Singular Value Decomposition (svd)

Pseudo-entropy and SVD entropy are generalizations of the entanglement entropy that involve post-selection. In this work we analyze their properties as measures on the spaces of quantum states and argue that their excess provides useful characterization of a difference between two (i.e. pre-selected and post-selected) states, which shares certain features and in certain cases can be identified as a metric. In particular, when applied to link complement states that are associated to topological links via Chern-Simons theory, these generalized entropies and their excess provide a novel quantification of a difference between corresponding links. We discuss the dependence of such entropy measures on the level of Chern-Simons theory and determine their asymptotic values for certain link states. We find that imaginary part of the pseudo-entropy is sensitive to, and can diagnose chirality of knots. We also consider properties of entropy measures for simpler quantum mechanical systems, such as generalized SU(2) and SU(1,1) coherent states, and tripartite GHZ and W states.

A big challenge that faces many applications in different fields suffers in dealing with datasets of massive
size. Additionally, retrieving and casting this data is somewhat time-consuming. Applications such as government or any
institution election, surveys, healthcare …etc., leverage techniques of data reduction, dimensionality reduction, matrix
decomposition, or compression such as the Singular Value Decomposition Technique. Our paper shows the use of this
technique as a method in certain circumstances where data is of binary type and can be retrieved, cast, or updated in less
time and in a smaller size without losing any information. In other words, we prove practically that the massive size of
binary values can be managed in a form of matrices with low rank (low rank is one of the bases used in the Singular
Value Decomposition technique) to return the exact matrix of information instead of dealing with the original large
matrix of data. The experimental results are implemented on a Lenovo machine, Intel Corei5, CPU 2.5GH with 8GB of
RAM, using visual basic, C#, in Visual Studio 2019 environment.

Regular E-voting systems for elections may count the votes in less time,less cost,save the privacy of citizens,but still considered risky as votes can be tampered.E-voting systems based on a network distributed ledger show fast results,more trusted,save privacy,cannot be tampered,and distributed in which no central organization controls the system.This paper illustrate an e-voting system to solve the challenge of a massive ledger that is distributed among network-nodes using a data reduction technique as a security-matching-tool,singular value decomposition(SVD) that handle a copy of election results in another form and matched with the SQL-database results to announce a successful election-event representing a transparency-powerful-secured-system

With the increasing availability of location-based services, location-based social networks and smart phones, standard rating schema of recommender systems that involve user and item dimensions is extended to three-dimensional (3-D) schema involving context information. Although there are models proposed for dealing with data in this form, the problem of combining it with additional features and constructing a general model suitable for different forms of recommendation system techniques has not been fully explored. This work proposes a technique to reduce 3-D rating data into 2-D for two reasons: employing already developed efficient methods for 2-D on a 3-D data and expanding it with additional features, which are usually 2-D also, if it is necessary. Our experiments show that this reduction is effective. The proposed 2-D model supports content-based, collaborative filtering and hybrid recommendation approaches effectively, whereas we have achieved the best accuracy results for pure collaborative filtering recommendation model. Since our method was built on efficient singular value decomposition-based dimension reduction idea, it also works very efficiently, and in our experiments, we have obtained better run-time results than standard methods developed for 3-D data using higher-order singular value decomposition.

Recent matrix completion based methods have not been able to properly model the Haplotype Assembly Problem (HAP) for noisy observations. To deal with such cases, we propose a new Minimum Error Correction (MEC) based matrix completion problem over the manifold of rank-one matrices. We then prove the convergence of a specific iterative algorithm to solve this problem. From the simulation results, the proposed method not only outperforms some well-known matrix completion based methods, but also shows a more accurate result compared to a most recent MEC based algorithm for haplotype estimation.

A new optimization design is proposed for matrix completion by weighting the measurements and deriving the corresponding error bound. Accordingly, the Haplotype reconstruction using nuclear norm minimization with Weighted Constraint (HapWeC) is devised for haplotype estimation. Computer simulations show the outperformance of the HapWeC compared to some recent algorithms in terms of the normalized reconstruction error and reconstruction rate.

We apply matrix completion methods for haplotype assembly from NGS reads to develop the new HapSVT, HapNuc, and HapOPT algorithms. This is performed by applying a mathematical model to convert the reads to an incomplete matrix and estimating unknown components. This process is followed by quantizing and decoding the completed matrix in order to estimate haplotypes. These algorithms are compared to the state-of-the-art algorithms using simulated data as well as the real fosmid data. It is shown that the SNP missing rate and the haplotype block length of the proposed HapOPT are better than those of HapCUT2 with comparable accuracy in terms of reconstruction rate and switch error rate. A program implementing the proposed algorithms in MATLAB is freely available at https://github.com/smajidian/HapMC.

Wav2vec2 self-supervised multilingual training learns speech units common to multiple languages, leading to better generalization capacity. However, Wav2vec2 is larger than other E2E ASR models such as the Conformer ASR. Therefore, the objective of this work is to reduce the Wav2vec footprint by pruning lines from the intermediate dense layers of the encoder block, since they represent about two thirds of the encoder parameters. We apply Genetic Algorithms (GA) to solve the combinatorial optimization problem associated with pruning, which means running many copies of the Wav2vec2 decoder in parallel using multiprocessing on a computer grid, so an effort was made to optimize the GA for good performance with few CPUs. The experiments show a small absolute word error rate damage of 0.21% (1.26% relative) for a pruning of 40% and compare this value with those of the usual L1-norm pruning and model restructuring by singular value decomposition.

In this paper the behavior of a novel, SVD-based adaptive controller is compared with that of the most sophisticated and popular method introduced by Slotine & Li by the use of a three degree of freedom paradigm, the cart + double pendulum system with dynamic friction. The essential difference between the two approaches is that while the Slotine-Li method tries to identify the parameters of the precise analytical model of the robot on the basis of the assumption that the generalized forces are known, the novel one makes do with the temporal observation of the desired vs. realized response of the system and does not assume the lack of unknown perturbations caused e.g. by internal friction. Its another advantge is that it needs the execution of the SVD only on a rough model of the system only one times, before the commencement of the control cycle within which it works with simple computations. The novel method has the deficiency that in principle it can get out of the region of its convergence so its design and use needs preliminary simulation investigations. However, simulation examples exemplify that its convergence can be guaranteed for practical purposes.

2MAM Group of Institutions, Siruganur, Tiruchirappalli 621 105, India Received 18 November 2011; revised 19 March 2012; accepted 21 March 2012 This study proposes a blind watermarking algorithm based on Double Haar Wavelet Transform (DHWT) for copyright protection of digital images. Watermark embedding is performed in wavelet transform domain. DHWT is applied to the original cover image and binary watermark. Singular value decomposition (SVD) is applied on selected subband of cover image and binary watermark. Eigen values of selected subband of cover image are replaced by Eigen values of selected subband of binary watermark, which are multiplied with an appropriate strength factor. Proposed algorithm achieved very high imperceptibility, evidenced by high PSNR value for gray scale images, and produced very high robustness against image processing attacks.

Dimension reduction is critical for many database and data mining applications, such as efficient storage and retrieval of high-dimensional data. In the literature, a well-known dimension reduction scheme is Linear Discriminant Analysis (LDA). The common aspect of previously proposed LDA based algorithms is the use of Singular Value Decomposition (SVD). Due to the difficulty of designing an incremental solution for the eigenvalue problem on the product of scatter matrices in LDA, there is little work on designing incremental LDA algorithms. In this paper, we propose an LDA based incremental dimension reduction algorithm, called IDR/QR, which applies QR Decomposition rather than SVD. Unlike other LDA based algorithms, this algorithm does not require the whole data matrix in main memory. This is desirable for large data sets. More importantly, with the insertion of new data items, the IDR/QR algorithm can constrain the computational cost by applying efficient QR-updating techniques. Finally, we evaluate the effectiveness of the IDR/QR algorithm in terms of classification accuracy on the reduced dimensional space. Our experiments on several real-world data sets reveal that the accuracy achieved by the IDR/QR algorithm is very close to the best possible accuracy achieved by other LDA based algorithms. However, the IDR/QR algorithm has much less computational cost, especially when new data items are dynamically inserted.

It has become an important task for many voltage stability studies to find a voltage stability index. The voltage stability indices provide reliable information about proximity of voltage instability in a power system. In this paper, the L indicator has been proposed, which aims to detect the weakest load buses in the electrical power networks. The L indicator has been checked by its application to the (WSCC 9-bus and IEEE 14-bus) test systems. Finally, the proposed indicator has been applied to the Iraqi power grid (400 kV) considering different contingencies, such as lines outage, generated power reduction and loading increase. The short computation time of this indicator and its efficient detection of the weakest load buses in the Iraqi power grid, allow the operators to apply it in online voltage stability monitoring based on measurements.

The paper examines changes in air temperature, precipitation, and river discharges on seasonal and annual scale over the Sava River watershed in Bosnia & Herzegovina during the period 1961–2016. Based upon data gathered from 11 meteorological stations and 3 hydrological stations, hydroclimatic variables trends were established by utilizing the nonparametric Mann-Kendall test and the nonparametric Sen’s slope estimator. The results show significant positive seasonal and annual trends (expect for autumn, during which upward trends were insignificant) in air temperature, whereas both positive and negative insignificant seasonal and annual precipitation trends are shown where determined for the entire watershed. Most prominent upward trends in air temperature were found in summer and afterwards in winter and spring, indicating a pronounced warming tendency over the Sava River watershed. Trends in river discharge displayed a negative tendency in all seasons. Nevertheless, a majority of e...

An algorithm for filtering the images contaminated by additive white Gaussian noise is proposed. The algorithm uses the groups of Hadamard transformed patches of discrete cosine coefficients to reject noisy components according to Wiener filtering approach. The groups of patches are found by the proposed block similarity search algorithm of reduced complexity performed on block patches in transform domain. When the noise variance is small, the proposed filter uses an additional stage based on principal component analysis; otherwise the experimental Wiener filtering is performed. The obtained filtering results are compared to the state of the art filters in terms of peak signal-to-noise ratio and structure similarity index. It is shown that the proposed algorithm is competitive in terms of signal to noise ratio and almost in all cases is superior to the state of the art filters in terms of structure similarity.

Epochal documents suffer from several types of noises that accumulate and evolve over time. This significantly affects their quality and makes their storage and the interpretation of their visual content problematic. Digital preservation seems the most viable and the most promising. Moreover, measuring the amount of degradation and quality assessment of degraded documents is highly desirable for applications such as selecting the proper algorithms for enhancement and analysis of document images, filtering the damaged images, tuning the processing algorithms parameters, document repairing, psychological study, etc. The first contribution of this work is the proposition of an efficient Multi-distortion Document Quality Measure (MDQM) for quality assessment of physically degraded document images. The proposed MDQM metric is based on three sets of spatial and frequency image features. These features are extracted from two layers of text and non-text and mapped to the mean opinion scores (MOS) using the regression function. The second contribution of this work is to estimate the probability of four common document image distortion types, namely, paper translucency, stain, readers annotations and worn holes in the degraded images. In our experiment, the correlations of seven no-reference image quality assessment (NR-IQA) metrics with the MOS values are evaluated on two available datasets. It is shown that the performance of MDQM metric is significantly better than the state-of-the-art NR-IQA metrics. Moreover, the experimental results demonstrate that MDQM metric not only leads to high efficacy for classification of the various degradations but also maintains a remarkable run-time efficiency. It is worth to mention that the proposed method has been conducted for Arabic documents

A novel method and software system for rational handling of time series of multi-channel measurements is presented. This quantitative learning tool, the On-The-Fly Processing (OTFP), develops reduced-rank bilinear subspace models that summarise massive streams of multivariate responses, capturing the evolving covariation patterns among the many input variables over time and space. Thereby, a considerable data compression can be achieved without significant loss of useful systematic information. The underlying proprietary OTFP methodology is relatively fast and simple-it is linear/bilinear and does not require a lot of raw data or huge cross-correlation matrices to be kept in memory. Unlike conventional compression methods, the approach allows the high-dimensional data stream to be graphically interpreted and quantitatively utilised-in its compressed state. Unlike adaptive moving-window methods, it allows all past and recent time points to be reconstructed and displayed simultaneously. This new approach is applied to four different case-studies: i) multi-channel Vis-NIR spectroscopy of the Belousov-Zhabotinsky reaction, a complex, ill understood chemical process; ii) quality control of oranges by hyperspectral imaging; iii) environmental monitoring by airborne hyperspectral imaging; iv) multisensor process analysis in the petrochemical industry. These examples demonstrate that the OTFP can automatically develop high-fidelity subspace data models, which simplify the storage/transmission and the interpretation of more or less continuous time series of high-dimensional measurements-to the extent there are covariations among the measured variables.

Grain yield stability is an important feature of crop breeding programs due mainly to the high annual variation in mean yield, particularly in arid and semi-arid areas. Conventional statistical models of stability analysis provide little or no insight into patterns of genotype × environment (GE) interaction, though the genotype plus GE (GGE) biplot method can more effectively account for the under GE interaction patterns. This study evaluated the yield stability of 20 spring durum wheat genotypes grown in five different warm locations in Iran across four cropping cycles (2009-2013) and used GGE biplot analysis to evaluate the yield stability of the genotypes and test locations by climatic factors. The combined analysis of variance revealed that the main effects of genotypes, locations, and years were significant, as well as the corresponding interaction effects. A polygon view of GGE biplot indicated that there were three winning genotypes (G10, G8, and G20) in three mega-environmen...

Research in the fields of machine learning and intelligent systems addresses essential problem of developing computer algorithms that can deal with huge amounts of data and then utilize this data in an intellectual way to solve a variety of real-world problems. In many applications, to interpret data with a large number of variables in a meaningful way, it is essential to reduce the number of variables and interpret linear combinations of the data. Principal Component Analysis (PCA) is an unsupervised learning technique that uses sophisticated mathematical principles to reduce the dimensionality of large datasets. The goal of this paper is to provide a complete understanding of the sophisticated PCA in the fields of machine learning and data dimensional reduction. It explains its mathematical aspect and describes its relationship with Singular Value Decomposition (SVD) when PCA is calculated using the covariance matrix. In addition, with the use of MATLAB, the paper shows the usefulness of PCA in representing and visualizing Iris dataset using a smaller number of variables.

Research in the fields of machine learning and intelligent systems addresses essential problem of developing computer algorithms that can deal with huge amounts of data and then utilize this data in an intellectual way to solve a variety of real-world problems. In many applications, to interpret data with a large number of variables in a meaningful way, it is essential to reduce the number of variables and interpret linear combinations of the data. Principal Component Analysis (PCA) is an unsupervised learning technique that uses sophisticated mathematical principles to reduce the dimensionality of large datasets. The goal of this paper is to provide a complete understanding of the sophisticated PCA in the fields of machine learning and data dimensional reduction. It explains its mathematical aspect and describes its relationship with Singular Value Decomposition (SVD) when PCA is calculated using the covariance matrix. In addition, with the use of MATLAB, the paper shows the usefulness of PCA in representing and visualizing Iris dataset using a smaller number of variables.

Uploading an identity card as an image for the account verification process or transactions online can be a threat to application users. Identity card theft can be carried out by irresponsible persons if the application can be hacked. Therefore, protection of the image is required for authentication. In this study, the proposed technique is watermarking. A watermark in the form of a binary image will be embedded into the image as ownership using a Discrete Cosine Transform. The Discrete Cosine Transform works in the frequency domain. The location of the embedding of different watermarks was analysed in each 8×8 DCT block. The results of the analysis to assess the imperceptibility of original images and watermarked images using PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index Measure), while assessing the watermark robustness embedded using NCC (Normalized Cross Correlation). The results show PSNR (Peak Signal to Noise Ratio) ≥ 54 dB with a watermark strength o...

With the increasing availability of location-based services, location-based social networks and smart phones, standard rating schema of recommender systems that involve user and item dimensions is extended to three-dimensional (3-D) schema involving context information. Although there are models proposed for dealing with data in this form, the problem of combining it with additional features and constructing a general model suitable for different forms of recommendation system techniques has not been fully explored. This work proposes a technique to reduce 3-D rating data into 2-D for two reasons: employing already developed efficient methods for 2-D on a 3-D data and expanding it with additional features, which are usually 2-D also, if it is necessary. Our experiments show that this reduction is effective. The proposed 2-D model supports content-based, collaborative filtering and hybrid recommendation approaches effectively, whereas we have achieved the best accuracy results for pure collaborative filtering recommendation model. Since our method was built on efficient singular value decomposition-based dimension reduction idea, it also works very efficiently, and in our experiments, we have obtained better run-time results than standard methods developed for 3-D data using higher-order singular value decomposition.

With the increasing availability of location-based services, location-based social networks and smart phones, standard rating schema of recommender systems that involve user and item dimensions is extended to three-dimensional (3-D) schema involving context information. Although there are models proposed for dealing with data in this form, the problem of combining it with additional features and constructing a general model suitable for different forms of recommendation system techniques has not been fully explored. This work proposes a technique to reduce 3-D rating data into 2-D for two reasons: employing already developed efficient methods for 2-D on a 3-D data and expanding it with additional features, which are usually 2-D also, if it is necessary. Our experiments show that this reduction is effective. The proposed 2-D model supports content-based, collaborative filtering and hybrid recommendation approaches effectively, whereas we have achieved the best accuracy results for pure collaborative filtering recommendation model. Since our method was built on efficient singular value decomposition-based dimension reduction idea, it also works very efficiently, and in our experiments, we have obtained better run-time results than standard methods developed for 3-D data using higher-order singular value decomposition.

In recent years, ecommerce applications in Cameroon have grown significantly, resulting in a wide array of products. However, improving user experience remains a major challenge for existing platforms, particularly with their categorical-based recommendation systems. These systems recommend products based on user purchases within a specific category, which has proven to be inefficient. With the rise of machine learning, alternative solutions offering improved performance have emerged. This report presents the development and evaluation of an ecommerce application with a machine learning-based recommendation system. The project aims to enhance personalized shopping experiences, increase company revenue, and improve customer satisfaction through accurate and relevant product recommendations. The recommendation system employs collaborative filtering, neural networks, content-based, and knowledge-based methods, trained on a dataset of 10,000 records from GroupLens capturing product ratings by hundreds of users in Cameroon. The evaluation indicates promising accuracy (60%), mean reciprocal rank (MRR) of 0.26, mean absolute error (MAE) of 0.214, root mean squared error (RMSE) of 0.370, precision of 0.8, and recall of 0.8. Recently, the ecommerce app was hosted at https://hooyia-market.onrender.com, attracting 13 new user registrations within a week. Where 45 products were added to the cart, with 15 directly influenced by the recommendation system, representing 33.3% of total cart additions. Additionally, the recommendation-driven purchases may lead to a 33.3% increase in sales. The findings demonstrate the hybrid recommendation system's effectiveness in providing accurate and relevant recommendations, significantly enhancing shopping experiences and user engagement in Cameroon. Overall, this project contributes to the field of ecommerce and machine learning, showcasing a successful implementation and evaluation of a hybrid recommendation system tailored for Cameroon. The results serve as a valuable reference for ecommerce companies seeking similar approaches to enhance customer experiences, increase revenue, and foster business growth.
Keywords: Ecommerce, Recommendation System, Hybrid Models, Cameroon, Sales Impact, Customer Satisfaction.

Machine Learning algorithms have a variety of important applications, and among them, Recommender systems are crucial. The internet hosts an extensive volume of information, making it challenging for users to navigate and find relevant content. Recommender systems have therefore emerged as valuable tools to bridge this gap. They facilitate the connection between users and relevant content by offering personalized recommendations. In recent years personalized recommendation service has become a hotspot of web technology, and is widely used in information, shopping, film and television, etc. Recommender systems have been proved to be an important response to the information overload problem.
In this research paper, we describe our approach for a Movie Recommender System Utilizing Mean Reversion via the Bollinger Bands formulae. Collaborative filtering is a popular technique used in Recommender systems. However, it poses a challenge in the form of the cold start issue, where new users are added to the system without any ratings, and the filter is unable to offer useful recommendations due to a lack of understanding of their preferences. Similarly, newly released movies without any ratings also suffer from the same issue, leading to recommendations reinforcing themselves.
To address this challenge, we incorporated the concept of Mean Reversion, which is a fundamental component of Natural Mathematics. Mean Reversion helps in mitigating the cold start issue by bringing new users and newly released movies into the fold of the Recommender system.
Mean reversion is a statistical concept that refers to the tendency of a series of values to return to its long-term average after experiencing temporary fluctuations. In the context of Recommender systems, Mean Reversion can be used to address the cold start issue by estimating the average rating for a movie and adjusting it based on a new user's preference. This technique can help improve the accuracy of recommendations, particularly for new users and newly released movies that lack sufficient data.

Digital watermarking is a technique of embedding some information (usually hidden copyright notices) into an image. Number of applications has been found in various fields like copyright protection, content authentication, document annotation, medical imaging. So, an enhanced semi-blind, hybrid digital image watermarking scheme based on discrete wavelet transform (DWT) and singular value decomposition (SVD) is our proposed approach in this paper. To increase and control the strength of the watermark, we used a scale factor. our proposed approach, the watermark is not embedded directly on the wavelet coefficients but rather than watermark wavelet coefficient are inserted on singular values of the cover images with modifying wavelet transform (DWT) HL1 sub band. Experimental results clearly show that this proposed scheme is quite resilient to various image processing attacks.

In this paper the behavior of a novel, SVD-based adaptive controller is compared with that of the most sophisticated and popular method introduced by Slotine & Li by the use of a three degree of freedom paradigm, the cart + double pendulum system with dynamic friction. The essential difference between the two approaches is that while the Slotine-Li method tries to identify the parameters of the precise analytical model of the robot on the basis of the assumption that the generalized forces are known, the novel one makes do with the temporal observation of the desired vs. realized response of the system and does not assume the lack of unknown perturbations caused e.g. by internal friction. Its another advantge is that it needs the execution of the SVD only on a rough model of the system only one times, before the commencement of the control cycle within which it works with simple computations. The novel method has the deficiency that in principle it can get out of the region of its convergence so its design and use needs preliminary simulation investigations. However, simulation examples exemplify that its convergence can be guaranteed for practical purposes.

Center Symmetric Local Binary Pattern (CSLBP) is widely used in texture and object detection, but its utilization in image hashing is still limited. Image hashing is a powerful technique to identify whether image content is changed or preserved. Two main issues in image hashing are its compact length and its robust discrimination power. To deal with these issues, a robust image hashing method is proposed by combining features of CSLBP and Discrete Wavelet Transform(DWT). CSLBP is applied on LL band of DWT for compact length hash. Discrimination power of hashing is enhanced by weigh factor which comprises information from all sub bands of 1-Level DWT. All sub-band images of 1-Level DWT is combined to form secondary image. Local statistical features like Standard Deviation and Magnitude Average are calculated to obtain local weight factor MASD (Magnitude Average and Standard Deviation). Weighted LL-CSLBP histogram is constructed using this weight factor. Experimental results are demonstrated with Receiver Operating Characteristics (ROC) and Normalized Hamming Distance (NHD). The results shows that, the proposed scheme is robust against content preserving operations and sensitive to malicious operations.

New software applications for linear multivariable system identification are presented. The incorporated algorithms use subspace-based techniques (MOESP, N4SID, or their combination) to find a standard discrete-time state-space description, and optionally the covariance matrices and Kalman predictor gain, using input and output (I/O) trajectories. For flexibility, separate applications are offered for obtaining the processed triangular factor of the structured, block-Hankel-block matrix of I/O data (using fast or standard QR factorization algorithms), for computing the system and predictor matrices, for estimating the initial state of the system, and for simulating and evaluating the model. The applications are encapsulated in Docker containers, which are managed by the Kubernetes platform on a Linux machine. This ensures greater flexibility, enhanced security, and fast execution. The services to be implemented are part of a
cloud-based open platform for process control applications.

This paper presents the design and finite difference time domain (FDTD) modeling of millimeter wave aperture coupled microstrip antenna that can be realized as a on chip antenna in wireless sensor nodes. At millimeter wave frequency, antenna form factor is very low and hence integration of this antenna with the transceiver components as a single system on-chip, minimizes power consumption and system cost. Offchip antenna increases the size of the sensor node and raises the system cost. The proposed antenna contributes impedance bandwidth of 3 GHz (59 GHz – 62 GHz) and maximum gain of 6.8 dBi. The proposed antenna occupies an area of 1500 μm × 2000 μm on a RT Duroid substrate of dimension 3000 μm × 3000 μm × 1500 μm. Due to very low antenna form factor, the proposed antenna along with the transceiver and sensor components can be integrated into a single system on chip with less system cost for wireless sensor networks.

In order to identify the weakest bus in a power system so that the Unified Power Flow Controller could be connected, an investigation of static and dynamic voltage stability is presented. Two stability indices, static and dynamic, have been proposed in the thesis. Multi-Input Multi-Output (MIMO) analysis has been used for the dynamic stability analysis. Results based on the Western System Coordinate Council (WSCC) 3-machine, 9-bus test system and IEEE 14 bus Reliability Test System (RTS) shows that these indices detect with the degree of accuracy the weakest bus, the weakest line and the voltage stability margin in the test system before suffering from voltage collapse. Recently, Flexible Alternating Current Transmission systems (FACTs) have become significant due to the need to strengthen existing power systems. The UPFC has been identified in literature as the most comprehensive and complex FACTs equipment that has emerged for the control and optimization of power flow in AC trans...

Problem statement: An important early sign of breast cancer is the clusters of micro calcifications in digital mammograms. To assist radiologists in the diagnosis of mammographic clusters a novel hybrid algorithm has been developed. Approach: A method, for detecting micro calcification in mammograms based on combined feature set with Ant Colony Optimization (ACO) was proposed. The diagonal matrix 'S' obtained from the Singular Value Decomposition (SVD) of LL band of wavelet transform was used as one of the feature set for classification of mammogram. A new approach for detecting micro calcifications in mammograms employing Jacobi Moments was proposed. The set of Jacobi polynomials were orthogonal and this ensured minimal information redundancy between the moments. Results and Conclusion: Jacobi moments include the properties of well-known Zernike, Legendre and Tchebichef moments. Ant Colony Optimization (ACO) was used for reducing the Jacobi feature set dimensionality through selecting a subset of features that performed well in the classification phase. The selected Jacobi feature set were combined with 'S' matrix to achieve the better classification rate of over 90%.

In this paper, a new no-reference image quality assessment (NR-IQA) metric for grey images is proposed using LIVE II image database. The features used are extracted from three well-known NR-IQA objective metrics based on natural scene statistical attributes from three different domains. These metrics may contain redundant, noisy or less informative features which affect the quality score prediction. In order to overcome this drawback, the first step of our work consists in selecting the most relevant image quality features by using Singular Value Decomposition (SVD) based dominant eigenvectors. The second step is performed by employing Relevance Vector Machine (RVM) to learn the mapping between the previously selected features and human opinion scores. Simulations demonstrate that the proposed metric performs very well in terms of correlation and monotonicity.

A new method is presented for simulation of nonlinear transmission line circuits based on proper orthogonal decomposition reduction techniques coupled with an efficient interpolatory algorithm. Evaluation of the nonlinear function and corresponding Jacobian is performed in the reduced domain. A key criterion is developed for a priori determination of the dimension of the interpolation space leading to a substantial reduction in the computational cost. The proposed algorithm is applicable to general nonlinear circuits and does not impose any constraints on the topology of the pertinent circuit or type of the nonlinear components.

This paper presents a novel hierarchical coding scheme for light fields based on transmittance patterns of low-rank multiplicative layers and Fourier disparity layers. The proposed scheme identifies multiplicative layers of light field view subsets optimized using a convolutional neural network for different scanning orders. Our approach exploits the hidden low-rank structure in the multiplicative layers obtained from the subsets of different scanning patterns. The spatial redundancies in the multiplicative layers can be efficiently removed by performing low-rank approximation at different ranks on the Krylov subspace. The intra-view and interview redundancies between approximated layers are further removed by HEVC encoding. Next, a Fourier disparity layer representation is constructed from the first subset of the approximated light field based on the chosen hierarchical order. Subsequent view subsets are synthesized by modeling the Fourier disparity layers that iteratively refine the representation with improved accuracy. The critical advantage of the proposed hybrid layered representation and coding scheme is that it utilizes not just spatial and temporal redundancies in light fields but efficiently exploits intrinsic similarities among neighboring sub-aperture images in both horizontal and vertical directions as specified by different predication orders. In addition, the scheme is flexible to

Identification and prediction of a lifetime of industrial cutting tools using minimal sensors is crucial to reduce production costs and downtime in engineering systems. In this paper, we provide a formal decision software tool to extract the dominant features enabling tool wear prediction. This decision tool is based on a formal mathematical approach that selects dominant features using the singular value decomposition of real-time measurements from the sensors of an industrial cutting tool. Selection of dominant features is important, as retaining only essential features allows reduced signal processing or even reduction in the number of required sensors, which cuts costs. It is shown that the proposed method of dominant feature selection is optimal in the sense that it minimizes the least-squares estimation error. The identified dominant features are used with the recursive least squares (RLS) algorithm to identify parameters in forecasting the time series of cutting tool wear. Experimental results on an industrial high-speed milling machine show the effectiveness in predicting the tool wear using only the dominant features. Index Terms-Least square error (LSE), principal component analysis (PCA), principal feature analysis (PFA), recursive least squares (RLS), singular value decomposition (SVD). NOMENCLATURE DFI Dominant feature identification. LSE Least square error. MRE Mean relative error. MRMs Multiple regression models. MSE Mean square error. NN Neural network.

In this study, an unknown input observer (UIO) is developed in explicit form to estimate unmeasurable states and unknown inputs (UIs) for nonlinear implicit systems represented by the discrete-time Takagi-Sugeno implicit systems (DTSIS) in the case of unmeasurable premise variables. The method employed is based on singular value decomposition (SVD) and augmenting the state vector, which is formed partly by the system state and partly by the UIs. The convergence of the augmented state estimation error is provided by a Lyapunov function ending with solving the linear matrix inequalities (LMI). An application to a model of the rolling disc is considered to evaluate the effectiveness of the developed approach. It appears that estimated variables converge to the true variables quickly and accurately.

In order to identify the weakest bus in a power system so that the Unified Power Flow Controller could be connected, an investigation of static and dynamic voltage stability is presented. Two stability indices, static and dynamic, have been proposed in the thesis. Multi-Input Multi-Output (MIMO) analysis has been used for the dynamic stability analysis. Results based on the Western System Coordinate Council (WSCC) 3-machine, 9-bus test system and IEEE 14 bus Reliability Test System (RTS) shows that these indices detect with the degree of accuracy the weakest bus, the weakest line and the voltage stability margin in the test system before suffering from voltage collapse. Recently, Flexible Alternating Current Transmission systems (FACTs) have become significant due to the need to strengthen existing power systems. The UPFC has been identified in literature as the most comprehensive and complex FACTs equipment that has emerged for the control and optimization of power flow in AC trans...

The study of the interaction of genotype and environment adaptability and yield stability of promising barley lines is one of the major issues in the race which is very important in The development of improved cultivars. In order to achieve these goals promising lines should be cultivated in different climatic conditions and evaluated. The test was done to determine the adaptability and yield stability of barley lines with 16 lines with 2 control for two years and two locations in a randomized complete block design with three ...

In this study, an unknown input observer (UIO) is developed in explicit form to estimate unmeasurable states and unknown inputs (UIs) for nonlinear implicit systems represented by the discrete-time Takagi-Sugeno implicit systems (DTSIS) in the case of unmeasurable premise variables. The method employed is based on singular value decomposition (SVD) and augmenting the state vector, which is formed partly by the system state and partly by the UIs. The convergence of the augmented state estimation error is provided by a Lyapunov function ending with solving the linear matrix inequalities (LMI). An application to a model of the rolling disc is considered to evaluate the effectiveness of the developed approach. It appears that estimated variables converge to the true variables quickly and accurately.

Individual images in dynamic molecular imaging studies are noisy because of short duration of frames. To reduce noise in these studies we used a method that employed the Hilbert transform and Singular Value Decomposition (SVD) processing. Use of this method, which we call the Complex Singular Value Decomposition (CSVD), significantly reduces noise while preserving signal intensity of dynamic images. Further, we used simulations to examine the effect of CSVD processing on estimates of receptor kinetic parameters. We found a significant reduction in variance when CSVD processing was applied to images that had Gaussian noise added to the signal. The signals were preserved even after adding noise, thus the simulations revealed that noise reduction was not at the cost of relevant signal. It therefore appears that CSVD processing can be used in dynamic molecular imaging and other similar studies to reduce noise and improve signal quality.

This paper we present a robust non blind watermarking scheme. The proposed scheme embeds the watermark into the color image. This watermarking scheme based on a sample spline approach by extracting distinctive invariant features from images. It can be used to perform reliable matching between different views of an object. This paper also describes an approach for object recognition using these invariant features. The recognition can be performed by matching individual features to a database of known features of objects using a fast nearest neighbour algorithm. In this paper we use the low frequency components of image blocks for data hiding to obtain high robustness against attacks. We take four samples of the approximation coefficients of the image blocks to construct a spline curve in the   2-D space. Here the slope of this spline curve is invariant to the gain factor, which is used for watermarking purpose. We embed the watermarking code by constructing a spline curve according t...

In this paper, three different transform techniques namely hybrid Discrete Wavelet Transform (DWT), Non Subsampled Contourlet Transform and Meta Heuristic Technique for image watermarking was proposed. In this proposed work, after decomposing the cover image using DWT, the SVD is applied to each band, then the singular values of each sub band of the host image are adjusted by dissimilar scaling aspects to implant the watermark. Modifications are optimized using Particle Swam Optimization to obtain the highest possible robustness without losing the transparency. Reformation in all frequencies permits the progression of a watermarking outline that is robust to a wide range of attacks. Also in this work, the viability of a powerful tool based on blind source separation technique namely Independent Component Analysis (ICA) is tested for watermark extraction. In this work, Supervised Independent Component Analysis (SICA) is proposed and implemented for digital images. The robustness of the above SICA technique is evaluated against various image processing attacks.