Search

The objective of image hiding is to conceal a secret image in a cover image inconspicuously. The challenges for image hiding focus on the embedding capacity, image quality and security. To contend with these challenges, this paper presents a novel image hiding method using Invertible Rescaling Net (IRN) and Similarity of Bits Pairs (SBP). Because of the downscaling ability of IRN, our method is able to hide a secret image into a cover image with the same dimensions. Moreover, the superior rescaling capabilities of IRN enable us to produce a recovered image of high-quality. We improve the SBP embedding technique and combine it with differential coding to boost the quality of the stego image. In the experiments, the quality of the recovered secret image and stego image is assessed using various quality evaluation metrics, and for the security, the anti-steganalysis performance is also evaluated in this paper. Extensive experimental results reveal that the quality of both the recovered secret image and the stego-image in our method outperforms several advanced methods and provides a high degree of security. • We apply invertible rescaling net (IRN) to image hiding task for the first time. • We improve the SBP encoding algorithm to prevent the degradation of the quality of the stego image. • Our method considers the robustness against the classical adversary's steganalysis. [ABSTRACT FROM AUTHOR]

The one-hot 0/1 encoding method is the most popularized encoding method of class labels for classification tasks. Despite its simplicity and popularity, it comes with limitations and weaknesses, like failing to capture the inherent uncertainty in data labels, and making classifiers more prone to overfitting. In this paper, these shortcomings are tackled with a framework for learning soft label embeddings. Two variants are proposed: first, a learnable general-class embedding which aims to capture information regarding inter-class similarities, and second, a neural architecture which can be added to any neural classifier and aims to learn inter-instance similarities. The inherent uncertainty in data labels is thus somewhat alleviated, allowing the network to focus on incorrectly classified samples, instead of difficult but correctly classified ones. The experimental study on multiple classification benchmarks of increasing difficulty, using neural networks of varying depth and width, show that the proposed method leads to better classification accuracy, highlighting its ability to generalize to unseen samples. • One-hot label encoding leads to classifier overfitting soft labels alleviate problem. • Learnable label embedding framework captures similarities between samples and classes. • Experiments on network of various depths and multiple datasets showcase effectiveness. [ABSTRACT FROM AUTHOR]

Many neural network methods such as ML-RBF and BP-MLL have been used for multi-label classification. Recently, extreme learning machine (ELM) is used as the basic elements to handle multi-label classification problem because of its fast training time. Extreme learning machine based auto encoder (ELM-AE) is a novel method of neural network which can reproduce the input signal as well as auto encoder, but it can not solve the over-fitting problem in neural networks elegantly. Introducing weight uncertainty into ELM-AE, we can treat the input weights as random variables following Gaussian distribution and propose weight uncertainty ELM-AE (WuELM-AE). In this paper, a neural network named multi layer ELM-RBF for multi-label learning (ML-ELM-RBF) is proposed. It is derived from radial basis function for multi-label learning (ML-RBF) and WuELM-AE. ML-ELM-RBF firstly stacks WuELM-AE to create a deep network, and then it conducts clustering analysis on samples features of each possible class to compose the last hidden layer. ML-ELM-RBF has achieved satisfactory results on single-label and multi-label data sets. Experimental results show that WuELM-AE and ML-ELM-RBF are effective learning algorithms. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) is one of the most important technologies in this century. As sensor nodes have limited energy resources, designing energy-efficient routing algorithms for WSNs has become the research focus. And because WSNs routing for maximizing the network lifetime is a NP-hard problem, many researchers try to optimize it with meta-heuristics. However, due to the uncertain variable number and strong constraints of WSNs routing problem, most meta-heuristics are inappropriate in designing routing algorithms for WSNs. This paper proposes an Improved Harmony Search Based Energy Efficient Routing Algorithm (IHSBEER) for WSNs, which is based on harmony search (HS) algorithm (a meta-heuristic). To address the WSNs routing problem with HS algorithm, several key improvements have been put forward: First of all, the encoding of harmony memory has been improved based on the characteristics of routing in WSNs. Secondly, the improvisation of a new harmony has also been improved. We have introduced dynamic adaptation for the parameter HMCR to avoid the prematurity in early generations and strengthen its local search ability in late generations. Meanwhile, the adjustment process of HS algorithm has been discarded to make the proposed routing algorithm containing less parameters. Thirdly, an effective local search strategy is proposed to enhance the local search ability, so as to improve the convergence speed and the accuracy of routing algorithm. In addition, an objective function model that considers both the energy consumption and the length of path is developed. The detailed descriptions and performance test results of the proposed approach are included. The experimental results clearly show the advantages of the proposed routing algorithm for WSNs. [ABSTRACT FROM AUTHOR]

In this paper, a novel solving method for speech signal chaotic time series prediction model was proposed. A phase space was reconstructed based on speech signal's chaotic characteristics and the genetic programming (GP) algorithm was introduced for solving the speech chaotic time series prediction models on the phase space with the embedding dimension m and time delay τ . And then, the speech signal's chaotic time series models were built. By standardized processing of these models and optimizing parameters, a speech signal's coding model of chaotic time series with certain generalization ability was obtained. At last, the experimental results showed that the proposed method can get the speech signal chaotic time series prediction models much more effectively, and had a better coding accuracy than linear predictive coding (LPC) algorithms and neural network model. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel visual tracking algorithm using the collaboration of generative and discriminative trackers under the particle filter framework. Each particle denotes a single task, and we encode all the tasks simultaneously in a structured multi-task learning manner. Then, we implement generative and discriminative trackers, respectively. The discriminative tracker considers the overall information of object to represent the object appearance; while the generative tracker takes the local information of object into account for handling partial occlusions. Therefore, two models are complementary during the tracking. Furthermore, we design an effective dictionary updating mechanism. The dictionary is composed of fixed and variational parts. The variational parts are progressively updated using Metropolis–Hastings strategy. Experiments on different challenging video sequences demonstrate that the proposed tracker performs favorably against several state-of-the-art trackers. [ABSTRACT FROM AUTHOR]

Problems in power distribution system reconfiguration (PDSR), such as service restoration, power loss reduction, and expansion planning, are usually formulated as complex multi-objective and multi-constrained optimization problems. Several evolutionary algorithms (EAs) have been developed to deal with PDSR problems, but the majority of EAs still demand high running time when applied to large-scale distribution systems (thousands of buses and switches). This paper presents a new approach for service restoration in large scale distribution systems that employs a discrete differential evolution with ancestor tree (DE-Tree). We combine the node-depth encoding (NDE) to represent computationally the electrical topology of the system and the ancestor tree presented here to implement differential evolution for service restoration problems. The ancestor tree is used to build a list of elementary movements that maps one solution in the search space into another, thus capturing the "difference" between forests encoded with the NDE, which is essential in the search engine of differential evolution. The use of an ancestor tree is not only central to implement differential mutation in our algorithm but also can track the sequence of switching operations in the restoration of the system after the optimization process is finished. The proposed approach makes differential evolution suitable for treating combinatorial optimization problems related to PDSR. Results presented on distribution system reconfiguration problems suggest the benefits and fast convergence of the proposed approach. [ABSTRACT FROM AUTHOR]