Biblio

In image forensics, to determine whether the image is impurely transformed, it extracts and examines the features included in the suspicious image. In general, the features extracted for the detection of forgery images are based on numerical values, so it is somewhat unreasonable to use in the CNN structure for image classification. In this paper, the extraction method of a feature vector is using a least-squares solution. Treat a suspicious image like a matrix and its solution to be coefficients as the feature vector. Get two solutions from two images of the original and its median filter residual (MFR). Subsequently, the two features were formed into a visualized pattern and then fed into CNN deep learning to classify the various transformed images. A new structure of the CNN net layer was also designed by hybrid with the inception module and the residual block to classify visualized feature vector patterns. The performance of the proposed image forensics detection (IFD) scheme was measured with the seven transformed types of image: average filtered (window size: 3 × 3), gaussian filtered (window size: 3 × 3), JPEG compressed (quality factor: 90, 70), median filtered (window size: 3 × 3, 5 × 5), and unaltered. The visualized patterns are fed into the image input layer of the designed CNN hybrid model. Throughout the experiment, the accuracy of median filtering detection was 98% over. Also, the area under the curve (AUC) by sensitivity (TP: true positive rate) and 1-specificity (FP: false positive rate) results of the proposed IFD scheme approached to `1' on the designed CNN hybrid model. Experimental results show high efficiency and performance to classify the various transformed images. Therefore, the grade evaluation of the proposed scheme is “Excellent (A)”.

In Compositional data, the relative proportions of the components contain important relevant information. In such case, Euclidian distance fails to capture variation when considered within data science models and approaches such as partial least squares discriminant analysis (PLS-DA). Indeed, the Euclidean distance assumes implicitly that the data is normally distributed which is not the case of compositional vectors. Aitchison transformation has been considered as a standard in compositional data analysis. In this paper, we consider two other transformation methods, Isometric log ratio (ILR) transformation and data-based power (alpha) transformation, before feeding the data to PLS-DA algorithm for classification [1]. In order to investigate the merits of both methods, we apply them in two challenging information system security applications namely spam filtering and intrusion detection.

In today's interconnected world, universities recognize the importance of protecting their information assets from internal and external threats. Being the possible insider threats to Information Security, employees are often coined as the weakest link. Both employees and organizations should be aware of this raising challenge. Understanding staff perception of compliance behaviour is critical for universities wanting to leverage their staff capabilities to mitigate Information Security risks. Therefore, this research seeks to get insights into staff perception based on factors adopted from several theories by using proposed constructs i.e. "perceived" practices/policies and "perceived" intention to comply. Drawing from the General Deterrence Theory, Protection Motivation Theory, Theory of Planned Behaviour and Information Reinforcement, within the context of Palestine universities, this paper integrates staff awareness of Information Security Policies (ISP) countermeasures as antecedents to ``perceived'' influencing factors (perceived sanctions, perceived rewards, perceived coping appraisal, and perceived information reinforcement). The empirical study is designed to follow a quantitative research approaches, use survey as a data collection method and questionnaires as the research instruments. Partial least squares structural equation modelling is used to inspect the reliability and validity of the measurement model and hypotheses testing for the structural model. The research covers ISP awareness among staff and seeks to assert that information security is the responsibility of all academic and administrative staff from all departments. Overall, our pilot study findings seem promising, and we found strong support for our theoretical model.

The pattern recognition in the sparse representation (SR) framework has been very successful. In this model, the test sample can be represented as a sparse linear combination of training samples by solving a norm-regularized least squares problem. However, the value of regularization parameter is always indiscriminating for the whole dictionary. To enhance the group concentration of the coefficients and also to improve the sparsity, we propose a new SR model called adaptive sparse representation classifier(ASRC). In ASRC, a sparse coefficient strengthened item is added in the objective function. The model is solved by the artificial bee colony (ABC) algorithm with variable step to speed up the convergence. Also, a partition strategy for large scale dictionary is adopted to lighten bee's load and removes the irrelevant groups. Through different data sets, we empirically demonstrate the property of the new model and its recognition performance.

Block recursive least square (BRLS) algorithm for dictionary learning in compressed sensing system is developed for surveillance video processing. The new method uses image blocks directly and iteratively to train dictionaries via BRLS algorithm, which is different from classical methods that require to transform blocks to columns first and then giving all training blocks at one time. Since the background in surveillance video is almost fixed, the residual of foreground can be represented sparsely and reconstructed with background subtraction directly. The new method and framework are applied in real image and surveillance video processing. Simulation results show that the new method achieves better representation performance than classical ones in both image and surveillance video.

Tensor decompositions, which are factorizations of multi-dimensional arrays, are becoming increasingly important in large-scale data analytics. A popular tensor decomposition algorithm is Canonical Decomposition/Parallel Factorization using alternating least squares fitting (CP-ALS). Tensors that model real-world applications are often very large and sparse, driving the need for high performance implementations of decomposition algorithms, such as CP-ALS, that can take advantage of many types of compute resources. In this work we present ReFacTo, a heterogeneous distributed tensor decomposition implementation based on DeFacTo, an existing distributed memory approach to CP-ALS. DFacTo reduces the critical routine of CP-ALS to a series of sparse matrix-vector multiplications (SpMVs). ReFacTo leverages GPUs within a cluster via MPI to perform these SpMVs and uses OpenMP threads to parallelize other routines. We evaluate the performance of ReFacTo when using NVIDIA's GPU-based cuSPARSE library and compare it to an alternative implementation that uses Intel's CPU-based Math Kernel Library (MKL) for the SpMV. Furthermore, we provide a discussion of the performance challenges of heterogeneous distributed tensor decompositions based on the results we observed. We find that on up to 32 nodes, the SpMV of ReFacTo when using MKL is up to 6.8× faster than ReFacTo when using cuSPARSE.

The gradient-descent total least-squares (GD-TLS) algorithm is a stochastic-gradient adaptive filtering algorithm that compensates for error in both input and output data. We study the local convergence of the GD-TLS algoritlun and find bounds for its step-size that ensure its stability. We also analyze the steady-state performance of the GD-TLS algorithm and calculate its steady-state mean-square deviation. Our steady-state analysis is inspired by the energy-conservation-based approach to the performance analysis of adaptive filters. The results predicted by the analysis show good agreement with the simulation experiments.

A new class of affine-projection-like (APL) adaptive-filtering algorithms is proposed. The new algorithms are obtained by eliminating the constraint of forcing the a posteriori error vector to zero in the affine-projection algorithm proposed by Ozeki and Umeda. In this way, direct or indirect inversion of the input signal matrix is not required and, consequently, the amount of computation required per iteration can be reduced. In addition, as demonstrated by extensive simulation results, the proposed algorithms offer reduced steady-state misalignment in system-identification, channel-equalization, and acoustic-echo-cancelation applications. A mean-square-error analysis of the proposed APL algorithms is also carried out and its accuracy is verified by using simulation results in a system-identification application.

Recently, there has been a pronounced increase of interest in the field of renewable energy. In this area power inverters are crucial building blocks in a segment of energy converters, since they change direct current (DC) to alternating current (AC). Grid connected power inverters should operate in synchronism with the grid voltage. In this paper, the structure of a power system based on adaptive filtering is described. The main purpose of the adaptive filter is to adapt the output signal of the inverter to the corresponding load and/or grid signal. By involving adaptive filtering the response time decreases and quality of power delivery to the load or grid increases. A comparative analysis which relates to power system operation without and with adaptive filtering is given. In addition, the impact of variable impedance of load on quality of delivered power is considered. Results which relates to total harmonic distortion (THD) factor are obtained by Matlab/Simulink software.