Forward Adaptive Research Articles

Arbitrary style transfer via multi-feature correlation

Recent research in arbitrary style transfer has highlighted challenges in maintaining the balance between content structure and style patterns. Moreover, the improper application of style patterns onto the content image often results in suboptimal quality. In this paper, a novel style transfer network, called MCNet, is proposed. It is based on multi-feature correlations. To better explore the intrinsic relationship between the style image and the content image and to transfer the most suitable style onto the content image, a novel Global Style-Attentional Transfer Module, named GSATM, is introduced in this work. GSATM comprises two parts: Forward Adaptive Style Transformation (FAST) and Delayed Style Transformation (DST). The former analyzes the relationship between style and content features and fine-tunes the style features, whereas the latter transfers the content features based on the fine-tuned style features. Moreover, a new encoding and decoding structure is designed to effectively handle the output of GSATM. Extensive quantitative and qualitative experiments fully demonstrate the superiority of our algorithm. Project page: https://github.com/XiangJinCherry/MCNet.

Analysis of Open Architecture 6R Robot Forward and Inverse Kinematics Adaptive to Structural Variations

This paper presents a kinematic analysis for an open architecture 6R robot controller, which is designed to control robots made by domestic manufactures with structural variations. Usually, robot kinematic studies are often introduced for specific robot types, and therefore, difficult to apply the kinematic model from one to another robot. This study incorporates most of the robot structural variations in one model so that it is convenient to switch robot types by modifying model parameters. By combining an adequate set of parameters, the kinematic models, especially the inverse kinematics, are derived. The kinematic models are proved to be suitable for many classic industrial robot types, such as Puma560, ABB IRB120/1600, KAWASAKI RS003N/RS010N, FANUC M6iB/M10iA, and therefore be applicable to those with similar structures. The analysis and derivation of the forward and inverse kinematic models are presented, and the results are proven to be accurate.

Forward Adaptive Dual-Mode Quantizer Based on the First-Degree Spline Approximation and Embedded G.711 Codec

Forward Adaptive Dual-Mode Quantizer Based on the First-Degree Spline Approximation and Embedded G.711 Codec

Simple Speech Transform Coding Scheme using Forward Adaptive Quantization for Discrete Input Signal

We propose a speech coding scheme based on the simple transform coding and forward adaptive quantization for discrete input signal processing in this paper. The quasi-logarithmic quantizer is applied to discretization of continuous input signal, i.e. for preparing discrete input. The application of forward adaptation based on the input signal variance provides more efficient bandwidth usage, whereas utilization of transform coding provides sub-sequences with more predictable signal characteristics that ensure higher quality of signal reconstruction at the receiving end. In order to provide additional compression, transform coding precedes adaptive quantization. As an objective measure of system performance we use signal-to-quantization-noise ratio. Sysem performance is discussed for two typical cases. In the first case, we consider that the information about continuous signal variance is available whereas the second case considers system performance estimation when we know only the information about discretized signal variance which means that there is a loss of input signal information. The main goal of such performance estimation comparison of the proposed speech signal coding model is to explore what is the objectivity of performance if we do not have information about a continuous source, which is a common phenomenon in digital systems.

Forward Adaptive Laplacian Source Coding Based on Restricted Quantization

A novel solution for Laplacian source coding based on three-level quantization is proposed in this paper. The restricted three-level quantizer is designed by assuming the restricted Laplacian distribution of the input signal. Quantizer and Huffman encoder are jointly designed. Forward adaptive scheme was employed, where the adaptation to the signal variance (power) was performed on frame-by frame basis. We employ switched model that consists of two restricted quantizers having unequal support regions. The simulation results (measured as SQNR) of the proposed scheme with a switched restricted three-level quantizer are compared to the cases when it involves three-level unrestricted quantizer and the Lloyd-Max quantizers having N=2 and N=4 levels. It is shown that the proposed solution offers performance comparable to the one of N=4 levels Lloyd-Max’s baseline with large savings in bit rate, while outperforming two other baselines.DOI: http://dx.doi.org/10.5755/j01.itc.47.2.16670

Forward Adaptive Transfer of Gaussian Process Regression

This paper proposes a forward adaptive transfer learning method, referred tp as forward adaptive transfer learning for Gaussian process regression, which allows robots to leverage previously learned Gaussian process regression models and use them as sources of information in new learning tasks. This is especially valuable when limited training data are available for the new target task. Forward adaptive transfer learning for Gaussian process regression decouples the kernel and hyperparameter selection for the target task from those of the source task, providing an inference framework that is desirable when dealing with real-world dynamic environments. Finally, because the source task has been learned a priori, the computational complexity of forward adaptive transfer learning for Gaussian process regression is lower as compared to other semiparametric Gaussian process approaches using transfer kernels.

Speech Signal Coding Using Forward Adaptive Quantization and Simple Transform Coding

The paper proposes a novel speech signal coding scheme that implements a simple transform coding and forward adaptive quantization. The proposed scheme is adapted to the input signal variance, providing highly efficient bandwidth usage, whereas implemented transform coding provides sub-sequences with more predictable signal characteristics, so that more suitable signal processing can be performed. The aforementioned transform coding precedes adaptive quantization, providing additional compression. The objective quality measure used for system performance estimation is SQNR (signal-to-quantization-noise ratio), which represents a standard measure for lossy coding types. The influence of transform coding is discussed by comparing the obtained results with the corresponding one achieved by applying only the same adaptive quantization. Furthermore, the comparison with system performance of PCM (pulse-code modulation) coding system confirms that the proposed coding scheme has a lot of potential for further implementation, since that the proposed system ensures SQNR gain up to 4.0983 [dB] for various values of system parameters. DOI: http://dx.doi.org/10.5755/j01.eie.22.3.15318

Design of Forward Adaptive Piecewise Uniform Scalar Quantizer with Optimized Reproduction Level Distribution per Segments

The problem we address in this paper is the design of nearly optimal scalar quantizer in a wide variance range of the Laplacian input signals, using the piecewise uniform quantizers while restricting the class of quantizers to be forward adaptive. Particularly, the design procedure of the piecewise uniform quantizer with an equidistant support region partion and the optimized reproduction level distribution per segments is presented along with the design procedure of its forward adaptive version. Reproduction level optimization is performed by optimizing the granular distortion of the proposed quantizer using the method of the Lagrange multipliers. For the proposed model we study the influence of the segment number on the SQNR, as well as the SQNR robustness in a wide variance range. Since the results obtained for the assumed Laplacian distribution indicate the SQNR improvement over the G.711 standard, one can expect that the proposed quantizer will be effective in the quantization of signals having the same distribution and the time varying characteristics. Ill. 4, bibl. 10 (in English; abstracts in English and Lithuanian).DOI: http://dx.doi.org/10.5755/j01.eee.119.3.1356

Forward and backward adaptive effects in global flash multifocal electroretinogram stimulation

Purpose: The present study investigated retinal adaptive responses in concert with the modulation of forward and backward adaptation induced by periodic global flashes using the global flash multifocal electroretinogram (mfERG).Methods: Six normal subjects were recruited for global flash mfERG measurements, which consisted of 103 scaled hexagonal elements followed by a global flash frame. In experiments I and II, with constant luminance maintained in both local and global flash frames, the number of dark frames was independently varied and these frames were either inserted prior to or following the global flash frame to investigate the forward or backward adaptive effect of the global flash on the mfERG. In experiment III, the number of dark frames was fixed but the luminance of the global flash frame was varied with constant luminance of the focal flash. This was used to demonstrate that the adaptive effect related not to time but to variation of luminance.Results: All the central, para‐central and peripheral direct component amplitudes were found to be significantly influenced by variation of the number of dark frames (p < 0.01). Reducing the forward adaptive effect of the global flash enhanced the direct component response and it became steady after five dark frames were inserted following the global flash. Reducing the backward adaptive effect of the global flash also enhanced the direct component response but it started reducing after four dark frames were inserted prior to the global flash frame. These changes were different with luminance modulation of the global flash intensity with fixed dark frames, while the direct component amplitude grew approximately linearly with decreasing mean luminance of the global flash stimulation.Conclusion: The retina plays a major role in visual adaptation. Both forward and backward adaptive effects of the global flash on the direct component have been illustrated in this study. The results show that the forward and backward adaptive phenomena in the global flash mfERG are different and demonstrate that backward adaptation is found at the retinal level.

Low Complex Forward Adaptive Loss Compression Algorithm and Its Application in Speech Coding

Low Complex Forward Adaptive Loss Compression Algorithm and Its Application in Speech CodingThis paper proposes a low complex forward adaptive loss compression algorithm that works on the frame by frame basis. Particularly, the algorithm we propose performs frame by frame analysis of the input speech signal, estimates and quantizes the gain within the frames in order to enable the quantization by the forward adaptive piecewise linear optimal compandor. In comparison to the solution designed according to the G.711 standard, our algorithm provides not only higher level of the average signal to quantization noise ratio, but also performs a reduction of the PCM bit rate for about 1 bits/sample. Moreover, the algorithm we propose completely satisfies the G.712 standard, since it provides overreaching the curve defined by the G.712 standard in the whole of variance range. Accordingly, we can reasonably believe that our algorithm will find its practical implementation in the high quality coding of signals, represented with less than 8 bits/sample, which as well as speech signals follow Laplacian distribution and have the time varying variances.

Design of Forward Adaptive Uniform Quantizer for Discrete Input Samples for Laplacian Source

In this paper, the problem of construction of the fixed and the forward adaptive uniform quantizer for input samples with discrete amplitude is analyzed, for Laplacian source. This quantizer is very common in practice; therefore its analysis is very significant. It is shown that design and performances of the quantiazer for discrete input samples are very different, compared to quantizer for continual input samples.

Forward Adaptive Logarithmic Quantizer with New Lossless Coding Method for Laplacian Source

The aim of this paper is to improve the G.711 standard, which is widely used, especially in the public switched telephone network (PSTN). Two solutions are proposed. The first solution uses only lossless coder, achieving a bit-rate decrease of 0.82 bits/sample, compared to the G.711 codec. The second solution uses forward adaptation and a lossless coder, further decreasing the bit-rate (by 1.25 bits/sample) and achieving higher average signal-to-quantization noise ratio (SQNR) in comparison with the G.711 codec. Also, the second solution is more robust than the G.711 codec, which means that it has near constant SQNR for a wide range of input signal power. That is very important for signals whose input power varies with time, such as speech and video signals. Our solutions are compatible with the G.711 codec, they have little additional complexity and delay and therefore can be applied in real-time systems, such as PSTN or VoIP. They can also be used in many other systems, such as WiMax and OFDM, as a replacement or improvement of the G.711 codec. Standardization process of the G.711.1 standard (which is a wide-band extension of the G.711 standard) is largely present. Our solutions fulfill all the requirements for that new standard; therefore they can be implemented in its low-frequency part.

Lloyd–Max's Algorithm Implementation in Speech Coding Algorithm Based on Forward Adaptive Technique

In this paper a detail analysis of speech coding algorithm based on forward adaptive technique is carried out. We consider an algorithm that works on frame-by-frame basis, where a frame consists of a certain number of speech samples. Buffering frame-by-frame an estimation of the gain defined as squared root of the frame variance is enabled. The information about the gain (side information) and the code book of a nonadaptive quantizer, which is designed for the unit variance case of the input signal, are further used when designing an adaptive quantizer. In such a way better quantizer adaptation to the varying input statistics is provided. Observe that the goal of this paper is to investigate the preference that for the wide range of variance change could be achieved when implementing in the forward adaptive speech coding algorithm, the recently developed effective method for the Lloyd-Max's algorithm initialization, which provides optimal Lloyd-Max's quantizer performances for the unit variance case of the input signal. We destine to consider the speech coding algorithm based on forward adaptive technique since the backward adaptation provides SQNR (signal to quantization noise ratio) within 1 dB of the forward adaptation. We provide theoretical and experimental results (performances of our algorithm) which are compared with the optimal results. Additionally, we discuss the performances of speech coding schemes designed according to G. 711 standard and we point out the benefits that can be achieved by using our algorithm. Finally, in order to find better solution for implementation of the proposed algorithm in practice we consider the performances of our algorithm when log-uniform as well as uniform scalar quantizer are used for gain quantizing.

Vehicle Architecture for Field Testing Forward Collision Warning and Adaptive Cruise Control

This paper describes the Prototype Vehicle Architecture that was developed as a basis for deployment vehicles to be used in field testing the Forward Collision Warning (FCW) and Adaptive Cruise Control (ACC) functions as a part of a joint program between National Highway Traffic Safety Administration (NHTSA) and General Motors Corporation. The background of the program is presented followed by functional description, architecture, and the detailed block diagram of the system.

A Range of Low and High Delay CELP Speech Codecs between 8 and 4 kbits/s

In this paper we study the performance and the error sensitivities of six CELP [1] based codecs operating between 8 and 4 kbits/s. Codecs using both forward and backward adaption of the linear prediction coefficients and the long term predictor (LTP) are described. Initially we describe four low delay codecs which all use backward adaption of the LPC coefficients but which differ in their use of LTP. These codecs all have frame-lengths of 3 ms or less, and their performance at various bit rates between 8 and 4 kbits/s is examined. Next the error sensitivity of these codecs, and means of improving it, are described. Then an algebraic CELP (ACELP) [2] codec operating at 6.2 kbits/s with a frame-length of 5 ms is described. Our final codec also uses ACELP and operates between 4.7 and 7.1 kbits/s, but it is forward adaptive and so it has a much longer frame-length of up to 30 ms. After describing this codec we compare the performance of our codecs in both error-free conditions and in the presence of channel errors. Surprisingly the error sensitivity of the low delay backward adaptive codec with no LTP is similar to that of the forward adaptive, high delay, ACELP codec.