Showing papers by "Shu-Chuan Chu published in 2020"

Improved Binary Grey Wolf Optimizer and Its application for feature selection

Abstract: Grey Wolf Optimizer (GWO) is a new swarm intelligence algorithm mimicking the behaviours of grey wolves. Its abilities include fast convergence, simplicity and easy realization. It has been proved its superior performance and widely used to optimize the continuous applications, such as, cluster analysis, engineering problem, training neural network and etc. However, there are still some binary problems to optimize in the real world. Since binary can only be taken from values of 0 or 1, the standard GWO is not suitable for the problems of discretization. Binary Grey Wolf Optimizer (BGWO) extends the application of the GWO algorithm and is applied to binary optimization issues. In the position updating equations of BGWO, the a parameter controls the values of A and D , and influences algorithmic exploration and exploitation. This paper analyses the range of values of A D under binary condition and proposes a new updating equation for the a parameter to balance the abilities of global search and local search. Transfer function is an important part of BGWO, which is essential for mapping the continuous value to binary one. This paper includes five transfer functions and focuses on improving their solution quality. Through verifying the benchmark functions, the advanced binary GWO is superior to the original BGWO in the optimality, time consumption and convergence speed. It successfully implements feature selection in the UCI datasets and acquires low classification errors with few features.

Quasi-Affine Transformation Evolutionary Algorithm With Communication Schemes for Application of RSSI in Wireless Sensor Networks

Abstract: QUasi-Affine TRansformation Evolutionary algorithm (QUATRE) is a new optimization algorithm based on population for complex multiple real parameter optimization problems in real world. In this paper, a novel multi-group multi-choice communication strategy algorithm for QUasi-Affine TRansformation Evolutionary (MM-QUATRE) algorithm is proposed to solve the disadvantage that the original QUATRE is always easily to fall into local optimization in the strategy of updating bad nodes with multiple groups and multiple choices. We compared it with other intelligent algorithms, the most advanced PSO variant, parallel PSO (P-PSO) variant, native QUATRE and parallel QUATRE (P-PSO) under CEC2013 large-scale optimization test suite. Thus, the performance of MM-QUATRE was verified. The conclusion that the MM-QUATRE algorithm is superior to other intelligent algorithms is proved by the experimental results. In addition, the application results of MM-QUATRE algorithm (MM-QUATRE-RSSI) based on RSSI in WSN node localization were analyzed and studied. The results appear that this method has higher localization accuracy than other similar algorithms.

A Hybrid Differential Evolution Algorithm and Its Application in Unmanned Combat Aerial Vehicle Path Planning

Abstract: CIPDE and JADE are two powerful and effective Differential Evolution (DE) algorithms with strong exploration and exploitation capabilities. In order to take advantage of these two algorithms, we present a hybrid differential evolution algorithm combining modified CIPDE (MCIPDE) with modified JADE (MJADE) called CIJADE. In CIJADE, the population is first partitioned into two subpopulations according to the fitness value, i.e., superior and inferior subpopulations, to maintain the population diversity. The superior subpopulation evolves using the operation defined in MCIPDE. The MCIPDE adds an external archive to the mutation scheme to enhance the population diversity and exploration capability of original CIPDE. While the inferior subpopulation evolves using the operation defined in MJADE. The MJADE modifies the original JADE by adjusting the parameter p in linear decreasing way to balance the exploration and exploitation ability of original JADE. A new crossover operation is designed to original JADE to deal with the problem of stagnation. Furthermore, the parameters CR and F values of CIJADE are updated according to a modified parameter adaptation strategy in each generation. We validate the performance of the proposed CIJADE algorithm over 28 benchmark functions of the CEC2013 benchmark set. The experimental results indicate that the proposed CIJADE performs better than the eleven popular stateof-the-art DE variants. What's more, we apply the proposed CIJADE to deal with Unmanned Combat Aerial Vehicle (UCAV) path planning problem. The simulation results show that the proposed CIJADE can efficiently find the optimal or near optimal flight path for UCAV.

A Compact Pigeon-Inspired Optimization for Maximum Short-Term Generation Mode in Cascade Hydroelectric Power Station

Abstract: Pigeon-inspired optimization (PIO) is a new type of intelligent algorithm. It is proposed that the algorithm simulates the movement of pigeons going home. In this paper, a new pigeon herding algorithm called compact pigeon-inspired optimization (CPIO) is proposed. The challenging task for multiple algorithms is not only combining operations, but also constraining existing devices. The proposed algorithm aims to solve complex scientific and industrial problems with many data packets, including the use of classical optimization problems and the ability to find optimal solutions in many solution spaces with limited hardware resources. A real-valued prototype vector performs probability and statistical calculations, and then generates optimal candidate solutions for CPIO optimization algorithms. The CPIO algorithm was used to evaluate a variety of continuous multi-model functions and the largest model of hydropower short-term generation. The experimental results show that the proposed algorithm is a more effective way to produce competitive results in the case of limited memory devices.

Optimizing Ontology Alignment in Vector Space

Abstract: Ontology matching technique aims at determining the identical entities, which can effectively solve the ontology heterogeneity problem and implement the collaborations among ontology-based intelligent systems. Typically, an ontology consists of a set of concepts which are described by various properties, and they define a space such that each distinct concept and property represents one dimension in that space. Therefore, it is an effective way to model an ontology in a vector space, and use the vector space based similarity measure to calculate two entities’ similarity. In this work, the entities’ structure information is utilized to model an ontology in a vector space, and then, their linguistic information is used to reduce the number of dimensions, which can improve the efficiency of the similarity calculation and entity matching process. After that, a discrete optimization model is constructed for the ontology matching problem, and a compact Evolutionary Algorithm (cEA) based ontology matching technique is proposed to efficiently address it. The experiment uses the benchmark track provided by Ontology Alignment Evaluation Initiative (OAEI) to test our proposal’s performance, and the comparing results with state-of-the-art ontology matching systems show that our approach can efficiently determine high-quality ontology alignments.

A Parallel Multi-Verse Optimizer for Application in Multilevel Image Segmentation

Abstract: Multi-version optimizer (MVO) inspired by the multi-verse theory is a new optimization algorithm for challenging multiple parameter optimization problems in the real world. In this paper, a novel parallel multi-verse optimizer (PMVO) with the communication strategy is proposed. The parallel mechanism is implemented to randomly divide the initial solutions into several groups, and share the information of different groups after each fixed iteration. This can significantly promote the cooperation individual of MVO algorithm, and reduce the deficiencies that the original MVO is premature convergence, search stagnation and easily trap into local optimal search space. To confirm the performance of the proposed scheme, the PMVO algorithm was compared with the other well-known optimization algorithms, such as gray wolf optimizer (GWO), particle swarm optimization (PSO), multi-version optimizer (MVO), and parallel particle swarm optimization (PPSO) under CEC2013 test suite. The experimental results prove that the PMVO is superior to the other compared algorithms. In addition, PMVO is also applied to solve complex multilevel image segmentation problems based on minimum cross entropy thresholding. The application results appear that the proposed PMVO algorithm can achieve higher quality image segmentation compared to other similar algorithms.

Improved Compact Cuckoo Search Algorithm Applied to Location of Drone Logistics Hub

Abstract: Drone logistics can play an important role in logistics at the end of the supply chain and special environmental logistics. At present, drone logistics is in the initial development stage, and the location of drone logistics hubs is an important issue in the optimization of logistics systems. This paper implements a compact cuckoo search algorithm with mixed uniform sampling technology, and, for the problem of weak search ability of the algorithm, this paper combines the method of recording the key positions of the search process and increasing the number of generated solutions to achieve further improvements, as well as implements the improved compact cuckoo search algorithm. Then, this paper uses 28 test functions to verify the algorithm. Aiming at the problem of the location of drone logistics hubs in remote areas or rural areas, this paper establishes a simple model that considers the traffic around the village, the size of the village, and other factors. It is suitable for selecting the location of the logistics hub in advance, reducing the cost of drone logistics, and accelerating the large-scale application of drone logistics. This paper uses the proposed algorithm for testing, and the test results indicate that the proposed algorithm has strong competitiveness in the proposed model.

A parallel WOA with two communication strategies applied in DV-Hop localization method

Abstract: Wireless sensor network (WSN) can effectively help us monitor the surrounding environment and prevent the occurrence of some natural disasters earlier, but we can only get the information of the surrounding environment correctly if we know the locations of nodes. How to know the exact positions of nodes is a strict challenge in WSN. Intelligent computing algorithms have been developed in recent years. They easily solve complex optimization problems, especially for those that cannot be modeled mathematically. This paper proposes a novel algorithm, named parallel whale optimization algorithm (PWOA). It contains two information exchange strategies between groups, and it significantly enhances global search ability and population diversity of the original whale optimization algorithm (WOA). Also, the algorithm is adopted to optimize the localization of WSN. Twenty-three mathematical optimization functions are accustomed to verifying the efficiency and effectiveness of the novel approach. Compared with some existing intelligent computing algorithms, the proposed PWOA may reach better results.

Identifying correctness data scheme for aggregating data in cluster heads of wireless sensor network based on naive Bayes classification

Abstract: Wireless sensor network (WSN) has been paid more attention by scholars due to the practical communication of a system of devices to transfer information gathered from a monitored field through wireless links. Precise and accurate data of aggregating messages from sensor nodes is a vital demand for a success WSN application. This paper proposes a new scheme of identifying the correctness data scheme for aggregating data in cluster heads in hierarchical WSN based on naive Bayes classification. The collecting environmental information includes temperature, humidity, sound, and pollution levels, from sensor nodes to cluster heads that classify data fault and aggregate and transfer them to the base station. The collecting data is classified based on the classifier to aggregate in the cluster head of WSN. Compared with some existing methods, the proposed method offers an effective way of forwarding the correct data in WSN applications.

An efficient surrogate-assisted quasi-affine transformation evolutionary algorithm for expensive optimization problems

Abstract: Many real-world engineering optimization problems usually need a lot of time for function evaluations or have massive decision variables. It is still a big challenge to address these problems effectively. Recently, surrogate-assisted meta-heuristic algorithms have drawn increasing attention, and have shown their potential to deal with such expensive complex optimization problems. In this study, a surrogate-assisted quasi-affine transformation evolutionary (SA-QUATRE) algorithm is proposed to further enhance the optimization efficiency and effectiveness. In SA-QUATRE, the global and the local surrogate models are effectively combined for fitness estimation. The global surrogate model is built based on all data in the database for global exploration. While, the local surrogate model is constructed with a predefined number of top best samples for local exploitation. Meanwhile, both the generation- and individual-based evolution controls as well as a top best restart strategy are incorporated in the global and the local searches. To enhance the exploration and the exploitation capabilities, the global search uses the mean of the population to be evaluated with the expensive real fitness function, while the local search chooses the individual with the best fitness according to the surrogate for real evaluation. The proposed SA-QUATRE is compared with five state-of-the-art optimization approaches over seven commonly used benchmark functions with dimensions varying from 10 to 100. Moreover, the proposed SA-QUATRE is also applied to solve the tension/compression spring design problem. The experimental results show that SA-QUATRE is promising for optimizing computationally expensive problems.

Symbiotic Organism Search Algorithm with Multi-Group Quantum-Behavior Communication Scheme Applied in Wireless Sensor Networks

Abstract: The symbiotic organism search (SOS) algorithm is a promising meta-heuristic evolutionary algorithm. Its excellent quality of global optimization solution has aroused the interest of many researchers. In this work, we not only applied the strategy of multi-group communication and quantum behavior to the SOS algorithm, but also formed a novel global optimization algorithm called the MQSOS algorithm. It has speed and convergence ability and plays a good role in solving practical problems with multiple arguments. We also compared MQSOS with other intelligent algorithms under the CEC2013 large-scale optimization test suite, such as particle swarm optimization (PSO), parallel PSO (PPSO), adaptive PSO (APSO), QUasi-Affine TRansformation Evolutionary (QUATRE), and oppositional SOS (OSOS). The experimental results show that MQSOS algorithm had better performance than the other intelligent algorithms. In addition, we combined and optimized the DV-hop algorithm for node localization in wireless sensor networks, and also improved the DV-hop localization algorithm to achieve higher localization accuracy than some existing algorithms.

Sine Cosine Algorithm with Multigroup and Multistrategy for Solving CVRP

Abstract: Sine Cosine Algorithm (SCA) has been proved to be superior to some existing traditional optimization algorithms owing to its unique optimization principle. However, there are still disadvantages such as low solution accuracy and poor global search ability. Aiming at the shortcomings of the sine cosine algorithm, a multigroup multistrategy SCA algorithm (MMSCA) is proposed in this paper. The algorithm executes multiple populations in parallel, and each population executes a different optimization strategy. Information is exchanged among populations through intergenerational communication. Using 19 different types of test functions, the optimization performance of the algorithm is tested. Numerical experimental results show that the performance of the MMSCA algorithm is better than that of the original SCA algorithm, and it also has some advantages over other intelligent algorithms. At last, it is applied to solving the capacitated vehicle routing problem (CVRP) in transportation. The algorithm can get better results, and the practicability and feasibility of the algorithm are also proved.

Phasmatodea population evolution algorithm and its application in length-changeable incremental extreme learning machine

Abstract: Extreme learning machine (ELM) is an effective classification and prediction learning algorithm based on feedforward neural network (FNN). This paper presents the Phasmatodea (stick insect) population evolution algorithm (PPE), which is different from other algorithms, in which each solution represents a population and has two attributes: quantity and growth rate. Combining the concept of similar evolution and the model of population competition, it is a new local search method. The algorithm is compared with the other algorithms on benchmark functions and engineering problems. Then use it to enhance a variant of the ELM model. The results show that the proposed algorithm has a certain competitiveness.

A Novel Pigeon-Inspired Optimization Based MPPT Technique for PV Systems

Abstract: The conventional maximum power point tracking (MPPT) method fails in partially shaded conditions, because multiple peaks may appear on the power–voltage characteristic curve. The Pigeon-Inspired Optimization (PIO) algorithm is a new type of meta-heuristic algorithm. Aiming at this situation, this paper proposes a new type of algorithm that combines a new pigeon population algorithm named Parallel and Compact Pigeon-Inspired Optimization (PCPIO) with MPPT, which can solve the problem that MPPT cannot reach the near global maximum power point. This hybrid algorithm is fast, stable, and capable of globally optimizing the maximum power point tracking algorithm. Therefore, the purpose of this article is to study the performance of two optimization techniques. The two algorithms are Particle Swarm Algorithm (PSO) and improved pigeon algorithm. This paper first studies the mechanism of multi-peak output characteristics of photovoltaic arrays in complex environments, and then proposes a multi-peak MPPT algorithm based on a combination of an improved pigeon population algorithm and an incremental conductivity method. The improved pigeon algorithm is used to quickly locate near the maximum power point, and then the variable step size incremental method INC (incremental conductance) is used to accurately locate the maximum power point. A simulation was performed on Matlab/Simulink platform. The results prove that the method can achieve fast and accurate optimization under complex environmental conditions, effectively reduce power oscillations, enhance system stability, and achieve better control results.

3-D Terrain Node Coverage of Wireless Sensor Network Using Enhanced Black Hole Algorithm

Abstract: In this paper, a new intelligent computing algorithm named Enhanced Black Hole (EBH) is proposed to which the mutation operation and weight factor are applied. In EBH, several elites are taken as role models instead of only one in the original Black Hole (BH) algorithm. The performance of the EBH algorithm is verified by the CEC 2013 test suit, and shows better results than the original BH. In addition, the EBH and other celebrated algorithms can be used to solve node coverage problems of Wireless Sensor Network (WSN) in 3-D terrain with satisfactory performance.

Applying Adaptive and Self Assessment Fish Migration Optimization on Localization of Wireless Sensor Network on 3-D Te rrain.

Abstract: This paper presents an improved fish migration optimization (FMO), which adopts novel update equations of individuals and energy. A chieftain concept is introduced and it can attract individuals to exploitation around it. Therefore, the novel algorithm reduced the randomness and improved the convergence ability of the original algorithm. A more flexible update equation of energy is introduced which adjusts the amplitude of energy increase of individuals according to its fitness quality. The performance of the new algorithm is verified by CEC 2013 benchmark function. Besides, the novel algorithm is applied in solving the localization problem of Wireless Sensor Network (WSN) on 3-D terrain.

A novel pigeon-inspired optimization with QUasi-Affine TRansformation evolutionary algorithm for DV-Hop in wireless sensor networks:

Abstract: In modern times, swarm intelligence has played an increasingly important role in finding an optimal solution within a search range. This study comes up with a novel solution algorithm named QUasi-A...

Parallel compact differential evolution for optimization applied to image segmentation

Abstract: A parallel compact Differential Evolution (pcDE) algorithm is proposed in this paper. The population is separated into multiple groups and the individual is run by using the method of compact Differential Evolution. The communication is implemented after predefined iterations. Two communication strategies are proposed in this paper. The first one is to replace the local optimal solution by global optimal solution in all groups, which is called optimal elite strategy (oe); the second one is to replace the local optimal solution by mean value of the local optimal solution in all groups, which is called mean elite strategy (me). Considering that the pcDE algorithm does not need to store a large number of solutions, the algorithm can adapt to the environment with weak computing power. In order to prove the feasibility of pcDE, several groups of comparative experiments are carried out. Simulation results based on the 25 test functions demonstrate the efficacy of the proposed two communication strategies for the pcDE. Finally, the proposed pcDE is applied to image segmentation and experimental results also demonstrate the superior quality of the pcDE compared with some existing methods.

Diversity Teams in Soccer League Competition Algorithm for Wireless Sensor Network Deployment Problem

Abstract: The drawback of several metaheuristic algorithms is the dropped local optimal trap in the solution to complicated problems. The diversity team is one of the promising ways to enhance the exploration of searching solutions in algorithm to avoid the local optimum trap. This paper proposes a diversity-team soccer league competition algorithm (DSLC) based on updating team member strategies for global optimization and its applied optimization of Wireless sensor network (WSN) deployment. The updating team consists of trading, drafting, and combining strategies. The trading strategy considers player transactions between groups after the ending season. The drafting strategy takes advantage of draft principles in real leagues to bring new players to the association. The combining strategy is a hybrid policy of trading and drafting one. Twenty-one benchmark functions of CEC2017 are used to test the performance of the proposed algorithm. The experimental results of the proposed algorithm compared with the other algorithms in the literature show that the proposed algorithm outperforms the competitors in terms of having an excellent ability to achieve global optimization. Moreover, the proposed DSLC algorithm is applied to solve the problem of WSN deployment and achieved excellent results.

A node location method in wireless sensor networks based on a hybrid optimization algorithm

Abstract: Wireless sensor networks (WSN) have gradually integrated into the concept of the Internet of Things (IoT) and become one of the key technologies. This paper studies the optimization algorithm in the field of artificial intelligence (AI) and effectively solves the problem of node location in WSN. Specifically, we propose a hybrid algorithm WOA-QT based on the whale optimization (WOA) and the quasi-affine transformation evolutionary (QUATRE) algorithm. It skillfully combines the strengths of the two algorithms, not only retaining the WOA’s distinctive framework advantages but also having QUATRE’s excellent coevolution ability. In order to further save optimization time, an auxiliary strategy for dynamically shrinking the search space (DSS) is introduced in the algorithm. To ensure the fairness of the evaluation, this paper selects 30 different types of benchmark functions and conducts experiments from multiple angles. The experiment results demonstrate that the optimization quality and efficiency of WOA-QT are very prominent. We use the proposed algorithm to optimize the weighted centroid location (WCL) algorithm based on received signal strength indication (RSSI) and obtain satisfactory positioning accuracy. This reflects the high value of the algorithm in practical applications.

Improved Binary Symbiotic Organism Search Algorithm With Transfer Functions for Feature Selection

Abstract: Symbiotic Organism Search (SOS) algorithm is highly praised by researchers for its excellent convergence performance, global optimization ability and simplicity in solving various continuous practical problems. However, in the real world, there are many binary problems, which can only take values of 0 and 1, that still need to be solved. Since the original SOS algorithm cannot directly solve the binary problem, the original ASOS Binary SOS (BSOS) algorithm has the disadvantage of premature convergence. In order to improve the limitations of the ASBSOS algorithm, we propose an Improved BSOS (IBSOS) algorithm. As we all know, the transfer function is very important in the binarization of continuous optimization algorithms. Therefore, we used 9 transfer functions in the IBSOS algorithm to binarize the continuous SOS algorithm and analyzed the impact of each transfer function on the performance of the BSOS algorithm. Moreover, we use the same three biological symbiosis strategies as the continuous SOS algorithm in our proposed IBSOS algorithm to binarize the SOS algorithm to improve The diversity of the algorithm execution process and the ability to balance algorithm exploration and development. In order to verify the performance of IBSOS using different transfer functions, we use 13 benchmark functions to show the global optimization capability and convergence speed of the BSOS algorithm. Finally, we apply the algorithm to feature selection in the ten data sets of UCI. The experimental results with low classification error and few features further verify the excellent performance of the IBSOS algorithm.

Adaptive Cat Swarm Optimization Algorithm and Its Applications in Vehicle Routing Problems

Abstract: This paper proposes a novel hybrid algorithm named Adaptive Cat Swarm Optimization (ACSO). It combines the benefits of two swarm intelligence algorithms, CSO and APSO, and presents better search results. Firstly, some strategies are implemented to improve the performance of the proposed hybrid algorithm. The tracing radius of the cat group is limited, and the random number parameter r is adaptive adjusted. In addition, a scaling factor update method, called a memory factor y, is introduced into the proposed algorithm. They can be learnt very well so as to jump out of local optimums and speed up the global convergence. Secondly, by comparing the proposed algorithm with PSO, APSO, and CSO, 23 benchmark functions are verified by simulation experiments, which consists of unimodal, multimodal, and fixed-dimension multimodal. The results show the effectiveness and efficiency of the innovative hybrid algorithm. Lastly, the proposed ACSO is utilized to solve the Vehicle Routing Problem (VRP). Experimental findings also reveal the practicability of the ACSO through a comparison with certain existing methods.

A Kernel-Based Probabilistic Collaborative Representation for Face Recognition

Abstract: A novel classifier for face recognition using an improved probabilistic collaborative representation named IPCR is proposed in this paper. The purpose of this paper is to improve the accuracy of face recognition. The testing sample is assumed to be linearly combined by a part of training samples in feature space. There is two-phase framework in IPCR. In the first phase, an adjusted parameter of the nearest neighbors of the samples is chosen for classification. In the second phase, a linear combination of the features and the sparse coefficients are used for new patterns. In the process of two-phase framework, the weight matrix is obtained according to the distance between all the training samples and each testing sample, and then it is applied to weight probabilistic collaborative representation coefficients. The kernel trick is implemented for the high-dimensional nonlinear information instead of linear information of data to improve the class separability. The second classifier named KPCR uses a kernel probabilistic collaborative representation for face recognition. Several renowned face databases, e.g., AR, GT, PIE, FERET, and LFW-crop are used for evaluating the performances of the proposed classifiers. The experimental results demonstrate that the proposed classifiers outperform the collaborative representation-based classification (CRC), the probabilistic collaborative representation-based classifier (ProCRC), and the other state-of-the-art classifiers in recognition accuracy.

An Efficient Differential Evolution Via Both Top Collective and p-Best Information

Abstract: This study proposes a novel DE variant for global optimizations based on both top collective information and p-best information (called CIpBDE). A combined mutation strategy (CIpBM) takes advantage of the mutation strategies “target-to-ci_pbest/1” and “target-to-pbest/1” is introduced trying to escape from stuck of local optima. A modified crossover operation (CIpBX) is proposed to handle the stagnation of DE. CIpBX adopts a collective vector or top p-best individual based on probability to execute crossover operation when stagnation occurs. An improved parameter adaptation strategy is figured out to adaptability to adjust the parameters crossover probability and scale factor value in each generation. To evaluate the performance of CIpBDE, comprehensive experiments are conducted on the CEC2013 benchmark test suit with 28 functions. Experimental results show that CIpBDE outperforms the seven state-of-the-art DE variants. What’s more, we also apply CIpBDE to the feature selection problem. Compared results on several standard data sets indicate that CIpBDE outperforms the four comparing algorithms in terms of classification accuracy.

Decentralized Private Information Sharing Protocol on Social Networks

Abstract: Social networks are becoming popular, with people sharing information with their friends on social networking sites. On many of these sites, shared information can be read by all of the friends; however, not all information is suitable for mass distribution and access. Although people can form communities on some sites, this feature is not yet available on all sites. Additionally, it is inconvenient to set receivers for a message when the target community is large. One characteristic of social networks is that people who know each other tend to form densely connected clusters, and connections between clusters are relatively rare. Based on this feature, community-finding algorithms have been proposed to detect communities on social networks. However, it is difficult to apply community-finding algorithms to distributed social networks. In this paper, we propose a distributed privacy control protocol for distributed social networks. By selecting only a small portion of people from a community, our protocol can transmit information to the target community.

Traffic collisions early warning aided by small unmanned aerial vehicle companion

Abstract: Most traffic surveillance systems are based on videos which captured by fixed cameras on bridges, intersections, etc. However, many traffic collisions may occur in many places without such surveillance systems, e.g., in rural highway. Researchers have developed a set of techniques to improve safety on these places, while it is still not enough to reduce collision risk. Based on a novel concept, this paper proposes a traffic collisions early warning scheme aided by small unmanned aerial vehicle (UAV) companion. Basically, it is a vision-based driver assistance system, and the difference in comparison with the available schemes lies in the camera is flying along with the host vehicle. In particular, the system’s framework and the vision-based vehicle collision detection algorithm are proposed. The small UAV works in two switchable modes, i.e., high speed flight or low speed motion. The high speed flight corresponds to the host vehicle moving in highway, while the low speed motion includes hover, vertical takeoff and landing. In addition, as the on-line machine learning is applied, the detection procedure can be implemented in real-time, which is critical in practical applications. Extensive experimental results and examples demonstrate the effectiveness of the proposed method, and its real-time performance outperforms typical tracking methods such as that based on Gaussian mixture model. Moreover, this scheme can be easily extended for some other similar application scenarios.