Genetic algorithm and support vector machine based aircraft intent inference algorithm in terminal area

Technological independence is important for every country in global competition. One of the technological advancements developed by the Indonesian government through BPPT is Automatic Dependent Surveillance Broadcast (ADS-B) type in, which functions as a flight monitoring system. The Indonesian Air Force (TNI AU) through Depohar 50 (Depot Maintenance 50) has also developed ADS-B type in, which is currently deployed in six radar units known as the Flight Monitoring System (FMS) Mode-S. Accordance with government regulations (Minister of Transportation Regulation No. 81 of 2017), the government has mandated the use of ADS-B for flight safety. ADS-B has two types, in and out. In the TNI AU, ADS-B out is installed on aircraft such as Grob, KT-1, and Cessna, while ADS-B in is installed on Weibel radar. However, since ADS-B is not yet installed on TNI AU aircraft, flight data from the Air Traffic Control (ATC) was communicated to the pilots, hence, they can be aware of the air traffic situation. Furthermore, due to the increasing air traffic, communication with ATC has become limited. A qualitative method was used in the development of the ADS-B type in TNI AU aircraft, and the previous ADS-B type in development could only be installed on the ground station. The information received from ADS-B on the aircraft was real-time air traffic, which helps pilots make decisions to enhance flight safety, such as reducing the risk of aircraft collisions. The use of this technology on TNI AU aircraft is important for improving flight safety and technological independence.

This paper presents a system in concept development that combines the integrity of the civil automatic dependant surveillance - broadcast (ADS-B) system for air-to-air conflict avoidance and air traffic management (ATM) surveillance with the military secure Mark XIIA Mode 5 Identification Friend or Foe (IFF) system as the data link. This new system, coined Military ADS-B (MADS-B), expands the traditional IFF surveillance data of range, azimuth, altitude, and identity (ID) to include each platformpsilas dynamic state of motion and status. This self-reporting system significantly improves positioning and status data between Tri-Service platforms and with Allies - who are also transitioning to the common Mode 5 system. Beyond MADS-Bpsilas securing of ADS-B data, it enables overcoming other surveillance and navigation shortfalls through future software based message additions. The paper summarizes ADS-B operations, the conversion of data to the Mode 5 Level 2 formats, and examples of message extensions providing surveillance enhancements.

This paper proposes a new traffic alert and collision avoidance system (TCAS) for general aviation (GA) that uses automatic dependent surveillance-broadcast (ADS-B). The proposed GA-TCAS alerts the pilot of upcoming potential conflicts, which are becoming increasingly common as the number of GA movements increases. Conflict detection and avoidance uses the ADS-B and GA maneuvers. The algorithm selects the angle according to the intruder’s heading and position in order to reduce the nuisance alerts. The detection algorithm has three stages: proximate advisory, traffic advisory, and resolution advisory. The relationship between the turn angle and the horizontal miss distance (HMD) are calculated to determine a resolution when an intruder enters the separation bubble. Using the encounter models for visual flight rule (VFR) to evaluate the performance of this TCAS algorithm, the resolution should follow the VFR and prioritize in different situations. In flight simulations, the proposed GA-TCAS is tested using real ultralight flight data. The system performance is demonstrated using flight trajectories from conflict detection and resolution.

This paper introduces a real-time means to detect and avoid conflicts for a conceptual Free Flight environment. The assumption of this paper is approximately the same as the model given by Lee C.Yang of MIT. The concept assumes that the datalinks (e.g. ADS-B IN) between different aircraft are available and that conflicts are primarily resolved on the flight deck. This paper provides the flight crew multiple ways to avoid the conflicts, including turn, acceleration, deceleration, climb and descent. The alerting logic is based on probabilistic analysis through modeling of aircraft sensors and trajectory uncertainties. Monte Carlo simulations are used to determine conflict probability for every possible encounter situation. The construction of conflict probability database (CPDB) before the aircraft takes off can reduce the computation time of the flight computer. The CPDB records the conflict probability corresponding to every possible air traffic situation in which there are only two aircraft. Due to the integrity of the constructed CPDB, CPDB is suitable to be used to study the characters of the air traffic conflict. The Avoidance Maneuver Database (AMDB) and the Redundant Maneuver Database (RMDB) have been constructed based on the CPDB which is established in advance. AMDB and RMDB are used in resolving conflicts in multiple aircraft scenario.

This paper designs, simulates, and tests a potential Automatic Dependent Surveillance-Broadcast (ADS-B) space-oriented message set to improve situational awareness of commercial space vehicles inside the National Airspace System (NAS), and to minimize their impacts and potential hazards on the NAS. ADS-B is considered as the solution to integrate the future commercial space transportation system with the air transportation system. To accommodate future space flight operations in the NAS, a potential ADS-B space-oriented message set is proposed to be exclusively transmitted from space vehicles to other traffic and air traffic controllers. New data fields are defined in the message set to cover a space vehicle's entire flight profile. The formats of these new data fields are demonstrated in details. A simulation is created containing space vehicle and aircraft trajectories to test the functionality of the ADS-B space-oriented message set. The message set is encoded at the space vehicle site, transmitted from space vehicle to aircraft via the Universal Access Transceiver (UAT) datalink, and decoded at the aircraft site. The simulation eventually reaches a conflict scenario. By using the Closest Point of Approach (CPA) algorithm, the aircraft analyzes its own state vector and the space vehicle's state vector decoded from ADS-B messages to perform conflict detection. Sensitivity studies are conducted based on the CPA algorithm concentrating on three ADS-B system parameters, which are message update rate, data latency, and state vector accuracy.

Quantifying the Severity of Traffic Conflict by Assuming Moving Elements as Rectangles at Intersection

The University of North Dakota is developing airspace within the state where Unmanned Aircraft Systems (UASs) can be flown without an onboard sense and avoid system or Temporary Flight Restrictions (TFRs). With funding from the U.S. Air Force, a mobile ground-based radar system capable of detecting aircraft operating in Class E airspace and the software to display such information to UAS operators is being developed. The current system uses an Automatic Dependent Surveillance - Broadcast (ADS-B) transceiver to detect any ADS-B-equipped aircraft within the vicinity, and a Ground Control Station (GCS) to detect and control the UAS. Once one or more ground-based radars are integrated into the system, it will also be capable of detecting non-cooperative aircraft (i.e. aircraft that aren't equipped with ADS-B transceivers) operating within the vicinity. The current system uses a portable, high-availability architecture. Since the system is intended to detect potential airspace conflicts from the ground, greater computational power is available to it than to onboard sense and avoid systems. The probability of a midair collision is dependent on the proximity of aircraft to each other, the performance characteristics of the aircraft, and the probabilities of pilots performing basic maneuvers with the aircraft. In this paper the authors present the results of data mining an ADS-B data set from 11 days in early 2010. Probabilistic models of pilot behavior were automatically extracted from the data using a genetic algorithm for cluster analysis.

Air-traffic optimization is an essential part of airspace operation reengineering, as the number of flights and the usage of routes increase in the world. The NextGen and SESAR projects are important initiatives that allow for more scalability and safety in air-traffic. One element of these projects is the Automatic Dependent Surveillance-Broadcast (ADS-B) system which allows airplanes to share their position and speed. The ADS-B antennas’ coverage is somewhat limited in less economically developed and oceanic areas, resulting in a lack of flight path data. This paper proposes a method based on artificial neural networks (ANN), interpolation and average computation to fill flight path data partially tracked by ADS-B antennas. While other methods are focused on one or two dimensions of the flight path, this work is focused on infilling the 4-dimensions present in the ADS-B data (latitude, longitude, altitude and ground speed). This work is useful in analyzing performance of historical flights related to limited coverage areas or in predicting flight path in air-traffic management systems (ATMs). The comparison between the real and estimated trajectories in a set of 517 flights has shown accuracy superior to 92% for the metrics distance flown, estimated burned fuel, and trajectory correlation.

In order to solve the shortcoming of support vector regression algorithm, sports economic activities income forecasting based on genetic support vector regression algorithm is presented in this paper. As the kernel parameter, insensitive loss parameter and penalty parameter have a great influence on the forecasting performance of support vector regression algorithm, genetic algorithm is used to perform the parameters optimization of support vector regression algorithm simultaneously in this study. The experimental results show that the sports economic activities income forecasting results of genetic support vector regression model trained by the four-dimension training samples are more excellent than those of genetic support vector regression model trained by the three-dimension training samples, and the sports economic activities income forecasting ability of genetic support vector regression model trained by the four- dimension training samples is better than that of support vector regression model trained by the four-dimension training samples. Thus, genetic support vector regression algorithm has a good application prospect in sports economic activities income forecasting.

This paper established evaluation index system of comprehensive utilization of land from the three aspects of economic benefits, ecological benefits and social benefits. Firstly, ridge regression (RR) is used to the indicator index sys- tem for screening, and then genetic algorithm and support vector machine (that is GASVM) is trained to the transformed samples. Moreover, the comprehensive evaluation results between the GASVM and ridge regression and genetic algo- rithm and support vector machine(that is RR-GASVM) is compared, which results by MATLAB show that using RR- GASVM is more accurate and higher efficient for the comprehensive utilization of land evaluation than that of GASVM. The combination of ridge regression and genetic algorithm and support vector machine can improve the decision ability of SVM, so that the decision has higher adaptability, which is the development direction of future research. At last, based on the results of this study, some suggestions are put forward accordingly. The area of Jiangsu, Zhejiang and Shanghai (that is Jiangzhehu) should consolidate the existing achievements and strengthen the innovation of the land management system on the basis of utilizing land comprehensively, realize the intensive, large-scale operation and speed up agricultural mod- ernization development by accelerating rural land circulation, and improve the efficiency of land utilization in order to save the land of urban construction. It is clear that people should insist the principle of paying equal attention to develop- ment and consolidation, and strengthen the cultivated land's ability to resist natural disasters in order to improve the eco- logical environment at the same time that improved the land utilization.

A robust hybrid between genetic algorithm and support vector machine for extracting an optimal feature gene subset

Hybrid genetic algorithms and support vector regression in forecasting atmospheric corrosion of metallic materials

Considering the increasingly tense relationship between construction land supply and demand, we study the inherent rules and the spatial evolution in construction land use. In order to solve the problem of parameter optimization effectively, we analysis the fundamental theory of Support Vector Machine and finally accomplish the combination of genetic algorithm and support vector machine. Meanwhile we apply this model to analysis the construction land use and propose a new model, which is based on the support vector machines with genetic algorithm, for construction land evolution. Taking Guandu district in Kunming, Yunnan as a case, we find out that the new model is far superior to recent models in terms of predicting accuracy, algorithm complexity and computational efficiency. And therefore, we believe that this is highly precise, practical and efficient model for forecasting construction land use and evolution.

For the safety problem of flight anti-collision in route area and terminal area, a flight conflict detection method is proposed based on Monte Carlo method. In the method, the ellipsoidal aircraft protection area model is selected and the position of aircraft is predicted through the stochastic differential equation, and then Monte Carlo method is used to calculate the probability of flight conflict in terminal area. The experiments show that the proposed method can obtain a more accurate overall flight conflict probability, thus verifying its feasibility in the application of conflict detection studies.

** † ‡ Development of a decision support system that uses real-time track data to estimate statistical parameters describing the stochastic traffic flow is described. Modern statistical decision theory is applied to optimize traffic flow. An advanced estimation algorithm provides the parameter estimates based on queuing network models of traffic flow. A hypothesis testing approach is developed for triggering traffic flow management initiatives in the terminal area, and a stochastic quadratic programming methodology is advanced to achieve flow control objectives such as runway load balancing. The use of this methodology is demonstrated using multi-day track data in the San Francisco terminal area. It is shown that the methodology can correctly identify the need for restricting the traffic flow into the terminal area, and provide decision support to balance the traffic flow at the runways under uncertain traffic flow conditions. The present approach can be extended to the creation of decision support tools for a wide variety of stochastic air traffic flow control situations.