Fine-Grained Domain Generalization (FGDG) presents greater challenges than conventional domain generalization due to the subtle inter-class differences and relatively pronounced intra-class variations inherent in fine-grained recognition tasks. Under domain shifts, the model becomes overly sensitive to fine-grained cues, leading to the suppression of critical features and a significant drop in performance. Cognitive studies suggest that humans classify objects by leveraging both common and specific attributes, enabling accurate differentiation between fine-grained categories. However, current deep learning models have yet to incorporate this mechanism effectively. Inspired by this mechanism, we propose Concept-Feature Structuralized Generalization (CFSG). This model explicitly disentangles both the concept and feature spaces into three structured components: common, specific, and confounding segments. To mitigate the adverse effects of varying degrees of distribution shift, we introduce an adaptive mechanism that dynamically adjusts the proportions of common, specific, and confounding components. In the final prediction, explicit weights are assigned to each pair of components. Extensive experiments on three single-source benchmark datasets demonstrate that CFSG achieves an average performance improvement of 9.87% over baseline models and outperforms existing state-of-the-art methods by an average of 3.08%. Additionally, explainability analysis validates that CFSG effectively integrates multi-granularity structured knowledge and confirms that feature structuralization facilitates the emergence of concept structuralization.

The Internet of Bio-Nano Things (IoBNT) enables nanoscale devices to interact with biological systems offering promising applications. Molecular communication (MC), which uses molecules as information carriers, is essential for the implementation of IoBNT systems. As in conventional communication systems, a clock signal is vital for reliable operation. However, in MC, generating a stable clock signal remains a significant challenge. This paper proposes a protein-based clock signal model in which the signal is generated by a mutually inhibitory protein oscillator inside the cell. The signal is transported through the cell membrane surrounding the oscillator via cell-penetrating peptides (CPPs) and diffusion to the transmitters and receivers in a MC system, thereby regulating their periodic activities. The performance of the clock signal in terms of amplitude, clock period and diffusion characteristics is evaluated. Additionally, two triggering mechanisms are introduced to shape the protein clock signals. The simulation results show that the proposed protein circuit generates a stable and periodic clock signal, and effectively regulate the operations of transmitters and receivers. This work lays the foundation for developing stable and efficient clock signal in IoBNT.

The Internet of nano things (IoNTs) envisions thousands of nanomachine nodes that sense, compute, actuate and communicate at the nanoscale. With the development of nanotechnology, DNA technology, a promising way to achieve precise manipulation in the microscopic world, have shown their potential as multiple nanomachine nodes within IoNTs, such as sensing and actuation. However, current DNA nanomachine research mostly focuses on solutions for specific diseases and lacks a generalizable and universal design. This will not only undoubtedly hinder the realization of DNA-based IoNTs but also limit the development of DNA nanomachine. In recent years, researchers has begun to realize this problem and proposed some more integrated and versatile DNA nanomachine designs, incorporating with logic and communication functions. Among these, the integration of molecular communication gives DNA nanomachine the potential to realize IoNTs, making it more promising for future applications. Therefore, this review comprehensively sorts out recent researches of DNA nanomachine over the past decade and discusses them from the perspective of IoNTs systems. In detail, we review and analyze existing DNA nanomachine researches from communication fundamental to various nodes within the network (computing, sensing, actuation, etc.), introduce the technology behind and evaluate the performance of DNA nanomachines. Finally, we present the development prospects of DNA-based IoNTs and discuss the challenges. We hope that this review will help inspire the design of more integrable DNA nanomachines and promote the progress of both DNA nanomachine and IoNTs research.

Class incremental learning (CIL) offers a promising framework for continuous fault diagnosis (CFD), allowing networks to accumulate knowledge from streaming industrial data and recognize new fault classes. However, current CIL methods assume a balanced data stream, which does not align with the long-tail distribution of fault classes in real industrial scenarios. To fill this gap, this article investigates the impact of long-tail bias in the data stream on the CIL training process through the experimental analysis. Observations show that long-tail bias in the data stream has a cascading effect, affecting the retention of old task knowledge and learning new tasks. Concurrently, the incremental model encounters challenges in identifying samples that conflict with its biases. Accordingly, we propose a CFD method called long-tail CIL via bias calibration (LTCIL-BC), which aims to improve the learning of bias-conflicting samples through bias exploration and debiasing. Specifically, LTCIL-BC simultaneously trains a primary debiased network and an auxiliary biased network. Then, a bias-indicating score is developed to provide insight into model bias and data bias based on the prediction error of the primary and auxiliary models, respectively. LTCIL-BC subsequently adjusts the logits of the debiased network using the bias-indicating score to guide optimization, thereby better utilizing the role of old class exemplars and reducing catastrophic forgetting. Experiments on power system (PS) and secure water treatment (SWaT) datasets demonstrate the superior performance of LTCIL-BC in CFD, achieving up to 9% improvement over state-of-the-art baselines in multiple long-tailed CIL setting. Comprehensive results demonstrate the effectiveness of LTCIL-BC in jointly addressing data and model bias during calibration and prioritizing bias-conflicting samples.

Explainability is a critical factor influencing the wide deployment of deep vision models (DVMs). Concept-based post-hoc explanation methods can provide both global and local insights into model decisions. However, current methods in this field face challenges in that they are inflexible to automatically construct accurate and sufficient linguistic explanations for global concepts and local circuits. Particularly, the intrinsic polysemanticity in semantic Visual Concepts (VCs) impedes the interpretability of concepts and DVMs, which is underestimated severely. In this paper, we propose a Chain-of-Explanation (CoE) approach to address these issues. Specifically, CoE automates the decoding and description of VCs to construct global concept explanation datasets. Further, to alleviate the effect of polysemanticity on model explainability, we design a concept polysemanticity disentanglement and filtering mechanism to distinguish the most contextually relevant concept atoms. Besides, a Concept Polysemanticity Entropy (CPE), as a measure of model interpretability, is formulated to quantify the degree of concept uncertainty. The modeling of deterministic concepts is upgraded to uncertain concept atom distributions. Finally, CoE automatically enables linguistic local explanations of the decision-making process of DVMs by tracing the concept circuit. GPT-4o and human-based experiments demonstrate the effectiveness of CPE and the superiority of CoE, achieving an average absolute improvement of 36% in terms of explainability scores.

Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of subtle features leads to a severe deterioration in model performance. Nevertheless, humans inherently demonstrate the capacity for generalizing to out-of-distribution data, leveraging structured multi-granularity knowledge that emerges from discerning the commonality and specificity within categories. Likewise, we propose a Feature Structuralized Domain Generalization (FSDG) model, wherein features experience structuralization into common, specific, and confounding segments, harmoniously aligned with their relevant semantic concepts, to elevate performance in FGDG. Specifically, feature structuralization (FS) is accomplished through joint optimization of five constraints: a decorrelation function applied to disentangled segments, three constraints ensuring common feature consistency and specific feature distinctiveness, and a prediction calibration term. By imposing these stipulations, FSDG is prompted to disentangle and align features based on multi-granularity knowledge, facilitating robust subtle distinctions among categories. Extensive experimentation on three benchmarks consistently validates the superiority of FSDG over state-of-the-art counterparts, with an average improvement of 6.2% in FGDG performance. Beyond that, the explainability analysis on explicit concept matching intensity between the shared concepts among categories and the model channels, along with experiments on various mainstream model architectures, substantiates the validity of FS.

Molecular communication (MC) is a promising way to achieve the Internet of nano things (IoNTs), and the theoretical system has been gradually improved in recent years. However, previous studies have more concentrated on system modeling, often simplifying the transceiver into an ideal point model due to the absence of a detailed transceiver design. In this paper, we choose DNA, the natural material to design the MC transceiver benefited from the promoting DNA technology. Specifically, we use DNA origami technology to design the transceiver and DNA strands as the information molecules (IMs). DNA strand displacement (DSD) reactions make up to the mechanism of the transmission and reception of IMs. Furthermore, amplifier is designed based on strand displacement amplification (SDA) mechanism, and the whole MC system works under the control of a timer mechanism which is achieved by the synergy of$\lambda$exonuclease ($\lambda$Exo) and fuel strands, one special DNA strands. For our designed nano transceiver, we modeled the MC system mathematically and analyzed the noise based on the properties of the transceiver. Based on the simulation results, we find the nano transceiver works well in nano-scale which promises the potential for further application in the future.

Explainability is a pivotal factor in determining whether a deep learning model can be authorized in critical applications. To enhance the explainability of models of end-to-end object DEtection with TRansformer (DETR), we introduce a disentanglement method that constrains the feature learning process, following a divide-and-conquer decoupling paradigm, similar to how people understand complex real-world problems. We first demonstrate the entangled property of the features between the extractor and detector and find that the regression function is a key factor contributing to the deterioration of disentangled feature activation. These highly entangled features always activate the local characteristics, making it difficult to cover the semantic information of an object, which also reduces the interpretability of single-backbone object detection models. Thus, an Explainability Enhanced object detection Transformer with feature Disentanglement (DETD) model is proposed, in which the Tensor Singular Value Decomposition (T-SVD) is used to produce feature bases and the Batch averaged Feature Spectral Penalization (BFSP) loss is introduced to constrain the disentanglement of the feature and balance the semantic activation. The proposed method is applied across three prominent backbones, two DETR variants, and a CNN based model. By combining two optimization techniques, extensive experiments on two datasets consistently demonstrate that the DETD model outperforms the counterpart in terms of object detection performance and feature disentanglement. The Grad-CAM visualizations demonstrate the enhancement of feature learning explainability in the disentanglement view.

Deep learning (DL) methods have been widely applied to intelligent fault diagnosis of industrial processes and achieved state-of-the-art performance. However, fault diagnosis with point estimate may provide untrustworthy decisions. Recently, Bayesian inference shows to be a promising approach to trustworthy fault diagnosis by quantifying the uncertainty of the decisions with a DL model. The uncertainty information is not involved in the training process, which does not help the learning of highly uncertain samples and has little effect on improving the fault diagnosis performance. To address this challenge, we propose a Bayesian hierarchical graph neural network (BHGNN) with an uncertainty feedback mechanism, which formulates a trustworthy fault diagnosis on the Bayesian DL (BDL) framework. Specifically, BHGNN captures the epistemic uncertainty and aleatoric uncertainty via a variational dropout approach and utilizes the uncertainty information of each sample to adjust the strength of the temporal consistency (TC) constraint for robust feature learning. Meanwhile, the BHGNN method models the process data as a hierarchical graph (HG) by leveraging the interaction-aware module and physical topology knowledge of the industrial process, which integrates data with domain knowledge to learn fault representation. Moreover, the experiments on a three-phase flow facility (TFF) and secure water treatment (SWaT) show superior and competitive performance in fault diagnosis and verify the trustworthiness of the proposed method.

To enhance high frequency details of image super-resolution restoration, an algorithm based on improved MAP estimation is proposed. In this paper, POCS and MAP are combined in a special way. POCS is used in the MAP estimation so that advantages of the both algorithms can be taken. Experiment shows it is effective by comparing with the results of typical MAP method.