Channel Relationships Research Articles

CR-GCN: Channel-Relationships-Based Graph Convolutional Network for EEG Emotion Recognition.

Electroencephalography (EEG) is recorded by electrodes from different areas of the brain and is commonly used to measure neuronal activity. EEG-based methods have been widely used for emotion recognition recently. However, most current methods for EEG-based emotion recognition do not fully exploit the relationship of EEG channels, which affects the precision of emotion recognition. To address the issue, in this paper, we propose a novel method for EEG-based emotion recognition called CR-GCN: Channel-Relationships-based Graph Convolutional Network. Specifically, topological structure of EEG channels is distance-based and tends to capture local relationships, and brain functional connectivity tends to capture global relationships among EEG channels. Therefore, in this paper, we construct EEG channel relationships using an adjacency matrix in graph convolutional network where the adjacency matrix captures both local and global relationships among different EEG channels. Extensive experiments demonstrate that CR-GCN method significantly outperforms the state-of-the-art methods. In subject-dependent experiments, the average classification accuracies of 94.69% and 93.95% are achieved for valence and arousal. In subject-independent experiments, the average classification accuracies of 94.78% and 93.46% are obtained for valence and arousal.

Class Guided Channel Weighting Network for Fine-Grained Semantic Segmentation

Deep learning has achieved promising performance on semantic segmentation, but few works focus on semantic segmentation at the fine-grained level. Fine-grained semantic segmentation requires recognizing and distinguishing hundreds of sub-categories. Due to the high similarity of different sub-categories and large variations in poses, scales, rotations, and color of the same sub-category in the fine-grained image set, the performance of traditional semantic segmentation methods will decline sharply. To alleviate these dilemmas, a new approach, named Class Guided Channel Weighting Network (CGCWNet), is developed in this paper to enable fine-grained semantic segmentation. For the large intra-class variations, we propose a Class Guided Weighting (CGW) module, which learns the image-level fine-grained category probabilities by exploiting second-order feature statistics, and use them as global information to guide semantic segmentation. For the high similarity between different sub-categories, we specially build a Channel Relationship Attention (CRA) module to amplify the distinction of features. Furthermore, a Detail Enhanced Guided Filter (DEGF) module is proposed to refine the boundaries of object masks by using an edge contour cue extracted from the enhanced original image. Experimental results on PASCAL VOC 2012 and six fine-grained image sets show that our proposed CGCWNet has achieved state-of-the-art results.

Pre-launch characterization of the spectrometer of Hard X-ray Imager (HXI) onboard the ASO-S mission

As one of the three payloads of the Advanced Space-based Solar Observatory (ASO-S), the pre-launch characterization of HXI includes the characterization of the collimator and the spectrometer. This article focuses on the pre-launch characterization of HXI's spectrometer, including detection efficiency, energy resolution, and energy to ADC channel (E-C) relationship. The detection efficiency characterization necessitates a sufficient number of calibrated energy points in the HXI observation energy range, with a refined measurement around the absorption edge of the lanthanum bromide crystal, and is calibrated with an X-ray beam. The characterization results are consistent with the simulations and show that the detection efficiency difference between detector modules is controlled within ±3%. Radioactive sources 133Ba and 137Cs are used to calibrate the energy resolution and E-C relationship. The characterization results show that all detector modules' energy resolutions are better than 26% at 32 keV, meeting the design specification. And their E-C relationships vary regularly with voltage. All of the characterization results indicate that the flight model of the HXI spectrometer meets the performance requirements and is capable of performing on-orbit observation activities.

Missing wind speed data reconstruction with improved context encoder network

Missing wind speed data are mainly caused by harsh weather, wind turbine failures, and data transmission errors, which have adverse effects on the performance of wind power forecasting, power curve modeling, and energy assessment. Inspired by context encoders (CE), this paper proposes an improved context encoder network (ICE) for missing wind speed data reconstruction. An auto-encoder architecture with multiple one-dimensional convolutional layers is established for data generation. During network training, a joint loss function that includes reconstruction loss and adversarial loss is presented to obtain the stable and near-real reconstructed wind speed data. We add an Inception layer to the generator network to automatically select the appropriate convolutional filters and then recalibrate the channel relationship between feature maps via the squeeze-and-excitation network. At last, this paper uses wind speed data collected from an on-shore wind farm to verify the effectiveness of the proposed network. The results show that the mean absolute error (MAE) and root mean square error (RMSE) of the ICE network in different data missing rates are 0.019–0.021 and 0.021–0.025, respectively. It has the lowest reconstruction errors compared with six typical data reconstruction methods.

Channel Attention Module for Efficient Action Recognition

For action recognition, 3D CNNs can achieve satisfactory performance, but they are parameter-rich and computationally intensive. Although conventional 2D CNNs have a small computational burden, they do not capture the channel relationships well. To mitigate this issue, we propose a plug-and-play channel attention module that is simple yet effective. Our CA module can perform adaptive refinement of the feature for the given input feature map by capturing channel-wise dependencies. Since the CA module is generic and lightweight, it can be easily integrated into regular convolutional neural networks. We embedded the CA module into TSM and evaluated it by conducting extensive experiments on the commonly used action recognition dataset: Kinetics-400 and gesture recognition dataset: Jester. For Kinetics-400, our CA module was able to improve the top-1 accuracy by 1.24%, 1.46%, 1.43% and 1.53% when using one crop, three crops, five crops and ten crops, respectively. Our experimental results showed that the CA module brings consistent performance improvements, proving the effectiveness of the CA module.

How does the value co-creation of e-commerce platform and manufacturers affect channel performance? The moderating role of innovation capability and market turbulence

The purpose of this paper is to examine the relationship between inter-firm value co-creation activities and channel performance. Specifically, we ask which discrete types of value co-creation affect economic and relational channel performance? What firm-level and environmental factors, if any, moderate these effects? Drawing on transaction cost theory, and using data from 154 manufacturer and e-commerce platforms, we make notable contributions to the e-commerce literature. We show that two discrete types of value co-creation activities (joint planning and flexibility to make adjustments) positively affect both economic and relational channel performance. A third type, joint problem solving, only affects economic performance. We identify two moderators of these relationships: innovation capability positively moderates the relationship between value co-creation and channel economic performance; market turbulence positively moderates the relationship between value co-creation and channel relationship performance. The results can help enterprises understand how to optimise their implementation of value co-creation processes.

An end-to-end face parsing model using channel and spatial attentions

Facial image parsing requires accurate extraction of facial components and features, and image segmentation can be used. Recently, various attention mechanisms showed excellent performance in segmentation by extracting features based on spatial and channel relationships for input images. In this paper, we propose a new face parsing technique using an attention block that combines the spatial attention block and the channel attention block to effectively utilize their functions. In this process, we improve the structure of the two blocks to compensate for their weaknesses. The attention block extracts features related to the shape of facial components from spatial relationships and concentrates on more important channels from correlation among channels. We built several segmentation models using the proposed block and compared their performance with well-known segmentation models. Experimental results showed that our combined block-based model can improve the segmentation accuracy by more than 5% in F1 score compared to other models.

MAFF-Net: Multi-Attention Guided Feature Fusion Network for Change Detection in Remote Sensing Images.

One of the most important tasks in remote sensing image analysis is remote sensing image Change Detection (CD), and CD is the key to helping people obtain more accurate information about changes on the Earth’s surface. A Multi-Attention Guided Feature Fusion Network (MAFF-Net) for CD tasks has been designed. The network enhances feature extraction and feature fusion by building different blocks. First, a Feature Enhancement Module (FEM) is proposed. The FEM introduces Coordinate Attention (CA). The CA block embeds the position information into the channel attention to obtain the accurate position information and channel relationships of the remote sensing images. An updated feature map is obtained by using an element-wise summation of the input of the FEM and the output of the CA. The FEM enhances the feature representation in the network. Then, an attention-based Feature Fusion Module (FFM) is designed. It changes the previous idea of layer-by-layer fusion and chooses cross-layer aggregation. The FFM is to compensate for some semantic information missing as the number of layers increases. FFM plays an important role in the communication of feature maps at different scales. To further refine the feature representation, a Refinement Residual Block (RRB) is proposed. The RRB changes the number of channels of the aggregated features and uses convolutional blocks to further refine the feature representation. Compared with all compared methods, MAFF-Net improves the F1-Score scores by 4.9%, 3.2%, and 1.7% on three publicly available benchmark datasets, the CDD, LEVIR-CD, and WHU-CD datasets, respectively. The experimental results show that MAFF-Net achieves state-of-the-art (SOTA) CD performance on these three challenging datasets.

Loose lips sink ships: The double-edged effect of distributor voice on channel relationship performance

Improving channel relationships is critical for marketers aiming to strategically manage and motivate their distribution partners. In this study, we explore distributor voice as an extra-role behavior and its influence on channel relationship quality. We propose that this behavior has a curvilinear effect on channel relationship quality, and such effect is conditional on channel interdependence and the presence of an opportunistic atmosphere between channel members. From a sample of 191 distributors in China, we find that distributor voice has an inverted U-shaped effect on channel relationship quality. This effect becomes stronger with high levels of channel interdependence or low levels of opportunism between distributors and suppliers. We also discuss the theoretical and practical implications of our findings.

Pengaruh Strategi Bauran Pemasaran Terhadap Perkembangan Ukm Di Dinas Koperasi Usaha Kecil Dan Menengah Kabupaten Bandung

This research was conducted to find out how much influence the marketing mix strategy has on SMEs development. To find out the obstacles that exist in the marketing mix strategy, and to find out the efforts that can be made by the SMEs development in cooperative anad SMEs in Bandung regency. The research method used in descriptiive quantitative method, the analysis technique used in person product moment analiysis technique with data processing using SPSS V22. The data obtained to explain the results of the study is to distribute questionnaires to 20 question to respondents of 51 respondents from the study sample.The results obtained by the correlation of 0,756 means that it has a strong relationship between the marketing mix strategy variabel the SMEs development variabel with an effect of 57.2 and the remaining 42.8% is influenced by other factors not examined by the aiuthors. The author concludes that the members of SMEs are already good in carrying out markeing mix strategy to develop their business. There are obstacles in efforts to improve the development of SMEs, Such as product quality standards and market access for SMEs products, this is based on the increasinglyWidespread competition of external product with lower prices and quality and market access that is still not broad. The auther’s suggestion in expected that SMEs member can improve product quality and broad market access by building nemerous distribution channel relationships so that the scope of their business is able to develop.

3D AGSE-VNet: an automatic brain tumor MRI data segmentation framework

BackgroundGlioma is the most common brain malignant tumor, with a high morbidity rate and a mortality rate of more than three percent, which seriously endangers human health. The main method of acquiring brain tumors in the clinic is MRI. Segmentation of brain tumor regions from multi-modal MRI scan images is helpful for treatment inspection, post-diagnosis monitoring, and effect evaluation of patients. However, the common operation in clinical brain tumor segmentation is still manual segmentation, lead to its time-consuming and large performance difference between different operators, a consistent and accurate automatic segmentation method is urgently needed. With the continuous development of deep learning, researchers have designed many automatic segmentation algorithms; however, there are still some problems: (1) The research of segmentation algorithm mostly stays on the 2D plane, this will reduce the accuracy of 3D image feature extraction to a certain extent. (2) MRI images have gray-scale offset fields that make it difficult to divide the contours accurately.MethodsTo meet the above challenges, we propose an automatic brain tumor MRI data segmentation framework which is called AGSE-VNet. In our study, the Squeeze and Excite (SE) module is added to each encoder, the Attention Guide Filter (AG) module is added to each decoder, using the channel relationship to automatically enhance the useful information in the channel to suppress the useless information, and use the attention mechanism to guide the edge information and remove the influence of irrelevant information such as noise.ResultsWe used the BraTS2020 challenge online verification tool to evaluate our approach. The focus of verification is that the Dice scores of the whole tumor, tumor core and enhanced tumor are 0.68, 0.85 and 0.70, respectively.ConclusionAlthough MRI images have different intensities, AGSE-VNet is not affected by the size of the tumor, and can more accurately extract the features of the three regions, it has achieved impressive results and made outstanding contributions to the clinical diagnosis and treatment of brain tumor patients.

FCAU-Net for the Semantic Segmentation of Fine-Resolution Remotely Sensed Images

The semantic segmentation of fine-resolution remotely sensed images is an urgent issue in satellite image processing. Solving this problem can help overcome various obstacles in urban planning, land cover classification, and environmental protection, paving the way for scene-level landscape pattern analysis and decision making. Encoder-decoder structures based on attention mechanisms have been frequently used for fine-resolution image segmentation. In this paper, we incorporate a coordinate attention (CA) mechanism, adopt an asymmetric convolution block (ACB), and design a refinement fusion block (RFB), forming a network named the fusion coordinate and asymmetry-based U-Net (FCAU-Net). Furthermore, we propose novel convolutional neural network (CNN) architecture to fully capture long-term dependencies and fine-grained details in fine-resolution remotely sensed imagery. This approach has the following advantages: (1) the CA mechanism embeds position information into a channel attention mechanism to enhance the feature representations produced by the network while effectively capturing position information and channel relationships; (2) the ACB enhances the feature representation ability of the standard convolution layer and captures and refines the feature information in each layer of the encoder; and (3) the RFB effectively integrates low-level spatial information and high-level abstract features to eliminate background noise when extracting feature information, reduces the fitting residuals of the fused features, and improves the ability of the network to capture information flows. Extensive experiments conducted on two public datasets (ZY-3 and DeepGlobe) demonstrate the effectiveness of the FCAU-Net. The proposed FCAU-Net transcends U-Net, Attention U-Net, the pyramid scene parsing network (PSPNet), DeepLab v3+, the multistage attention residual U-Net (MAResU-Net), MACU-Net, and the Transformer U-Net (TransUNet). Specifically, the FCAU-Net achieves a 97.97% (95.05%) pixel accuracy (PA), a 98.53% (91.27%) mean PA (mPA), a 95.17% (85.54%) mean intersection over union (mIoU), and a 96.07% (90.74%) frequency-weighted IoU (FWIoU) on the ZY-3 (DeepGlobe) dataset.

Distribution Channel Relationships in the Presence of Multimarket Contact

Traditional analyses of firms that compete in multiple markets examine settings in which firms sell directly to consumers. However, in many industries, firms sell their products through intermediaries. Importantly, these firms usually have common intermediaries, and the degree of this overlap varies across markets and over time. We empirically study the effect of the asymmetry of distribution channel relationship overlap across markets on retail prices. An increase in distribution channel relationship asymmetry can provide firms with an enhanced ability to punish rivals through shared distribution relationships in addition to shared markets. This increased ability to punish can then soften competition (increase prices), that is, the mutual forbearance mechanism. However, an increase in distribution channel relationship asymmetry can also make it difficult for firms to pursue similar goals with their rivals, and thus weakening the potential for tacit coordination. This can then intensify competition (reduce prices), that is, the goal congruence mechanism. Due to these opposing mechanisms, the net impact of distribution channel relationship asymmetry on competitive intensity is not clear. Using extensive scanner panel data for multiple product categories, on average, we find that an increase in distribution channel relationship asymmetry results in higher retail prices. Consistent with the mutual forbearance mechanism, this effect becomes more positive (or less negative) when (i) the manufacturer size or the number of retail stores in the focal market increases or (ii) when the manufacturer is a public (vs. private) firm. Conversely, the effect becomes less positive when the strategic similarity among manufacturers increases, in line with the goal congruence mechanism.

A Discriminative Channel Diversification Network for Image Classification.

Channel attention mechanisms in convolutional neural networks have been proven to be effective in various computer vision tasks. However, the performance improvement comes with additional model complexity and computation cost. In this paper, we propose a light-weight and effective attention module, called channel diversification block, to enhance the global context by establishing the channel relationship at the global level. Unlike other channel attention mechanisms, the proposed module focuses on the most discriminative features by giving more attention to the spatially distinguishable channels while taking account of the channel activation. Different from other attention models that plugin the module in between several intermediate layers, the proposed module is embedded at the end of the backbone networks, making it easy to implement. Extensive experiments on CIFAR-10, SVHN, and Tiny-ImageNet datasets demonstrate that the proposed module improves the performance of the baseline networks by a margin of 3% on average.

An empirical study on the predictors of long-term orientation in interfirm channel relationships: fast moving consumer goods distributors' perspective

An empirical study on the predictors of long-term orientation in interfirm channel relationships: fast moving consumer goods distributors' perspective

Red Tide Detection Method for HY−1D Coastal Zone Imager Based on U−Net Convolutional Neural Network

Existing red tide detection methods have mainly been developed for ocean color satellite data with low spatial resolution and high spectral resolution. Higher spatial resolution satellite images are required for red tides with fine scale and scattered distribution. However, red tide detection methods for ocean color satellite data cannot be directly applied to medium–high spatial resolution satellite data owing to the shortage of red tide responsive bands. Therefore, a new red tide detection method for medium–high spatial resolution satellite data is required. This study proposes the red tide detection U−Net (RDU−Net) model by considering the HY−1D Coastal Zone Imager (HY−1D CZI) as an example. RDU−Net employs the channel attention model to derive the inter−channel relationship of red tide information in order to reduce the influence of the marine environment on red tide detection. Moreover, the boundary and binary cross entropy (BBCE) loss function, which incorporates the boundary loss, is used to obtain clear and accurate red tide boundaries. In addition, a multi−feature dataset including the HY−1D CZI radiance and Normalized Difference Vegetation Index (NDVI) is employed to enhance the spectral difference between red tides and seawater and thus improve the accuracy of red tide detection. Experimental results show that RDU−Net can detect red tides accurately without a precedent threshold. Precision and Recall of 87.47% and 86.62%, respectively, are achieved, while the F1−score and Kappa are 0.87. Compared with the existing method, the F1−score is improved by 0.07–0.21. Furthermore, the proposed method can detect red tides accurately even under interference from clouds and fog, and it shows good performance in the case of red tide edges and scattered distribution areas. Moreover, it shows good applicability and can be successfully applied to other satellite data with high spatial resolution and large bandwidth, such as GF−1 Wide Field of View 2 (WFV2) images.

CAAGP: Rethinking channel attention with adaptive global pooling for liver tumor segmentation

Channel attention, a channel-wise method often used in computer vision tasks, including liver tumor segmentation tasks, is able to model the channel relationship to augment the representation ability of feature maps. Channel attention could adaptively generate channel-wise responses using global pooling, which aggregates spatial information roughly. Actually, global pooling may introduce the loss of fine information, which is vital for segmentation tasks. Hence, we rethink the problem and propose the channel attention with adaptive global pooling(short for CAAGP), which preserves spatial and fine-grained information for liver tumor segmentation tasks when channel attention is generated. The model consists of three main parts, including improved self-attention, adaptive global pooling and responses generation modules. Self-attention achieves excellent performance in the computing of the spatial attention, while introducing serious calculation and memory burdens. In order to remedy these burdens, we improve self-attention and consider aggregating spatial information from x and y directions respectively. Extensive experiments have been conducted to verify the effectiveness of our proposed method. Our CAAGP outperforms other attention mechanisms significantly in liver tumor segmentation, especially for tumors with small size.

Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification

In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classification and reduce model complexity, this paper proposes an asymmetric coordinate attention spectral-spatial feature fusion network (ACAS2F2N) to capture distinguishing hyperspectral features. Specifically, adaptive asymmetric iterative attention was proposed to obtain the discriminative spectral-spatial features. Different from the common feature fusion method, this feature fusion method can adapt to most skip connection tasks. In addition, there is no manual parameter setting. Coordinate attention is used to obtain accurate coordinate information and channel relationship. The strip pooling module was introduced to increase the network’s receptive field and avoid irrelevant information brought by conventional convolution kernels. The proposed algorithm is tested on the mainstream hyperspectral datasets (IP, KSC, and Botswana), experimental results show that the proposed ACAS2F2N can achieve state-of-the-art performance with lower time complexity.

Characterization of a gamma spectrometer–neutron counter background correlation in mobile radiological search systems

The mobile radiological search system (MRSS) is frequently employed to locate radiological material that may be used in nuclear terrorism. Because they are mobile, an MRSS has difficulties characterizing the radiation background during operations, particularly in their neutron counters. Operators of these systems noted a potential relationship between the MRSS’s background neutron count rate and the count rate in its scintillator’s “overflow” channel (a channel that counts all signals with energies greater than 3 MeV). Previous work indicated that this overflow channel is the result of muons. That result coupled with the fact that both muons and background neutrons are produced by cosmic ray interactions meant that the neutron-overflow channel relationship is non-trivial. To fully characterize the neutron–muon relationship, this research collected and analyzed MRSS data from throughout the continental United States. These data were collected by three different organizations (one university and two MRSS operators), each with a unique MRSS setup. The locations measured accounted for the changes in neutron and muon background as a result of three variables: elevation, latitude, and the local environment (i.e. nearby buildings). Analysis of this data indicated that the average neutron count rate varied with the average muon count rate by a power law function. This relationship sufficiently accounts for all three variables that change both count rates, and its presence indicates that an MRSS can estimate its background neutron count rate by simply measuring the muon count rate. However, the data also indicated one complication with applying this relationship more broadly: each organization’s relationship had slightly different power law equations, which appears to be dependent on individual MRSS setup.

Factors Related to Participation of BPJS Mandiri


 
 
 
 Based on the data obtained from BPJS of Lampung Province in 2020, Tulang Bawang Barat Regency is the regency with the lowest number of BPJS participation in Lampung Province compared to 12 other regencies. The total number of BPJS Mandiri participants in 2020 was 45,738 people, which is still below the set target of 117,000 people. The purpose of this research is to determine the factors related to the participation of BPJS Mandiri in Tulang Bawang Barat Regency in 2021. The research is a quantitative descriptive type, with the research design in this research is analytic with a cross sectional approach. The population is 9,848 people, the sample size is 117, the sampling technique is stratified random sampling. The technique of collecting data on research variables about products, prices, distribution channels, promotions and membership of BPJS Mandiri in this study is filling out a questionnaire directly by respondents who are assisted by 5 enumerators, then after filling in the data directly collected on the same day. Univariate data analysis using percentage measures, bivariate analysis using chi square test and multivariate analysis using multiple logistic regression statistical tests. The results showed that the distribution of BPJS product frequency was higher in the poor category by 82 people (70.1%), BPJS prices were higher in the poor category by 84 people (71.8%), distribution channels were higher in the poor category by 68 people (58.1%), BPJS Mandiri promotion was higher in the poor category by 71 people (60.7%), BPJS Mandiri participation was higher in the category of non BPJS Mandiri participants by 60 people (51.3%). The results of the chi square test showed that there was a product relationship (p value = 0.009 < 0.05), there was a price relationship (p value = 0.001 < 0.05), there was no distribution channel relationship (p value = 0.542 > 0.05) and there is a promotion relationship (p value = 0.007 < 0.05) with BPJS Mandiri participation. Price variable is the most dominant variable related to BPJS Mandiri participation (p value = 0.019 < 0.05).