Position-sensitive Information Research Articles

Global remote feature modulation end-to-end detection

Object detector based on fully convolutional network achieves excellent performance. However, existing detection algorithms still face challenges such as low detection accuracy in dense scenes and issues with occlusion of dense targets. To address these two challenges, we propose an Global Remote Feature Modulation End-to-End (GRFME2E) detection algorithm. In the feature extraction phase of our algorithm, we introduces the Concentric Attention Feature Pyramid Network (CAFPN). The CAFPN captures direction-aware and position-sensitive information, as well as global remote dependencies of features in deep layers by combining Coordinate Attention and Multilayer Perceptron. These features are used to modulate the front-end shallow features, enhancing inter-layer feature adjustment to obtain comprehensive and distinctive feature representations.In the detector part, we introduce the Two-Stage Detection Head (TS Head). This head employs the First-One-to-Few (F-O2F) module to detect slightly or unobstructed objects. Additionally, it uses masks to suppress already detected instances, and then feeds them to the Second-One-to-Few (S-O2F) module to identify those that are heavily occluded. The results from both detection stages are merged to produce the final output, ensuring the detection of objects whether they are slightly obscured, unobstructed, or heavily occluded. Experimental results on the pig detection dataset demonstrate that our GRFME2E achieves an accuracy of 98.4%. In addition, more extensive experimental results show that on the CrowdHuman dataset, our GRFME2E achieves 91.8% and outperforms other methods.

Multi-classification prediction model of lung cancer tumor mutation burden based on residual network

Medical studies have found that tumor mutation burden (TMB) is positively correlated with the efficacy of immunotherapy for non-small cell lung cancer (NSCLC), and TMB value can be used to predict the efficacy of targeted therapy and chemotherapy. However, the calculation of TMB value mainly depends on the whole exon sequencing (WES) technology, which usually costs too much time and expenses. To deal with above problem, this paper studies the correlation between TMB and slice images by taking advantage of digital pathological slices commonly used in clinic and then predicts the patient TMB level accordingly. This paper proposes a deep learning model (RCA-MSAG) based on residual coordinate attention (RCA) structure and combined with multi-scale attention guidance (MSAG) module. The model takes ResNet-50 as the basic model and integrates coordinate attention (CA) into bottleneck module to capture the direction-aware and position-sensitive information, which makes the model able to locate and identify the interesting positions more accurately. And then, MSAG module is embedded into the network, which makes the model able to extract the deep features of lung cancer pathological sections and the interactive information between channels. The cancer genome map (TCGA) open dataset is adopted in the experiment, which consists of 200 pathological sections of lung adenocarcinoma, including 80 data samples with high TMB value, 77 data samples with medium TMB value and 43 data samples with low TMB value. Experimental results demonstrate that the accuracy, precision, recall and F1 score of the proposed model are 96.2%, 96.4%, 96.2% and 96.3%, respectively, which are superior to the existing mainstream deep learning models. The model proposed in this paper can promote clinical auxiliary diagnosis and has certain theoretical guiding significance for TMB prediction.

Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification

Hyperspectral images contain rich features in both spectral and spatial domains, which bring opportunities for accurate recognition of similar materials and promote various fine-grained remote sensing applications. Although deep learning models have been extensively investigated in the field of hyperspectral image classification (HSIC) tasks, classification performance is still limited under small sample conditions, and this has been a longstanding problem. The features extracted by complex network structures with large model size are redundant to some extent and prone to overfitting. This paper proposes a low-rank constrained attention-enhanced multiple feature fusion network (LAMFN). Firstly, factor analysis is used to extract very few components that can describe the original data using covariance information to perform spectral feature preprocessing. Then, a lightweight attention-enhanced 3D convolution module is used for deep feature extraction, and the position-sensitive information is supplemented using a 2D coordinate attention. The above widely varying spatial–spectral feature groups are fused through a simple composite residual structure. Finally, low-rank second-order pooling is adopted to enhance the convolutional feature selectivity and achieve classification. Extensive experiments were conducted on four representative hyperspectral datasets with different spatial–spectral characteristics, namely Indian Pines (IP), Pavia Center (PC), Houston (HU), and WHU-HongHu (WHU). The contrast methods include several advanced models proposed recently, including residual CNNs, attention-based CNNs, and transformer-based models. Using only five samples per class for training, LAMFN achieved overall accuracies of 78.15%, 97.18%, 81.35%, and 87.93% on the above datasets, which has an improvement of 0.82%, 1.12%, 1.67%, and 0.89% compared to the second-best model. The running time of LAMFN is moderate. For example, the training time of LAMFN on the WHU dataset was 29.1 s, and the contrast models ranged from 3.0 s to 341.4 s. In addition, ablation experiments and comparisons with some advanced semi-supervised learning methods further validated the effectiveness of the proposed model designs.

Transductive Prototypical Attention Reasoning Network for Few-Shot SAR Target Recognition

Deep learning-based synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms have achieved outstanding performance under the condition of hundreds or thousands of training samples in recent years. Nevertheless, it is often rare to acquire great quantities of target samples in real SAR application scenarios. This article proposes a novel ATR method called transductive prototypical attention reasoning network (TPARN) to solve the problem of SAR target recognition with only a few training samples. To be specific, a region awareness-based feature extraction model is first developed, which can effectively focus on the target region of interest and suppress the background clutter by embedding direction-aware and position-sensitive information to extract more transferable knowledge. To heighten the discrimination of the sample features, a cross-feature spatial attention module is then proposed following the feature embedding model. Finally, a transductive prototype reasoning method is presented to realize the identity reasoning of the target, which can continuously update each class prototype with training samples and test samples together, thereby improving the classification accuracy. In addition, a marginal adaptive hybrid loss is proposed to obtain a discriminative feature embedding space with intra-class compactness and inter-class divergence, aiming to facilitate subsequent target identity reasoning. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset reveal that the proposed method outperforms some state-of-the-arts under different few-shot SAR ATR tasks.

Concrete Surface Crack Recognition Based on Coordinate Attention Neural Networks.

In highway transportation infrastructure such as highways and tunnels, the proportion of concrete consumption is the highest, and concrete cracks are common concrete problems. Concrete cracks will greatly affect the bearing capacity and safety of the structure, easily leading to the interruption of transportation lines, causing great economic losses, and endangering personnel safety. Therefore, the effective identification and timely reporting of concrete cracks is of great significance for the maintenance of infrastructure such as roads and tunnels. In this paper, the CaNet, a deep learning network for identifying concrete cracks, is proposed, which takes ResNet50 as the backbone network. In order to capture the area with a small proportion of cracks, we added coordinate attention to the residual unit of ResNet50 to capture the cross-channel information, direction-aware information, and position-sensitive information from many vertical and horizontal directions so that the network can more accurately locate the narrow crack area. In experiments 3.2 and 3.3, the CaNet has an accuracy rate of 89.6%, which is higher than that of the compared network. In addition, the recall, F1 score, and precision of the CaNet network are 86%, 85%, and 87% , respectively. Therefore, the CaNet model is effective for identifying concrete cracks.

Integrating Hybrid Pyramid Feature Fusion and Coordinate Attention for Effective Small Sample Hyperspectral Image Classification

In recent years, hyperspectral image (HSI) classification (HSIC) methods that use deep learning have proved to be effective. In particular, the utilization of convolutional neural networks (CNNs) has proved to be highly effective. However, some key issues need to be addressed when classifying hyperspectral images (HSIs), such as small samples, which can influence the generalization ability of the CNNs and the HSIC results. To address this problem, we present a new network that integrates hybrid pyramid feature fusion and coordinate attention for enhancing small sample HSI classification results. The innovative nature of this paper lies in three main areas. Firstly, a baseline network is designed. This is a simple hybrid 3D-2D CNN. Using this baseline network, more robust spectral-spatial feature information can be obtained from the HSI. Secondly, a hybrid pyramid feature fusion mechanism is used, meaning that the feature maps of different levels and scales can be effectively fused to enhance the feature extracted by the model. Finally, coordinate attention mechanisms are utilized in the network, which can not only adaptively capture the information of the spectral dimension, but also include the direction-aware and position sensitive information. By doing this, the proposed CNN structure can extract more useful HSI features and effectively be generalized to test samples. The proposed method was shown to obtain better results than several existing methods by experimenting on three public HSI datasets.

Kilogram Sample Analysis by Nuclear Analytical Techniques: Complementary Opportunities for the Mineral and Geosciences

Sample-size reduction including homogenization is often required to obtain a test portion for element compositional analysis. Analyses of replicate test portions may provide insight into the sampling constant, and often much larger quantities are needed to limit the contribution of sampling error. In addition, it cannot be demonstrated that the finally obtained test portion is truly representative of the originally collected material. Nuclear analytical techniques such as neutron and photon activation analysis and (neutron-induced) prompt gamma activation analyses can now be used to study and overcome these analytical problems. These techniques are capable of obtaining multi-element measurements from irregularly shaped objects with masses ranging from multiple grams to multiple kilograms. Prompt gamma analysis can be combined with neutron tomography, resulting in position-sensitive information. The analysis of large samples provides unprecedented complementary opportunities for the mineral and geosciences. It enables the experimental assessment of the representativeness of test portions of the originally collected material, as well as the analysis of samples that are not allowed to be sub-sampled or dissolved, the analysis of materials that are difficult to be homogenized at large, and studies on the location of inhomogeneities. Examples of such applications of large-sample analyses are described herein.

Turning Image Sensors into Position and Time Sensitive Quantitative Colorimetric Data Sources with the Aid of Novel Image Processing/Analysis Software.

Still images and video images acquired from image sensors are very valuable sources of information. From still images, position-sensitive, quantitative intensity, or colorimetric information can be obtained. Video images made of a time series of still images can provide time-dependent, quantitative intensity, or colorimetric information in addition to the position-sensitive information from a single still image. With the aid of novel image processing/analysis software, extraction of position- and time-sensitive quantitative colorimetric information was demonstrated from still image and video images of litmus test strips for pH tests of solutions. Visual inspection of the color change in the litmus test strips after chemical reaction with chemical solutions is typically exercised. Visual comparison of the color of the test solution with a standard color chart provides an approximate pH value to the nearest whole number. Accurate colorimetric quantification and dynamic analysis of chemical properties from captured still images and recorded video images of test solutions using novel image processing/analysis software are proposed with experimental feasibility study results towards value-added image sensor applications. Position- and time-sensitive quantitative colorimetric measurements and analysis examples are demonstrated.

Real-Time Detection and Motion Recognition of Human Moving Objects Based on Deep Learning and Multi-Scale Feature Fusion in Video

At present, human body moving target detection and recognition algorithms based on deep learning have made breakthrough progress. However, in some applications with high real-time requirements, the existing deep learning real-time detection and recognition network is difficult to achieve high detection accuracy. Therefore, how to achieve accurate positioning and recognition of human moving targets while ensuring real-time detection is still an urgent problem in this field. Based on the single shot multi-box detector (SSD) real-time detection network, this paper proposes a real-time detection positioning and recognition network based on multi-scale feature fusion (IMFF-SSD), which improves the positioning accuracy and identification accuracy. First, this article analyzes the multi-scale features extracted from the SSD network. It combines the position-sensitive information provided by low-level detail features with the context information provided by high-level semantic features through feature fusion, which effectively improves positioning accuracy of the target prediction layer in the SSD network. Secondly, a feature embedded prediction structure is designed to strengthen the semantics of target features without changing the spatial resolution of the SSD prediction layer, and embed low-scale detailed features in high-semantic features for collaborative prediction of targets. This improves the accuracy of the SSD network's recognition of human moving targets at all scales. The experimental results show that by combining the above two improvements, the real-time monitoring and recognition network based on multi-scale feature fusion proposed in this paper has achieved a greater degree of improvement in positioning accuracy and motion recognition accuracy than the original SSD, which is better than some current the human body moving object detection and recognition algorithm has great advantages.

Position sensitivity in the visual word form area.

Seeing words involves the activity of neural circuitry within a small region in human ventral temporal cortex known as the visual word form area (VWFA). It is widely asserted that VWFA responses, which are essential for skilled reading, do not depend on the visual field position of the writing (position invariant). Such position invariance supports the hypothesis that the VWFA analyzes word forms at an abstract level, far removed from specific stimulus features. Using functional MRI pattern-classification techniques, we show that position information is encoded in the spatial pattern of VWFA responses. A right-hemisphere homolog (rVWFA) shows similarly position-sensitive responses. Furthermore, electrophysiological recordings in the human brain show position-sensitive VWFA response latencies. These findings show that position-sensitive information is present in the neural circuitry that conveys visual word form information to language areas. The presence of position sensitivity in the VWFA has implications for how word forms might be learned and stored within the reading circuitry.

Dark matter detectors and the use of interaction location information for background suppression

Detector requirements, particularly the need for background rejection, in the search for weakly Interacting Massive Particles, one of the possible solutions to the cold dark matter problem, are broadly reviewed. The use of liquid Xenon as a target material is discussed in detail for the ZEPLIN I detector, a single phase scintillation detector operated by the UK Dark Matter Collaboration. The use of position sensitive information to remove photomultiplier based events, reduce backgrounds and help identify potential signal events is outlined.

Application of tomographic techniques to an investigation of elemental distributions following neutron irradiations

The use of tomographic image reconstruction techniques for the creation of three-dimensional images of the distribution of activity in solid samples has been examined. The aim has been to determine whether the method offers a finish to neutron activation procedures wich is capable of providing detailed position-sensitive information. Investigations with a phantom have shown that good images can be produced, even with relatively low-cost equipment.