No abstract

In this study, a public key image encryption algorithm is proposed based on pixel information and random number insertion. In the first step, two large prime numbers and the public key are selected randomly to produce the private key. According to the pixel information of the plain image and utilizing the Rivest-Shamir-Adleman (RSA) algorithm, the corresponding cipher information can be obtained by using the public key to encrypt the plain information extracted from the plain image. Both the plain and cipher information are then converted into the initial keys of the chaotic system based on a key transformation mapping. Consequently, the keystreams are generated based on iterative calculations. In the second step, different keystreams are selected for pixel arrangement and modulo operation preprocessing for the plain image. Subsequently, random numbers are inserted in the preprocessed image to obtain an extended image. The final cipher image can be got by selecting different keystreams to encrypt the extended image using XOR diffusion and add modulus operations. Combined with public key cryptosystem RSA, the proposed algorithm can achieve the effect of a onetime pad. Finally, experimental test results show that the cipher image obtained using our algorithm is highly random and robust, and can effectively resist violent, statistical, and differential attacks. A series of security analyses are implemented to validate the proposed asymmetric image encryption algorithm.

Adaptive boost (AdaBoost) is a prominent example of an ensemble learning algorithm that combines weak classifiers into strong classifiers through weighted majority voting rules. AdaBoost’s weak classifier, with threshold classification, tries to find the best threshold in one of the data dimensions, dividing the data into two categories-1 and 1. However, in some cases, this Weak Learning algorithm is not accurate enough, showing poor generalization performance and a tendency to over-fit. To solve these challenges, we first propose a new Weak Learning algorithm that classifies examples based on multiple thresholds, rather than only one, to improve its accuracy. Second, in this paper, we make changes to the weight allocation scheme of the Weak Learning algorithm based on the AdaBoost algorithm to use potential values of other dimensions in the classification process, while the theoretical identification is provided to show its generality. Finally, comparative experiments between the two algorithms on 18 datasets on UCI show that our improved AdaBoost algorithm has a better generalization effect in the test set during the training iteration.

Ship collision avoidance is a complex process that is influenced by numerous factors. In this study, we propose a novel method called the Optimal Collision Avoidance Point (OCAP) for unmanned surface vehicles (USVs) to determine when to take appropriate actions to avoid collisions. The approach combines a model that accounts for the two degrees of freedom in USV dynamics with a velocity obstacle method for obstacle detection and avoidance. The method calculates the change in the USV’s navigation state based on the critical condition of collision avoidance. First, the coordinates of the optimal collision avoidance point in the current ship encounter state are calculated based on the relative velocities and kinematic parameters of the USV and obstacles. Then, the increments of the vessel’s linear velocity and heading angle that can reach the optimal collision avoidance point are set as a constraint for dynamic window sampling. Finally, the algorithm evaluates the probabilities of collision hazards for trajectories that satisfy the critical condition and uses the resulting collision avoidance probability value as a criterion for course assessment. The resulting collision avoidance algorithm is optimized for USV maneuverability and is capable of handling multiple moving obstacles in real-time. Experimental results show that the OCAP algorithm has higher and more robust path-finding efficiency than the other two algorithms when the dynamic obstacle density is higher.

No abstract