Multimodal change detection (MCD) has important applications in disaster assessment, but the nonlinear distortion of features and spatial misalignment caused by sensor imaging differences make it difficult to obtain changes through direct comparison. To overcome the above problems, this study aims to realize MCD by capturing the modality-independent structural commonality features between Multimodal Remote Sensing Images (MRSIs). To achieve this, we devise a basic Graph Kolmogorov-Arnold Network (GKAN) to excavate spatial structural relationships and cross-modal nonlinear mappings simultaneously. Based on this, we propose a Dual-branch GKAN (DGKAN) for unsupervised MCD, which can capture spatial-spectral structural commonality features and compare them directly to detect changes. Concretely, the GKAN is used within the DGKAN to build two autoencoders consisting of a Siamese encoder and two independent decoders to learn spatial-spectral structural commonality features through feature reconstruction. Besides, we introduce a Covariance Structural Commonality Loss (CSCL), which guides the network in extracting spatial-spectral structural commonality features between MRSIs by unsupervised constraints on the distributional consistency of cross-modal features. Experiments on several MCD datasets show that the proposed DGKAN can achieve convincing results, and ablation studies verify the effectiveness of the GKAN and CSCL.

Contrastive learning plays an important role in the semi-supervised medical image segmentation. However, existing contrastive learning methods struggle to capture the correlation of global and local features and improve feature discrimination for complex medical scenes, resulting in poor segmentation performance in challenging polyp segmentation. To overcome these limitations, we propose a semi-supervised polyp segmentation method using Hierarchical Granularity Contrastive Learning (HGCL). HGCL has two advantages. First, we design a hierarchical spatial contrastive learning module to divide the feature maps into large and small regions and perform different region-level contrastive learning, which can effectively capture the correlation of global and local information and improve the intra-class cohesion and inter-class separation. Second, we design a fine-granularity contrastive learning module, which can perform finer pixel-level contrastive learning to capture finer subtle local features and improve the generalization capacity of HGCL for complex medical scenes. Extensive experiments on three publicly available polyp datasets demonstrate that HGCL can achieve the better segmentation performance than existing popular semi-supervised methods. The code is available at https://github.com/Milk-White/HGCL.

Underwater images suffer from light absorption and scattering, impairs their visibility and applications. Existing underwater image restoration (UIR) methods based on generative models struggle are difficult to adapt to the complex and dynamic underwater environments characterized by illumination interference, low-light conditions, and non-uniform turbidity. To address these issues, we propose Water-CDM, a novel Adaptive Double-Branch Fusion Conditional Diffusion Model for underwater image restoration. Specifically, an adaptive double-branch fusion conditional diffusion model is presented utilizing a U-shaped full-attention network and Guided Multi-Scale Retinex with Brightness Correction (GMSRBC) to restore the challenging regions within underwater images. More precisely, to correct color casts and enhance the sharpness of underwater images, a U-shaped full-attention network incorporating Attention Blocks is designed for noise estimation during the reverse process of the conditional diffusion model. Concurrently, to mitigate overexposure during the enhancement of low-light underwater images under illumination interference, the GMSRBC method, featuring an Adaptive Brightness Correction Module, is proposed to efficiently adjust the brightness of underwater images. Experimental results demonstrate that the proposed Water-CDM significantly improves the quality of underwater images in challenging scenarios. Encouragingly, our proposed Water-CDM yields superior restoration outcomes compared to current state-of-the-art methods on three challenging publicly available datasets. Our codes will be released at: https://github.com/HKandWJJ/Water-CDM.

Multimodal change detection (MCD) has garnered significant interest due to its capacity to address a variety of emergencies in a timely and effective manner. However, discrepancies in sensors and imaging techniques often hinder the direct comparison of heterogeneous remote sensing images (HRSIs), making it difficult to extract change information. To overcome this challenge, we propose a novel superpixel-based AutoEncoder Kolmogorov-Arnold Network (AEKAN) for unsupervised MCD. The primary objective of AEKAN is to excavate the latent commonality features between HRSIs. Notably, commonality features in unchanged regions are generally more pronounced than those in changed regions, which can be leveraged to assess change magnitude. To achieve this, the proposed method utilizes the Kolmogorov-Arnold Network (KAN), renowned for its capability to model data distributions, to extract these commonality features between HRSIs. Concretely, the proposed AEKAN consists of a Siamese KAN encoder and dual KAN decoders. The Siamese encoder aims to map HRSIs and extract latent commonality features, while the dual decoders reconstruct original bitemporal images from these features. In addition, we incorporate a hierarchical commonality loss function within the Siamese encoder to train AEKAN. This loss function is designed to intentionally guide the network in capturing commonality features by minimizing the discrepancies in features extracted from HRSIs at each layer of the Siamese encoder. The extracted commonality features are then adopted to quantify the change magnitude between images through mean square error (MSE). Extensive experiments on five MCD datasets demonstrate that the proposed AEKAN outperforms existing methods. The source code is available at:https://github.com/TongfeiLiu/AEKAN-for-MCD.

The following three factors restrict the application of existing low-light image enhancement methods: corruptions induced by the light-up process, color distortion, and a restricted generalization capacity due to limited paired training data. To address these limitations, we first combine HSV theory and Transformer, proposing a robust unsupervised low-light image enhancement framework, named HSVFormer. Secondly, we introduce brightness disturbance and design an unsupervised value enhancement network, which estimates brightness information and restores degraded brightness information to obtain enhanced reflectance. Finally, we utilize the V-subspace and devise a value-guided multi-head channel self-attention to capture brightness representations of regions with different brightness conditions and guide the modeling of non-local interactions. Experiment results on publicly available datasets demonstrate that HSVFormer can achieve superior performance compared with state-of-the-art approaches. The code is available at https://github.com/m0fig/HSVFormer.

Polyp segmentation is of great importance for the diagnosis and treatment of colorectal cancer. However, it is difficult to segment polyps accurately due to a large number of tiny polyps and the low contrast between polyps and the surrounding mucosa. To address this issue, we design an Adaptive Tiny-object Enhanced Network (ATENet) for tiny polyp segmentation. The proposed ATENet has two advantages: First, we design an adaptive tiny-object encoder containing three parallel branches, which can effectively extract the shape and position features of tiny polyps and thus improve the segmentation accuracy of tiny polyps. Second, we design a simple enhanced feature decoder, which can not only suppress the background noise of feature maps, but also supplement the detail information to improve further the polyp segmentation accuracy. Extensive experiments on three benchmark datasets demonstrate that the proposed ATENet can achieve the state-of-the-art performance while maintaining low computational complexity.

Convolutional neural networks (CNNs) have achieved significant success in medical image segmentation. However, they also suffer from the requirement of a large number of parameters, leading to a difficulty of deploying CNNs to low-source hardwares, e.g., embedded systems and mobile devices. Although some compacted or small memory-hungry models have been reported, most of them may cause degradation in segmentation accuracy. To address this issue, we propose a shape-guided ultralight network (SGU-Net) with extremely low computational costs. The proposed SGU-Net includes two main contributions: it first presents an ultralight convolution that is able to implement double separable convolutions simultaneously, i.e., asymmetric convolution and depthwise separable convolution. The proposed ultralight convolution not only effectively reduces the number of parameters but also enhances the robustness of SGU-Net. Secondly, our SGU-Net employs an additional adversarial shape-constraint to let the network learn shape representation of targets, which can significantly improve the segmentation accuracy for abdomen medical images using self-supervision. The SGU-Net is extensively tested on four public benchmark datasets, LiTS, CHAOS, NIH-TCIA and 3Dircbdb. Experimental results show that SGU-Net achieves higher segmentation accuracy using lower memory costs, and outperforms state-of-the-art networks. Moreover, we apply our ultralight convolution into a 3D volume segmentation network, which obtains a comparable performance with fewer parameters and memory usage.

Popular semi-supervised medical image segmentation networks often suffer from error supervision from unlabeled data since they usually use consistency learning under different data perturbations to regularize model training. These networks ignore the relationship between labeled and unlabeled data, and only compute single pixel-level consistency leading to uncertain prediction results. Besides, these networks often require a large number of parameters since their backbone networks are designed depending on supervised image segmentation tasks. Moreover, these networks often face a high over-fitting risk since a small number of training samples are popular for semi-supervised image segmentation. To address the above problems, in this paper, we propose a novel adversarial self-ensembling network using dynamic convolution (ASE-Net) for semi-supervised medical image segmentation. First, we use an adversarial consistency training strategy (ACTS) that employs two discriminators based on consistency learning to obtain prior relationships between labeled and unlabeled data. The ACTS can simultaneously compute pixel-level and image-level consistency of unlabeled data under different data perturbations to improve the prediction quality of labels. Second, we design a dynamic convolution-based bidirectional attention component (DyBAC) that can be embedded in any segmentation network, aiming at adaptively adjusting the weights of ASE-Net based on the structural information of input samples. This component effectively improves the feature representation ability of ASE-Net and reduces the overfitting risk of the network. The proposed ASE-Net has been extensively tested on three publicly available datasets, and experiments indicate that ASE-Net is superior to state-of-the-art networks, and reduces computational costs and memory overhead. The code is available at: https://github.com/SUST-reynole/ASE-Nethttps://github.com/SUST-reynole/ASE-Net.

Popular semi-supervised image segmentation networks suf-fer from two problems: firstly, supervision is only performed on the last layer of the decoder, resulting in the network's weak generalization ability; secondly, the geometry shape constraints of targets are frequently disregarded in these net-works, leading to poor segmentation results. To address these issues, we propose a novel shape-guided dual consistency semi-supervised learning framework for 3D medical image segmentation. The proposed framework makes two contri-butions. Initially, we introduce a shape constraint to learn the shape representation, which converts the difference be-tween two networks into an unsupervised loss and lets the model learn the boundary information of targets. Addition-ally, we develop a deep-supervised knowledge transfer strat-egy that improves the generalization ability of the network without increasing extra computation costs. Experiments demonstrate that the proposed framework outperforms state-of-the-art semi-supervised methods due to the strong ability of knowledge mining on unlabeled data.

Abstract As an enabling technology for edge computing scenarios, indoor localization has a broad prospect in a variety of location-based applications, such as tracking, navigating, and monitoring in indoor environments. In order to improve the location accuracy, numerous machine learning (ML)-based indoor localization schemes with fingerprint fusion have been proposed recently, which take advantage of the fusion of signal gathered from multiple wireless technologies (e.g., WiFi and BLE) and require a site survey to construct the fingerprint database. However, most solutions are based on cloud framework and thus pose a serious privacy leakage because users’ sensitive information (e.g., locations) is computed from the fingerprint database by the untrusted localization service provider. Furthermore, the site survey is time-consuming and labor-intensive. In this paper, we propose a differentially private fingerprint fusion semi-supervised extreme learning machine for indoor localization in the edge computing, called Adp-FSELM. The Adp-FSELM firstly employs a multi-level edge network-based privacy-preserving system framework to meet the requirements of ML-based fingerprint indoor localization for lightweight, low latency, and real-time response. Then, the Adp-FSELM extends the $$\varepsilon$$ ε -differential privacy to the fingerprint fusion semi-supervised extreme learning machine for indoor localization in edge computing through a three-phase private process consisting of private labeled sample obfuscation, differentially private feature fusion, and differentially private model training. Theoretical and comprehensive experimental results in real indoor environments demonstrate that the Adp-FSELM provides a high $$\varepsilon$$ ε -differential privacy guarantee for users’ location privacy while reducing human calibration effort and effectively resists Bayesian inference attacks. Compared with the existing semi-supervised learning-based localization methods, the mean absolute error of location accuracy of the Adp-FSELM is restricted to 2.22% at most, and the additional time consumption can be almost ignored. Thus, our mechanism can balance the trade-off among location privacy, location accuracy, and time consumption.

In order to prepare graduates with “competences to act”, vocational education and training require new approaches that enable the future employees to act independently in real work situations. The work-process-oriented curriculum and action-oriented learning could be considered as such a kind of curricula and a pedagogic method. However, how to provide computer-mediate scaffoldings to support online action-oriented learning within a work-process-oriented curriculum is still a challenge. This paper reports our work to scaffold online action-oriented learning by specifying an integrated learning-work process using a scripting language as a formal learning-work process model, called a unit of learning. Such a process model can be interpreted by a language-compatible learning platform to guide and foster the learning-work activities through configuring the learning-work environment dynamically. This paper also reports a case study conducted at a high-level vocational school. The results reveal that the computer-mediated scaffoldings in our process-oriented learning platform are useful to support online action-oriented learning.

U-Net and a large number of variants of U-Net have been successfully used for liver and liver-tumor segmentation. In this paper, we propose a novel network called quartet attention U-Net (QAU-Net). First, QAU-Net employs quartet attention including four branches to capture inner and cross-dimensional interactions between channels and spatial locations. Secondly, QAU-Net employs long-short skip-connection to instead of the vanilla skip-connection, which avoids the duplicate process of low-resolution information and improves the feature fusion of low-resolution and high-resolution information. We evaluate the proposed method on the public LITS dataset. Experiments demonstrate that QAU-Net has better feature representation and higher liver and liver-tumor segmentation accuracy. The available code of QAU-Net we proposed is opened at https://github.com/15029257158/QAU-Net.

Abstract Many biomedical applications require accurate non‐rigid image registration that can cope with complex deformations. However, popular diffeomorphic Demons registration algorithms suffer from difficulties for complex and serious distortions since they only use image greyscale and gradient information. To address these difficulties, a new diffeomorphic Demons registration algorithm is proposed using hierarchical neighbourhood spectral features namely HNSF Log‐Demons in this paper. In view of three important properties of hierarchical neighbourhood spectral features based on line graph such as rotation invariance, invariance of linear changes of brightness, and robustness to noise, the hierarchical neighbourhood spectral features of a reference image and a moving image is first extracted and these novel spectral features are incorporated into the energy function of the diffeomorphic registration framework to improve the capability of capturing complex distortions. Secondly, the Nystrm approximation based on random singular value decomposition is employed to effectively enhance the computational efficiency of HNSF Log‐Demons. Finally, the hybrid multi‐resolution strategy based on wavelet decomposition in the registration process is utilised to further improve the registration accuracy and efficiency. Experimental results show that the proposed HNSF Log‐Demons not only effectively ensures the generation of smooth and reversible deformation field, but also achieves better performance than state‐of‐the‐art algorithms.

Work process knowledge (WPK) is a kind of knowledge that is constructed in the workplace and can be used directly at work. It is a synthesis of theoretical knowledge with experiential knowledge gained on the job. Many efforts have been made to support work-learning activities by exploiting various potentials of information and communication technologies in an educational context. However, existing approaches and e-learning environments provide insufficient support for acquiring work process knowledge. This paper proposes an advanced approach to make it easy and helpful to acquire work process knowledge in the school through conducting a blended work-process-oriented curriculum. Through developing an exemplar work-process-oriented curriculum “the development of power-distribution systems” with an integrated remote power-distribution work environment, it has been demonstrated that this technical approach is feasible. Through an investigation it was reported that such an approach of learning is helpful for constructing work process knowledge.

Work-process-orientation is a new approach to voca¬tional education and training (VET). The content and structure of a work-process-oriented curriculum (WPOC) are derived from a typical professional task in an occupation and based on work processes. Existing approaches and learning platforms relevant to WPOC provide insufficient support. This paper proposes a technical approach to systematically supporting learning activities in a work context compatible with WPOC through integrating a learning design platform with mixed-reality environments. Through implementation and exemplary usage of the platform, the feasibility of this technical approach and its usability have been demonstrated.

The proliferation of location‐based services, representative services for the mobile networks, has posed a serious threat to users’ privacy. In the literature, several privacy mechanisms have been proposed to preserve location privacy. Location obfuscation enforced using cloaking region is a widely used technique to achieve location privacy. However, it requires a trusted third‐party (TTP) and cannot sufficiently resist various inference attacks based on background information and thus is vulnerable to location privacy breach. In this paper, we propose a context‐aware location privacy‐preserving solution with differential perturbations, which can enhance the user’s location privacy without requiring a TTP. Our scheme utilizes the modified Hilbert curve to project every 2‐d location of the user in the considered map to 1‐d space and randomly generates the reasonable perturbation by adding Laplace noise via differential privacy. In order to solve the resource limitation of mobile devices, we use a quad‐tree based scheme to transform and store the user context information as bit stream which achieves the high compression ratio and supports efficient retrieval. Security analysis shows that our proposed scheme can effectively preserve the location privacy. Experimental evaluation shows that our scheme retrieval accuracy is increased by an average of 15.4% compared with the scheme using standard Hilbert curve. Our scheme can provide strong privacy guarantees with a bounded accuracy loss while improving retrieval accuracy.

Field programmable memory BIST controllers are becoming a necessity to target manufacturing defects in embedded memories. For 65nm and below, random defects are not the only ones affecting the yield of a process. Systematic as well as parametric defects are now the predominant causes of memory failures and have to be addressed. Conventional memory BIST algorithms are usually targeted to catch random defects. In order to catch such systematic and parametric defects, it is necessary to have the flexibility to apply new algorithms to embedded memories after manufacturing. In this paper, a field programmable memory BIST architecture is proposed to support multiple loops within a test step of an algorithm, including nested loops. These controllers, therefore, guarantee supporting complex algorithm necessary to target defects during failure analysis that could help yield ramp up or reduce test escapes. In addition, the proposed architecture is modular in nature and allows optimizing the complexity of the controller along with area and performance

A full-speed field-programmable memory BIST controller is proposed. The proposed instruction and architecture designs enable full-speed operation of not only March algorithms but also some non-linear algorithms that are becoming more and more important in modern memory testing, diagnosis, and failure analysis.

A memory BIST enhancement, ESP short for exercising system paths, is described that allows the efficiency and functional capabilities of standard approaches while addressing two important problems. Conventional Memory BIST techniques require MUXes at the inputs of the memory that allow for the inputs to be driven either by system signals or by test signals. These MUXes add delays, in the system path going to the memory, which often has critical timing. ESP eliminates such delays by implementing the MUXing function 'before' scan cells. ESP also uses scan cells to capture the memory output for feeding back to the BIST controller. This output may have traveled through some logic before getting to the recording scan cells. By including the delays of the system input and output paths, ESP allows for verifying that the memory will work correctly as part of the system rather than just as an isolated unit. Using ESP, a memory BIST can catch transition and delay faults that are impractical, or even impossible, to catch otherwise. Therefore, ESP can be useful for all memories but may be crucial for the memories which cannot tolerate the addition of the MUX delay to functional paths.

Critical paths are analyzed in a CAM and minimum test patterns are proposed to detect delay faults in a CAM. The test patterns derived are shown to be covered by the basic algorithm proposed earlier in (G. Giles et al, Proc. Int. Test Conf. p.471-474, 1985).