Adaptive Channel Research Articles

Adaptive Wireless Image Transmission Transformer Architecture for Image Transmission and Reconstruction

The advancement of 6G (6th Generation Mobile Networks) communication technology has posed challenges for traditional communication network architectures in meeting the demands for communication efficiency and quality. Semantic communication technology, characterized by its “understand before transmit” approach, has emerged as a pivotal technology driving the progress of 6G due to its ability to enhance communication efficiency and quality. The Wireless Image Transmission Transformer (WITT) model, which operates as a semantic communication system leveraging vision transformer technology for the transmission of semantic images, has shown efficacy in transmitting input images through processes of feature extraction and channel adaptation. This study introduces an advanced channel adaptive module that is informed by deep learning methodologies and the adaptive modulation principles of the Variational Information Bottleneck (VIB). This innovation enhances the original WITT model, resulting in the development of the Adaptive Wireless Image Transmission Transformer (ADWITT) architecture. Comprehensive experimental results have unequivocally shown that the transmission performance of the ADWITT architecture substantially surpasses that of the conventional WITT (Wavelet Image Transmission Technique) model, particularly in scenarios characterized by harsh and detrimental channel conditions. These findings underscore the robustness and adaptability of the ADWITT approach, which is poised to improve the field of image transmission by offering superior performance and resilience in environments where traditional methods falter.

Joint hybrid recursive feature elimination based channel selection and ResGCN for cross session MI recognition

In the field of brain-computer interface (BCI) based on motor imagery (MI), multi-channel electroencephalography (EEG) data is commonly utilized for MI task recognition to achieve sensory compensation or precise human-computer interaction. However, individual physiological differences, environmental variations, or redundant information and noise in certain channels can pose challenges and impact the performance of BCI systems. In this study, we introduce a channel selection method utilizing Hybrid-Recursive Feature Elimination (H-RFE) combined with residual graph neural networks for MI recognition. This channel selection method employs a recursive feature elimination strategy and integrates three classification methods, namely random forest, gradient boosting, and logistic regression, as evaluators for adaptive channel selection tailored to specific subjects. To fully exploit the spatiotemporal information of multi-channel EEG, this study employed a graph neural network embedded with residual blocks to achieve precise recognition of motor imagery. We conducted algorithm testing using the SHU dataset and the PhysioNet dataset. Experimental results show that on the SHU dataset, utilizing 73.44% of the total channels, the cross-session MI recognition accuracy is 90.03%. Similarly, in the PhysioNet dataset, using 72.5% of the channel data, the classification result also reaches 93.99%. Compared to traditional strategies such as selecting three specific channels, correlation-based channel selection, mutual information-based channel selection, and adaptive channel selection based on Pearson coefficients and spatial positions, the proposed method improved classification accuracy by 34.64%, 10.8%, 3.25% and 2.88% on the SHU dataset, and by 46.96%, 5.04%, 5.81% and 2.32% on the PhysioNet dataset, respectively.

Emotion Detection using EEG Signals in Image and Video Processing: A Survey

Brain serves as the body's processing of knowledge and management centre. The central nervous system directly produces ElectroEncephaloGram (EEG) physiological signals, which are strongly associated with human emotions. In the upcoming years, there will be an increase in interest for identifying emotion using brain waves by EEG (ElectroEncephaloGraphy) signals. It takes efficient and effective signal processing and feature extraction techniques for detection of emotions from human biological brain signals. Current approaches gather valuable information from a fixed number of ElectroEncephaloGraphy (EEG) channels utilizing variety of methodologies. This work analyses the different difficulties and problems associated with EEG signals for emotion identification and provides a comprehensive summary of several contemporary approaches. Pre-processing, feature extraction, and categorization are the first steps in the process of recognizing emotions from EEG signals. The main goal of this survey is to sought and enhance brain signal-based emotion detection ability by comparing all novel and adaptive channel selection technique that recognize the distinct changes in brain activities that varies between individuals and emotional states.

LARS: Remote Sensing Small Object Detection Network Based on Adaptive Channel Attention and Large Kernel Adaptation

LARS: Remote Sensing Small Object Detection Network Based on Adaptive Channel Attention and Large Kernel Adaptation

Study on heat transfer characteristics and enhancement mechanism of supercritical carbon dioxide in adaptive channels

Supercritical CO2 power cycles have promising applications in many fields, the heat transfer of supercritical CO2 is critical to the efficiency and safe operation of cycle system. The adaptive channel was previously proposed by our group to improve heat transfer of supercritical CO2, the performance of heat exchanger with adaptive channel was experimentally studied. Whereas the effect of adaptive channel on heat transfer deterioration of supercritical CO2 and the mechanism remain unclear. In this study, the effect of adaptive channel on heat transfer deterioration of supercritical CO2 and the mechanism are analyzed numerically based on a single channel, the effect of structure on heat transfer is analyzed through the maximum wall temperature and average heat transfer coefficient under the same length and heat transfer area. The results reveal adaptive channel is effective at alleviating heat transfer deterioration with no local peak in wall temperature distribution. The channel variation length of adaptive channel need to be increased from 0.4 to 0.8 with the aggravation of heat transfer deterioration in order to eliminate local wall temperature peak. For the heat transfer deterioration conditions, the maximum wall temperature lowers first and then increases as channel variation length increases, there is a length that makes the maximum wall temperature lowest, which is lowered by more than 40 °C compared with straight channel. The average heat transfer coefficient can be increased by 1.1 ∼ 1.5 times as channel variation length increases. For the no heat transfer deterioration conditions, the maximum wall temperature increases about 30 °C whereas average heat transfer coefficient can be increased by 58 %∼76 % with channel variation length increasing. The mechanism of adaptive channel alleviating heat transfer deterioration is as follows: the fluid velocity always presents an inverted U-shaped distribution along the radial direction in adaptive channel, the radial density difference is less and buoyancy effects heat transfer weakly. The turbulent kinetic energy is kept at high, so the heat near the wall is transferred to the main flow timely.

Adaptive Channel Equalization for Digital Communication with Tunicate Swarm Algorithm

In wireless communication systems, the information is transferred as digital symbols these symbols are affected by noise interference while transmitting through the wireless channel. In today’s world, the increased demand for rapid data transmission rates leads to more inter-symbol interference in the received signal. To diminish the effects of inter-symbol interference adaptive channel equalization is utilized in digital communication. In this paper, the inter-symbol interference effect in the finite impulse response channel is reduced in terms of an adaptive equalizer method. The weights/coefficients of the equalizer are optimized through a tunicate swarm algorithm. Channel equalization involves optimizing the channel coefficients to mitigate the impact of inter-symbol interference. This equalization process can be viewed as an iterative optimization task, aimed at lessening the mean square error among the transmitted signal and the equalizer’s output. The implementation of the proposed method is executed using MATLAB software. We assess its effectiveness through a comparative analysis, considering metrics such as mean square error, learning rate, bit error rate, convergence rate, and computational time. Furthermore, we conduct a comparative evaluation with other optimization approaches, including the Bat Algorithm, Slime Mould Algorithm, and Harris Hawks Optimization Algorithm. This comparison demonstrates the superiority of the proposed algorithm over traditional optimization techniques.

Enhancing energy efficiency in tyre pressure and temperature monitoring systems

This study addresses the pivotal challenge of enhancing power efficiency in tyre pressure and temperature monitoring systems (TPMS) for heavy vehicles and trailers. Employing field-programmable gate arrays (FPGA) and adaptive channel frequency hopping in bluetooth low energy (BLE) communication, the research focuses on mitigating power consumption issues specific to heavy vehicles with multiple tyres. The proposed solution incorporates strategic BLE channel blocking and adaptive frequency hopping on the FPGA platform to alleviate channel congestion and interference, ultimately reducing TPMS power consumption. The FPGA's adaptability tailors frequency hopping strategies to automotive TPMS nuances, optimizing channel selection and minimizing energy-intensive processes. Empirical results showcase a significant reduction in power consumption, with the TPMS operating at 100 MHz during active mode consuming 66 mW, dropping to 11 mW in sleep mode, and reaching 0 mW in hibernate mode for the majority of operational time. This research establishes a practical FPGA-based approach for power optimization in commercial TPMS, promising heightened reliability, safety improvements, and environmental impact reduction in the automotive sector.

A gradual self distillation network with adaptive channel attention for facial expression recognition

Facial expression recognition (FER) is widely applied in various real-world applications, such as security, human–computer interaction, and healthcare, leading to high demands for fast and accurate FER techniques. However, it remains a challenging task to design effective and efficient FER techniques that meet the requirements of real-world applications. In this paper, we propose a lightweight Gradual Self Distillation Network with adaptive channel attention (GSDNet) for accurate and efficient FER. Especially, we propose a novel gradual self distillation strategy which enables the network to learn from itself in a gradual and adaptive way. Specifically, the proposed GSDNet consists of a feature extraction backbone with multiple basic blocks. We plug an adaptive classifier after each basic block. Every two neighbor classifiers form “student & teacher” relationship for gradual knowledge distillation. In particular, the gradual self distillation strategy enables the transfer of key knowledge from deep to shallow layers gradually. Besides, an Adaptive Channel Attention Module (ACAM) is designed to enhance the representation capability of each block for adaptively capturing important features and achieve better FER performance. Extensive experiments on three real-world datasets show that the proposed method GSDNet outperforms the baselines, including state-of-the-art methods. Specifically, the accuracy of GSDNet on the RAF-DB, Affect-net, and FERPlus datasets is 90.91%, 66.11%, and 90.32%, separately. The code is available at https://github.com/Emy-cv/GSDNet.

(r, Q) stock replenishment in multi-mode distribution systems with uncertain delivery channels and adaptive channel allocation

To mitigate the impact of uncertainty in goods distribution systems, multiple channels and transportation modes may be used. In this paper, a discrete-time model of supplier-depot interaction involving multiple channels of goods relocation is constructed using the concepts of dynamic systems theory. The considered class of systems faces two types of uncertainty: a priori unknown variations of market demand and unpredictable changes of lead-time delay, different for each channel. The variation pattern is arbitrary. As a control mechanism, the nonlinear (r, Q) replenishment policy (provide Q units of goods when the stock falls below r) is considered. As opposed to the previous studies, the policy is demonstrated robust to both sources of uncertainty acting simultaneously using a formal mathematical argument. Moreover, it is shown how to select the policy parameters to obtain full demand realization, thus eliminating backorders, irrespective of the pattern of delay and demand fluctuations. It is also discussed how to assign the depot capacity so that emergency storage will not be required even though deliveries from a few periods arrive concurrently, or out of order. In addition, a new channel allocation strategy, dynamically adapting itself to the channel temporal characteristics, is developed. As evidenced in the tests, the proposed adaptive strategy, by reducing the waiting time for the lot reassembly at the depot, allows for holding cost reduction by several percent with respect to a static strategy.

HPS: A Hybrid Proactive Scheduler with adaptive channel selection for industrial 6TiSCH networks

The Industrial Internet of Things (IIoT) plays a vital role in Industry 4.0, thanks to advanced wireless protocols like IEEE 802.15.4 Time-Slotted Channel Hopping (TSCH) and their incorporation in the IPv6 stack via 6TiSCH. These protocols rely on carefully constructed schedules generated by a Scheduling Function (SF). The Minimal Scheduling Function (MSF) serves as the standard SF established by the 6TiSCH WG, prescribing the management and adaptation of the communication schedule based on traffic patterns. However, MSF has a notable drawback in adapting to traffic variability and burstiness and fails to account for link quality when updating TSCH cells. To address these limitations, this paper introduces the Hybrid Proactive Scheduler with Adaptive Channel Selection (HPS). HPS calculates cell requirements by considering resource utilization, ETX (Expected Transmission Count), and buffer allocation. It incorporates a fast response mechanism for burst traffic, implemented through an autonomous scheduling mechanism. Additionally, HPS utilizes a whitelisting mechanism to select optimal communication channels. The proposed scheme is implemented in Contiki-ng and evaluated in both simulated environments and real-world testbed. Obtained results demonstrate the potential of HPS to significantly enhance reliability and reduce delays compared to state-of-the-art SFs. Specifically, HPS consistently demonstrates reliability levels surpassing 90% across diverse scenarios accompanied with a noticeable gain in latency and power consumption of approximately 70% and 25%, respectively. These findings highlight the effectiveness of HPS in improving network performance and addressing the limitations of existing SFs.

EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction

Background:The seizure prediction algorithms have demonstrated their potential in mitigating epilepsy risks by detecting the pre-ictal state using ongoing electroencephalogram (EEG) signals. However, most of them require high-density EEG, which is burdensome to the patients for daily monitoring. Moreover, prevailing seizure models require extensive training with significant labeled data which is very time-consuming and demanding for the epileptologists. Method:To address these challenges, here we propose an adaptive channel selection strategy and a semi-supervised deep learning model respectively to reduce the number of EEG channels and to limit the amount of labeled data required for accurate seizure prediction. Our channel selection module is centered on features from EEG power spectra parameterization that precisely characterize the epileptic activities to identify the seizure-associated channels for each patient. The semi-supervised model integrates generative adversarial networks and bidirectional long short-term memory networks to enhance seizure prediction. Results:Our approach is evaluated on the CHB-MIT and Siena epilepsy datasets. With utilizing only 4 channels, the method demonstrates outstanding performance with an AUC of 93.15% on the CHB-MIT dataset and an AUC of 88.98% on the Siena dataset. Experimental results also demonstrate that our selection approach reduces the model parameters and training time. Conclusions:Adaptive channel selection coupled with semi-supervised learning can offer the possible bases for a light weight and computationally efficient seizure prediction system, making the daily monitoring practical to improve patients’ quality of life.

Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer with Adaptive Channel Expansion

Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in the ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present VigSet, a pioneering dataset for vignetting removal. VigSet includes 983 pairs of both vignetting and vignetting-free high-resolution (over 4k) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we propose the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at https://github.com/CXH-Research/DeVigNet.

Correlation Matching Transformation Transformers for UHD Image Restoration

This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high features and reconstructs the residual images, while the latter explores more representative features learning from the high-resolution ones to facilitate better restoration. To better improve feature representation in low-resolution space, we propose to build feature transformation from the high-resolution space to the low-resolution one. To that end, we propose two new modules: Dual-path Correlation Matching Transformation module (DualCMT) and Adaptive Channel Modulator (ACM). The DualCMT selects top C/r (r is greater or equal to 1 which controls the squeezing level) correlation channels from the max-pooling/mean-pooling high-resolution features to replace low-resolution ones in Transformers, which can effectively squeeze useless content to improve the feature representation in low-resolution space to facilitate better recovery. The ACM is exploited to adaptively modulate multi-level high-resolution features, enabling to provide more useful features to low-resolution space for better learning. Experimental results show that our UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring. The source codes will be made available at https://github.com/supersupercong/UHDformer.

ALNet: An adaptive channel attention network with local discrepancy perception for accurate indoor visual localization

Visual localization, a fundamental component of several computer vision tasks, has been predominantly realized by scene coordinate regression (SCoRe) techniques. These methods leverage neural networks for scene coordinates prediction, followed by a PnP algorithm to recover the 6-DOF camera pose. However, similar image patches are prevalent in indoor scenes, which results in the extraction of comparable features for the regression of different scene coordinates. As a result, the localization accuracy is severely declined. In this work, we develop ALNet, a novel SCoRe method that incorporates a local discrepancy perception module (LDPM) and an adaptive channel attention module (ACAM) to address this challenge. For LDPM, our key insight lies in that scene attributes around different similar image patches are inconsistent. Technically, for each image patch, LDPM identifies a certain number of the most dissimilar patches around it and computes difference vectors to enrich its own features, thereby enabling the differentiation of similar image patches. Considering geometric attributes are beneficial for distinguishing similar patches while semantic context is conducive to encoding regression issues, integrating multi-level features is an effective approach to elevate the localization accuracy. Therefore, ACAM concatenates multi-level features together and leverages both average pooling and max pooling to generate reliable channel-wise weighting coefficient, thereby modeling the correlation among channels to integrate multi-level features effectively. Comprehensive experiments are conducted on mainstream indoor localization benchmarks and an actual environment, showing that ALNet achieves impressive performance. Source code and the experimental results video are available at https://github.com/DAMMONGAO/alnet.

Concentration-Driven Evolution of Adaptive Artificial Ion Channels or Nanopores with Specific Anticancer Activities.

In nature, ceramides are a class of sphingolipids possessing a unique ability to self-assemble into protein-permeable channels with intriguing concentration-dependent adaptive channel cavities. However, within the realm of artificial ion channels, this interesting phenomenon is scarcely represented. Herein, we report on a novel class of adaptive artificial channels, Pn-TPPs, based on PEGylated cholic acids bearing triphenylphosphonium (TPP) groups as anion binding motifs. Interestingly, the molecules self-assemble into chloride ion channels at low concentrations while transforming into small molecule-permeable nanopores at high concentrations. Moreover, the TPP groups endow the molecules with mitochondria-targeting properties, enabling them to selectively drill holes on the mitochondrial membrane of cancer cells and subsequently trigger the caspase 9 apoptotic pathway. The anticancer efficacies of Pn-TPPs correlate with their abilities to form nanopores. Significantly, the most active ensembles formed by P5-TPP exhibits impressive anticancer activity against human liver cancer cells, with an IC50 value of 3.8 μM. While demonstrating similar anticancer performance to doxorubicin, P5-TPP exhibits a selectivity index surpassing that of doxorubicin by a factor of 16.8.

Concentration‐Driven Evolution of Adaptive Artificial Ion Channels or Nanopores with Specific Anticancer Activities

AbstractIn nature, ceramides are a class of sphingolipids possessing a unique ability to self‐assemble into protein‐permeable channels with intriguing concentration‐dependent adaptive channel cavities. However, within the realm of artificial ion channels, this interesting phenomenon is scarcely represented. Herein, we report on a novel class of adaptive artificial channels, Pn‐TPPs, based on PEGylated cholic acids bearing triphenylphosphonium (TPP) groups as anion binding motifs. Interestingly, the molecules self‐assemble into chloride ion channels at low concentrations while transforming into small molecule‐permeable nanopores at high concentrations. Moreover, the TPP groups endow the molecules with mitochondria‐targeting properties, enabling them to selectively drill holes on the mitochondrial membrane of cancer cells and subsequently trigger the caspase 9 apoptotic pathway. The anticancer efficacies of Pn‐TPPs correlate with their abilities to form nanopores. Significantly, the most active ensembles formed by P5‐TPP exhibits impressive anticancer activity against human liver cancer cells, with an IC50 value of 3.8 μM. While demonstrating similar anticancer performance to doxorubicin, P5‐TPP exhibits a selectivity index surpassing that of doxorubicin by a factor of 16.8.

ACGMA: Adaptive Channel Gain Multiple Access Scheme for Data Rate Improvement in Ultra-Dense Networks

ACGMA: Adaptive Channel Gain Multiple Access Scheme for Data Rate Improvement in Ultra-Dense Networks

An Adaptive Channel Selection Method for Assimilating the Hyperspectral Infrared Radiances

Abstract Hyperspectral infrared (IR) satellites can provide high-resolution vertical profiles of the atmospheric state, which significantly contributes to the forecast skill of numerical weather prediction, especially for regions with sparse observations. One challenge in assimilating the hyperspectral radiances is how to effectively extract the observation information, due to the interchannel correlations and correlated observation errors. An adaptive channel selection method is proposed, which is implemented within the data assimilation scheme and selects the radiance observation with the maximum reduction of variance in observation space. Compared to the commonly used channel selection method based on the maximum entropy reduction (ER), the adaptive method can provide flow-dependent and time-varying channel selections. The performance of the adaptive selection method is evaluated by assimilating only the synthetic Fengyun-4A (FY-4A) GIIRS IR radiances in an observing system simulation experiment (OSSE), with model resolutions from 7.5 to 1.5 km and then 300 m. For both clear-sky and all-sky conditions, the adaptive method generally produces smaller RMS errors of state variables than the ER-based method given similar amounts of assimilated radiances, especially with fine model resolutions. Moreover, the adaptive method has minimum RMS errors smaller than or approaching those with all channels assimilated. For the intensity of the tropical cyclone, the adaptive method also produces smaller errors of the minimum dry air mass and maximal wind speed at different levels, compared to the ER-based selection method. Significance Statement Assimilating satellite radiances has been essential for numerical weather prediction. Hyperspectral infrared satellites provide high-resolution vertical profiles for the atmospheric state and can further improve the numerical weather prediction. Due to limited computational resources, and correlated observations and associated errors, efficient and effective ways to assimilate the hyperspectral radiances are needed. An adaptive channel selection method that is incorporated with data assimilation is proposed. The adaptive channel selection can effectively extract the information from hyperspectral radiances under both clear- and all-sky conditions, with increased model resolutions from kilometers to subkilometers.

Domain Adaptive Channel Pruning

Domain adaptation is an effective approach to improve the generalization ability of deep learning methods, which makes a deep model more stable and robust. However, these methods often suffer from a deployment problem when deep models are deployed on different types of edge devices. In this work, we propose a new channel pruning method called Domain Adaptive Channel Pruning (DACP), which is specifically designed for the unsupervised domain adaptation task, where there is considerable data distribution mismatch between the source and the target domains. We prune the channels and adjust the weights in a layer-by-layer fashion. In contrast to the existing layer-by-layer channel pruning approaches that only consider how to reconstruct the features from the next layer, our approach aims to minimize both classification error and domain distribution mismatch. Furthermore, we propose a simple but effective approach to utilize the unlabeled data in the target domain. Our comprehensive experiments on two benchmark datasets demonstrate that our newly proposed DACP method outperforms the existing channel pruning approaches under the unsupervised domain adaptation setting.

ERCP-Net: a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network

Plant leaf diseases are a major cause of plant mortality, especially in crops. Timely and accurately identifying disease types and implementing proper treatment measures in the early stages of leaf diseases are crucial for healthy plant growth. Traditional plant disease identification methods rely heavily on visual inspection by experts in plant pathology, which is time-consuming and requires a high level of expertise. So, this approach fails to gain widespread adoption. To overcome these challenges, we propose a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network (ERCP-Net). It consists of channel extension residual block (CER-Block), adaptive channel attention block (ACA-Block), and bidirectional information fusion block (BIF-Block). Meanwhile, an application for the real-time detection of plant leaf diseases is being created to assist precision agriculture in practical situations. Finally, experiments were conducted to compare our model with other state-of-the-art deep learning methods on the PlantVillage and AI Challenger 2018 datasets. Experimental results show that our model achieved an accuracy of 99.82% and 86.21%, respectively. Also, it demonstrates excellent robustness and scalability, highlighting its potential for practical implementation.