Search

Learning embeddings representations of users and items lies at the core of modern recommender systems. Existing methods based on Graph Convolutional Network (GCN) and sequential recommendation typically obtain a user’s or an item’s embedding by mapping from pre-existing features into better embeddings for users and items, such as ID and attributes. GCN integrates the user-item interaction as the bipartite graph structure into the embedding process, which can better represent sparse data, but cannot capture users’ long-term interests. Sequential recommendation seek to capture the “context” of users’ activities based on their historical actions, but requires dense data to support it. The goal of our work is to combine the advantages of GCN and sequential recommendation models by proposing a novel Self-Attention based Sequential recommendation with Graph Convolutional Networks (SASGCN). It uses multiple lightweight GCN layers to capture high-order connectivity between users and items, and by introducing ratings as auxiliary information into the user-item interaction matrix, it provides richer information. By incorporating self-attention based methods, the proposed model capture long-term semantics through relatively few actions. Extensive experiments on three benchmark datasets show that our model outperforms various state-of-the-art models consistently.

After the works on High Efficiency Video Coding (HEVC) standard, the standard organizations continued to study the next generation of video coding standard, named Versatile Video Coding (VVC). The compression capacity of the VVC standard is expected to be substantially improved relative to the current HEVC standard by evolving the potential coding tools greatly. Transform is a key technique for compression efficiency, and core experiment 6 (CE6) in JVET is established to explore the transform-related coding tools. In this paper, we propose a novel signal-independent separable transform based on the Karhunen-Loève transform (KLT) to improve the efficiency of both intra and inter residual coding. In the proposed method, the drawbacks of the traditional KLT are addressed. A group of mode-independent intra transform matrices is calculated from abundant intra residual samples of all intra modes, while the inter separable KLT matrices are trained with the residuals that cannot be efficiently processed by the discrete cosine transform type II (DCT-II). The separable KLT is developed as an additional transform type apart from DCT-II. The experimental results show that the proposed method can achieve 2.7% and 1.5% bitrate saving averagely under All Intra and Random Access configurations on top of the reference software of VVC (VTM-1.1). In addition, the consistent performance improvement on test set also validates the property of signal independency and the strong generalization capacity of the proposed separable KLT.

This paper presents a novel adaptive predictive current controller (PCC) with improved flux estimator for a sensorless direct field oriented control (DFOC) induction motor (IM) drive. Classical PCC performance depends on the stator resistance of the motor which varies with temperature. In the proposed method, a discrete stator resistance estimator is developed to increase the robustness of the system toward stator resistance variations. An improved nonlinear discrete stator flux estimator is also developed to replace the pure integrator which reduces the initial value and dc offset problems. Sensorless operation of IM drive has advantages of reduced overall cost and increased reliability of motor operation. Dynamic and steady-state performances of the IM under different operating conditions are analyzed in MATLAB/Simulink as well as experimentally using dSPACE1104 controller and have been compared with conventional PCC. The simulation results of the classical and proposed methods are also validated experimentally. Smooth starting, reduced oscillations in speed and flux at low speed operation, fast speed and torque dynamics, robust operation of drive against load and variation in stator resistance, fast and smooth speed reversal are the main advantages of the proposed method over classical PCC-based DFOC IM drive. [ABSTRACT FROM AUTHOR]

Transform, as one of the most important modules of mainstream video coding systems, seems very stable over the past several decades. However, recent developments indicate that bringing more options for transform can lead to coding efficiency benefits. In this paper, we go further to investigate how the coding efficiency can be improved over the state-of-the-art method by adapting a transform for each block. We present a variable block-sized signal-dependent transforms (SDTs) design based on the High Efficiency Video Coding (HEVC) framework. For a coding block ranged from $4\times4$ to $32\times32$ , we collect a quantity of similar blocks from the reconstructed area and use them to derive the Karhunen–Loève transform. We avoid sending overhead bits to denote the transform by performing the same procedure at the decoder. In this way, the transform for every block is tailored according to its statistics, to be signal-dependent. To make the large block-sized SDTs feasible, we present a fast algorithm for transform derivation. Experimental results show the effectiveness of the SDTs for different block sizes, which leads to up to 23.3% bit-saving. On average, we achieve BD-rate saving of 2.2%, 2.4%, 3.3%, and 7.1% under AI-Main10, RA-Main10, RA-Main10, and LP-Main10 configurations, respectively, compared with the test model HM-12 of HEVC. The proposed scheme has also been adopted into the joint exploration test model for the exploration of potential future video coding standard. [ABSTRACT FROM AUTHOR]

Transformers are known as one of the most important equipment in power system transmission and distribution networks. Partial Discharge (PD) measurement and PRPD interpretation is a powerful tool to monitor the situation and evaluating the risk of power transformer failure. Multiple discharge sources affect the accuracy of interpretation of PRPD. This paper presents a PD signal separation algorithm based on extraction of high level image features. The time-frequency S transform (ST) is applied to the PD signal waveforms, acquired by digital detection instruments at 100 MS/s. The resultant ST matrix is then converted to gray scale image from which high level features are extracted using Bag of Words (BoW). Principle component analysis (PCA) transform is applied to BoW feature to reduce the dimension of features. Calinski-Harabasz criterion is calculated to identify the number of active sources and then Gaussian mixture model (GMM) clustering is used to discover clusters in the feature space. The proposed separation algorithm is examined with mixed current impulse signals acquired from PD experiments on artificial multi-defect models. The separation results indicate that the proposed algorithm is effective for identifying the number of active sources and separating mixed PD signals initiated from multiple sources. [ABSTRACT FROM AUTHOR]

Previously, the synthesis of reversible and quantum permutative circuits based on products of Exclusive-OR (EXOR) sums of inputs (POE) was explored as an approach to reduce quantum cost. Herein, the mathematical representation used in POE expressions is formally detailed and contrasted with the pseudoproduct-based theory of Luccio and Pagli. The theory and practice of product transformation, or computation of equivalent POE expressions, is presented. To demonstrate the generality of the mathematical representations outside of the reversible domain, a new method to synthesize incompletely specified functions as EXOR-AND-OR circuits is introduced. The method is heuristic. It first uses spectral information from the Walsh–Hadamard transform to compute a set of POE implicants for a function, and then uses product transformation to minimize both the total number of literals and unique EXOR sums (ignoring polarity) used in the POE implicants. The product transformation minimization extends to multioutput functions. The new method has no performance guarantees, i.e., it does not have a fallback mode of minimum or near-minimum sum of products; therefore, it is suited to a tournament synthesis approach. When synthesizing benchmark functions of up to 26 inputs, the new method is shown to typically produce lower cost circuits than heuristic pseudoproduct-based methods. [ABSTRACT FROM PUBLISHER]

Transform is used to compact the energy of the blocks into a small number of coefficients and is widely used in recent image/video coding standards. In the latest video coding standard high efficiency video coding (HEVC), a combination of discrete cosine transform (DCT) and discrete sine transform (DST) is adopted to transform the residuals from intra prediction. Since the DCT and DST are the fixed transforms that are derived from the Gauss–Markov model, some of residual blocks may not be compacted well by the DCT/DST. In this paper, we propose a signal dependent transform based on singular value decomposition (SVD) for HEVC intracoding. The proposed transform (SDT-SVD) is derived by performing SVD on the synthetic block and applied to the residual block considering the structural similarity between them. Furthermore, we extend SDT-SVD to template matching prediction (TMP) to further improve the intracoding performance. Experimental results show that the proposed transform on angular intra prediction (AIP) outperforms the latest HEVC reference software with a bit rate reduction of 1.0% on average and it can be up to 2.1%. When the proposed transform is extended to TMP-based intracoding, the overall bit rate reduction is 2.7% on average and can be up to 5.8%. [ABSTRACT FROM PUBLISHER]

Today's content delivery is characterized by key trends such as converged media delivery over HTTP, increasing volumes of multimedia content delivered over IP, and elevated user expectations on quality-of-experience. In this respect, server provisioning is a critical phase of CDN management, which affects both incumbent and entrant CDN operators as well as internet service providers. However, existing tools and approaches to solve server placement problems have serious shortcomings: they offer only coarse tuning knobs and limit servers to a set of candidate sites given a priori. Our conversations with CDN operators reveal that a new provisioning mechanism is necessary to take advantage of emerging opportunities such as faster speed to roll out new locations and more access networks. In this paper, we present the design of DISC, a decision support system to help CDN operators systematically investigate different design tradeoffs and evaluate what-if scenarios. The key enabler underlying DISC is a network coordinate-based data analysis workflow that can flexibly embed different cost, performance, and workload characteristics without sacrificing the fidelity. We describe practical use cases and experiences in applying DISC to a large country-wide deployment. The results show that DISC significantly reduces average latency, deployment cost, and interdomain traffic. [ABSTRACT FROM PUBLISHER]

This paper presents a modified approach based on symmetrical components in time domain for the detection and classification of various power-quality (PQ) disturbances. Single-phase PQ disturbance signal along with the two other ideal phases generated using phase-locked loop (PLL) is processed to find out the symmetrical components of all phases in time domain. Triggering points for PQ disturbances have been detected from the negative-sequence component of disturbance phase and have been easily classified from the signatures of the waveforms using the summation of the positive- and negative-sequence components. PQ disturbances, such as voltage sag, swell, interruption, harmonics, flicker, transients, notches, and spike present in a distribution system, have been investigated and are easily localized and segmented with this technique. Being a time-domain technique, it can be adopted for the online monitoring and assessment of the PQ disturbances. Simulated and real-time results are presented for a number of PQ disturbances to show the effectiveness of the proposed method for the PQ disturbances’ detection and classification. [ABSTRACT FROM PUBLISHER]

The directional intra prediction (IP) in H.264/AVC and HEVC tends to cause the residue to be anisotropic. To transform the IP residue, Mode Dependent Directional Transform (MDDT) based on Karhunen Loève transform (KLT) can achieve better energy compaction than DCT, with one transform assigned to each prediction mode. However, due to the data variation, different residue blocks with the same IP mode may not have the same statistical properties. Instead of constraining one transform for each IP mode, in this paper, we propose a novel rate-distortion optimized transform (RDOT) scheme which allows a set of specially trained transforms to be available to all modes, and each block can choose its preferred transform to minimize the rate-distortion (RD) cost. We define a cost function which is an estimate of the true RD cost and use the Lloyd-type algorithm (a sequence of transform optimization and data reclassification alternately) to find the optimal set of transforms. The proposed RDOT scheme is implemented in HM9.0 software of HEVC. Experimental results suggest that RDOT effectively achieves 1.6% BD-Rate reduction under the Intra Main condition and 1.6% BD-Rate reduction under the Intra High Efficiency (HE) 10bit condition. [ABSTRACT FROM PUBLISHER]

Existing video coding standards use only 4\,\times\,4 and 8\,\times\,8 transforms for energy compaction. Recent research has found that the use of larger transforms, such as 16\,\times\,16, together with the existing transforms can improve coding performance especially in high-definition (HD) videos which are becoming more and more common. This raises the interest of seeking high-performance higher-order transforms with low computation requirement. In this paper, a method to derive orthogonal integer cosine transforms is proposed. The order-2N transform is defined using the order-N transform. A family of these integer transforms, Loeffler, Ligtenberg, and Moschytz (LLM) integer cosine transform, is derived using this method. Its fast algorithm structure is the same as LLM fast discrete cosine transform (DCT) algorithm but requires integer operations only. This new family of transforms is not only very close to the DCT but also has excellent coding performance. [ABSTRACT FROM AUTHOR]

This paper presents a directional transform scheme for coding interprediction errors in block-based hybrid video coding. It proposes a two-layer transform structure, where the first layer uses discrete wavelet transform to compact the residue energy to the LL band and then the second layer uses 2-D nonseparable directional transforms to deal with the arbitrary edge directions in the four subbands. By doing this, the edges in a macroblock are efficiently compacted to a few coefficients and at the same time the overhead used to indicate the transform directions is affordable. Experimental results show that the proposed scheme provides peak signal-to-noise ratio gain up to 0.46 dB, compared with H.264/AVC High Profile. [ABSTRACT FROM PUBLISHER]

This paper presents a design of new video coding scheme targeting substantial compression performance with reasonable complexity for next-generation high-resolution video sources. While it takes a conventional block-based MC+DCT hybrid coding approach that is suitable for hardware implementation of a high-resolution video codec, the proposed scheme achieved significant improvement of coding efficiency by introducing various technical optimizations in each functional block, especially allowing the use of larger blocks for motion compensation and transform than conventional standards. According to our experimental analysis, the proposed scheme achieves approximately 26% bit-rate savings on average compared to the state-of-the-art standard AVC/H.264 high profile. We also study the tradeoff between complexity and performance of the codec towards its standardization and implementation. [ABSTRACT FROM PUBLISHER]

In this paper, a novel algorithm called spatially varying transform (SVT) is proposed to improve the coding efficiency of video coders. SVT enables video coders to vary the position of the transform block, unlike state-of-art video codecs where the position of the transform block is fixed. In addition to changing the position of the transform block, the size of the transform can also be varied within the SVT framework, to better localize the prediction error so that the underlying correlations are better exploited. It is shown in this paper that by varying the position of the transform block and its size, characteristics of prediction error are better localized, and the coding efficiency is thus improved. The proposed algorithm is implemented and studied in the H.264/AVC framework. We show that the proposed algorithm achieves 5.85% bitrate reduction compared to H.264/AVC on average over a wide range of test set. Gains become more significant at medium to high bitrates for most tested sequences and the bitrate reduction may reach 13.50%, which makes the proposed algorithm very suitable for future video coding solutions focusing on high fidelity video applications. The gain in coding efficiency is achieved with a similar decoding complexity which makes the proposed algorithm easy to be incorporated in video codecs. However, the encoding complexity of SVT can be relatively high because of the need to perform a number of rate distortion optimization (RDO) steps to select the best location parameter (LP), which indicates the position of the transform. In this paper, a novel low complexity algorithm is also proposed, operating on a macroblock and a block level, to reduce the encoding complexity of SVT. Experimental results show that the proposed low complexity algorithm can reduce the number of LPs to be tested in RDO by about 80% with only a marginal penalty in the coding efficiency. [ABSTRACT FROM AUTHOR]

Maintaining reconstructed signals at a desired level of quality is crucial for lossy ECG data compression. Wavelet-based approaches using a recursive decomposition process are unsuitable for real-time ECG signal recoding and commonly obtain a nonlinear compression performance with distortion sensitive to quantization error. The sensitive response is caused without compromising the influences of word-length-growth (WLG) effect and unfavorable for the reconstruction quality control of ECG data compression. In this paper, the 1-D reversible round-off nonrecursive discrete periodic wavelet transform is applied to overcome the WLG magnification effect in terms of the mechanisms of error propagation resistance and significant normalization of octave coefficients. The two mechanisms enable the design of a multivariable quantization scheme that can obtain a compression performance with the approximate characteristics of linear distortion. The quantization scheme can be controlled with a single control variable. Based on the linear compression performance, a linear quantization scale prediction model is presented for guaranteeing reconstruction quality. Following the use of the MIT-BIH arrhythmia database, the experimental results show that the proposed system, with lower computational complexity, can obtain much better reconstruction quality control than other wavelet-based methods. [ABSTRACT FROM AUTHOR]

The latest video coding standards achieve high coding gains but result in high complexity. To reduce the computation involved and speed up the encoder, various A 11- Zero Block (AZB) early detection algorithms are designed to skip transform coding and quantization. In this paper, the orthogonal transformations are analyzed using the Euclid Space theory first, and then the sufficient and necessary conditions for AZB detection and non-AZB detection are derived. Based on sufficient conditions, new features for the refined classification and the corresponding thresholds are found. Finally, a general AZB detection method with a constrained false detection rate is proposed. The proposed detection scheme is applied to the 4x4 and 8x8 transforms in H.264/A VC. The experiment results show that up to 80% of the computations for transform and quantization are saved as compared to those for the encoder without AZB detection. [ABSTRACT FROM AUTHOR]

Gao's algorithm similar to Shiozaki's algorithm for decoding nonsystematic Reed-Solomon (RS) codes which is a subclass of the redundant residue polynomial codes is considered here. This algorithm computes the message polynomial directly without explicitly finding the error-locator polynomial and error- evaluator polynomial. In this letter, a simplified decoding algorithm to correct both errors and erasures is used in conjunction with Gao's algorithm for efficiently decoding RS codes. In addition, we show that the extended Gao algorithm similar to the Shiozaki-Truong-Cheung-Reed algorithm significantly reduces the decoding complexity. [ABSTRACT FROM AUTHOR]

The S-transform is becoming popular for time-frequency analysis and data-adaptive filtering thanks to its simplicity. While this transform works well in the continuous domain, its discrete version may fail to achieve accurate results. This paper compares and contrasts this transform with the better known continuous wavelet transform, and defines a relation between both. This connection allows a better understanding of the S-transform, and makes it possible to employ the wavelet reconstruction formula as a new inverse S-transform and to propose several methods to solve some of the main limitations of the discrete S-transform, such as its restriction to linear frequency sampling. [ABSTRACT FROM PUBLISHER]

Integer cosine transform (ICT) is adopted by H.264/AVC for its bit-exact implementation and significant complexity reduction compared to the discrete cosine transform (DCT) with an impact in peak sigal-to-noise ratio (PSNR) of less than 0.02 dB. In this paper, a new technique, named prescaled integer transform (PIT), is proposed. With PIT, while all the merits of ICT are kept, the implementation complexity of decoder is further reduced compared to corresponding conventional ICT, which is especially important and beneficial for implementation on low-end processors. Since not all PIT kernels are good in respect of coding efficiency, design rules that lead to good PIT kernels are considered in this paper. Different types of PIT and their target applications are examined. Both fixed block-size transform and adaptive block-size transform (ABT) schemes of PIT are also studied. Experimental results show that no penalty in performance is observed with PIT when the PIT kernels employed are derived from the design rules. Up to 0.2 dB of improvement in PSNR for all intra frame coding compared to H.264/AVC can be achieved and the subjective quality is also slightly improved when PIT scheme is carefully designed. Using the same concept, a variation of PIT, Post-scaled Integer Transform, can also be potentially designed to simplify the encoder in some special applications. PIT has been adopted in audio video coding standard (AVS), Chinese National Coding standard. [ABSTRACT FROM AUTHOR]

In this letter, we derive the theoretical complex cepstrum (TCC) of the discrete cosine transform (DCT) and warped DCT (WDCT) filters. Using these derivations, we intend to develop an analytic model of the warped discrete cosine transform cepstrum (WDCTC), which was recently introduced as a speech processing feature. In our derivation, we start with the filter bank structure for the DCT, where each basis is represented by a finite impulse response (FIR) filter. The WDCT filter bank is obtained by substituting z-1 in the DCT filter bank with a first-order all-pass filter. Using the filter bank structures, we first derive the transfer functions for the DCT and WDCT, and subsequently, the TCC for each filter is computed. We analyze the DCT and WDCT filter transfer functions and the TCC by illustrating the corresponding pole-zero maps and cepstral sequences. Moreover, we also use the derived TCC expressions to compute the cepstral sequence for a synthetic vowel/aa/where the observations on the theoretical cepstrum corroborate well with our practical findings. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method for representing and recognizing objects, based on invariants of the object's regions. We apply the method to articulated objects in low-resolution, noisy range images. Articulated objects such as a back-hoe can have many degrees of freedom, in addition to the unknown variables of viewpoint. Recognizing such an object in an image can involve a search in a high-dimensional space that involves all these unknown variables. Here, we use invariance to reduce this search space to a manageable size. The low resolution of our range images makes it hard to use common features such as edges to find invariants. We have thus developed a new "featureless" method that does not depend on feature detection. Instead of local features, we deal with whole regions of the object. We define a "transform" that converts the image into an invariant representation on a grid, based on invariant descriptors of entire regions centered around the grid points. We use these region-based invariants for indexing and recognition. While the focus here is on articulation, the method can be easily applied to other problems such as the occlusion of fixed objects. [ABSTRACT FROM AUTHOR]