Adaptive Coding Research Articles

Adaptive hash code balancing for remote sensing image retrieval

ABSTRACT Remote sensing image retrieval (RSIR) refers to finding images from an image database that contain the same instance as the query image, which is an essential task in remote sensing applications. Traditional depth-based hashing algorithms usually convert the image library into a hash matrix with a specified number of digits. On the one hand, the quality of hash matrices generated by traditional methods is low and cannot guarantee good clustering between pictures of the same class. On the other hand, the ability to extract features using backbone networks must be improved. This paper proposes a deep hashing model called adaptive hash code balancing (AHCB) to solve two existing problems. The model introduces a balanced binary method to maximize the hash value entropy so that the generated hash has better clustering. Graph convolutional networks(GCNs) are introduced to automatically detect relevant data points in the graph, perform back-propagation, and propagate the updated network feedback to the feature extraction layer to improve the ability to extract features. It enables the model to learn the intrinsic data structure between remote sensing images. Experimental results on three public datasets show that the proposed method outperforms the current state-of-the-art deep hashing remote sensing image retrieval algorithms by a large margin.

Lossless Image Coding Using Non-MMSE Algorithms to Calculate Linear Prediction Coefficients.

This paper presents a lossless image compression method with a fast decoding time and flexible adjustment of coder parameters affecting its implementation complexity. A comparison of several approaches for computing non-MMSE prediction coefficients with different levels of complexity was made. The data modeling stage of the proposed codec was based on linear (calculated by the non-MMSE method) and non-linear (complemented by a context-dependent constant component removal block) predictions. Prediction error coding uses a two-stage compression: an adaptive Golomb code and a binary arithmetic code. The proposed solution results in 30% shorter decoding times and a lower bit average than competing solutions (by 7.9% relative to the popular JPEG-LS codec).

Adaptive coding across visual features during free-viewing and fixation conditions

Theoretical studies have long proposed that adaptation allows the brain to effectively use the limited response range of sensory neurons to encode widely varying natural inputs. However, despite this influential view, experimental studies have exclusively focused on how the neural code adapts to a range of stimuli lying along a single feature axis, such as orientation or contrast. Here, we performed electrical recordings in macaque visual cortex (area V4) to reveal significant adaptive changes in the neural code of single cells and populations across multiple feature axes. Both during free viewing and passive fixation, populations of cells improved their ability to encode image features after rapid exposure to stimuli lying on orthogonal feature axes even in the absence of initial tuning to these stimuli. These results reveal a remarkable adaptive capacity of visual cortical populations to improve network computations relevant for natural viewing despite the modularity of the functional cortical architecture.

Digital Programmable Metasurface with Element-Independent Visible-Light Sensing

The application of jointing multiple physical field sensing with electromagnetic (EM) wave manipulation is a hot research topic recently. Refined perception and unit-level independent regulation of metasurfaces still have certain challenges. In this paper, we propose a digital programmable metasurface that can adaptively achieve various EM functions by sensing the color changes of the incident light, which enables unit-level sensing and modulation. Integrating trichromatic sensors, FPGA, and algorithm onto the metasurface has established a metasurface architecture for electromagnetic scattering field modulation from complex optics to microwave wavelengths, which enables a wide variety of light sensing for modulation. The metasurface integrated with PIN diodes and trichromatic color sensors forms a complete intelligent system of adaptive and reconfigurable coding patterns, within the pre-designed control of FPGA. We fabricated the metasurface using standard printed circuit board (PCB) technology and measured the metasurface in far-fields. The measurement results show good agreement with the simulation results, verifying our design. We envision that the proposed programmable metasurface with visible light sensing will provide a new dimension of manipulation from this perspective.

Modulation and coding methods in 5th generation networks

The fifth generation (5G) of wireless communication networks represents a groundbreaking shift in the realm of connectivity, enabling a wide array of transformative applications and services. This article delves into the pivotal role played by modulation and coding methods in the context of 5G networks. It explores their significance, delves into recent research and publications within the field, and outlines the direction for future research endeavors. Modulation and coding (M&C) are fundamental for 5G networks, enhancing data rates, reliability, and reducing interference. This article delves into their role in 5G networks, addressing challenges, including fading channels, interference, and diverse user needs. Recent research explores advanced modulation schemes like 256-QAM and 1024-QAM, requiring error correction coding techniques like Turbo codes and LDPC codes. Massive MIMO, using multiple antennas at both ends, is supported by adaptive coding and modulation. Adaptive Modulation and Coding (AMC) dynamically adjusts schemes based on real-time channel conditions, balancing data rate and reliability. Non-Orthogonal Multiple Access (NOMA) accommodates massive device connectivity, allowing multiple users to share resources with different power levels and modulation schemes. The study aims to comprehensively analyze 5G's M&C methods, assess modulation schemes for higher data rates, evaluate error correction coding, investigate Massive MIMO and adaptive modulation for spectral efficiency, and scrutinize NOMA's potential for massive device connectivity. Results highlight the importance of advanced modulation schemes, efficient error correction coding, and adaptive techniques in realizing 5G objectives, enabling higher data rates, lower latency, and improved reliability. NOMA is promising for accommodating many connected devices in 5G. M&C are essential for efficient and reliable data transmission in 5G, with ongoing research refining techniques for 6G and beyond. Integrating machine learning and AI into M&C algorithms holds promise for enhancing network efficiency and reliability.

Adaptive Coding is Optimal in Reinforcement Learning

Adaptive Coding is Optimal in Reinforcement Learning

Adaptive Coding and Ordered-Index Extended Scrambling Based RDH in Encrypted Images

Adaptive Coding and Ordered-Index Extended Scrambling Based RDH in Encrypted Images

A robust transmission with enhancement of 5G PHY using FBMC and AMC for machine-to-machine communication node

Advancement of 5G new radios has enabled more robust communication for the Machine-to-Machine (M2M) communication node, using filter bank multicarrier (FBMC). This paper focuses on robust transmission over random fluctuations of the channel and also enhances the battery life for the massive machine type communication (mMTC) node. Filter bank multicarrier and Adaptive Modulation Coding (AMC) have been utilized together to enhance the performance of the 5G (NR) PHY layer. A frame-to-frame implementation is used to diminish the impact of fading using AMC, while efficient utilization of spectrum is achieved using FBMC. The selection of the AMC profile is obtained through the analysis of uplink packets using the Distance Statistics (DS). The FBMC is incorporated with 5G PHY in place of OFDM to achieve the optimum utilization of spectrum and also obtain a significant reduction in peak to average power ratio (PAPR) for robust transmission, which saves 10% of the battery requirement. On the basis of channel state information, distance statistics were employed to optimize the AMC. The optimum selection of AMC with FBMC will reduce the bit error rate (BER) against multipath fading and ensure the better utilization of available spectrum to attain the optimum utilization of the power amplifier.

Chaotic image encryption algorithm based on elliptic curve and adaptive DNA coding

Chaotic image encryption algorithm based on elliptic curve and adaptive DNA coding

Adaptive Rate Polar Code for DCT-Based Digital Image Transmission

Adaptive Rate Polar Code for DCT-Based Digital Image Transmission

Analysis of the Limitations of Further Improvement of the Efficiency of VVC-CABAC

Hybrid video compression plays an invaluable role in digital video transmission and storage services and systems. It performs several-hundred-fold reduction in the amount of video data, which makes these systems much more efficient. An important element of hybrid video compression is entropy coding of the data. The state-of-the-art in this field is the newest variant of the Context-based Adaptive Binary Arithmetic Coding (CABAC) entropy compression algorithm which recently became part of the new Versatile Video Coding (VVC) technology. This work is a part of research that is currently underway to further improve the CABAC technique. This paper provides analysis of the potential for further improvement of the CABAC by more accurate calculation of probabilities of data symbols. The CABAC technique calculates those probabilities by the use of idea of the two-parameters hypothesis. For the needs of analysis presented in this paper, an extension of the aforementioned idea was proposed which consists of three- and four-parameters hypothesis. In addition, the paper shows the importance of proper calibration of parameter values of the method on efficiency of data compression. Results of experiments show that for the considered in the paper variants of the algorithm improvement the possible efficiency gain is at levels 0.11% and 0.167%, for the three- and four-parameter hypothesis, respectively.

Adaptive Polynomial Coding of Multi-base Hybrid Compression

With increasing demand for the intensive use of images, especially linked to online applications as well as the massive, continuous revolution of mobile phone technology, the need has emerged for efficient, standard image compression techniques that ensure simplicity and speed. These must be compatible with user needs, but also meet the challenges of improving compression techniques. Polynomial coding is one such techniques still under development, based on a modelling concept of deterministic and probabilistic coding bases. This paper introduces a new mathematical iterative polynomial model to represent both coding bases. The model proposes an efficient hybrid way where coefficients are represented as lossless while residuals are presented as a lossy but with minimum loss, which ensures effective performance in terms of compression ratios and quality. Results show that while the technique has some limitations, the proposed system achieves equivalent compression ratios as the standard JPEG technique, but with superior quality for the same compression ratio.

Toward Semantic Communications: Deep Learning-Based Image Semantic Coding

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and apply techniques in Natural Language Processing (NLP) to interpret the meaning of the text. In this paper, we conceive the semantic communications for image data that is much more richer in semantics and bandwidth sensitive. We propose an reinforcement learning based adaptive semantic coding (RL-ASC) approach that encodes images beyond pixel level. Firstly, we define the semantic concept of image data that includes the category, spatial arrangement, and visual feature as the representation unit, and propose a convolutional semantic encoder to extract semantic concepts. Secondly, we propose the image reconstruction criterion that evolves from the traditional pixel similarity to semantic similarity and perceptual performance. Thirdly, we design a novel RL-based semantic bit allocation model, whose reward is the increase in rate-semantic-perceptual performance after encoding a certain semantic concept with adaptive quantization level. Thus, the task-related information is preserved and reconstructed properly while less important data is discarded. Finally, we propose the Generative Adversarial Nets (GANs) based semantic decoder that fuses both locally and globally features via an attention module. Experimental results demonstrate that the proposed RL-ASC is noise robust and could reconstruct visually pleasant and semantic consistent image in low bit rate condition.

Adaptive coding of reward in schizophrenia, its change over time and relation to negative symptoms

Adaptive coding of reward in schizophrenia, its change over time and relation to negative symptoms

Deep Graph Convolutional Quantization Networks for Image Retrieval

To achieve real-time online search, most image retrieval methods aim to learn compact feature representation while keeping their semantic information or intra-class relevance. In this paper, we propose a new compact feature learning method to embed the underlying manifold information from database. It integrates deep convolutional neural network (CNN) and graph convolutional neural networks (GCN) into a unified end-to-end learning framework. In the proposed method, the deep feature extracted by CNN is automatically embedded with the information from its neighbors by GCN, which possesses the ability of exploring the semantic relevance on the database manifold. Since constructing a graph over the whole database costs unaffordable memory, we build a landmark graph as database sketch. The landmark graph contains two kinds of nodes, including codewords and memory bank samples. Given an image, the deep architecture outputs the discriminative feature and its similarity with all the graph nodes. We directly use the indices of the most similar codeword nodes as the compact feature representation. To make the proposed method scalable to large datasets, a multi-graph strategy is adopted to generate compact features with adaptable code length. The experiments on two benchmark datasets demonstrate the effectiveness of the proposed method.

ПІДВИЩЕННЯ ЕФЕКТИВНОСТІ БЕЗПРОВОДОВИХ СИСТЕМ ПЕРЕДАЧІ ДАНИХ В УМОВАХ ЗАСТОСУВАННЯ ЗАСОБІВ РАДІОЕЛЕКТРОННОЇ БОРОТЬБИ

The article discusses some of the technologies that ensure the autonomy of unmanned aerial vehicles (UAVs) on the battlefield, methods of increasing the efficiency of UAV communication channels in the context of electronic warfare (EW). The author analyzes the threats to autonomous UAVs that may arise from the use of electronic warfare, and also presents the characteristics of one of the typical modern electronic warfare complexes. This article discusses the development of a test model of a wireless data transmission channel designed to develop technologies for countering electronic warfare and traininga neural network. The use of this model will allow the development of original domestic algorithms for countering enemy electronic warfare. The requirements of manufacturers to the electronic equipment of autonomous UAVs are analyzed. The possibility of using non-professional SDR radio equipment and open source software and hardware platforms for the develop-ment and verification of these countermeasures algorithms is considered. The algorithm for changing data transmission pa-rameters in the event of interference is determined. The choice of the type of neural network for use in the cognitive radio system of the UAV is substantiated. The idea of applying adaptive coding in UAV communication channels using multicompo-nent turbo codes in combination with neural networks that are simultaneously used for cognitive radio was further developed. Using information from the neural network about subsequent changes in the communication channel will reduce the adaptation time of the coding system, which will reduce the number of errors in data transmission and increase the reliability of commu-nication, especially when using dynamic spectrum access.The article is devoted to the problems of creating methods and models that use software-defined radio (SDR), cognitive radio, and multi-level parametric adaptation of turbo-code structures using artificial intelligence to improve the efficiency of wireless data transmission systems in the context of active use of electronic warfare by ensuring the reliability of information

DNA Synthetic Steganography Based on Conditional Probability Adaptive Coding

Steganography is an important technology for ensuring the security of cyberspace and the privacy of communications. In the last decade, emerging biotechnology has made it possible for DNA to be used as a promising steganographic carrier with high hidden capacity, high imperceptibility and high feasibility. However, severe statistical distortion might appear in steganographic carriers generated by existing DNA steganographies when they are compared with the natural ones. Therefore, efforts are being made to seek an advanced strategy to generate quasi-natural steganographic carriers with a strong anti-steganalysis capability. In this work, we first thoroughly analyze and model the numerous complicated statistical properties that exist in natural DNA chains, and then utilize the LSTM model to learn the serialized statistical properties. After obtaining an optimal sequence model that highly satisfies the statistical properties of natural DNA chains, we utilize the Adaptive Dynamic Grouping (ADG) algorithm to perform information hiding. In addition, we have carried out experimental analysis and verification from the perspectives of perceptual-imperceptibility, statistical-imperceptibility, and anti-steganalysis capability, all of which show that our proposed steganography method vastly outperforms previous DNA steganographic methods, taking a successful step towards achieving higher security DNA steganography.

Multiple-Objective Packet Routing Optimization for Aeronautical Ad-Hoc Networks

Providing Internet service above the clouds is of ever-increasing interest and in this context aeronautical <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad-hoc</i> networking (AANET) constitutes a promising solution. However, the optimization of packet routing in large ad hoc networks is quite challenging. In this article, we develop a discrete <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> multi-objective genetic algorithm ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> -DMOGA) for jointly optimizing the end-to-end latency, the end-to-end spectral efficiency (SE), and the path expiration time (PET) that specifies how long the routing path can be relied on without re-optimizing the path. More specifically, a distance-based adaptive coding and modulation (ACM) scheme specifically designed for aeronautical communications is exploited for quantifying each link's achievable SE. Furthermore, the queueing delay at each node is also incorporated into the multiple-objective optimization metric. Our <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> -DMOGA assisted multiple-objective routing optimization is validated by real historical flight data collected over the Australian airspace on two selected representative dates.

THE USE OF COGNITIVE RADIO TECHNOLOGY TO IMPROVE THE EFFICIENCY OF WIRELESS DATA TRANSMISSION SYSTEMS IN THE CONDITIONS OF ACTIVE USE OF ELECTRONIC WARFARE

The article discusses the development of a method for improving the efficiency of communication channels of unmanned aerial vehicles (UAVs) in the context of electronic warfare (EW). The threats that can be caused by the use of electronic warfare against autonomous UAVs are analyzed. A review of some technologies that can be used to create original domestic algorithms for countering electronic warfare and improve the autonomy of UAVs on the battlefield is carried out. The possibility of using non-professional SDR radio equipment and open source hardware and software platforms for the development and verification of these countermeasures algorithms is considered. The idea of applying adaptive coding in UAV communication channels using multicomponent turbo codes in conjunction with neural networks, which are simultaneously used for cognitive radio, was further developed. The article is devoted to the problems of creating models and methods for ensuring the integrity of information in wireless data transmission systems in the context of active use of electronic warfare.

Expansion of a finite-size photoplasma in an electrostatic field with M-type electrode configuration using a novel adaptive mesh 2D-PIC code

A two-dimensional electrostatic particle-in-cell code is developed with an adaptive mesh feature to investigate the dynamics of photoplasma in M-type electrode configurations. This adaptive mesh is designed by using a one-dimensional pseudo mesh, where at the starting of each pseudo cell the quasineutrality and density of charged particles are checked, which decides the coarseness of the actual computational mesh. Through this developed particle-in-cell code, the ion extraction process from a finite-size photoplasma is simulated for parallel plate and M-type electrode configurations. Subsequently, the ion extraction time from the photoplasma is investigated by using the different potential waveforms, i.e. constant and two-step potential. On the basis of this numerical hypothesis, it is observed that the efficacy of M-type configuration is better than the parallel plate electrode configuration. Moreover, ion collection efficiency is also improved using a two-step potential waveform.