Knowledge-Based Systems最新文献

Artificial Intelligence (AI) is seen as a disruptive solution to the ever increasing security threats on network infrastructures. To automate the process of defending networked environments from such threats, approaches such as Reinforcement Learning (RL) have been used to train agents in cyber adversarial games. One primary challenge is how contextual information could be integrated into RL models to create agents which adapt their behaviour to adversarial posture. Two desirable characteristics identified for such models are that they should be interpretable and causal.

To address this challenge, we propose an approach through the integration of a causal rewards model with a modified Proximal Policy Optimisation (PPO) agent in Meta’s MBRL-Lib framework. Our RL agents are trained and evaluated against a range of cyber-relevant scenarios in the Dstl YAWNING-TITAN (YT) environment. We have constructed and experimented with two types of reward functions to facilitate the agent’s learning process. Evaluation metrics include, among others, games won by the defence agent (blue wins), episode length, healthy nodes and isolated nodes.

Results show that, over all scenarios, our causally aware agent achieves better performance than causally-blind state-of-the-art benchmarks in these scenarios for the above evaluation metrics. In particular, with our proposed High Value Target (HVT) rewards function, which aims not to disrupt HVT nodes, the number of isolated nodes is improved by 17% and 18% against the model-free and Neural Network (NN) model-based agents across all scenarios. More importantly, the overall performance improvement for the blue wins metric exceeded that of model-free and NN model-based agents by 40% and 17%, respectively, across all scenarios.

One of the main challenges in applying preference-based approaches to many-objective optimization problems is that decision makers (DMs) initially have only a vague notion of the solution they want and can obtain. In this paper, we propose an interactive approach that aids DMs in articulating a preference model in a progressive way. The quality of a solution is determined in terms of its “preference closeness” to an aspiration point, which is a subjective concept that can be outlined by the DM. Our proposal is based on compensatory fuzzy logic, which allows for the construction of predicates that are expressed in language that is close to natural. One main advantage is that the model can be optimized via metaheuristics, and we utilize an ant colony optimization algorithm for this. Our model complies with the principles of hybrid augmented intelligence, not only because the algorithm is enriched with knowledge from the DM, but also because the DM also learns the concept of “preference closeness” throughout the process. The proposed model is validated on benchmarks with five and 10 objective functions, and is compared with two state-of-the-art algorithms. Our approach allows for better convergence to the best compromise solutions. The advantages of our approach are supported by statistical tests of the results.

Sequential recommendation (SR) has become a research hotspot recently. In our research, we observe that most existing SR models only leverage each user’s own interaction sequence to make recommendation. We argue that leveraging global contextual information across different interaction sequences could enrich item representations and thereby improve recommendation performance. To achieve this, we formulate a global graph from different sequences, providing global contextual information for each sequence. Specifically, we propose to conduct graph contrastive learning on a subgraph sampled from the global graph and a local sequence graph built from each sequence to augment item representations within each sequence. At the same time, we observe that structural dependencies, referring to relationships between items based on the graphic structure, can be extracted from the constructed global graph. Capturing structural dependencies between items may enrich the item representations. To leverage structural dependencies, we propose a new attention mechanism referred to as the Jaccard attention. While prevalent Transformer-based SR models capture semantic dependencies, referring to relationships between items based on item embeddings, in a sequence through self-attention. Therefore, it is beneficial to capture both semantic and structural dependencies between items in a sequence to further enrich item representations. Specifically, we employ two sequence encoders based on the self-attention and the proposed Jaccard attention to capture semantic and structural dependencies between items in a sequence, respectively. Overall, we propose a Global Contextual enhanced Structural-aware Transformer (GC-ST) for SR. Extensive experiments carried out on three widely used datasets demonstrate the effectiveness of GC-ST.

Person re-identification (Re-ID) has achieved tremendous success in the fields of computer vision and security. However, Re-ID models are susceptible to adversarial examples, which are crafted by introducing imperceptible perturbations to benign person images. These adversarial examples often display high success rates in white-box settings but their transferability to black-box settings is relatively low. To improve the transferability of adversarial examples, this paper proposes a novel approach called the adaptive gradient similarity attack (AGS), which encompasses two essential components: gradient similarity and enhanced second moment. Specifically, a gradient similarity modulation is established to better harness the information in the neighborhood of the adjacent input, which can adaptively correct the update direction. Additionally, this paper formulates an enhanced second moment to adjust the update step at each iteration to address the issue of poor transferability. Extensive experiments confirm that AGS achieves the best performance compared with the state-of-the-art gradient-based attacks. Moreover, AGS is a versatile approach that can be integrated with existing input transformation attack techniques. Code is available at https://github.com/ZezeTao/similar_Attack4.

Defect recognition of flat metals is paramount for ensuring quality control during the production process. However, the diverse origins of metal surface damage, ranging from mechanical impacts to chemical corrosion, and the resulting varied morphology and scale of surface defects, particularly numerous microdefects and elongated defects with high aspect ratios, complicate defect recognition. Existing methods fail to select the most beneficial features during extraction and commonly lose critical feature information during gradient sampling. To overcome these challenges, we propose a lightweight network to optimize feature screening for defect recognition. First, we propose a deformable context–guided block that employs deformable convolution to dynamically adapt the perception of the spatial context, providing precise guidance of relevant semantic information in complex surface textures. Second, we develop a content-aware feature compression block that implements adaptive weighting of features, which significantly reduces information loss during the downsampling stage. Finally, we introduce an intra-scale feature interaction transformer block, which optimizes high-order semantic features to enhance the accuracy and reliability of defect detection. Experimental validation on the NEU-DET, APS-DET, and GC10-DET datasets demonstrated significant improvements in the detection accuracy and parameter efficiency, confirming the proposed method's robust generalizability.

A knowledge transfer-based cross-domain recommender system is currently a research hotspot. Existing research has reached a high level of maturity in mining potential knowledge and establishing transfer mechanisms. However, most of them ignore the impact of the dissimilarity of potential knowledge on the transfer performance. Herein, a cross-domain recommender system based on knowledge correlation-induced the embedding and mapping approach is proposed, denoted by KCEM-CDRS. First, we propose a knowledge correlation measure, which captures the consistency of knowledge between the target and source domains to build the bridge for knowledge transfer. Second, we construct a joint matrix triple factorization model to solve the data sparsity in the target domain while introducing graph regularization to solve the problem of negative knowledge transfer. Results of extensive experiments on real Amazon metadata indicate that compared with three existing cross-domain recommendation methods, KCEM-CDRS shows performance improvements of 0.05–9.55 % and 0.02–2.63 % on mean absolute error and root mean square error, respectively. Additionally, the results of the ablation experiments indicate that consideration of the knowledge correlation between domains is beneficial for knowledge transfer when the density of the source domain is rich.

The purpose of this study is to perform the numerical results of the global stability of infectious disease mathematical model by using the stochastic computing scheme. The design of proposed solver is presented by one of the efficient and reliable schemes named as Bayesian regularization neural network (BRNN). The global stability of infectious disease mathematical nonlinear model is categorized into susceptible, infected, recovered and vaccinated. The construction of dataset is performed through the Runge-Kutta scheme in order to lessen the mean square error (MSE) by dividing the statics as training 74 %, while 13 % for both testing and endorsement. The proposed stochastic process contains log-sigmoid merit function, twenty neurons and optimization through RBNN for the numerical solutions of the global stability of infectious disease mathematical system. The best training values for each model's case are performed around 10^–11. The scheme's correctness is performed by the matching of the results and the minor calculated absolute error performances. Moreover, the regression, state transmission, error histogram and MSE indicate the trustworthiness of the designed solver.

Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study’s input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.

Cognitive diagnostics is a pivotal area within educational data mining, focusing on deciphering students’ cognitive status via their academic performance. Traditionally, cognitive diagnostic models (CDMs) have evolved from manually designed probabilistic graphical models to sophisticated automated learning models employing neural networks. Despite their enhanced fitting capabilities, contemporary neuro-cognitive diagnostic models frequently overlook critical process information from students and suffer from reduced interpretability. To address these limitations, this paper introduces a neuro-cognitive diagnostic model that integrates multidimensional features (MFNCD) by incorporating students’ response time as process information. This approach facilitates the simultaneous modeling of students’ response accuracy and response speed using neural networks, thereby enhancing both the fitting capability and precision of the method. Furthermore, a multi-channel attention mechanism is employed to effectively capture the complex interactions between students and exercise characteristics, simulating the process of students answering questions and thereby improving the model's interpretability. Validated on four diverse datasets, MFNCD model demonstrates superior accuracy compared to other state-of-the-art (SOAT) baseline models. Additionally, our experiments confirm significant correlations between cognitive attributes, revealing interesting educational patterns, such as a positive correlation between speed and ability, and between ability and accuracy. These findings provide deeper insights into learning patterns that incorporate multidimensional features and suggest potential pathways for targeted educational interventions.

With the rapid development of the IoT (Internet of Things), the network data present the characteristics of large volume and high dimension. Convolutional neural networks (CNNs) have become one of the most important intrusion detection methods due to their advantages in processing high-dimensional data. The conventional intrusion detection model based on CNN lacks an effective data purification means in the process of converting unstructured data into image data, and too many parameters are generated due to the complex structure of the model in the training process, leading to the problems of high time complexity and low detection rate of the model, which limits the application of the CNN in intrusion detection of the IoT. First, based on the principle of liquid molecular distillation, a data purification algorithm (DPA) for unstructured data is proposed in this paper, which reduces the "redundant" data generated in the process of converting unstructured data to image data. Second, based on the rigid-motion convolution principle of a separable wavelet, separable convolution is used to improve the CNN structure, and then a lightweight detection algorithm LSCNN (lightweight CNN based on separable convolution) is developed to reduce the number of parameters in the network structure and improve the time efficiency and accuracy of the algorithm. The experimental results on real intrusion detection datasets show that the LSCNN trained on DPA purified data has higher time efficiency and detection accuracy than the conventional CNN, and compared with the conventional machine learning algorithm, it has higher accuracy.