In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at this https URL

Hypertrophic cardiomyopathy (HCM) and cardiac amyloidosis (CA) are both heart conditions that can progress to heart failure if untreated. They exhibit similar echocardiographic characteristics, often leading to diagnostic challenges. This paper introduces a novel multi-view deep learning approach that utilizes 2D echocardiography for differentiating between HCM and CA. The method begins by classifying 2D echocardiography data into five distinct echocardiographic views: apical 4-chamber, parasternal long axis of left ventricle, parasternal short axis at levels of the mitral valve, papillary muscle, and apex. It then extracts features of each view separately and combines five features for disease classification. A total of 212 patients diagnosed with HCM, and 30 patients diagnosed with CA, along with 200 individuals with normal cardiac function(Normal), were enrolled in this study from 2018 to 2022. This approach achieved a precision, recall of 0.905, and micro-F1 score of 0.904, demonstrating its effectiveness in accurately identifying HCM and CA using a multi-view analysis.

Quantum algorithms rely on quantum computers for implementation, but the physical connectivity constraints of modern quantum processors impede the efficient realization of quantum algorithms. Qubit mapping, a critical technology for practical quantum computing applications, directly determines the execution efficiency and feasibility of algorithms on superconducting quantum processors. Existing mapping methods overlook intractable quantum hardware fidelity characteristics, reducing circuit execution quality. They also exhibit prolonged solving times or even failure to complete when handling large-scale quantum architectures, compromising efficiency. To address these challenges, we propose a novel qubit mapping method HAQA. HAQA first introduces a community-based iterative region identification strategy leveraging hardware connection topology, achieving effective dimensionality reduction of mapping space. This strategy avoids global search procedures, with complexity analysis demonstrating quadratic polynomial-level acceleration. Furthermore, HAQA implements a hardware-characteristic-based region evaluation mechanism, enabling quantitative selection of mapping regions based on fidelity metrics. This approach effectively integrates hardware fidelity information into the mapping process, enabling fidelity-aware qubit allocation. Experimental results demonstrate that HAQA significantly improves solving speed and fidelity while ensuring solution quality. When applied to state-of-the-art quantum mapping techniques Qsynth-v2 and TB-OLSQ2, HAQA achieves acceleration ratios of 632.76 and 286.87 respectively, while improving fidelity by up to 52.69% and 238.28%

Due to the emergence of many sign language datasets, isolated sign language recognition (ISLR) has made significant progress in recent years. In addition, the development of various advanced deep neural networks is another reason for this breakthrough. However, challenges remain in applying the technique in the real world. First, existing sign language datasets do not cover the whole sign vocabulary. Second, most of the sign language datasets provide only single view RGB videos, which makes it difficult to handle hand occlusions when performing ISLR. To fill this gap, this paper presents a dual-view sign language dataset for ISLR named NationalCSL-DP, which fully covers the Chinese national sign language vocabulary. The dataset consists of 134140 sign videos recorded by ten signers with respect to two vertical views, namely, the front side and the left side. Furthermore, a CNN transformer network is also proposed as a strong baseline and an extremely simple but effective fusion strategy for prediction. Extensive experiments were conducted to prove the effectiveness of the datasets as well as the baseline. The results show that the proposed fusion strategy can significantly increase the performance of the ISLR, but it is not easy for the sequence-to-sequence model, regardless of whether the early-fusion or late-fusion strategy is applied, to learn the complementary features from the sign videos of two vertical views.

Few-Shot Class-Incremental Fault Diagnosis (FSC-FD), which aims to continuously learn from new fault classes with only a few samples without forgetting old ones, is critical for real-world industrial systems. However, this challenging task severely amplifies the issues of catastrophic forgetting of old knowledge and overfitting on scarce new data. To address these challenges, this paper proposes a novel framework built upon Dual-Granularity Representations, termed the Dual-Granularity Guidance Network (DGGN). Our DGGN explicitly decouples feature learning into two parallel streams: 1) a fine-grained representation stream, which utilizes a novel Multi-Order Interaction Aggregation module to capture discriminative, class-specific features from the limited new samples. 2) a coarse-grained representation stream, designed to model and preserve general, class-agnostic knowledge shared across all fault types. These two representations are dynamically fused by a multi-semantic cross-attention mechanism, where the stable coarse-grained knowledge guides the learning of fine-grained features, preventing overfitting and alleviating feature conflicts. To further mitigate catastrophic forgetting, we design a Boundary-Aware Exemplar Prioritization strategy. Moreover, a decoupled Balanced Random Forest classifier is employed to counter the decision boundary bias caused by data imbalance. Extensive experiments on the TEP benchmark and a real-world MFF dataset demonstrate that our proposed DGGN achieves superior diagnostic performance and stability compared to state-of-the-art FSC-FD approaches. Our code is publicly available at this https URL

In the field of deep learning, traditional attention mechanisms face significant challenges related to high computational complexity and large memory consumption when processing long sequence data. To address these limitations, we propose Opt-GPTQ, an optimized Gradient-based Post Training Quantization (GPTQ) combining the Grouped Query Attention (GQA) mechanism with paging memory management, optimizing the traditional Multi-Head Attention (MHA) mechanism by grouping query heads and sharing key-value vectors. Optimized GQA (Opt-GQA) effectively reduces computational complexity, minimizes memory fragmentation, and enhances memory utilization for large-scale models. Opt-GPTQ is optimized for Data Center Units (DCUs) and integrated into the vLLM model to maximize hardware efficiency. It customizes GPU kernels to further enhance attention computation by reducing memory access latency and boosting parallel computing capabilities. Opt-GQA integrates Attention with Linear Biases (ALiBi) to reduce overhead and enhance long-sequence processing. Experimental results show that Opt-GPTQ significantly reduces computation time and memory usage while improving model performance.

Physics-informed neural networks (PINNs) integrate fundamental physical principles with advanced data-driven techniques, driving significant advancements in scientific computing. However, PINNs face persistent challenges with stiffness in gradient flow, which limits their predictive capabilities. This paper presents an improved PINN (I-PINN) to mitigate gradient-related failures. The core of I-PINN is to combine the respective strengths of neural networks with an improved architecture and adaptive weights containingupper bounds. The capability to enhance accuracy by at least one order of magnitude and accelerate convergence, without introducing extra computational complexity relative to the baseline model, is achieved by I-PINN. Numerical experiments with a variety of benchmarks illustrate the improved accuracy and generalization of I-PINN. The supporting data and code are accessible at this https URL, enabling broader research engagement.

Accurate power load forecasting is crucial for improving energy efficiency and ensuring power supply quality. Considering the power load forecasting problem involves not only dynamic factors like historical load variations but also static factors such as climate conditions that remain constant over specific periods. From the model-agnostic perspective, this paper proposes a parallel structure network to extract important information from both dynamic and static data. Firstly, based on complexity learning theory, it is demonstrated that models integrated through parallel structures exhibit superior generalization abilities compared to individual base learners. Additionally, the higher the independence between base learners, the stronger the generalization ability of the parallel structure model. This suggests that the structure of machine learning models inherently contains significant information. Building on this theoretical foundation, a parallel convolutional neural network (CNN)-gate recurrent unit (GRU) attention model (PCGA) is employed to address the power load forecasting issue, aiming to effectively integrate the influences of dynamic and static features. The CNN module is responsible for capturing spatial characteristics from static data, while the GRU module captures long-term dependencies in dynamic time series data. The attention layer is designed to focus on key information from the spatial-temporal features extracted by the parallel CNN-GRU. To substantiate the advantages of the parallel structure model in extracting and integrating multi-source information, a series of experiments are conducted.

Machine learning approaches are widely studied in the production prediction of CBM wells after hydraulic fracturing, but merely used in practice due to the low generalization ability and the lack of interpretability. A novel methodology is proposed in this article to discover the latent causality from observed data, which is aimed at finding an indirect way to interpret the machine learning results. Based on the theory of causal discovery, a causal graph is derived with explicit input, output, treatment and confounding variables. Then, SHAP is employed to analyze the influence of the factors on the production capability, which indirectly interprets the machine learning models. The proposed method can capture the underlying nonlinear relationship between the factors and the output, which remedies the limitation of the traditional machine learning routines based on the correlation analysis of factors. The experiment on the data of CBM shows that the detected relationship between the production and the geological/engineering factors by the presented method, is coincident with the actual physical mechanism. Meanwhile, compared with traditional methods, the interpretable machine learning models have better performance in forecasting production capability, averaging 20% improvement in accuracy.

The igneous rocks in deep formation have the characteristics of hardness, poor drillability and high abrasiveness, which is a difficulty in speeding up drilling. The drilling efficiency of existing conventional bits is low in igneous rocks. Based on the characteristics of igneous rocks, rock mechanical parameters and drillability experiments of granite, sandstone and other rocks were carried out. The rock drilling experiments of composite bit, tri-cone bit and PDC bit were carried out. Experiments have shown that in granite with very high strength, the drilling efficiency of conventional cone bit is very low, and it is extremely difficult for PDC bit to penetrate. The impact crushing effect of the cone of the composite bit can make the rock at the bottom of the well produce pits and cracks, which can assist the PDC cutters to penetrate into the formation, and solve the problem of the PDC cutters difficulty in penetrating in hard formations. In softer formations, the rock-breaking advantage of composite bit is not obvious, and the rock-breaking efficiency is lower than that of PDC bit. However, in hard formations, the advantage of composite bit is obvious, with higher drilling efficiency than PDC bit and cone bits. The personalized composite bit developed for deep igneous rocks formations has fast drilling speed, strong sustained drilling ability, long footage, and significant drilling speed-up effect. It significantly reduces the number of runs in deep drilling operations and achieves good application results. The composite bit is suitable for drilling in deep igneous hard-to-drill formations, and it has obvious advantages in deep igneous formations. It is a good choice for drilling speed-up in this kind of hard-to-drill formation.

The porous media community extensively utilizes digital rock images for core analysis. High-resolution digital rock images that possess sufficient quality are essential but often challenging to acquire. Super-resolution (SR) approaches enhance the resolution of digital rock images and provide improved visualization of fine features and structures, aiding in the analysis and interpretation of rock properties, such as pore connectivity and mineral distribution. However, there is a current shortage of real paired microscopic images for super-resolution training. In this study, we used two types of Scanning Electron Microscopes (SEM) to obtain the images of shale samples in five regions, with 1X, 2X, 4X, 8X and 16X magnifications. We used these real scanned paired images as a reference to select the optimal method of image generation and validated it using Enhanced Deep Super Resolution (EDSR) and Very Deep Super Resolution (VDSR) methods. Our experiments show that the bilinear algorithm is more suitable than the commonly used bicubic method, for establishing low-resolution datasets in the SR approaches, which is partially attributed to the mechanism of Scanning Electron Microscopes (SEM).

The picture fuzzy set, characterized by three membership degrees, is a helpful tool for multi-criteria decision making (MCDM). This paper investigates the structure of the closed operational laws in the picture fuzzy numbers (PFNs) and proposes efficient picture fuzzy MCDM methods. We first introduce an admissible order for PFNs and prove that all PFNs form a complete lattice under this order. Then, we give some specific examples to show the non-closeness of some existing picture fuzzy aggregation operators. To ensure the closeness of the operational laws in PFNs, we construct a new class of picture fuzzy operators based on strict triangular norms, which consider the interaction between the positive degrees (negative degrees) and the neutral degrees. Based on these new operators, we obtain the picture fuzzy interactional weighted average (PFIWA) operator and the picture fuzzy interactional weighted geometric (PFIWG) operator. They are proved to be monotonous, idempotent, bounded, shift-invariant, and homogeneous. We also establish a novel MCDM method under the picture fuzzy environment applying PFIWA and PFIWG operators. Furthermore, we present an illustrative example for a clear understanding of our method. We also give the comparative analysis among the operators induced by six classes of famous triangular norms.

Neutral atom quantum computers are one of the most promising quantum architectures, offering advantages in scalability, dynamic reconfigurability, and potential for large-scale implementations. These characteristics create unique compilation challenges, especially regarding compilation efficiency while adapting to hardware flexibility. However, existing methods encounter significant performance bottlenecks at scale, hindering practical applications. We propose Physics-Aware Compilation (PAC), a method that improves compilation efficiency while preserving the inherent flexibility of neutral atom systems. PAC introduces physics-aware hardware plane partitioning that strategically allocates hardware resources based on physical device characteristics like AOD and SLM trap properties and qubit mobility constraints. Additionally, it implements parallel quantum circuit division with an improved Kernighan-Lin algorithm that enables simultaneous execution across independent regions while maintaining circuit fidelity. Our experimental evaluation compares PAC with state-of-the-art methods across increasingly larger array sizes ranging from 16x16 to 64x64 qubits. Results demonstrate that PAC achieves up to 78.5x speedup on 16x16 arrays while maintaining comparable circuit quality. PAC's compilation efficiency advantage increases with system scale, demonstrating scalability for practical quantum applications on larger arrays. PAC explores a viable path for practical applications of neutral atom quantum computers by effectively addressing the tension between compilation efficiency and hardware flexibility.

We theoretically study the reentrant condensation of a polyelectrolyte in the presence of an oppositely-charged surfactant,a phenomenon whose phase-transition mechanism remains under discussion. We focus on the adsorption and attraction effects of surfactant near/on polymer chains, and ignore their own non-essential mixing effects if surfactant molecules are far away from polymer chains. This approach allows us to construct a simple mean-field theory and solve it analytically, and finally rationalize the essential features (such as the "egg shape" of spinodal phase diagrams) of the reentrant condensation of a polyelectrolyte induced by diluted oppositely-charged surfactants. By theoretical analysis, we found that a strong electrostatic adsorption between the ionic monomers and surfactant ions is critical to understand the peculiar phenomenon that both the collapse and reentry transitions of polyelectrolytes can occur when the concentration of surfactant is lower than its bulk critical micelle concentration (CMC). The analytical solution of the theory indicates that a minimum coupling energy for the nonlinear hydrophobic-aggregation effect of adsorbed surfactant is essential for phase transition to occur,which explains why polyelectrolytes show phase transition only if the surfactant chain length is longer than a minimum length. The obtained results will shed light on a deep understanding of liquid-liquid phase separation in biological systems where ionic surfactant-like proteins/peptides bound to bio-polyelectrolytes play an important role.

Reducing radiation doses benefits patients, however, the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) shows promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to address these privacy concerns; however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCAN-PhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures being scanned, we design a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM), respectively. Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy (PVQS), which ensures consistent performance across new clients by quantifying the unseen scanning code as one of the codes in the scanning codebook. Extensive experimental results demonstrate the superior performance of SCAN-PhysFed on public datasets.

This paper numerically investigates the influence of a fixed downstream control cylinder on the flow-induced vibration of an elastically-supported primary cylinder. These two cylinders are situated in a tandem arrangement with small dimensionless centre-to-centre spacing ($L/D$, $L$ is the intermediate spacing, and $D$ is the cylinder diameter). The present two-dimensional (2D) simulations are carried out in the low Reynolds number ($Re$) regime. The primary focus of this study is to reveal the underlying flow physics behind the transition from vortex-induced vibration to galloping in the response of the primary cylinder due to the presence of another fixed downstream cylinder. Two distinct flow field regimes, namely steady flow and alternate attachment regimes, are observed for different $L/D$ and Re values. Depending on the evolution of the near-field flow structures, four different wake patterns - `2S', `2P', `2C', and `aperiodic' - are observed. The corresponding vibration response of the upstream cylinder is characterized as interference galloping and extended vortex-induced vibration. As the $L/D$ ratio increases, the lift enhancement due to flow-induced vibration is seen to be weakened. The detailed correlation between the force generation and the near-wake interactions is investigated. The present findings will augment the understanding of vibration reduction or flow-induced energy harvesting of tandem cylindrical structures.

Feature extraction is critical for TLS traffic analysis using machine learning techniques, which it is also very difficult and time-consuming requiring huge engineering efforts. We designed and implemented DeepTLS, a system which extracts full spectrum of features from pcaps across meta, statistical, SPLT, byte distribution, TLS header and certificates. The backend is written in C++ to achieve high performance, which can analyze a GB-size pcap in a few minutes. DeepTLS was thoroughly evaluated against two state-of-the-art tools Joy and Zeek with four well-known malicious traffic datasets consisted of 160 pcaps. Evaluation results show DeepTLS has advantage of analyzing large pcaps with half analysis time, and identified more certificates with acceptable performance loss compared with Joy. DeepTLS can significantly accelerate machine learning pipeline by reducing feature extraction time from hours even days to minutes. The system is online at this https URL, where test artifacts can be viewed and validated. In addition, two open source tools Pysharkfeat and Tlsfeatmark are also released.

Naked eye recognition of age is usually based on comparison with the age of others. However, this idea is ignored by computer tasks because it is difficult to obtain representative contrast images of each age. Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation. We let the input of transfer learning as the binary code of age natural number to obtain continuous age feature information. The learned two groups of values in Binary code mapping are corresponding to the mean and standard deviation of the comparison ages. In summary, our method consists of four parts: FaceEncoder, DAA operation, Binary code mapping, and AgeDecoder modules. After getting the delta age via AgeDecoder, we take the average value of all comparison ages and delta ages as the predicted age. Compared with state-of-the-art methods, our method achieves better performance with fewer parameters on multiple facial age datasets.