Chi-Min Li, Kuei-Jang Huang · IEEE Systems Journal · 2018
Long-term evolution advanced (LTE-A) is currently the most popular 4G wireless communication system worldwide. LTE-A system defines eight transmit antennas in downlink and adopts the precoding matrices to reduce the effect of interference and improve the received signal quality at the receiver. In this paper, three algorithms adopting the unique overlapped angle of direction of the beams for the LTE-A precoding matrices and the Euclidean Norm relation are proposed to reduce the calculations during precoding selection. Computer simulations and experiment results show that the proposed low-complexity precoding selection method can reduce more than 70% computational complexity and still maintains a good bit error rate performance compared with literary full search method.
Cited by 4
Fengyu Liang, Yunlong Cai · 2024
Recently, analog-digital hybrid precoding has emerged as a promising technique for mmWave (mmWave) multiuser multiple-input multiple-output (MU-MIMO) systems. However, it encounters two practical challenges in codebook design and beam selection. Traditional codebooks, once deployed, lack adaptability to the changing wireless landscape, while existing beam selection algorithms often fail to achieve optimal performance within reasonable complexity constraints. To address these issues, we propose a machine learning-enabled framework for joint codebook design and beam selection in mmWave MU-MIMO systems. Firstly, we design a learnable codebook using deep neural networks (NN). Then, we create a novel three-layer network architecture to enable the codebook’s dynamic adaptation to changes in the wireless environment. Subsequently, the beam selection problem is formulated as a Markov decision process, effectively solved using a double deep Q-network algorithm. Then, the joint training of the above two NNs is developed to jointly optimize the codebook and beam selection. Simulation results demonstrate that the proposed approach significantly improves the system’s sum-rate compared to traditional methods.
Cited by 2
Duanpo Wu, Chengjun Gong, Yuhan Gao et al. · SSRN Electronic Journal · 2025
Cited by 0Open access
Ramireddy, Venkatesh, Großmann, Marcus, Landmann, Markus · Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) · 2021
A method for providing feedback about a MIMO channel between a transmitter and a receiver in a wireless communication system is described. The includes receiving, at the receiver, a radio signal via the MIMO channel, the radio signal including reference signals, like a CSI-RS signal, according to at least one reference signal configuration, the reference signal configuration being known at the receiver and indicating an antenna port or a plurality of antenna ports that is/are associated with a reference signal or a plurality of reference signals; estimating, at the receiver, the MIMO channel based on measurements on the one or more reference signals received over the plurality of antenna ports indicated in the reference signal configuration; determining, at the receiver, a precoding vector or matrix to be used at the transmitter so as to achieve a predefined property for a communication over the MIMO channel, the precoding vector or matrix being determined based on the estimated MIMO channel, on one or more vectors or one or more combinations of vectors selected from at least one port-selection codebook and on a set of precoding coefficients, wherein the port-selection codebook comprises a set of vectors, each vector being associated with one of the antenna ports and having a single element which is one and the remaining elements being zeros; and reporting, by the receiver, a feedback to the transmitter, the feedback indicating the precoding vector or matrix determined by the receiver.
Cited by 0Open access
Lorenz Diener, Matthias Janke, Tanja Schultz · 2015
This paper reports on our recent advances in using Unit Selection to directly synthesize speech from facial surface electromyographic (EMG) signals generated by movement of the articulatory muscles during speech production. We achieve a robust Unit Selection mapping by using a more sophisticated unit codebook. This codebook is generated from a set of base units using a two stage unit clustering process. The units are first clustered based on the audio and afterwards on the EMG feature vectors they cover, and a new codebook is generated using these cluster assignments. We evaluate different cluster counts for both stages and revisit our evaluation of unit sizes in light of this clustering approach. Our final system achieves a significantly better Mel-Cepstral distortion score than the Unit Selection based EMG-to-Speech conversion system from our previous work while, due to the reduced codebook size, taking less time to perform the conversion.
Cited by 3
Mette Langaas · 1995
This report is the companion to the report "Mixture Codebook Classification, Part 1: Method Outline" by Langaas (1995b). A mixture codebook is a set of parameters and weights of a hierarchy of class-conditional finite mixture models. The concept of mixture codebook classification (MC 2 ) consists in estimating a mixture codebook and using it to construct a classification rule. In this report aspects of model selection and parameter estimation are discussed. Model selection is concentrated in two areas; choice of component distributions, where Gaussian and multivariate Student-t distributions are considered, and choice of component architecture. Parameter estimation is concentrated on comparing different optimization criteria and on regularization. A small comparative study involving mixture codebook classification, static neural networks and statistical methods for discrimination and classification is presented.
Cited by 0
Yichi Chen, Shang-Ho Tsai, Gene C. H. Chuang · 2011
This paper proposes a codebook design that considers transmit antenna selection and beamforming simultaneously. Under the same amount of feedback bits, the proposed codebook can reduce the number of RF units more than half while its performance is still maintained closely (within 0.1 dB loss) to the codebook designs that use all transmit antennas. Since RF units are expensive, the proposed codebook can greatly reduce the hardware implementational cost with slight performance degradation. Moreover, we analyze the proposed codebook and derive a lower bound of symbol error rate (SER). The derived SER lower bound generally matches the simulation results. Simulation results show the proposed codebook with around half active transmit antennas performs comparable to the Lloyd codebook design with full active antennas.
Cited by 0
Khushboo Sahu, Bhavesh Sonwani, Amit Shrivastava et al. · 2023
<p>In this paper, a one-bit beamforming codebook for Reconfigurable Intelligent Surface (RIS) is designed for an indoor environment. Each codeword in a codebook is a phase pattern at RIS elements that reflects the signal to a desired angle. For a specific reflection angle, those codewords are computed that maximizes the signal-to-noise ratio (SNR) at the receiver (RX). Since multiple codewords can maximize the SNR, an algorithm to reduce the size of the codebook is proposed. This ensures that the codebook does not contain repetitive codewords. In addition, after the codebook design, the codeword selection procedure is performed using an Autoencoder (AE) that minimizes the Bit Error Rate (BER) at the receiver. The proposed method shows promising results compared to existing techniques in terms of BER with reduced codebook size.</p>
Cited by 0Open access
Khushboo Sahu, Bhavesh Sonwani, Amit Shrivastava et al. · 2023
<p>In this paper, we designed a one-bit beamforming codebook for reconfigurable intelligent surfaces (RIS). Each codeword in a codebook is a phase pattern at RIS elements that reflects the signal to a desired angle. Those codewords are computed for a specific reflection angle that maximizes the signal-to-noise ratio (SNR) at the receiver (Rx). Since multiple codewords can maximize the SNR, an algorithm to reduce the size of the codebook is proposed. It ensures that the codebook does not contain repetitive codewords. Then, a deep neural network-based codeword selection procedure is performed using an autoencoder (AE) that minimizes the bit error rate (BER) at the receiver. The proposed method shows promising results compared to existing techniques regarding BER with reduced codebook size. </p>
Cited by 0Open access
Khushboo Sahu, Bhavesh Sonwani, Amit Shrivastava et al. · 2023
<p>In this paper, we designed a one-bit beamforming codebook for reconfigurable intelligent surfaces (RIS). Each codeword in a codebook is a phase pattern at RIS elements that reflects the signal to a desired angle. Those codewords are computed for a specific reflection angle that maximizes the signal-to-noise ratio (SNR) at the receiver (Rx). Since multiple codewords can maximize the SNR, an algorithm to reduce the size of the codebook is proposed. It ensures that the codebook does not contain repetitive codewords. Then, a deep neural network-based codeword selection procedure is performed using an autoencoder (AE) that minimizes the bit error rate (BER) at the receiver. The proposed method shows promising results compared to existing techniques regarding BER with reduced codebook size. </p>
Cited by 0Open access
Youqi Shen, Guiyong Li, Lulin Shi · International Journal of Advanced Science and Technology · 2016
In this paper, on LTE-A system based MIMO pre-coding codebook selection algorithm are researched. Traditional pre-coding selection algorithm requires to complete the corresponding code to traverse, however improved traversal algorithm are optimized than traditional traversal algorithms, but it has high complexity. Based on the stud-y of the two kinds of pre-coding selection algorithm, we propose a modified algorithm, then the algorithm in EPA5, EVA5, ETU70 on the type of channel simulation and analysis, Simulation results show that the algorithm performance with almost no loss compared with the traditional method, while significantly lower the complexity.
Cited by 0
Samra Siddiqui, Muhammad Attique Khan, Khalid Bashir et al. · International Journal of Applied Pattern Recognition · 2018
Human activity recognition (HAR) has significance in the domain of pattern recognition. HAR handles the complexity of human physical changes and heterogeneous formats of same human actions performed under dissimilar subjects. This research contributes a unique method focusing on the changes in human movement. The purpose is to identify and categorise human actions from video sequences. The interest points (IPs) are extracted from the subject video and motion history images (MHIs) are constructed and analysed after image segmentation. Discriminative features (DFs) are selected and the visual vocabulary is learned from the extracted DF (EDF). The EDF are then quantised by using visual vocabulary and images are represented based upon frequencies of visual words (VW). VW are formed from the EDF and then, a histogram of VW is developed based on the feature vectors extracted from MHI. These feature vectors are used for training support vector machine (SVM) for the classification of actions into various categories. Benchmark datasets like KTH, Weizmann and HMDB51 are used for evaluation and comparison with existing action recognition approaches depicts the better performance of adopted strategy.
Cited by 24
Jihyung Kim, Jaeho Lee, Jinkyu Kang · 2025
To address the practical control complexity of Reconfigurable Intelligent Surfaces (RIS), this paper proposes a lightweight, deterministic scheme operating at a computational cost comparable to the conventional discrete Fourier transform (DFT) codebook search. The proposed method integrates a Top-K pre-selection mechanism with a subsequent single-step phase refinement to achieve an effective balance between search efficiency and performance. Simulation results show that, within a similar time budget, our approach enhances the weighted sum-rate (WSR) and mitigates the outage probability compared to the DFT baseline, remaining effective across a range of complexity budgets.
Cited by 0
Veerapathirapillai Vinoharan, Amirthalingam Ramanan · 2018
In a patch-based object classification system, one of the most popular image representation approach is the bag-of-features (BoF) representation. However, the number of patch-based features extracted from images to create the BoF vector is usually very large, which causes two problems: (i) Increased amount of computational needs during the vector quantisation step, and (ii) Ambiguous descriptors from training images increase false positive rate in the classification. To overcome these issues we introduce a one-pass feature selection approach followed by an entropy-based filtering technique to eliminate the ambiguous features from initial large feature set. In this work, a discriminative BoF representation for object recognition is constructed using patch-based descriptors that are informative in distinguishing object categories. Following the construction of a codebook a subset of codewords which is not activated enough in images is eliminated based on statistical measures and visual-bit representation of codewords. The proposed technique is evaluated on (i) Xerox7, (ii) UIUCTex, (iii) PASCAL VOC 2007, and (iv) Caltech101 image datasets. The proposed feature selection step increases the discriminant power of a codebook, while the codeword selection method maintains the codebook to be more compact. The proposed framework would help to optimise the BoF representation to be effective with stable performance.
Cited by 0
Mengling Zhao, Hongwei Liu · SHILAP Revista de lepidopterología · 2013
In the area of digital image compression, the vector quantization algorithm is a simple, effective and attractive method. After the introduction of the basic principle of the vector quantization and the classical algorithm for vector quantization codebook design, the paper, based on manifold distance, presents a clonal selection code book design method, using disintegrating method to produce initial code book and then to obtain the final code book through optimization with the clonal selection cluster method based on the manifold distance. Through experiment, based on manifold distance, compared the clonal selection codebook design algorithm (MDCSA) with the hereditary codebook design algorithm and LBG algorithm. According to the result of the experiment, MDCSA is more suitable for the evolution algorithm of the image compression. \n
Cited by 2Open access
Thomas Drugman, Alexis Moinet, Thierry Dutoit et al. · arXiv (Cornell University) · 2019
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as to construct a more realistic source signal. First a limited codebook of typical excitations is built from some training database. During the synthesis part, HMMs are used to generate filter and source coefficients. The latter coefficients contain both the pitch and a compact representation of target residual frames. The source signal is obtained by concatenating excitation frames picked up from the codebook, based on a selection criterion and taking target residual coefficients as input. Subjective results show a relevant improvement compared to the basic technique.
Cited by 0Open access
Pallab Kanti Podder (2558800), Manoranjan Paul (2558803), Manzur Murshed (2558806) · Figshare · 2016
<p>Codebook of the proposed binary pattern templates for subset of inter-mode selection.</p>
Cited by 0Open access
Denis Esiunin, Alexei Davydov · arXiv (Cornell University) · 2026
This paper addresses the problem of adaptive codebook (CB) selection for downlink (DL) precoder quantization in channel state information (CSI) reporting. The accuracy of precoder quantization depends on propagation conditions, requiring independent parameter adaptation for each user equipment (UE). To enable optimal CB selection, this paper proposes UE-assisted CB selection at the base station (BS) using reported by the UE statistical channel properties across time, frequency, and spatial domains. The reported assistance information serves as input to a neural network (NN), which predicts the quantization accuracy of various CB types for each served user. The predicted accuracy is then used to select the optimal CB while considering the associated CSI reporting overhead and precoding performance. System-level simulations demonstrate that the proposed approach reduces total CSI overhead while maintaining the target system throughput performance.
Cited by 0Open access
Denis Esiunin, Alexei Davydov · arXiv (Cornell University) · 2026
This paper addresses the problem of adaptive codebook (CB) selection for downlink (DL) precoder quantization in channel state information (CSI) reporting. The accuracy of precoder quantization depends on propagation conditions, requiring independent parameter adaptation for each user equipment (UE). To enable optimal CB selection, this paper proposes UE-assisted CB selection at the base station (BS) using reported by the UE statistical channel properties across time, frequency, and spatial domains. The reported assistance information serves as input to a neural network (NN), which predicts the quantization accuracy of various CB types for each served user. The predicted accuracy is then used to select the optimal CB while considering the associated CSI reporting overhead and precoding performance. System-level simulations demonstrate that the proposed approach reduces total CSI overhead while maintaining the target system throughput performance.
Cited by 0Open access
Masafumi Tsutsui, Hiroyuki Seki · 2007
We have been proposing multi-beam MIMO (MB-MIMO) as an evolved UTRA downlink MIMO scheme for 3GPP long term evolution (LTE). MB-MIMO is a pre-coding MIMO scheme that uses a simple combination of multi-beam multiple-data-stream transmission and user equipment (UE)-based adaptive beam selection. The scheme benefits from its simple uplink feedback signaling, because MB-MIMO requires only a subset of the beam (codebook) indices to be fed back. However, a hardware calibrator (HW-CAL), which increases the complexity of RF components at a transmitter, should be installed in order to achieve a high beam-forming gain with a small codebook size. In this paper, we propose a novel codebook design for MB-MIMO, which realizes a superior performance without any HW-CAL with a small increase of the codebook size and the feedback signaling. We performed a computer simulation to evaluate the throughput performance of the proposed scheme, considering the phase variation between antenna elements in a spatially distributed multi-path fading channel model.
Cited by 2