Graph construction using adaptive Local Hybrid Coding scheme

Non-negative and local sparse coding based on l2-norm and Hessian regularization

We propose a new transductive label propagation method, termed Adaptive Neighborhood Propagation (Adaptive-NP) by joint L2,1-norm regularized sparse coding, for semi-supervised classification. To make the predicted soft labels more accurate for predicting the labels of samples and to avoid the tricky process of choosing the optimal neighborhood size or kernel width for graph construction, Adaptive-NP seamlessly integrates sparse coding and neighborhood propagation into a unified framework. That is, the sparse reconstruction error and classification error are combined for joint minimization, which clearly differs from traditional methods that explicitly separate graph construction and label propagation into independent steps, which may result in inaccurate predictions. Note that our Adaptive-NP alternately optimize the sparse codes and soft labels matrices, where the sparse codes are used as adaptive weights for neighborhood propagation at each iteration, so the tricky process of determining neighborhood size or kernel width is avoided. Besides, for enhancing sparse coding, we use the L2,1-norm constraint on the sparse coding coefficients and the reconstruction error at the same time for delivering more accurate and robust representations. Extensive simulations show that our model can deliver state-of-the-art performances on several public datasets for classification.

Semi-supervised two phase test sample sparse representation classifier

With the development of the underwater acoustic (UWA) adaptive communication system, energy-efficient transmission has become a critical topic in underwater acoustic (UWA) communications. Due to the unique characteristics of the underwater environment, the transmitter node will almost always have outdated channel state information (CSI), which results in low energy efficiency. In this paper, we take full advantage of bidirectional links and propose an adaptive modulation and coding (AMC) scheme that aims to maximize the long-term energy efficiency of a single link by jointly scheduling the coding rate, modulation order, and transmission power. Considering the complexity characteristics of UWA channels, we proposed a bit error ratio (BER) estimation method based on deep neural networks (DNN). The proposed network could realize channel estimation, feature extraction, and BER estimation by using a fixed pilot of the feedback link. Then, we design a channel classification method based on the estimated BERs of the modulation and coding scheme (MCS) and further model the UWA channels as a finite-state Markov chain (FSMC) with an unknown transition probability. Thus, we formulate the AMC problem as a Markov Decision Process (MDP) and solve it through a reinforcement learning framework. Considering the large state-action pairs, a double deep Q-network (DDQN) based scheme is proposed. Simulation results demonstrate that the proposed AMC scheme outperforms the fixed MCS with a perfect channel information state, and achieves near-optimal energy efficiency.

The challenge of the adaptive modulation and coding (AMC) scheme is to make a decision when to switch between different modulation and coding scheme. This is difficult because the performance of the AMC system is very sensitive to channel quality estimation errors and other channel impairments. In this paper, block error rate (BLER) performance of the wideband code division multiple access (WCDMA) system using AMC techniques are studied with nonideal channel and signal-to-interference-and-noise ratio (SINR) estimation and with the presence of multiuser interference. Also, the throughput of the adaptive system is simulated.

Code division multiple access (CDMA) in which the spreading code assignment to userscontains a random element has recently become a cornerstone of CDMA research. Therandom element in the construction is particularly attractive as it provides robustnessand flexibility in utilizing multi-access channels, whilst not making significantsacrifices in terms of transmission power. Random codes are generated from someensemble; here we consider the possibility of combining two standard paradigms,sparsely and densely spread codes, in a single composite code ensemble. Thecomposite code analysis includes a replica symmetric calculation of performance inthe large system limit, and investigation of finite systems through a compositebelief propagation algorithm. A variety of codes are examined with a focus onthe high multi-access interference regime. We demonstrate scenarios both in thelarge size limit and for finite systems in which the composite code has typicalperformance exceeding those of sparse and dense codes at equivalent signal to noiseratio.

Long Term Evolution (LTE) network offers a high throughput with low latency that makes it the best choice for Evolved Multimedia Broadcast Multicast Service (E-MBMS). E-MBMS transmits data to all users simultaneously using the same channel and same Modulation and Coding Scheme (MCS) level. Each user experiences different channel condition, so an MCS level should be selected properly to satisfy all users. Typically, MCS level is selected on the basis of users' worst channel condition which results in wasting network resources. Since the E-MBMS performance directly depends on the selected MCS level, an efficient Adaptive Modulation and Coding (AMC) scheme is essentially needed. This paper introduces a new mechanism that uses the Standard Deviation (SD) of MCS level of E-MBMS user group operated on single cell mode to efficiently select its optimal MCS level. Simulation results show that the proposed mechanism increase the spectrum efficiency, throughput, and lower Packet Loss Ratio compared to the Worst User Channel Condition mechanism and Fixed Predefined MCS mechanism.

Sparse Representation Classifier (SRC) and its variants were considered as powerful classifiers in the domains of computer vision and pattern recognition. However, classifying test samples is computationally expensive due to the $$\ell _1$$ norm minimization problem that should be solved in order to get the sparse code. Therefore, these classifiers could not be the right choice for scenarios requiring fast classification. In order to overcome the expensive computational cost of SRC, a two-phase coding classifier based on classic Regularized Least Square was proposed. This classifier is more efficient than SRC. A significant limitation of this classifier is the fact that the number of the samples that should be handed over to the next coding phase should be specified a priori. This paper overcomes this main limitation and proposes five data-driven schemes allowing an automatic estimation of the optimal size of the local samples. These schemes handle the three cases that are encountered in any learning system: supervised, unsupervised, and semi-supervised. Experiments are conducted on five image datasets. These experiments show that the introduced learning schemes can improve the performance of the two-phase linear coding classifier adopting ad-hoc choices for the number of local samples.

Recognition of emotional content in music is an issue that arises recently. Music received by live applications are often exposed to noise, thus prone to reducing the recognition rate of the application. The solution proposed in this study is a robust music emotion recognition system for live applications. The proposed system consists of two major parts, i.e. subspace-based noise suppression and a hierarchical sparse representation classifier, which is based on sparse coding and a sparse representation classifier (SRC). The music is firstly enhanced by fast subspace based noise suppression. Nine classes of emotion are then used to construct a dictionary, and the vector of coefficients is obtained by sparse coding. The vector can be divided into nine parts, and each of which models a specific emotional class of a signal. Since the proposed descriptor can provide emotional content analysis of different resolutions for emotional music recognition, this work regards vectors of coefficients as feature representations. Finally, a sparse representation based classification method is employed for classification of music into four emotional classes. The experimental results confirm the highly robust performance of the proposed system in emotion recognition in live music.

Image representation using local features and sparse coding (SC) plays a very important role in image classification when the dataset is fairly large. Despite of its worldwide popularity, there are still some improving space in classification efficiency and computational investment in training and coding phrase of SC. In this paper, we put forward a novel object categories recognition method from two aspects. First, the contextual relevance between image patches are fully utilized by merging local feature of every sub-patch with its neighboring ones into strong context features to generate the multiple sparse representations, which are received by the SC and multi-scale max pooling SPM(Spatial Pyramid Matching), respectively. Second, while calculating the sparse coefficients of SC, we need to solve L1-regularized least square problem. Screening out the zero coefficients and discarding the corresponding inactive codewords before solving Lasso problem can remarkably speed up the optimization. The proposed method outperforms state-of-the-art performance in a large number of image categorization experiments on several benchmarks: the ground truth dataset (21 Land-Use database), the event dataset (UIUC-Sport dataset), and the object recognition dataset (Caltech101 dataset).

Image representation using local features and sparse coding (SC) plays a very important role in image classification when the dataset is fairly large. Despite of its worldwide popularity, there are still some improving space in classification efficiency and computational investment in training and coding phrase of SC. In this paper, we put forward a novel object categories recognition method from two aspects. First, the contextual relevance between image patches are fully utilized by merging local feature of every sub-patch with its neighboring ones into strong context features to generate the multiple sparse representations, which are received by the SC and multi-scale max pooling SPM(Spatial Pyramid Matching), respectively. Second, while calculating the sparse coefficients of SC, we need to solve L1-regularized least square problem. Screening out the zero coefficients and discarding the corresponding inactive codewords before solving Lasso problem can remarkably speed up the optimization. The proposed method outperforms state-of-the-art performancein a large number of image categorization experiments on several benchmarks: the ground truth dataset (21 Land-Use database), the event dataset (UIUC-Sport dataset), and the object recognition dataset (Caltech101 dataset).

Parallel sparse and dense information coding streams in the electrosensory midbrain

In this paper, we develop a new efficient graph construction algorithm that is useful for many learning tasks. Unlike the main stream for graph construction, our proposed data self-representativeness approach simultaneously estimates the graph structure and its edge weights through sample coding. Compared with the recent l1 graph that is based on sparse coding, our proposed objective function has an analytical solution (based on self-representativeness of data) and thus is more efficient. This paper has two main contributions. Firstly, we introduce the Two Phase Weighted Regularized Least Square (TPWRLS) graph construction. Secondly, the obtained data graph is used, in a semi-supervised context, in order to categorize detected objects in driving/urban scenes using Local Binary Patterns as image descriptors. The experiments show that the proposed method can outperform competing methods.

Based on multiple maximum scatter difference discrimination Dictionary learning, a novel face recognition algorithm is proposed. Dictionary used for sparse coding plays a key role in sparse representation classification. In this paper, a multiple maximum scatter difference discriminated criterion is used for dictionary learning. During the process of dictionary learning, the multiple maximum scatter difference computes its discriminated vectors from both the range of the between class scatter matrix and the null space of the within-class scatter matrix. The proposed algorithm is theoretically elegant and easy to calculate. Extensive experimental studies conducted on the AR database and Extended Yale Database B in comparison with existing basic sparse representation and other classification methods, it shows that the performance is a little better than the original sparse representation methods with lower complexity.

Classic sparse representation for classification (SRC) method fails to incorporate the label information of training images, and meanwhile has a poor scalability due to the expensive computation for l_1 norm. In this paper, we propose a novel subspace sparse coding method with utilizing label information to effectively classify the images in the subspace. Our new approach unifies the tasks of dimension reduction and supervised sparse vector learning, by simultaneously preserving the data sparse structure and meanwhile seeking the optimal projection direction in the training stage, therefore accelerates the classification process in the test stage. Our method achieves both flat and structured sparsity for the vector representations, therefore making our framework more discriminative during the subspace learning and subsequent classification. The empirical results on 4 benchmark data sets demonstrate the effectiveness of our method.