Safe binary particle swam algorithm for an enhanced unsupervised label refinement in automatic face annotation

Mining web facial images on the internet has become as a profitable and important paradigm towards auto face annotation technique. The unsupervised label refinement (ULR) is an effective method that can fix weakly labeled facial images data which are collected from the internet and included some images with wrong label. In order to improve the correction accuracy of ULR, particle swarm optimization (PSO) and binary particle swarm optimization (BPSO) are used for solving binary constraint optimization task in this study. A novel method named safe binary particle swam optimization (SBPSO) is also proposed to improve BPSO which has the probability over range problem for using the ULR. In addition, SBPSO is also employed for an enhanced ULR (EULR) objective function which is created by modifying the original formula of ULR to improve the accuracy of labeled facial image. An experimental database is queried from IMDb website which collected the actors who were bored in 1950 to 1990. Some error flags are randomly added in the database for the correction tests by different methods. The results showed that the SBPSO Algorithm for the EULR in automatic face annotation have the better label correction rate and convergence effect.     

Dual image watermarking by exploiting the properties of selected DCT coefficients with JND modeling

Multimedia Tools and Applications - The distinctive properties of partly sign-altered (PSA) coefficients in discrete cosine transform (DCT) domain are explored to achieve effective dual blind image...     

Design of Two-Step Random Access Procedure for URLLC Applications

The idea of Smart City incorporates a few ideas being technology, economy, governance, people, management, and infrastructure. This implies a Smart City can have distinctive communication needs. Wireless technologies, for example, WiFi, Zig Bee, Bluetooth, WiMax, 4G or LTE have introduced themselves as a solution for the communication in Smart City activities. Nonetheless, as the majority of them utilize unlicensed interference, coexistence and bands issues are increasing. So to solve the problem IoT is used in smart cities. This paper addresses the issues of both resource allocation and routing to propose an energy efficient, congestion aware resource allocation and routing protocol (ECRR) for IoT network based on hybrid optimization techniques. The first contribution of proposed ECRR technique is to employ the data clustering and metaheuristic algorithm for allocate the large-scale devices and gateways of IoT to reduce the total congestion between them. The second contribution is to propose a queue based swarm optimization algorithm for select a better route for future route based on multiple constraints, which improves the route discovering mechanism. The proposed ECRR technique is implemented in Network Simulator (NS-2) tool and the simulation results are compared with the existing state-of-art techniques in terms of energy consumption, node lifetime, throughput, end-to-end delay, packet delivery ratio and packet overheads.