not affect long-term averages; 4) Sensor failures may be masked by congestion or incidents. This project examined several quality control issues on one of the nation’s busiest sections of Interstate, the Borman expressway (I-80/94). Various tests such as speed and volume comparisons, data availability and average effective vehicle length test were developed and applied, revealing significant inconsistency in data quality provided by different detection technologies. Results that document these problems are presented in this study and causes of non-random changes are identified. Finally, several recommendations for improving construction and configuration procedures are proposed. Several simple performance metrics are also documented that transportation agencies can use to assess the quality of traffic data and sustain that quality over time.

The active development of unmanned vehicles, in control systems of which most of the currently created artificial intelligence technologies are used, from machine vision systems to decision-making in multi-criteria control tasks, has led to the emergence of such vehicles on public roads and, in fact, has become an objective reality of ours. life. In such a situation, the person driving needs additional information to drive safely. Currently, the road infrastructure is dynamically developing, forming into a developed distributed telecommunication system with accompanying services. And now it is increasingly associated with the concept of "intelligent transport system" (ITS), to which are connected automotive equipment subsystems, wireless communication subsystems, roadside equipment subsystems and a global navigation satellite system module. Unmanned vehicles, which are integrated into the road environment, form a single telecommunication system for controlling the movement of vehicles with it. Wireless technologies and digital models of road infrastructure are important components of such a system. The information technology concept, which implies the integration of computing resources into physical entities, in particular autonomous robots and unmanned vehicles, is called the concept of cyber-physical systems. The computational component in it is distributed throughout the system. The study of the possibility of constructing digital models of roads and road infrastructure with their subsequent intrasystem transfer between interacting objects is undoubtedly of considerable interest. At the research stage of the implementation of such a technology, it is important to analyze the possibility of building and deploying modern ITS, highlight the main problems associated with the visualization of digital ITS models, and propose ways to solve the tasks. As part of the study, an overview of modern wireless technologies and communication standards with the prospect of their application in the infrastructure of the road environment is given, foreign experience of deploying such systems, their features and limitations, is considered. The functional structure of the intelligent transport system is proposed. The results of modeling the road network (creating a digital model of roads) and the practical implementation of software for compiling local maps are presented. The developed software took into account the shortcomings of specialized products on the market, and also implemented the possibility of converting a digital model of roads into the MAPEM format. After preprocessing MAPEM files, they are placed on the server of the intelligent transport system, from where they are then sent via RSU. RSUs start broadcasting this information, and it goes to the unmanned vehicle, which, in turn, processes the received file and waits for a request to move. Upon receipt of such a request, it builds the trajectory of the path and starts moving. The techniques obtained as a result of the research were implemented and applied at the test site.

This study is about development of technology system for an advanced deep-sea unmanned underwater robot of S. Korea analysed by the application of scenario planning. It was developed a 6000m class next-generation deep-sea unmanned underwater vehicle(or robot, UUV) system, soonly ROV 'Hemire' and Depressor 'Henuvy' in 2006 at S. Korea and motion control, adaptive control algolithm, a work-space manipulator control algolithm, especially the underwater inertial-acoustic navigation system robust to initial errors and sensor failures. But there are remained matters on position tracking of the USBL, inertial-acoustic navigation system, attitude sensor, designed sonar sensors. So this study suggest the new idea for settle the matters and then this idea help the development of the underwater inertial-acoustic navigation system robust to initial errors and sensor failures, such as acoustic signal drop-out, by modifying the error covariance of the failed sonar signal when drop-out occurs. As a result, the future policy for deep-sea unmanned underwater robot of S. Korea is to further spur the development of new technology and more improvement of the technology level for deep-sea unmanned underwater robot system with indicator and imaginary wall as external device.

The paper presents the analysis on stability of digital control system for unmanned vehicle with numerical analysis. The objective of this study is mainly emphasized on the fulfillment of the advanced control techniques according to the fundamental concepts of digital control system approaches for unmanned aerial vehicle system design. The targeted unmanned aerial vehicle system was designed based on the simple construction under the idea of fixed wing flight system approaches. The stability analyses on unmanned aerial vehicle are vital role to enhance the real world applications. The background concepts on digital control system for stability analysis on dynamic control system like unmanned aerial vehicle system. The appropriate controller design for dynamic control system of unmanned aerial vehicle is vital role to analyze the accurate stability condition for reality. The implementation of numerical analysis on compensator design has been developed by using MATLAB. The physical parameters in these analyses are based on the experimental outcomes from the recent research works in dynamical system implementations. The mathematical approaches are very helpful for numerical analysis on compensator design for the unmanned aerial vehicles schemes. The simulation results confirm that the high performance stability test on unmanned aerial vehicle system has been met with the theoretical works.

Distortions during comparator pulse gate transformation of noisy signals are analyzed using the statistical method and its variants. The distortions are characterized with a systemic error in measuring the input signal’s amplitude. The studies are carried out for a low number of operations of comparing a signal with a constant threshold. Systemic errors of the main statistical method and error correction methods are compared. It is shown that the correction ensured using the combined approach is almost ideal. The results of the studies can be used in ultrawideband radio detection (UWB).

With large volumes of data arriving in near real time from environmental sensors, there is a need for automated detection of anomalous data caused by sensor or transmission errors or by infrequent system behaviors. This study develops and evaluates three automated anomaly detection methods using dynamic Bayesian networks (DBNs), which perform fast, incremental evaluation of data as they become available, scale to large quantities of data, and require no a priori information regarding process variables or types of anomalies that may be encountered. This study investigates these methods' abilities to identify anomalies in eight meteorological data streams from Corpus Christi, Texas. The results indicate that DBN‐based detectors, using either robust Kalman filtering or Rao‐Blackwellized particle filtering, outperform a DBN‐based detector using Kalman filtering, with the former having false positive/negative rates of less than 2%. These methods were successful at identifying data anomalies caused by two real events: a sensor failure and a large storm.

Aiming at the key problems of traffic flow prediction and road condition recognition in Intelligent Transportation System (ITS), this paper puts forward an optimized framework of pattern recognition algorithm which integrates multi-source data and dynamic weight adjustment. Firstly, a spatio-temporal semantic model integrating sensor, traffic flow and event information is constructed, and graph neural network (GNN) is used to capture the link association. Then, an adaptive weighting mechanism based on attention and reinforcement learning (RL) is designed to improve the prediction robustness in complex scenes. Combined with Transformer-LSTM and Particle Swarm Optimization (PSO), the computational overhead is reduced and edge deployment is supported. Experiments are carried out based on PeMSD4 data and real-time data of an industrial park. The results show that the proposed method is superior to traditional and deep learning models in traffic flow forecasting performance. The root mean square error (RMSE) of 15-minute forecasting task is 23.4, the mean absolute percentage error (MAPE) is 8.7%, and the sudden congestion error is 28.9%. In the aspect of road condition recognition, the accuracy rate is 94.7% in normal weather, F1-score is 0.93, 88.4% in heavy rain, F1-score 0.85, 85.2% in sensor failure, and F1-score 0.82, which shows high robustness and reliability. At the same time, the parameters of the model are reduced from 43.2MB to 9.8MB, the reasoning delay is reduced from 121ms to 36ms, and the energy consumption is reduced from 293mJ to 87mJ, which has obvious lightweight characteristics and provides an efficient, accurate and adaptable solution for traffic flow prediction and road condition identification in ITS.

Fuzzy Kalman filtering

Multiscale fuzzy Kalman filtering

The article deals with issues related to the use of unmanned vehicles as part of transport convoys for military cargo delivery and offers a new way to manage the intelligent transport system when controlling the convoy’s movement. Based on the analysis, it is concluded that the use of the proposed method and system for its implementation can improve the efficiency, reliability, pace and stability of transport communication. Key words Method, hierarchical control, manned vehicle, unmanned vehicle, convoy, logistics, automated control system, un-manned aerial vehicle, UAV, repeater.

With the maturity of the Internet of Things, 5G communication, big data and artificial intelligence technologies, open-pit mine intelligent transportation systems based on unmanned vehicles has become a trend in smart mine construction. Traditional open-pit mine transportation systems rely on human power for command, which often causes vehicle delay and congestion. The operation of unmanned vehicles in an open pit mine relies on many sensors. Using big data from the sensors, we optimize vehicle paths and build an efficient intelligent transportation system. Based on large amounts of data, such as unmanned vehicle GPS data, vehicle equipment information, production plan data, etc., with the goal of reducing vehicle transportation costs, total unmanned vehicle delay time, and ore content fluctuation rate, a multi-objective intelligent scheduling model for open-pit mine unmanned vehicles was established, and it is aligned with actual open pit mine production. Next, we use artificial intelligence algorithms to solve the scheduling problem. To improve the convergence, distribution and diversity of the classical fast non-dominated sorting genetic algorithm (NSGA-II) to solve constrained high-dimensional multi-objective problems, we propose a decomposition-based constrained dominance principle genetic algorithm (DBCDP-NSGA-II), retaining feasible and non-feasible solutions in sparse areas, and compare it with four other commonly-used multi-objective optimization algorithms. Simulation analysis shows our algorithm provides the best overall performance results of the multi-objective models. Furthermore, we apply intelligent scheduling models and optimization algorithms to mining practice and obtain new truck operation routes and schedules, reducing truck operation costs by 18.2%, truck waiting time by 55.5%, and ore content fluctuation by 40.3%. For open-pit mine unmanned transportation, the approach provides a variety of optimized solutions for minimum transportation costs, minimum waiting time, minimum ore content fluctuation rate, and a balance of the three indicators. Through an artificial intelligence algorithm, this study realizes intelligent unmanned vehicle path planning and improves the operation efficiency of open-pit mine intelligent transportation systems.