U-shaped Structure Research Articles

Liver tumor segmentation method based on U-Net architecture: a review

Liver cancer is a disease with a high incidence and high probability of deterioration, and for the rapid diagnosis of liver disease, CT scans must be used to segment the liver tumors. For the past few years, with the rapid development of deep learning, many deep learning methods for liver tumor segmentation using abdominal computed tomography (CT) images have appeared, and the clinical application of these methods is of important significance for computer-aided diagnosis of liver tumors. The U-Net, with its unique U-shape network structure, exhibits excellent performance in medical image segmentation field and has been extensively utilized in various medical image segmentation applications. In this paper, we summarize the researches of U-Net and its improved networks in CT image segmentation of liver tumors by deep learning methods and classify various U-Net-based convolutional neural networks (CNNs) into 2D (two-dimensional), 3D (three-dimensional), and 2.5D (2.5-dimensional). In this paper, 2D, 3D, and 2.5D convolutional neural networks are summarized. In addition, this paper summarizes the advantages and disadvantages as well as the improvement methods of each type of network, which provides a useful reference for the studies of deep learning based on liver tumor segmentation field. Finally, this paper envisions future research trends for deep learning segmentation methods in the context of liver tumors.

OESA-UNet: An Adaptive and Attentional Network for Detecting Diverse Magnetopause under the Limited Field of View

Imaging has been an important strategy for exploring space weather. The Solar wind Magnetosphere Ionosphere Link Explorer (SMILE) is a joint Chinese Academy of Sciences (CAS) and European Space Agency (ESA) mission, aiming at studying the interaction between Earth’s magnetosphere and solar wind near the subsolar point via soft X-ray imaging. As the boundary of Earth’s magnetosphere, magnetopause is a significant detection target to mirror solar wind’s change for the SMILE mission. In preparation for inverting three-dimensional magnetopause, we proposed an OESA-UNet model to detect the magnetopause position. The model obtains magnetopause with a U-shaped structure, in an end-to-end manner. Inspired by attention mechanisms, these blocks are integrated into ours. OESA-UNet captures low and high-level feature maps by adjusting the receptive field for precise localization. Adaptively pre-processing the image provides a prior for the network. Availability metrics are designed to determine whether it can serve three-dimensional inversion. Lastly, we provided ablation and comparison experiments by qualitative and quantitative analysis. Our recall, precision, and f1 score are 93.8%, 92.1%, and 92.9%, respectively, with an average angle deviation of 0.005 under the availability metrics. Results indicate that OESA-UNet outperforms other methods. It can better serve the purpose of magnetopause tracing from an X-ray image.

Spatial-Pooling-Based Graph Attention U-Net for Hyperspectral Image Classification

In recent years, graph convolutional networks (GCNs) have attracted increasing attention in hyperspectral image (HSI) classification owing to their exceptional representation capabilities. However, the high computational requirements of GCNs have led most existing GCN-based HSI classification methods to utilize superpixels as graph nodes, thereby limiting the spatial topology scale and neglecting pixel-level spectral–spatial features. To address these limitations, we propose a novel HSI classification network based on graph convolution called the spatial-pooling-based graph attention U-net (SPGAU). Specifically, unlike existing GCN models that rely on fixed graphs, our model involves a spatial pooling method that emulates the region-growing process of superpixels and constructs multi-level graphs by progressively merging adjacent graph nodes. Inspired by the CNN classification framework U-net, SPGAU’s model has a U-shaped structure, realizing multi-scale feature extraction from coarse to fine and gradually fusing features from different graph levels. Additionally, the proposed graph attention convolution method adaptively aggregates adjacency information, thereby further enhancing feature extraction efficiency. Moreover, a 1D-CNN is established to extract pixel-level features, striking an optimal balance between enhancing the feature quality and reducing the computational burden. Experimental results on three representative benchmark datasets demonstrate that the proposed SPGAU outperforms other mainstream models both qualitatively and quantitatively.

FTUNet: A Feature-Enhanced Network for Medical Image Segmentation Based on the Combination of U-Shaped Network and Vision Transformer

Semantic Segmentation has been widely used in a variety of clinical images, which greatly assists medical diagnosis and other work. To address the challenge of reduced semantic inference accuracy caused by feature weakening, a pioneering network called FTUNet (Feature-enhanced Transformer UNet) was introduced, leveraging the classical Encoder-Decoder architecture. Firstly, a dual-branch Encoder is proposed based on the U-shaped structure. In addition to employing convolution for feature extraction, a Layer Transformer structure (LTrans) is established to capture long-range dependencies and global context information. Then, an Inception structural module focusing on local features is proposed at the Bottleneck, which adopts the dilated convolution to amplify the receptive field to achieve deeper semantic mining based on the comprehensive information brought by the dual Encoder. Finally, in order to amplify feature differences, a lightweight attention mechanism of feature polarization is proposed at Skip Connection, which can strengthen or suppress feature channels by reallocating weights. The experiment is conducted on 3 different medical datasets. A comprehensive and detailed comparison was conducted with 6 non-U-shaped models, 5 U-shaped models, and 3 Transformer models in 8 categories of indicators. Meanwhile, 9 kinds of layer-by-layer ablation and 4 kinds of other embedding attempts are implemented to demonstrate the optimal structure of the current FTUNet.

Sliding transformer with uncertainty estimation for vestibular schwannoma automatic segmentation.

Objective.Automated segmentation of vestibular schwannoma (VS) using magnetic resonance imaging (MRI) can enhance clinical efficiency. Though many advanced methods exist for automated VS segmentation, the accuracy is hindered by ambivalent tumor borders and cystic regions in some patients. In addition, these methods provide results that do not indicate segmentation uncertainty, making their translation into clinical workflows difficult due to potential errors. Providing a definitive segmentation result along with segmentation uncertainty or self-confidence is crucial for the conversion of automated segmentation programs to clinical aid diagnostic tools.Approach.To address these issues, we propose a U-shaped cascade transformer structure with a sliding window that utilizes multiple sliding samples, a segmentation head, and an uncertainty head to obtain both the segmentation mask and uncertainty map. We collected multimodal MRI data from 60 clinical patients with VS from Xuanwu Hospital. Each patient case includes T1-weighted images, contrast-enhanced T1-weighted images, T2-weighted images, and a tumor mask. The images exhibit an in-plane resolution ranging from 0.70 × 0.70 to 0.76 × 0.76 mm, an in-plane matrix spanning from 216 × 256 to 284 × 256, a slice thickness varying between 0.50 and 0.80 mm, and a range of slice numbers from 72 to 120.Main results.Extensive experimental results show that our method achieves comparable or higher results than previous state-of-the-art brain tumor segmentation methods. On our collected multimodal MRI dataset of clinical VS, our method achieved the dice similarity coefficient (DSC) of 96.08% ± 1.30. On a publicly available VS dataset, our method achieved the mean DSC of 94.23% ± 2.53.Significance.The method efficiently solves the VS segmentation task while providing an uncertainty map of the segmentation results, which helps clinical experts review the segmentation results more efficiently and helps to transform the automated segmentation program into a clinical aid diagnostic tool.

UViT: Efficient and lightweight U-shaped hybrid vision transformer for human pose estimation

Pose estimation plays a crucial role in human-centered vision applications and has advanced significantly in recent years. However, prevailing approaches use extremely complex structural designs for obtaining high scores on the benchmark dataset, hampering edge device applications. In this study, an efficient and lightweight human pose estimation problem is investigated. Enhancements are made to the context enhancement module of the U-shaped structure to improve the multi-scale local modeling capability. With a transformer structure, a lightweight transformer block was designed to enhance the local feature extraction and global modeling ability. Finally, a lightweight pose estimation network— U-shaped Hybrid Vision Transformer, UViT— was developed. The minimal network UViT-T achieved a 3.9% improvement in AP scores on the COCO validation set with fewer model parameters and computational complexity compared with the best-performing V2 version of the MobileNet series. Specifically, with an input size of 384×288, UViT-T achieves an impressive AP score of 70.2 on the COCO test-dev set, with only 1.52 M parameters and 2.32 GFLOPs. The inference speed is approximately twice that of general-purpose networks. This study provides an efficient and lightweight design idea and method for the human pose estimation task and provides theoretical support for its deployment on edge devices.

River valley-inspired, high-sensitivity, and rapid-response capacitive three-dimensional force tactile sensor based on U-shaped groove structure

High-performance three-dimensional force (3D-force) tactile sensors with the capability of distinguishing normal and tangential forces in sync play a vital role in emerging wearable devices and smart electronics. And there is an urgent need for 3D-force tactile sensors with fast response and high flexibility. Herein, we design a capacitive 3D-force tactile sensors inspired by the U-shaped river valley surface morphology, which has satisfactory performance in terms of rapid response/recovery time (∼36 ms/∼ 36 ms), low hysteresis (4.2%), and high sensitivity (0.487 N−1). A theoretical model of general value for congener sensors is also proposed, obtaining a higher sensitivity through optimizing parameters. To verify the application potential of our device in actual scenarios, the robustness testing and gripping gamepad application were carried out. And it can recognize different motions in humans. Furthermore, principal component analysis is also conducted to demonstrate the distinct classification of different motions. Therefore, our work is eligible for the applications in wearable electronics, human–machine interaction, and soft intelligent robots.

ResU-Former: Advancing Remote Sensing Image Segmentation with Swin Residual Transformer for Precise Global–Local Feature Recognition and Visual–Semantic Space Learning

In the field of remote sensing image segmentation, achieving high accuracy and efficiency in diverse and complex environments remains a challenge. Additionally, there is a notable imbalance between the underlying features and the high-level semantic information embedded within remote sensing images, and both global and local recognition improvements are also limited by the multi-scale remote sensing scenery and imbalanced class distribution. These challenges are further compounded by inaccurate local localization segmentation and the oversight of small-scale features. To achieve balance between visual space and semantic space, to increase both global and local recognition accuracy, and to enhance the flexibility of input scale features while supplementing global contextual information, in this paper, we propose a U-shaped hierarchical structure called ResU-Former. The incorporation of the Swin Residual Transformer block allows for the efficient segmentation of objects of varying sizes against complex backgrounds, a common scenario in remote sensing datasets. With the specially designed Swin Residual Transformer block as its fundamental unit, ResU-Former accomplishes the full utilization and evolution of information, and the maximum optimization of semantic segmentation in complex remote sensing scenarios. The standard experimental results on benchmark datasets such as Vaihingen, Overall Accuracy of 81.5%, etc., show the ResU-Former’s potential to improve segmentation tasks across various remote sensing applications.

Experimental and Numerical Modeling of the Freeze–thaw Response of U-Shaped Channel Lining on Sulfate Saline Soil Foundation

Under the influence of seasonal freeze-thaw cycles, the concrete lining of channels situated on saline soil foundations is highly vulnerable to an array of deleterious phenomena, such as frost heave, salt expansion, and corrosion. To investigate the synergistic interplay among saline soil substrates, U-shaped channel lining structures, and ambient temperatures during freeze-thaw cycles, a novel Hydraulic-Thermal-Salt-Mechanical (HTSM) model is established in this study. The HTSM model elucidates the migration of moisture and salt solute, ice-water phase transitions, and sodium sulfate crystallization within unsaturated saline soils throughout the freeze-thaw cycles. It considers the variations in volume and pore solution volume before and after the phase transition of sodium sulfate. Temperature and salt frost heaving force measurements obtained from outdoor freeze-thaw cycles are compared with numerical simulation results to validate the efficacy of the HTSM model and investigate the distribution patterns of salt frost heaving force (frost swelling force) along the channel. The results showed that the frost swelling force and depth exhibit a great linear relationship and the maximum stress of the U-shaped channel appears at the bottom of the channel, highlighting the good arching force characteristics of the U-shaped structure which prove that bottom of the channel is also the most prone to fracture. Significantly, the initial water content significantly impacts the frost swelling force—it increases by 4% while the frost swelling force increases by 76%. Comparing the numerical simulation results of temperature variations, moisture changes, and salt-frost heaving forces with the outdoor experimental data, it is evident that the proposed HTSM model effectively simulates the salt-frost heaving patterns observed in U-shaped channel linings.

Can the digital economy boost rural residents’ income? Evidence from China based on the spatial Durbin model

The digital economy, as a new economic form, has the potential to be a considerable driving force for promoting agricultural modernisation, accelerating the flow of information between urban and rural areas and increasing the income of rural residents, thereby contributing to rural revitalisation. However, it may also inevitably lead to issues such as widening the digital divide between urban and rural areas, which can impact the extent to which rural residents effectively benefit from the digital economy. This study employs provincial panel data from 2011 to 2020 and conducts a temporal global principal component analysis to measure the level of China's digital economy development. Based on this, the spatial Durbin model is employed for empirical testing and regional analysis of the impact and mechanisms of digital economy development on the per capita disposable income of rural residents. The partial linear function coefficient model is used for supplementary analysis. The results indicate the following: (1) there are regional disparities in China's digital economy development, with the highest levels in the eastern region, followed by the western region and the lowest levels in the central region, forming a U-shaped spatial structure; (2) the development of the digital economy has a suppressing effect on the per capita disposable income of rural residents in both the home province and neighbouring provinces, indicating that the digital economy has not become a growth booster for rural revitalisation; (3) regional results show that the negative spatial effects of the digital economy are in the eastern region, whereas the western region has considerable positive spatial spillover effects. In contrast, no notable spatial effects exist in the central region. Therefore, under the backdrop of the digital economy, it is necessary to promote agricultural transformation and increase rural residents’ income by tailoring strategies to regional characteristics.

MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images

Mangrove forests are significant participants in coastal ecological environment systems. For the development of protection strategies, it is crucial to automatically and accurately detect the distribution and area of mangroves using satellite images. Although many deep-learning-based mangrove detection and segmentation algorithms have made notable progress, the complex regional structures and the great similarity between mangroves and the surrounding environment, as well as the diversity of mangroves, render the task still challenging. To cover these issues, we propose a novel deep-supervision-guided feature aggregation network for mangrove detection and segmentation called MangroveSeg, which is based on a U-shaped structure with ResNet, combining an attention mechanism and a multi-scale feature extraction framework. We also consider the detection and segmentation of mangroves as camouflage detection problems for the improvement and enhancement of accuracy. To determine more information from extracted feature maps in a hidden layer, a deep supervision model is introduced in up-sampling to enhance feature representation. The spatial attention mechanism with attention gates is utilized to highlight significant regions and suppress task-independent feature responses. The feature fusion module can obtain multi-scale information by binding each layer to the underlying information and update feature mappings. We validated our framework for mangrove detection and segmentation using a satellite image dataset, which includes 4000 images comprising 256 × 256 pixels; we used 3002 for training and 998 for testing. The satellite images dataset was obtained from the Dongzhaigang National Nature Reserve located in Haikou City, Hainan Province, China. The proposed method achieved a 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU. We also used the trained MangroveSeg model to detect mangroves on satellite images from other regions. We evaluated the statistical square measure of some mangrove areas and found that the evaluation accuracy can reach 96% using MangroveSeg. The proposed MangroveSeg model can automatically and accurately detect the distribution and area of mangroves from satellite images, which provides a method for monitoring the ecological environment.

Research on self phase-locked two-channel narrow linewidth laser

We have designed and constructed a self phase-locked two-channel narrow linewidth solid-state laser based on reflective volume Bragg grating (RVBG) as the output mirror. The resonant cavity of the laser is designed as a U-shaped structure, and two independent laser diode (LD)-side-pumped modules achieve passive phase locking of the output laser through mutual injection of photon energy. Compression of the linewidth is achieved by the RVBG. When the LD pump power was 70 W, the output powers of the two-channel lasers were 1.59 W and 1.61 W, the measured central wavelengths of the spectra were 1064.23 nm and 1064.24 nm, and the linewidths were 0.10 nm and 0.11 nm, respectively. The slope efficiencies of the two lasers are 9.5 % and 9.56 %, respectively, and their powers stability were both better than 3 %. The beam quality factors were Mx2=1.29, My2=1.31 and Mx2=1.32, My2=1.36, respectively. The interference fringes formed by the coherent superposition of two laser beams in the far field were observed through CCD, which verified the phase-locked coherence characteristics of the two lasers. The output power of the coherent combination laser is 2.64 W, with a corresponding efficiency of coherent combination is 82.5 %. The experimental results show that the laser can directly obtain two-channel narrow-linewidth continuous wave lasers output with phase locking and consistent laser intensity. Our research provides a new idea for obtaining a new type of high-quality narrow-linewidth coherent laser source

Thermoforming Simulation of Woven Carbon Fiber Fabric/Polyurethane Composite Materials

A finite element simulation was utilized in this work to analyze the thermoforming process of woven carbon fiber fabric/polyurethane thermoplastic composite sheets. In the simulation that may be classified as a discrete method, the woven carbon fiber fabric was treated as an undulated fill yarn crossed over an undulated warp yarn, and the resin was considered separately. Then, they were combined to represent the composite sheets. To verify this simulation, bias extension tests under three constant temperatures were executed. After that, the composite was thermoformed into a U-shaped structure and small luggage. From the bias extension tests, the finite element simulation and material properties of the fiber and resin were confirmed. From the comparison of the thermoformed products, the present simulation could provide the deformed profile and fiber-included angles and has good agreement with the experiment. The results also indicate that the stacking sequences of [(0°/90°)]4 and [(+45°/−45°)]4 have quite different product profiles and fiber-included angles.

Differential Diagnosis of Benign and Malignant Pulmonary Nodules in CT Images Based on Multitask Learning.

Artificial intelligence-based aided diagnostic systems for pulmonary nodules can be divided into subtasks such as nodule detection, segmentation, and benign and malignant differentiation. Most current studies are limited to single-target tasks. However, aided diagnosis aims to distinguish benign from malignant pulmonary nodules, which requires the fusion of multiple-scale features and comprehensive discrimination based on the results of multiple learning tasks. This study focuses on the aspects of model design, network structure, and constraints and proposes a novel model that integrates the learning tasks of pulmonary nodule detection, segmentation, and classification under weakly supervised conditions. The main innovations include the following three aspects: (1) a two-dimensional sequence detection model based on a ConvLSTM (Convolutional Long Short-Term Memory) network and U-shaped structure network is proposed to obtain the context space features of image slices fully; (2) a differential diagnosis of benign and malignant pulmonary nodules based on multitask learning is proposed, which uses the annotated data of different types of tasks to mine the potential common features among tasks; and (3) an optimization strategy incorporating prior knowledge of computed tomography images and dynamic weight adjustment of multiple tasks is proposed to ensure that each task can efficiently complete training and learning. Experiments on the LIDC-IDRI and LUNA16 datasets showed that our proposed method achieved a final competition performance metric score of 87.80% for nodule detection and a Dice similarity coefficient score of 83.95% for pulmonary nodule segmentation. The cross-validation results of the LIDC-IDRI and LUNA16 datasets show that our model achieved 87.80% of the final competition performance metric score for nodule detection and 83.95% of the DSC score for pulmonary nodule segmentation, representing the optimal result for that dataset.

Synthetic ramoplanin analogues are accessible by effective incorporation of arylglycines in solid-phase peptide synthesis.

The threat of antimicrobial resistance to antibiotics requires a continual effort to develop alternative treatments. Arylglycines (or phenylglycines) are one of the signature amino acids found in many natural peptide antibiotics, but their propensity for epimerization in solid-phase peptide synthesis (SPPS) has prevented their use in long peptide sequences. We have now identified an optimized protocol that allows the synthesis of challenging non-ribosomal peptides including precursors of the glycopeptide antibiotics and an analogue of feglymycin (1 analogue, 20%). We have exploited this protocol to synthesize analogues of the peptide antibiotic ramoplanin using native chemical ligation/desulfurization (1 analogue, 6.5%) and head-to-tail macrocyclization in excellent yield (6 analogues, 3-9%), with these compounds extensively characterized by NMR (U-shaped structure) and antimicrobial activity assays (two clinical isolates). This method significantly reduces synthesis time (6-9 days) when compared with total syntheses (2-3 months) and enables drug discovery programs to include arylglycines in structure-activity relationship studies and drug development.

U²-Former: Nested U-Shaped Transformer for Image Restoration via Multi-View Contrastive Learning

While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer in the typical encoder-decoder framework for image restoration, resulting from heavy self-attention computation load and inefficient communications across different depth (scales) of layers. In this paper, we present a deep and effective Transformer-based network for image restoration, termed as U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Former, which is able to employ self-attention of Transformer as the core operation for feature learning to perform image restoration in a deep encoding and decoding space. Specifically, it leverages the nested U-shaped structure to facilitate the interactions across different layers with different scales of feature maps. Furthermore, we optimize the computational efficiency for the basic Transformer block by introducing a simple yet effective feature-filtering mechanism to compress the token representation. Apart from the typical supervision ways for image restoration, our U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Former also performs multi-view contrastive learning, which constructs positive pairs in various aspects, to learn noise-sensitive but content-irrelevant features and further decouple the noise component from the background image. Extensive experiments on various image restoration tasks, including reflection removal, rain streak removal and dehazing respectively, demonstrate the effectiveness of the proposed U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Former.

RAU-Net++: River Channel Extraction Methods for Remote Sensing Images of Cold and Arid Regions

Extracting river channels from remote sensing images is crucial for locating river water bodies and efficiently managing water resources, especially in cold and arid regions. The dynamic nature of river channels in these regions during the flood season necessitates a method that can finely delineate the edges of perennially changing river channels and accurately capture information about variable fine river branches. To address this need, we propose a river channel extraction method designed specifically for detecting fine river branches in remote sensing images within cold and arid regions. The method introduces a novel river attention U-shaped network structure (RAU-Net++), leveraging the rich convolutional features of VGG16 for effective feature extraction. For optimal feature extraction along channel edges and fine river branches, we incorporate a CBAM attention module into the upper sampling area at the end of the encoder. Additionally, a residual attention feature fusion module (RAFF) is embedded at each short jump connection in the dense jump connection. Dense skip connections play a crucial role in extracting detailed texture features from river channel features with varying receptive fields obtained during the downsampling process. The integration of the RAFF module mitigates the loss of river information, optimizing the extraction of lost river detail feature information in the original dense jump connection. This tightens the combination between the detailed texture features of the river and the high-level semantic features. To enhance network performance and reduce pixel-level segmentation errors in medium-resolution remote sensing imagery, we employ a weighted loss function comprising cross-entropy (CE) loss, dice loss, focal loss, and Jaccard loss. The RAU-Net++ demonstrates impressive performance metrics, with precision, IOU, recall, and F1 scores reaching 99.78%, 99.39%, 99.71%, and 99.75%, respectively. Meanwhile, both ED and ED′ of the RAU-Net++ are optimal, with values of 1.411 and 0.003, respectively. Moreover, its effectiveness has been validated on NWPU-RESISC45 datasets. Experimental results conclusively demonstrate the superiority of the proposed network over existing mainstream methods.

AuNPs/GO Coated U-Shape Polished SMF Based Localized SPR Sensor for Musta’mal Water Identification

Potential of hybrid gold nanoparticles/graphene oxide (AuNPs/GO) coated single mode fiber (SMF) sensor by exploiting localized surface plasmon resonance (LSPR) effect for Musta’mal water identification was studied. Three structure shapes of fiber optics such as straight-shape, loop-shape and u-shape had been prepared. Three layers of AuNPs with 50 nm in diameter were drop-casted onto the partially unclad polished single mode fiber (SMF) to observe the maximum sensitivity of LSPR. To enhance the LSPR effect, one layer of GO was deposited on top of the AuNPs layer. Two optical light sources with least attenuation (1310 nm and 1550 nm) were employed to study the optical power output as the sensor immersed in different type of water samples. The u-shape SMF portrayed the maximum output power about 24.2 dBm at 1550 nm wavelength. According to the analysis, the deployment of 1550 nm laser wavelength resulted in better sensitivity with 23.2% improvement compared to 1310 nm wavelength. Apparently, the LSPR phenomenon created by AuNPs/GO able to enhance the plasmonic signal up to 51.9% than the uncoated SMF. The thinnest diameter of SMF’s cladding, d=0.1195 mm with U-shape structure exhibited the highest power different of 1.10 dBm, in which suggested the best sensing performance. In conclusion, the optimization of AuNPs/GO u-shape polished SMF resulted in the maximum sensitivity with value of S=72.7 dBm/RIU for Musta'mal water identification.

A Fast Attention-Guided Hierarchical Decoding Network for Real-Time Semantic Segmentation.

Semantic segmentation provides accurate scene understanding and decision support for many applications. However, many models strive for high accuracy by adopting complex structures, decreasing the inference speed, and making it challenging to meet real-time requirements. Therefore, a fast attention-guided hierarchical decoding network for real-time semantic segmentation (FAHDNet), which is an asymmetric U-shaped structure, is proposed to address this issue. In the encoder, we design a multi-scale bottleneck residual unit (MBRU), which combines the attention mechanism and decomposition convolution to design a parallel structure for aggregating multi-scale information, making the network perform better at processing information at different scales. In addition, we propose a spatial information compensation (SIC) module that effectively uses the original input to make up for the spatial texture information lost during downsampling. In the decoder, the global attention (GA) module is used to process the feature map of the encoder, enhance the feature interaction in the channel and spatial dimensions, and enhance the ability to mine feature information. At the same time, the lightweight hierarchical decoder integrates multi-scale features to better adapt to different scale targets and accurately segment objects of different sizes. Through experiments, FAHDNet performs outstandingly on two public datasets, Cityscapes and Camvid. Specifically, the network achieves 70.6% mean intersection over union (mIoU) at 135 frames per second (FPS) on Cityscapes and 67.2% mIoU at 335 FPS on Camvid. Compared to the existing networks, our model maintains accuracy while achieving faster inference speeds, thus enhancing its practical usability.

Personalized Fair Split Learning for Resource-Constrained Internet of Things.

With the flourishing development of the Internet of Things (IoT), federated learning has garnered significant attention as a distributed learning method aimed at preserving the privacy of participant data. However, certain IoT devices, such as sensors, face challenges in effectively employing conventional federated learning approaches due to limited computational and storage resources, which hinder their ability to train complex local models. Additionally, in IoT environments, devices often face problems of data heterogeneity and uneven benefit distribution between them. To address these challenges, a personalized and fair split learning framework is proposed for resource-constrained clients. This framework first adopts a U-shaped structure, dividing the model to enable resource-constrained clients to offload subsets of the foundational model to a central server while retaining personalized model subsets locally to meet the specific personalized requirements of different clients. Furthermore, to ensure fair benefit distribution, a model-aggregation method with optimized aggregation weights is used. This method reasonably allocates model-aggregation weights based on the contributions of clients, thereby achieving collaborative fairness. Experimental results demonstrate that, in three distinct data heterogeneity scenarios, employing personalized training through this framework exhibits higher accuracy compared to existing baseline methods. Simultaneously, the framework ensures collaborative fairness, fostering a more balanced and sustainable cooperation among IoT devices.