Abstract: Introduce GSAM model by incorporating genetic algorithm in SAM learning process.GSAM learning has lower computational costs and higher efficiency compared to SAM.Employ wavelet transformation for feature extraction in high-dimensional datasets.This is the first application of fuzzy SAM method in medical diagnosis.This is the first combination of wavelets and fuzzy SAM applied in classification. Healthcare plays an important role in promoting the general health and well-being of people around the world. The difficulty in healthcare data classification arises from the uncertainty and the high-dimensional nature of the medical data collected. This paper proposes an integration of fuzzy standard additive model (SAM) with genetic algorithm (GA), called GSAM, to deal with uncertainty and computational challenges. GSAM learning process comprises three continual steps: rule initialization by unsupervised learning using the adaptive vector quantization clustering, evolutionary rule optimization by GA and parameter tuning by the gradient descent supervised learning. Wavelet transformation is employed to extract discriminative features for high-dimensional datasets. GSAM becomes highly capable when deployed with small number of wavelet features as its computational burden is remarkably reduced. The proposed method is evaluated using two frequently-used medical datasets: the Wisconsin breast cancer and Cleveland heart disease from the UCI Repository for machine learning. Experiments are organized with a five-fold cross validation and performance of classification techniques are measured by a number of important metrics: accuracy, F-measure, mutual information and area under the receiver operating characteristic curve. Results demonstrate the superiority of the GSAM compared to other machine learning methods including probabilistic neural network, support vector machine, fuzzy ARTMAP, and adaptive neuro-fuzzy inference system. The proposed approach is thus helpful as a decision support system for medical practitioners in the healthcare practice.

Abstract: The quantization techniques have shown competitive performance in approximate nearest neighbor search. The state-of-the-art algorithm, composite quantization, takes advantage of the compositionabity, i.e., the vector approximation accuracy, as opposed to product quantization and Cartesian k-means. However, we have observed that the runtime cost of computing the distance table in composite quantization, which is used as a lookup table for fast distance computation, becomes nonnegligible in real applications, e.g., reordering the candidates retrieved from the inverted index when handling very large scale databases. To address this problem, we develop a novel approach, called sparse composite quantization, which constructs sparse dictionaries. The benefit is that the distance evaluation between the query and the dictionary element (a sparse vector) is accelerated using the efficient sparse vector operation, and thus the cost of distance table computation is reduced a lot. Experiment results on large scale ANN retrieval tasks (1M SIFTs and 1B SIFTs) and applications to object retrieval show that the proposed approach yields competitive performance: superior search accuracy to product quantization and Cartesian k-means with almost the same computing cost, and much faster ANN search than composite quantization with the same level of accuracy.

Abstract: This paper presents a new approach to index color images using the features extracted from the error diffusion block truncation coding (EDBTC). The EDBTC produces two color quantizers and a bitmap image, which are further processed using vector quantization (VQ) to generate the image feature descriptor. Herein two features are introduced, namely, color histogram feature (CHF) and bit pattern histogram feature (BHF), to measure the similarity between a query image and the target image in database. The CHF and BHF are computed from the VQ-indexed color quantizer and VQ-indexed bitmap image, respectively. The distance computed from CHF and BHF can be utilized to measure the similarity between two images. As documented in the experimental result, the proposed indexing method outperforms the former block truncation coding based image indexing and the other existing image retrieval schemes with natural and textural data sets. Thus, the proposed EDBTC is not only examined with good capability for image compression but also offers an effective way to index images for the content-based image retrieval system.

Abstract: A new space-vector-based sigma delta modulation scheme for any general N-level voltage source inverter is proposed in this paper, which directly quantizes the reference space vector. The proposed scheme uses the sigma delta modulation with the quantizer implemented by the proposed space vector quantizer. A new scheme is proposed for directly quantizing the reference space vector to the multilevel inverter switching vectors without mapping it into two-level inverter vector space. Voronoi regions of the multilevel inverter vector space in the proposed space vector quantizer are defined as a parallelogram with the inverter switching vectors as its vertices. The property of the integer values of the inverter switching vectors in 60° coordinates is utilized for the direct vector quantization of the instantaneous reference voltage space vector. The proposed scheme is implemented for five-level inverters realized by an open-end-winding induction motor fed with two three-level inverters from either side having symmetrical dc-link voltages, and results are presented.

Abstract: Bag-of-Words (BoWs) model based on Scale Invariant Feature Transform (SIFT) has been widely used in large-scale image retrieval applications. Feature quantization by vector quantization plays a crucial role in BoW model, which generates visual words from the high- dimensional SIFT features, so as to adapt to the inverted file structure for the scalable retrieval. Traditional feature quantization approaches suffer several issues, such as necessity of visual codebook training, limited reliability, and update inefficiency. To avoid the above problems, in this paper, a novel feature quantization scheme is proposed to efficiently quantize each SIFT descriptor to a descriptive and discriminative bit-vector, which is called binary SIFT (BSIFT). Our quantizer is independent of image collections. In addition, by taking the first 32 bits out from BSIFT as code word, the generated BSIFT naturally lends itself to adapt to the classic inverted file structure for image indexing. Moreover, the quantization error is reduced by feature filtering, code word expansion, and query sensitive mask shielding. Without any explicit codebook for quantization, our approach can be readily applied in image search in some resource-limited scenarios. We evaluate the proposed algorithm for large scale image search on two public image data sets. Experimental results demonstrate the index efficiency and retrieval accuracy of our approach.

Abstract: Due to a large number of parameters in deep neural networks (DNNs), it is challenging to design a small-footprint DNN-based speech recognition system while maintaining a high recognition performance. Even with a singular value matrix decomposition (SVD) method and scalar quantization, the DNN model is still too large to be deployed on many mobile devices. Common practices like reducing the number of hidden nodes often result in significant accuracy loss. In this work, we propose to split each row vector of weight matrices into sub-vectors, and quantize them into a set of codewords using a split vector quantization (split-VQ) algorithm. The codebook can be fine-tuned using back-propagation when an aggressive quantization is performed. Experimental results demonstrate that the proposed method can further reduce the model size by 75% to 80% and save 10% to 50% computation on top of an already very compact SVD-DNN without a noticeable performance degradation. This results in a 3.2 MB-footprint DNN giving similar recognition performance as what a 59.1 MB standard DNN can achieve.

Abstract: In this paper, we present a statistical analysis of JPEG noises, including the quantization noise and the rounding noise during a JPEG compression cycle. The JPEG noises in the first compression cycle have been well studied; however, so far less attention has been paid on the statistical model of JPEG noises in higher compression cycles. Our analysis reveals that the noise distributions in higher compression cycles are different from those in the first compression cycle, and they are dependent on the quantization parameters used between two successive cycles. To demonstrate the benefits from the analysis, we apply the statistical model in JPEG quantization step estimation. We construct a sufficient statistic by exploiting the derived noise distributions, and justify that the statistic has several special properties to reveal the ground-truth quantization step. Experimental results demonstrate that the proposed estimator can uncover JPEG compression history with a satisfactory performance.

Abstract: Many self-organizing maps (SOMs) implemented on hardware restrict their neighborhood function values to negative powers of two. In this paper, we propose a novel hardware friendly neighborhood function that is aimed to improve the vector quantization performance of hardware SOM. The quantization performance of the hardware SOM with the proposed neighborhood function is examined by simulations. Simulation results show that the proposed function can improve the hardware SOM’s vector quantization capability even though the function value is restricted to negative powers of two. Then, the hardware SOM is implemented on field-programmable gate array to find out the hardware cost and performance speed of the proposed neighborhood function. Experimental results show that the proposed neighborhood function can improve SOM’s quantization performance without additional hardware cost or slowing down the operating speed. Due to fully parallel operation, the proposed SOM with $16\times 16$ neurons achieves a performance of 25 344 million connections updates per second.

Abstract: Local binary pattern (LBP) is a simple and effective descriptor for texture classification. However, it has two main disadvantages: 1) different structural patterns sometimes have the same binary code and 2) it is sensitive to noise. In order to overcome these disadvantages, we propose a new local descriptor named local vector quantization pattern (LVQP). In LVQP, different kinds of texture images are chosen to train a local pattern codebook, where each different structural pattern is described by a unique codeword index. Contrarily to the original LBP and its many variants, LVQP does not quantize each neighborhood pixel separately to 0/1, but aims at quantizing the whole difference vector between the central pixel and its neighborhood pixels. Since LVQP deals with the structural pattern as a whole, it has a high discriminability and is less sensitive to noise. Our experimental results, achieved by using four representative texture databases of Outex, UIUC, CUReT, and Brodatz, show that the proposed LVQP method can improve classification accuracy significantly and is more robust to noise.

Abstract: Annoying compression artifacts exist in most of lossy coded videos at low bit rates, which are caused by coarse quantization of transform coefficients or motion compensation from distorted frames. In this paper, we propose a compression artifact reduction approach that utilizes both the spatial and the temporal correlation to form multi-hypothesis predictions from spatio-temporal similar blocks. For each transform block, three predictions with their reliabilities are estimated, respectively. The first prediction is constructed by inversely quantizing transform coefficients directly, and its reliability is determined by the variance of quantization noise. The second prediction is derived by representing each transform block with a temporal auto-regressive (TAR) model along its motion trajectory, and its corresponding reliability is estimated from local prediction errors of the TAR model. The last prediction infers the original coefficients from similar blocks in non-local regions, and its reliability is estimated based on the distribution of coefficients in these similar blocks. Finally, all the predictions are adaptively fused according to their reliabilities to restore high-quality videos. The experimental results show that the proposed method can efficiently reduce most of the compression artifacts and improve both subjective and objective quality of block transform coded videos.

Abstract: We propose a discriminative compact scene descriptor for single-view cross-season place recognition. Unlike previous bag-of-words approaches which rely on a library of vector quantized visual features, the proposed scene descriptor is based on a library of raw image data (such as available visual experience, images shared by other colleague robots, and publicly available image data on the web) that is directly mined to find nearest neighbor (NN) visual features (i.e., landmarks) for effectively explaining the input image. Our scene matcher adopts naive Bayes nearest neighbor (NBNN) techniques, where (1) raw visual features are used without vector quantization, and (2) image-to-class (rather than image-to-image) distance is used for scene comparison. Finally, we acquire a challenging cross-season place recognition dataset and validate the effectiveness of the proposed scene descriptor

Abstract: In the range of biometric we consider the variability of discourse flag because of the vicinity of clam or which impressively corrupts the productivity of ASR in genuine ecological condition. Speaker-vocal attributes exist in discourse signals and because of distinctive resonances of diverse speakers speaker acknowledgment framework checks the speaker. These distinctions can be misused by extricating element vectors like Mel-Frequency Cepstral Coefficient (MFCCs) from the discourse signal. In this paper we have utilized MFCC and Shifted MFCC with Vector Quantization and fuzzy demonstrating strategies correspondingly to enhance the execution of ASR even in boisterous environment with the assistance of redesigned discourse data which are available at high recurrence in otherworldly area. The mix of fuzzy demonstrating and shifted MFCC makes an in number total calculation which has the sensibly high vigour to clamour. In exploratory results, we have discovered 10–20% upgraded precision even at 5–8dB SNR in the vicinity of music foundation, boisterous natural condition furthermore in the vicinity of repetitive sound.

Abstract: This paper represents a very strong mathematical algorithm for Automatic Speaker Recognition (ASR) system using MFCC and vector quantization technique in the digital world. MFCC and vector quantization techniques are the most preferable and promising these days so as to support a technological aspect and motivation of the significant progress in the area of voice recognition. Our goal is to develop a real-time speaker recognition system that has been trained for a particular speaker and verifies the speaker. ASR is a type of biometric that uses an individual’s voice for recognition processes. Speaker-vocal discriminative parameters exist in speech signals and due to dissimilar resonances of different speakers speaker recognition system verifies the speaker. These different characteristics can be accomplished by extracting features in vector form like MelFrequency Cepstral Coefficient (MFCCs) from the audio signal. The Vector Quantization (VQ) technique maps vectors from a large vector space to a limited number of regions in the same multidimensional space. LBG (Linde, Buzo and Gray) algorithm is mostly used and preferred for clustering a set of L acoustic vectors into a set of M codebook vectors in speaker recognition.

Abstract: In this letter, we present a novel technique for unsupervised change analysis that leads to a method of ranking the changes that occur between two satellite images acquired at different moments of time. The proposed change analysis is based on binary descriptors and uses the Hamming distance as a similarity metric. In order to render a completely unsupervised solution, the obtained distances are further classified using vector quantization methods (i.e., Lloyd's algorithm for optimal quantization). The ultimate goal in the change analysis chain is to build change intensity maps that provide an overview of the severeness of changes in the area under analysis. In addition, the proposed analysis technique can be easily adapted for change detection by selecting only two levels for quantization. This discriminative method (i.e., between changed/unchanged zones) is compared with other previously developed techniques that use principal component analysis or Bayes theory as starting points for their analysis. The experiments are carried on Landsat images at a 30-m spatial resolution, covering an area of approximately $59 \times 51\ \mbox{km}^{2}$ over the surroundings of Bucharest, Romania, and containing multispectral information.

Abstract: In general, techniques are described for coding of vectors decomposed from higher-order ambisonic coefficients. A device comprising a memory and a processor may perform the techniques. The memory may be configured to store audio data. The processor may be configured to determine whether to perform vector dequantization or scalar dequantization with respect to a decomposed version of the plurality of HOA coefficients.

Abstract: A device for decoding video data is configured to determine for one or more blocks of the video data that adaptive color transform is enabled; determine a quantization parameter for the one or more blocks; in response to a value of the quantization parameter being below a threshold, modify the quantization parameter to determine a modified quantization parameter; and dequantize transform coefficients based on the modified quantization parameter.

Abstract: Real time pattern recognition applications often deal with high dimensional data, which require a data reduction step which is only performed offline. However, this loses the possibility of adaption to a changing environment. This is also true for other applications different from pattern recognition, like data visualization for input inspection. Only linear projections, like the principal component analysis, can work in real time by using iterative algorithms while all known nonlinear techniques cannot be implemented in such a way and actually always work on the whole database at each epoch. Among these nonlinear tools, the Curvilinear Component Analysis (CCA), which is a non-convex technique based on the preservation of the local distances into the lower dimensional space, plays an important role. This paper presents the online version of CCA. It inherits the same features of CCA, is adaptive in real time and tracks non-stationary high dimensional distributions. It is composed of neurons with two weights: one, pointing to the input space, quantizes the data distribution, and the other, pointing to the output space, represents the projection of the first weight. This on-line CCA has been conceived not only for the previously cited applications, but also as a basic tool for more complex supervised neural networks for modelling very complex high dimensional data. This algorithm is tested on 2-D and 3-D synthetic data and on an experimental database concerning the bearing faults of an electrical motor, with the goal of novelty (fault) detection.

Abstract: In this paper, an image compression scheme is proposed, based on discrete cosine transform (DCT). This scheme is a hybrid method, which combines vector quantization (VQ) and differential pulse code modulation (DPCM). This scheme begins with transforming image from spatial domain to frequency domain using DCT. Then the block data is transformed into a vector according to zigzag order, and then truncated. After that, the vector is split into DC coefficient and AC coefficients. After scale quantization, DC coefficient is coded using DPCM. AC coefficients are coded using multistage vector quantization (MSVQ). Then, entropy encoding is performed on index-tables and DC part, separately. The experimental results show that, compared to conventional VQ and DCTVQ schemes, proposed scheme has a better performance.

Abstract: Methods and apparatuses for fronthaul signal compression and decompression. An apparatus for fronthaul signal compression includes a receiver, signal processing circuitry, and a fronthaul interface. The receiver is configured to receive one or more signals comprising complex samples. The signal processing circuitry is configured to construct vectors representing at least a portion of the complex samples; map the vectors to codeword indices in a vector quantization codebook; and process the codeword indices into an output signal. The fronthaul interface is configured to transmit the output signal via a fronthaul communication link of a wireless network. The vectors may be constructed according to the selected vectorization method. The vector quantization codebook may be selected from a set of vector quantization codebooks generated based on training signals and signaled.

Abstract: Speaker Recognition is one of the most useful biometric recognition techniques in this world where insecurity is a major concern. This book introduces a method for speaker recognition on the basis of the individual information included in speech waves. This can mainly be divided into two parts speaker identification and speaker verification. Speaker Identification find outs which speaker has uttered the given speech and Speaker Verification verifies their identity. Speaker recognition technology is the most potential technology to create new services that will make our everyday lives more secured.

Abstract: In the current era, most of the digital information is in the form of multimedia with a giant share of videos. Videos do have audio and visual content where the visual content has number of frames put in a sequence. Most of the consecutive frames do have very little discriminative contents. In video summarization process, several frames containing similar information do need to get processed. This leads to redundant slow processing speed and complexity, time consumption. Video summarization using key frames can ease the speed up of video processing. In this paper, novel key frames extraction method is proposed with Kekere's Proportionate Error (KPE) codebook generation techniques of vector quantization with ten different codebook sizes and two color spaces (RGB and KLUV). Experimentation done with help of the test bed of videos has shown that higher codebook sizes of KPE have given better completeness in key frame extraction for video summarization. The LUV color space with Euclidean Distance with 512 codebook size gives best performance. In square chord Distance, Mean Square Error and Euclidean Distance LUV color space gives better completeness than RGB color space for proposed KPE based video Key frame Extraction