Knowledge-Based Systems最新文献

Modern spectral analysis techniques are rapidly advancing, with Laser-induced breakdown spectroscopy (LIBS) gaining attention for its revolutionary potential in analytical chemistry. However, poor repeatability due to spectral fluctuation remains a common challenge. Improving LIBS repeatability involves improving instrument performance, standardizing sample handling, and refining data processing. While instrument performance and sample handling can be standardized, optimizing data processing is crucial for improving spectral reproducibility. This research addresses this issue through a 7-day experiment by proposing a cross-modal data augmentation empowered fuzzy neural network (CFNet). We first introduce a cross-modal data augmentation method that considers the spatial distribution of LIBS elemental lines. This method expands from a single spectrum modality to an image-spectrum dual modality, enhancing the ability to capture spectral fluctuation and thereby improving LIBS repeatability. We then introduce a cross-modal data augmentation empowered fuzzy neural network, which allows each spectrum to belong to multiple categories simultaneously, increasing adaptability to spectral fluctuation. Results show that both Accuracy and MacF exceed 91% across three tests, demonstrating the CFNet’s effectiveness in managing data fluctuation and serving as a reference for other spectral technologies. Integrating fuzzy logic into spectroscopy not only expands its applications but also improves the repeatability of spectral data. The cross-modal augmented data is available at https://github.com/aoao0206/CFNet.

As essential components of machinery equipment, rolling bearings directly affect the safety of the machinery equipment. The timely diagnosis of bearing faults can effectively prevent equipment lapses. However, bearings are often inconsistently distributed. This has resulted in a significant decrease in their availability. Moreover, the performances of traditional models are poor when fault samples are scarce. The unsupervised domain adaptation (UDA) model based on the transfer learning theory can solve the above problems in static scenarios. However, source domain data are often not directly accessible for privacy protection. Therefore, achieving the robustness of UDA models is significantly challenging. Source-free UDA can achieve a positive transfer from the source domain to the target domain based only on a pretrained source-domain model and unlabeled target-domain data. In this study, we built a source-free robust UDA approach with pseudo-label uncertainty estimation (SFRDA-PLUE) for diagnosing bearing faults using a limited number of samples. First, we designed a robust feature extractor (SANet) and proposed a novel binary soft-constrained information entropy. This was applied to solve the problem that standard information entropy cannot effectively estimate the uncertainty of pseudo-labels. In addition, we constructed a weighted comparison filter strategy to smoothen the fuzzy samples. Finally, we introduced an information-maximizing loss strategy to optimize the performance of the source domain classifier and the pseudo-label estimator. Thus, the robustness of the pseudo-label uncertainty estimation was significantly improved. The experimental results validated that the SFRDA-PLUE approach can achieve excellent diagnostic performance under a limited number of samples.

This article proposes a hyperparameter optimization method for density-based spatial clustering of applications with noise (DBSCAN) with constraints, termed HC-DBSCAN. While DBSCAN is effective at creating non-convex clusters, it cannot limit the number of clusters. This limitation is difficult to address with simple adjustments or heuristic methods. We approach constrained DBSCAN as an optimization problem and solve it using a customized alternating direction method of multipliers Bayesian optimization (ADMMBO). Our custom ADMMBO enables HC-DBSCAN to reuse clustering results for enhanced computational efficiency, handle integer-valued parameters, and incorporate constraint functions that account for the degree of violations to improve clustering performance. Furthermore, we propose an evaluation metric, penalized Davies–Bouldin score, with a computational cost of $O\left(N\right)$. This metric aims to mitigate the high computational cost associated with existing metrics and efficiently manage noise instances in DBSCAN. Numerical experiments demonstrate that HC-DBSCAN, equipped with the proposed metric, generates high-quality non-convex clusters and outperforms benchmark methods on both simulated and real datasets.

Accurate machine learning predictions of passenger flow data for mass rapid transit (MRT) systems can considerably improve operational efficiency by enabling better allocation of train and human resources. However, such predictions are challenging because MRT networks have complex structures with route dependence and transfer stations. Although the static state of an MRT network has been computed in previous studies, a comprehensive understanding of an MRT network requires characterizing its dynamics. Therefore, this paper proposes a dynamic traffic network representation (DTNR) model that captures station features from historical traffic flows and geographical information of MRT stations. Furthermore, a multilevel attention network (MLAN) model is proposed to predict MRT passenger flow as a downstream task following the pretraining of the DTNR model. The experimental results of this study indicate that the developed DTNR and MLAN models can accurately predict MRT passenger flow. These models are widely applicable to different MRT systems and passenger flow situations, making them a valuable tool for transportation planners and operators.

A scientific paper recommender system (RS) is very helpful for literature searching in that it (1) helps novice researchers explore their own field and (2) helps experienced researchers explore new fields outside their area of expertise. However, existing RSs usually recommend relevant papers based on users’ static interests, i.e., papers they cited in their past publication(s) or reading histories. In this paper, we propose a novel recommendation task based on users’ dynamic interests during their paper-writing activity. This dynamism is revealed in (for example) the topic shift while writing the Introduction vs. Related Works section. In solving this task, we developed a new pipeline called “Section-based Sequential Scientific Paper Recommendation (S3PaR)”, which recommends papers based on the context of the given user’s currently written paper section. Our experiments demonstrate that this unique task and our proposed pipeline outperform existing standard RS baselines.

Recently, with the continuous advancement of deep learning techniques, research on sketch synthesis has been progressing. However, existing methods still face challenges in generating human-like freehand sketches from real-world natural images at both object and scene levels. To address this, we propose SketchDiffusion, a text-guided freehand sketch synthesis method based on conditional stable diffusion. In SketchDiffusion, we design a novel image enhancing module to efficiently extract high-quality image features. Moreover, we utilize additional guidance from global and local features extracted by a U-shaped diffusion guidance network to control the noise addition and denoising process of the diffusion model, thereby significantly improving controllability and performance in freehand sketch synthesis. Beyond the model architecture, we leverage the designed BLIP-based text generation method to create 70,280 text prompts for foreground, background, and panorama sketch synthesis in the extensive SketchyCOCO dataset, thereby improving the overall effectiveness of model training. Compared to the state-of-the-art methods, our proposed SketchDiffusion has shown an average improvement of over 16.4%, 16.75%, and 12.8% on three quantitative metrics (sketch recognition, sketch-based retrieval, and user perceptual study), respectively. Furthermore, our approach not only excels in synthesizing freehand sketches containing multiple abstract objects but also has multiple applications in supporting human–computer interaction.

Few-shot text classification (FSTC) strives to predict classes not involved in the training by learning from a few labeled examples. Currently, most tasks construct meta-tasks in a randomized manner that fails to give more priority to hard-to-identify classes and samples. Besides, some tasks incorporated a contrast strategy, but the sample could only be compared to positive or negative examples individually. In this work, we propose a Meta-learning Triplet Contrast Network (Meta-TCN) with bidirectional contrast capability to solve the above problem. Specifically, Meta-TCN uses external knowledge with labeled information as the class examples, which decouples the embedding of prototypes from the support pool. Meanwhile, the class examples combine the support samples to construct triplet pairs used for learning. Unlike previous studies, the model can learn negative and positive knowledge simultaneously, ensuring that understanding is enriched and enhances learning. Further, we improve the shortcomings of randomness in the meta-task construction process by proposing a Dynamic Rate of Change (DRC) sampling strategy. DRC enhances the model’s focus on difficult-to-classify samples. We conducted extensive experiments on six benchmark datasets such as Huffpost and RCV1. Experiments show that the average accuracy of Meta-TCN can achieve state-of-the-art performance in the vast majority of tasks.

The rationality of pipeline design is directly related to its energy efficiency, reliability, and safety. Pipeline vibration may lead to negative effects such as mechanical loss and fatigue damage. Therefore, this study utilizes pipeline optimization design to mitigate these effects. Recently, neural networks have been widely used in structure design optimization. In the study, a backpropagation neural network (BP) combined with a variant slime mould algorithm (SMA) is utilized to solve the pipeline structure design optimization problem. Pipeline transport plays a crucial role in the efficient movement of various commodities, including but not limited to gas, oil, water, and other liquid substances. The interaction between liquid and pipeline can cause pipeline vibration and even damage. Therefore, based on the simulation model considering FSI (fluid-structure interaction), machine learning methods such as BP can predict vibration characteristics of fluid-conveying pipelines. However, existing research has shown that BP has insufficient parsing ability in structure mechanics problems, especially in solving the overall characteristics of complex structures (such as maximum structural strain). This study proposes an Arithmetic-based slime mould algorithm (ACSMA) with an adaptive decision strategy and a chaotic mapping strategy. A hybrid algorithm named ACSMA-BP is presented to promote the model's prediction ability. At last, to verify the effectiveness of the proposed pipeline structure design optimization approach, the ACSMA-BP model is utilized to complete a structure design optimization case for a simulated pipeline. The numerical results indicate that compared with AOA, CWOA, ESSAWOA, NGS_WOA, and RSA, the ACSMA has the best optimization ability.

Sensor nodes can be deployed in harsh or hostile environments in many applications, making these nodes more prone to failure. The illegal movement monitoring within the sensor networks is a most challenging problem. The mobile malicious nodes are preferred by the attacker to maximize his impact. For a dynamic environment, a promising technology of sensor networks is expected to Intrusion detection. Multi-mobile agents utilize many approaches, after verification that collects data from sensor nodes. However, these approaches are inefficient to verify all the sensor nodes (SNs) of the network, due to its high delay, energy consumption, and mobility. The proposed Dunnock Ibis optimization LSTM model (DIO opt LSTM) solves this problem. Here, the sensor nodes are grouped into clusters; hence, mobile agent performs verification only the cluster heads instead of verifying all the SNs. The proposed DIO optimization combines the unique behavior of Egret Swam and Ibis optimization algorithm which efficiently tunes the LSTM classifier, resulting in the model providing better convergence. The simulation results show the proposed system shows a better result than the existing system by utilizing the database IDS 2018 Intrusion CSVs, the analysis is done based on performance metrics such as End-end-delay (ED), normalized energy (NE), and throughput. At 200 nodes and 1500 rounds, the DIO opt LSTM method has efficiently performed 146 numbers of alive nodes, 0.46 ms of delay, 0.15 J of normalized energy, and 0.89 bps of throughput.

Tabular data are widely used in machine-learning tasks because of their prevalence in various fields; however, the potential risks of data breaches in tabular data and privacy protection regulations render such data almost unavailable. Tabular data generation methods alleviate data unavailability by synthesizing privacy-free data, and generating data using language models is a novel innovation. Language models can synthesize high-quality datasets by learning knowledge from nondestructive information and recognizing the semantics of table columns. However, when current language models function as generators, their encoding methods are hindered by complicated decoding processes, and the limited predictive ability of language models restricts their generative capability. To this end, we propose an encoding method based on interactive data structures such as JavaScript Object Notation for converting tabular data. We design TabSAL, which is a pluggable tabular data generation framework with small agent assisted language models, to boost the predictive capability, resulting in high-quality synthetic datasets with a much lower computational resource cost. In addition, a benchmark that integrates eight datasets, three methods, and three assessment directions has been issued, which indicates that TabSAL surpasses the state of the art by up to 60%.